Description:FIELD OF INVENTION
[0001] The present invention relates to imaging and, more particularly, to optical coherence tomography (OCT) and related imaging systems using optical computed tomography.

BACKGROUND
[0002] Imaging systems for acquiring fundus images are designed to image adult population for major eye diseases, such as glaucoma and macular-degeneration. Such systems are generally capable of moving in a vertical direction capturing various fundus images for an adult subject occupying a seated position.

[0003] However, the system fails to obtain images of infant, toddlers and sick adults incapable of positioning themselves in front of the OCT machines.

[0004] Moreover, a system designed for a mature eye may not be well suited for a broad range of applications. For example, pediatric applications have their own distinct requirements. The pediatric eye, by definition, is a developing eye, and the neonatal eye is considerably smaller than the mature eye. With the increasing incidence of successful births of premature babies, pediatric patients may exhibit a broad range of congenital malformations and genetic disorders, frequently with a dramatic deviation from normal pathology. A premature baby in the neonatal intensive care unit (NICU) may be at risk for a host of chronic diseases, including retinopathy of prematurity, that typically require careful diagnosis and management.

[0005] Hence, there exists a need for a system for obtaining fundus image for a range of patients who cannot be seated while performing the diagnostic procedure, including but not limited to pregnant women, infants, toddlers and sick adults.

SUMMARY
[0006] Some embodiments of the present invention provide optical coherence tomography (OCT) imaging systems, the system comprising an image capturing device 102 having a fixed arm 104 and a movable arm 106, the movable arm 106 encasing an image capturing device 102 and configured for moving in a movable arm 106 path of a predetermined length, the movement of the movable arm 106 path being controlled by a movable arm 106 adjustment module coupled to the fixed arm 104, a receiver adapted to receive an input from the image capturing device 102 based on a plurality of parameters of the image capturing device 102, wherein the input is the fundus image of the patient, an image analyzing module 108 configured for selecting at least one image of a predetermined quality based on one or more predefined parameters, wherein the quality of each captured image being dynamically analyzed by the image analyzing module 108 based on the one or more predefined parameters and an image processing module 110 adapted to process a selected image, the image processing module 110 configured to identify a plurality of indicators throughout the fundus image using a convolutional network to detect a presence or absence of a retinal disease based the identified indicators using the convolutional network and classify a severity of the retinal disease based on the presence or absence of the retinal disease using the convolutional network.

[0007] Further, the predetermined length covered by the movable arm 106 path is set based on the age of a subject and wherein the movable arm 106 path is running parallel to the patient table.

[0008] In one embodiment, the fixed arm 104 and the movable arm 106 are positioned perpendicular to each other. The fixed arm 104 is configured to be stationary and the movable arm 106 is configured to move along a guided path for a predetermined length so as to enable imaging of the subject in order to obtain fundus image of predetermined quality.

[0009] In further embodiments of the present invention, the OCT system may be portable such that the OCT system is provided to the subject where the subject is located. In some embodiments of the present invention, the portable OCT system may be configured to provide imaging to a subject independent of the orientation of the subject. The portable OCT system may be configured to be moved to a location of the subject, unplugged and/or receive new samples without being shutdown.

[0010] In further embodiments of the present invention, the portable OCT system may be configured to provide a visible light that reflects off a cornea of the eye of the subject to enable accurate positioning of the portable OCT system.
[0011] In further embodiments of the present invention, the portable OCT system may be configured to continuously acquire images until detection of an image capture trigger is detected; and record a predetermined buffered portion of the acquired image upon detection of the image capture trigger. In certain embodiments, the buffered image comprises the most recent from about 2.0 seconds to about 30 seconds of the acquired image.

[0012] In some embodiments of the present invention, the continuously acquired image may be streamed to a non-volatile storage for a predetermined period of time.

[0013] In further embodiments of the present invention, the system includes a quality assessing module configured to display an acquired image to an image acquisition technician; trigger adjustment of the movable arm 106 path length and/or focusing of at least one image capturing device 102 in the fixed arm 104 based on an assessed quality of the displayed image; and trigger the OCT system to initiate or continue acquisition of the image after adjustments are made.

[0014] Still further embodiments of the present invention provide methods for imaging an eye in an optical coherence tomography (OCT) imaging system including setting a target movable arm 106 path length of the OCT system such that the movable arm 106 path length is based on an eye length of a subject; obtaining additional information about the subject relevant to the target movable arm 106 path length; recalibrating the movable arm 106 path length based on the obtained information; and automatically adjusting the movable arm 106 path length based on the recalibrated movable arm 106 path length.

[0015] In some embodiments of the present invention, an image is acquired using the OCT system having the adjusted movable arm 106 path length. The method may further include assessing the image quality of the acquired image; determining if the adjusted movable arm 106 path length is optimum; further adjusting the movable arm 106 path length if it is determined that the adjusted movable arm 106 path length is not optimum; and reacquiring the image using the OCT system having the further adjusted movable arm 106 path length.

[0016] In further embodiments of the present invention, the steps of assessing, determining, further adjusting and reacquiring may be repeated until an image having a desired quality is obtained.

[0017] In still further embodiments of the present invention, further adjusting is followed by determining if a focus of at least one objective lens of the OCT system is optimum; and adjusting focus position of the at least one objective lens of the OCT system if it is determined that the focus of the at least one objective lens is not optimum, wherein reacquiring the image further comprises reacquiring the image using the OCT system having the further adjusted movable arm 106 path length and the adjusted focus.

[0018] Some embodiments of the present invention provide computer program products for imaging an eye in OCT imaging systems including computer readable storage medium having computer readable program code embodied in said medium. The computer readable program code includes computer readable program code configured to set a target movable arm 106 path length of the OCT system such that the movable arm 106 path length is based on an eye length of a subject; computer readable program code configured to obtain additional information about the subject relevant to the target movable arm 106 path length; computer readable program code configured to recalibrate the movable arm 106 path length based on the obtained information; computer readable program code configured to automatically adjust the movable arm 106 path length based on the recalibrated movable arm 106 path length; and computer readable program code configured to acquire an image using the OCT system having the adjusted movable arm 106 path length and display the acquired image on an electronic display associated with the OCT system.

BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The present invention is described by way of embodiments illustrated in the accompanying drawings wherein:

[0020] FIG. 1 shows a block diagram depicting a system for acquiring and analyzing fundus image for detecting presence of retinal diseases, as described in an embodiment of the invention;

[0021] FIG. 2 shows a block diagram depicting a convolutional neural network employed by the image processing module 110 configured for processing the fundus image for detecting presence of retinal diseases, as described in an embodiment of the invention; and

[0022] FIG. 3 shows a flow diagram depicting a method for acquiring and analyzing fundus image for detecting presence of retinal diseases, as described in an embodiment of the invention.

DETAILED DESCRIPTION OF THE DRAWINGS

[0023] OCT systems in accordance with some embodiments of the present invention are configured with a movable arm 106 adjustment module. The movable arm 106 adjustment module may include any combination of the collimator assembly, the variable attenuator, the mirror assembly, the movable arm 106 variable path length adjustment and the path length matching position of the movable arm 106 discussed above. In particular, the movable arm 106 adjustment module is configured to manually or automatically adjust the movable arm 106 path length such that the movable arm 106 path length is based on an eye length of the subject. The presence of this module allows the OCT system to adjust to patients having different eye lengths, thus allowing eyes of patients having immature eyes (pediatric patients), for example, eyes having a length of less than 25 mm, to be accurately imaged. Eye length is measured as the distance between the cornea and the retina. A mature adult eye typically has a length of about 25 mm and a pediatric eye length can be from about 14 mm to about 25 mm. Accordingly, the movable arm 106 adjustment module in accordance with some embodiments of the present invention may be made capable to accommodate eye lengths ranging from about 10 mm to about 30 mm.

[0024] In some embodiments of the present invention, the movable arm 106 adjustment module is configured to set a target movable arm 106 path length based on an age of the subject and/or a refractive status of the eye of the subject. The target movable arm 106 path length may be set using the patient's age and a standard table for the growth of an eye.

[0025] As discussed above, OCT systems in accordance with some embodiments of the present invention, the image capturing device 102 may further include at least one lens in the movable arm 106 such that the at least one lens in combination with the optical attributes of the subject eye has a field curvature that matches a curvature of a retina of the eye of the subject. In other words, the lenses may be switched to conform to the eye length, for example, 25 mm or 14 mm, of the patient. Thus, OCT systems discussed herein can be configured to image both a mature eye and a pediatric eye.

[0026] Images may be acquired using the portable OCT system using many methods. For example, the portable OCT system may provide two synchronous images to illustrate orthogonal pathology of an eye of the subject to facilitate aiming of the portable OCT system during image acquisition. In other words, the device may be aimed at the portion of the eye to be imaged, present images of nasal-temporal (horizontal) physiology side-by-side with images of inferior-superior (vertical) physiology and acquired by pushing a capture button on the device.

[0027] In some embodiments, the portable OCT system may be configured to acquire, process and display images until an image capture button is activated at which point a most recent portion of the acquired image is stored in a buffer having a predetermined size. In some embodiments, the buffered image may include the most recent from about 2.0 seconds to about 30 seconds of the acquired image. In certain embodiments, the continuously acquired image may be streamed to non-volatile memory in a first-in, first-out fashion for a predetermined period of time, such that, for example, a half hour or more of streaming image may be captured.

[0028] Turning now to figures, Figure 1 illustrates a block diagram of a system 1000 in accordance with the invention. The system 1000 comprises at least one image capturing device 102, an image analyzing module 108 and an image processing module 110. The system further comprises one or more storage devices 114 configured to store software instructions configured for execution by the image processing module 110 in order to cause the system 1000 to: receive a fundus image of a patient; identify a plurality of indicators throughout the fundus image using a convolutional network; detect a presence or absence of a retinal disease based the identified indicators using the convolutional network; and classify a severity of the retinal disease based on the presence or absence of the retinal disease using the convolutional network.

[0029] The fundus image, herein, refers to a two-dimensional array of digital image data, however, this is merely illustrative and not limiting of the scope of the invention. The one or more storage devices 114 is, for example, a database to store a structured collection of data. In an embodiment, the one or more storage devices 114 may be an internal part of the system 1000. In another embodiment, the one or more storage devices 114 may be remotely located and accessed via a network. The one or more storage devices 114 may be, for example, removable and/or non-removable data storage such as a tape, a magnetic disk, an optical disks, a flash memory card, etc. The one or more storage devices 114 may comprise, for example, random access memory (RAM), read only memory (ROM), electrically erasable programmable read-only memory (EEPROM), a digital versatile disks (DVD), a compact disk (CD), a flash memory, a magnetic tape, a magnetic disk storage, or any combination thereof that can be used to store and access information and is a part of the system 1000.

[0030] The indicator is one of an abnormality, a retinal feature or the like. The retinal feature is an optic disc, a macula, a blood vessel or the like. The abnormality is one of a lesion like a venous beading, a venous loop, an intra retinal microvascular abnormality, an intra retinal hemorrhage, a micro aneurysm, a soft exudate (cotton-wool spots), a hard exudate, a vitreous/preretinal hemorrhage, neovascularization, a drusen or the like. The retinal disease is one of diabetic retinopathy, diabetic macular edema, glaucoma, coloboma, retinal tear, retinal detachment or the like. The severity of the retinal disease are represented as levels of increasing seriousness of the retinal disease.

[0031] The image processing module 110 of the system 1000 receives a reference dataset from one or more input devices. The reference dataset comprises a plurality of fundus images. Hereafter, the fundus images in the reference dataset are referred to as reference fundus images. The input device is, for example, a camera incorporated into a mobile device such as a smartphone, a server, a network of personal computers, or simply a personal computer, a mainframe, a tablet computer, etc. The system 1000 stores the reference dataset in the one or more storage devices 114 of the system 1000.

[0032] The reference fundus image is a two-dimensional array of digital image data used for the purpose of training the system 1000. In this invention, the term ‘training’ generally refers to a process of developing the system 1000 for the detection and classification of the retinal disease based the reference dataset and a reference ground- truth file. The reference ground-truth file comprises a label and a reference fundus image identifier for each of the reference fundus image. The label provides information about the reference fundus image such as a presence or absence of a retinal disease, the type of retinal disease and the corresponding severity of the retinal disease identified in the reference fundus image. The reference fundus image identifier of a reference fundus image is, for example, a name or identity assigned to the reference fundus image.

[0033] In an embodiment, an annotator annotates each of the reference fundus images using an annotation platform 101 of the system 1000. The annotation platform 101 is a graphical user interface (GUI) provided for the annotator to interact with the system 1000. The annotator accesses the reference fundus images via the annotation platform 101. The annotator creates a label with information about a presence or absence of a retinal disease, the type of retinal disease and the corresponding severity of the retinal disease based on the annotation. The annotator is usually a trained/certified specialist in accurately annotating the fundus image by analyzing the indicators present in the reference fundus image. In an example, consider that the annotator annotates the reference fundus images for the retinal disease - diabetic retinopathy (DR). The annotator may consider one or more standard DR grading standards such as the American ophthalmology DR grading scheme, the Scottish DR grading scheme, the UK DR grading scheme, etc., to annotate the reference fundus images. The annotator may assign a DR severity grade 0 (representing no DR), grade 1 (representing mild DR), grade 2 (representing moderate DR), grade 3 (representing severe DR) or grade 4 (representing proliferative DR) to each of the reference fundus image. The label of the reference fundus image represents the DR severity level associated with the patient.

[0034] For example, the annotator labels each of the reference fundus image as one of five severity classes- ‘No DR’, ‘DR1’, ‘DR2’, ‘DR3’ and ‘DR4’based on an increasing seriousness of DR. Here, ‘No DR’, ‘DR1’, ‘DR2’, ‘DR3’ and ‘DR4’ represents the labels indicating different levels of increasing severity of DR associated with the patient. The annotator analyses the indicators in the retinal fundus image and accordingly marks the label. If the annotator detects a microaneurysm, then the annotator considers it as a mild level of DR and marks the label as DR1 for the reference fundus image. Similarly, if the annotator detects one or more of the following – a hard exudate, a soft exudate, a hemorrhage, a venous loop, a venous beading, etc., then the annotator marks the label as DR2 for the reference fundus image. The label DR2 indicates a moderate level of DR. The annotator marks the label as DR3 for the reference fundus image with a severe level of DR upon detection of multiple hemorrhages, hard or soft exudates, etc., and DR4 for the reference fundus image with a proliferative level of DR upon detection of vitreous hemorrhage, neovascularization, etc. The reference fundus image with no traces of DR is marked with the label as ‘No DR’ by the annotator.

[0035] The annotator stores the label and the reference fundus image identifier for each of reference fundus image in the reference ground-truth file located in the one or more storage devices 114 . The label provides information about the type of retinal disease and the corresponding severity of the retinal disease as annotated by the annotator. The reference fundus image identifier of a reference fundus image is, for example, a name or identity assigned to the reference fundus image.

[0036] In another embodiment, the image processing module 110 identifies the indicators throughout each of the reference fundus image to detect the presence or absence of the retinal disease using image analysis techniques. The image processing module 110 classifies the severity of the retinal disease based on the presence of the retinal disease using a set of predetermined rules. The predetermined rules comprise considering a type of each of the indicators, a count of each indicators, a region of occurrence of each of the indicators, a contrast level of each of the indicators, a size of each of the indicators or any combination thereof to recognize the retinal disease and the severity of the retinal disease. The image processing module 110 classifies each of the detected retinal diseases according to a corresponding severity grading and generates the label. The image processing module 110 communicates with the one or more storage devices 114 to store the label and the reference fundus image identifier for each of reference fundus image in the reference ground-truth file.

[0037] The image processing module 110 utilizes the reference dataset to train the convolutional network for subsequent detection and classification of the retina disease in the fundus image. Hereafter, the fundus image which is subsequently analyzed by the image processing module 110 is referred to as an input fundus image for clarity.

[0038] The image processing module 110 pre-processes each of the reference fundus images. For each of the reference fundus image, the image processing module 110 executes the following steps as part of the pre-processing. The image processing module 110 separates any text matter present at the border of the reference fundus image. The image processing module 110 adds a border to the reference fundus image with border pixel values as zero. The image processing module 110 increases the size of the reference fundus image by a predefined number of pixels, for example, 20 pixels width and height. The additional pixels added are of a zero value. The image processing module 110 next converts the reference fundus image from a RGB color image to a grayscale image. The image processing module 110 now binarize the reference fundus image using histogram analysis. The image processing module 110 applies repetitive morphological dilation with a rectangular element of size [5, 5] to smoothen the binarized reference fundus image. The image processing module 110 acquires all connected regions such as retina, text matter of the smoothen reference fundus image to separate text matter present in the reference fundus image from a foreground image. The image processing module 110 determines the largest region among the acquired connected regions as the retina. The retina is assumed to be the connected element with the largest region. The image processing module 110 calculates a corresponding bounding box for the retina. The image processing module 110, thus identifies retina from the reference fundus image.

[0039] Once the image processing module 110 identifies the retina in the reference fundus image, the image processing module 110 further blurs the reference fundus image using a Gaussian filter. The image processing module 110 compares an image width and an image height of the blurred reference fundus image based on Equation 1.

Image width > 1.2(image height) -------Equation 1

[0040] The image processing module 110 calculates a maximum pixel value of a left half, a maximum pixel value of a right half and a maximum background pixel value for the blurred reference fundus image when the image width and the image height of the blurred identified retina satisfies the Equation 1. The maximum background pixel value (Max_background pixel value) is given by the below Equation 2. The term ‘max_pixel_left’ in Equation 2 is the maximum pixel value of the left half of the blurred identified retina. The term ‘max_pixel_right’ in Equation 2 is the maximum pixel value of the right half of the blurred reference fundus image.

Max_background pixel value = max(max_pixel_left, max_pixel_right) ------Equation 2

[0041] The image processing module 110 further extracts foreground pixel values from the blurred reference fundus image by considering pixel values which satisfy the below Equation 3.

All pixel values > max_background_pixel_value + 10 Equation 3

[0042] [0026] The image processing module 110 calculates a bounding box using the extracted foreground pixel values from the blurred reference fundus image. The image processing module 110 processes the bounding box to obtain a resized image using cubic interpolation of shape, for example, [256, 256, 3]. The reference fundus image at this stage is referred to as the pre-processed reference fundus image. The image processing module 110 stores the pre-processed reference fundus images in a pre-processed reference dataset. The ground-truth file associated with the reference dataset holds good even from the pre-processed reference dataset. The image processing module 110 stores the pre-processed reference dataset in the one or more storage devices 114.

[0043] The image processing module 110 splits the pre-processed reference dataset into two sets – a training set and a validation set. Hereafter, the pre-processed reference fundus images in the training set is termed as training fundus images and the pre-processed reference fundus images in the validation set is termed as validation fundus images for simplicity. The training set is used to train the convolutional network to assess the training fundus images based on the label associated with each of the training fundus image. The validation set is typically used to test the accuracy of the convolutional network.

[0044] The image processing module 110 augments the training fundus images in the training set. The image processing module 110 preforms the following steps for the augmentation of the training set. The image processing module 110 randomly shuffles the training fundus images to divide the training set into a plurality of batches. Each batch is a collection of a predefined number of training fundus images. The image processing module 110 randomly samples each batch of training fundus images. The image processing module 110 processes each batch of the training fundus images using affine transformations. The image processing module 110 translates and rotates the training fundus images in the batch randomly based on a coin flip analogy. The image processing module 110 also adjusts the color and brightness of each of the training fundus images in the batch randomly based on the results of the coin flip analogy.

[0045] The image processing module 110 trains the system 1000 using the batches of augmented training fundus images via the convolutional network. In general, the convolutional network is a class of deep artificial neural networks that can be applied to analyzing visual imagery. The general arrangement of the convolutional network is as follows. The convolutional network comprising ‘n’ convolutional stacks applies a convolution operation to the input and passes an intermediate result to a next layer. Each convolutional stack comprises a plurality of convolutional layers. A first convolution stack is configured to convolve pixels from an input with a plurality of filters to generate a first indicator map. The first convolutional stack also comprises a first subsampling layer configured to reduce a size and variation of the first indicator map. The first convolutional layer of the first convolutional stack is configured to convolve pixels from the input with a plurality of filters. The first convolutional stack passes an intermediate result to the next layer. Similarly, each convolutional stack comprises a sub-sampling layer configured to reduce a size (width and height) of the indicators stack. The input is analyzed based on reference data to provide a corresponding output.

[0046] Similar to the training set, the image processing module 110 groups the validation fundus images of the validation set into a plurality of batches. Each batch comprises multiple validation fundus images. The image processing module 110 validates each of the validation fundus images in each batch of the validation set using the convolutional network. The image processing module 110 compares a result of the validation against a corresponding label of the validation fundus image by referring to the reference ground-truth file. The image processing module 110 thus evaluates a convolutional network performance of the convolutional network for the batch of validation set.

[0047] The image processing module 110 optimizes the convolutional network parameters using an optimizer, for example, a Nadam optimizer which is an Adam optimizer with Nesterov Momentum. The optimizer iteratively optimizes the parameters of the convolutional network during multiple iterations using the training set. Here, each iteration refers to a batch of the training set. The image processing module 110 evaluates a convolutional network performance of the convolutional network after a predefined number of iterations on the validation set. Here, each iteration refers to a batch of the validation set.

[0048] Thus, the image processing module 110 trains the convolutional network based on the augmented training set and tests the convolutional network based on the validation set. Upon completion of training and validation of the convolution network based on the convolutional network performance, the system 1000 is ready to assess the input fundus image based on the indicators present in the input fundus image.

[0049] The image processing module 110 of the system 1000 receives the input fundus image from one of the input devices. The image processing module 110 pre-processes the input fundus image similar to that of the reference fundus image. The image processing module 110 test-time augments the preprocessed input fundus image. The image processing module 110 performs the following step to test- time augment the preprocessed input fundus image. The image processing module 110 converts the preprocessed input fundus image into a plurality of test time images, for example, twenty test time images, using deterministic augmentation. The image processing module 110 follows the same steps to augment the input fundus image as that of the training fundus image, except that the augmentations are deterministic. Thus, the image processing module 110 generates deterministically augmented twenty test time images of the preprocessed input fundus image. The image processing module 110 processes the deterministically augmented twenty test time images of the preprocessed input fundus image using the convolutional network comprising ‘n’ convolutional stacks. The predicted probabilities of the twenty test time images are averaged over to get a final prediction result. The final prediction result provides a probability value for each of the retinal disease and a corresponding retinal disease severity level associated with the input fundus image. The probability value is an indication of a confidence that identified indicators are of a particular retinal disease and a corresponding severity of the retinal disease. The output indicates a presence or absence of a retinal disease and related severity of the retinal disease associated with the input fundus image.

[0050] Figure 2 exemplary illustrates the convolutional network to compute the presence or absence of a retinal disease and related severity of the retinal disease associated with the input fundus image. The deterministically augmented twenty test time images of the preprocessed input fundus image is the input to a first convolutional stack (CS1) of the convolutional network. Each of the deterministically augmented twenty test time images is processed by the convolutional network.

[0051] The deterministically augmented test time image is, for example, represented as a matrix of width 448 pixels and height 448 pixels with ‘3’ channels. That is, the deterministically augmented test time image is a representative array of pixel values is 448 x 448 x 3. The input to the first convolutional stack (CS1) is a color image of size 448 x 448. The first convolution stack (CS1) comprises the following sublayers - a first convolutional layer, a first subsampling layer, a second convolutional layer, a third convolutional layer and a second subsampling layer in the same order. The output of a sublayer is an input to a consecutive sublayer. In general, a subsampling layer is configured to reduce a size and variation of its input and a convolutional layer convolves its input with a plurality of filters, for example, filters of size 3x3. The output of the first convolutional stack (CS1) is a reduced image represented as a matrix of width 112 pixels and height 112 pixels with n1 channels. That is, the output of the first convolutional stack (CS1) is a representative array of pixel values 112 x 112 x n1.

[0052] This is the input to a second convolutional stack (CS2). The second convolutional stack (CS2) comprises the following sublayers - four convolutional layers and a subsampling layer arranged in the same order. Again, the output of a sublayer is an input to a consecutive sublayer. The second convolutional stack (CS2) convolves the representative array of pixel values 112 x 112 x n1 and reduces it to a representative array of pixel values of 56 x 56 x n2. The representative array of pixel values of 56 x 56 x n2 is an input to a third convolutional stack (CS3).

[0053] The third convolutional stack (CS3) comprises the following sublayers - four convolutional layers and a subsampling layer arranged in the same order. Again, the output of a sublayer is an input to a consecutive sublayer. The third convolutional stack (CS3) convolves the representative array of pixel values 56 x 56 x n2 and reduces it to a representative array of pixel values of 28 x 28 x n3. The representative array of pixel values of 28 x 28 x n3 is an input to a fourth convolutional stack (CS4).

[0054] The fourth convolutional stack (CS4) comprises the following sublayers -four convolutional layers and a subsampling layer arranged in the same order. Again, the output of a sublayer is an input to a consecutive sublayer. The fourth convolutional stack (CS4) convolves the representative array of pixel values 28 x 28 x n3 and reduces it to a representative array of pixel values of 14 x 14 x n4. The representative array of pixel values of 14 x 14 x n4 is an input to a fifth convolutional stack (CS4).

[0055] The fifth convolutional stack (CS5) comprises the following sublayers - four convolutional layers and a subsampling layer arranged in the same order. Again, the output of a sublayer is an input to a consecutive sublayer. The fifth convolutional stack (CS5) convolves the representative array of pixel values 14 x 14 x n4 and reduces it to a representative array of pixel values of 7 x 7 x n5. The representative array of pixel values of 7 x 7 x n5 is a first input to a concatenation block (C).

[0056] The output of the third convolutional stack (CS3) is an input to a first subsampling block (SS1). The representative array of pixel values of 28 x 28 x n3 is the input to the first subsampling block (SS1). The first subsampling block (SS1) reduces the input with a stride of 4 to obtain an output of a representative array of pixel with value of 7 x 7 x n3. This is a second input to the concatenation block (C).

[0057] The output of the fourth convolutional stack (CS4) is an input to a second subsampling block (SS2). The representative array of pixel values of 14 x 14 x n4 is the input to the second subsampling block (SS2). The second subsampling block (SS2) reduces the input with a stride of 2 to obtain an output of a representative array of pixel with value of 7 x 7 x n4. This is a third input to the concatenation block (C).

[0058] The concatenation block (C) receives the first input from the fifth convolutional stack (CS5), the second input from the first subsampling block (SS1) and the third input from the second subsampling block (SS2). The concatenation block (C) concatenates the three inputs received to generate an output of value 7 x 7 x (n5 + n4 + n3). The output of the concatenation block (C) is an input to a probability block (P).

[0059] The probability block (P) provide a probability of the presence or absence of the retinal disease and related severity of the retinal disease. The predicted probabilities of the twenty test time images are averaged to get a final prediction result. The output of the convolutional network provides a probability value for each of the retinal disease and a corresponding retinal disease severity level associated with the input fundus image. The probability block (P) as shown in the Figure 2 provides five values by considering the retinal disease to be DR. The output of the probability block are five values depicting the probability for each DR severity level – DR0 (no DR), DR1 (mild DR level), DR2 (moderate DR level), DR3 (severe DR level) and DR4 (proliferative DR level).

[0060] The system 1000 considers an image capture device characteristics of an image capture device also as one of the parameters to assess the input fundus image. The image capture device characteristics is a resolution, an illumination factor, a field of view or any combination thereof. The image capture device is, for example, a fundus camera, a camera attached to a smartphone, etc., used to capture the input fundus image. For example, the image capture device is the input device used to capture the input fundus image.

[0061] In an embodiment, the image processing module 110 of the system 1000 considers a manufacturer and version of the image capture device to determine a predefined score for the image capture device characteristics of the image capture device. This predefined score for the image capture device characteristics is used to assess the input fundus image. The predefined score for the image capture device characteristics denotes a superiority of the image capture device characteristics. The predefined score for the image capture device characteristics is a numeric value within the range of [0, 1]. Here, 0 defines a least value and 1 defines a highest value of the predefined score for the image capture device characteristics. For example, the predefined score for the image capture device characteristics for multiple manufacturers of image capture device is initially stored in the one or more storage devices 114 by an operator of the system 1000. By considering the image capture device characteristics of an image capture device to assess the quality of the input fundus image, the flexibility of the system 1000 is increased, thereby providing customized results for the input fundus image captured using the image capture device of multiple manufacturers. Thus, the image processing module 110 considers the output of the convolutional network and the image capture device characteristics of the image capture device to determine the presence or absence of a retinal disease and/or related severity of the retinal disease associated with the input fundus image. The image processing module 110 thereby considers the quality of the input fundus image along with the output of the convolutional network to determine the presence or absence of a retinal disease and/or related severity of the retinal disease associated with the input fundus image.

[0062] The image processing module 110 displays the presence or absence of a retinal disease and/or related severity of the retinal disease associated with the input fundus image via a display 104 to a user. For example, suitable suggestions with a set of instructions to the user may also be included and provided via a pop-up box displayed on a screen. The system 1000 may also generate a report comprising the input fundus image, the type of the retinal disease and the severity of the retinal disease and communicated to the patient via an electronic mail. The report could also be stored in the one or more storage devices 114 of the system 1000.

[0063] In an embodiment, the image processing module 110 assesses a quality measure of each of the reference fundus images in the reference dataset. The quality measure is also stored as a part of the label associated with the reference fundus image. The image processing module 110 trains the convolutional network to learn the quality measure of the reference fundus image along with the identification of the indicators in the reference fundus image. The image processing module 110 assesses the input fundus image based on the training. The image processing module 110 identifies the quality measure of the input fundus image using the convolutional network. The image processing module 110 may also refer to a user defined threshold to define the quality measure of the input fundus image. The user defined threshold is user defined to increase a flexibility of the system 1000. The user defined threshold is the variable factor which may be used to vary the quality measure of the input fundus image to conveniently suit the requirements of the user, for example, medical practitioner. The user defined threshold may be varied to vary the quality measure of the input fundus image based on the doctor’s grading experience. The system 1000 may further display 104 a message to an operator to retake another fundus image of the patient when the quality measure of the input fundus image is below a threshold. The system 1000 may further consider characteristics of a device used to capture the input fundus image of the patient as an additional parameter to assess the quality measure of the input fundus image. For example, the device is a fundus camera and the characteristics of the device is a resolution level of the fundus camera.

[0064] In another embodiment, the system 1000 detects the presence of several diseases, for example, diabetes, stroke, hypertension, cardiovascular diseases, etc., and not limited to retinal diseases based on changes in the retinal feature. The image processing module 110 trains the convolutional network to identify and classify the severity of these diseases using the fundus image of the patient.

[0065] In some embodiments of the present invention, the OCT system may be portable such that the OCT the system is provided to the subject where the subject is located. The portable OCT system may be configured to be moved to a location of the subject, unplugged and/or receive new samples without being shutdown.

[0066] In some embodiments of the present invention, the OCT system may be portable such that the OCT the system is provided to the subject in any orientation of the subject. The portable OCT system may be aligned to the subject whether the subject is sitting, standing, lying prone, lying supine, at any associated angle.

[0067] In further embodiments of the present invention, the portable OCT system may include a portable handheld OCT probe; a battery backup device associated with the portable handheld probe; and a moveable rack configured to receive the portable handheld probe and/or the battery backup device.

[0068] In still further embodiments of the present invention, the portable OCT system may further include a fixation target for the subject configured to provide a comfort image to the subject during image acquisition. The fixation target may be configured to provide a continuously variable patient comfort image. The fixation target may include an image of a character, a photograph, or an icon, and the image photograph or icon may be animated to maintain the subject's attention and relaxation.

[0069] In some embodiments of the present invention, the portable OCT system may be configured to provide a visible light that reflects off a cornea of the eye of the subject to enable accurate positioning of the portable OCT system.
[0070] In further embodiments of the present invention, the portable OCT system may include a video and/or digital fundus camera. The video and/or digital fundus camera may be aligned and calibrated to the OCT system.

[0071] In still further embodiments of the present invention, the portable OCT system may further include a foot peddle and/or finger trigger configured to control focus adjustment, movable arm 106 path length adjustment and/or trigger acquisition of an image.

[0072] In still further embodiments of the present invention, the portable OCT system may further include a foot peddle and/or finger trigger configured to control the OCT source power, attenuation of OCT signal power in the movable arm 106 path, the power of the illumination for the video or digital fundus camera.

[0073] In further embodiments of the present invention, the portable OCT system may be configured to continuously acquire, process and display images until detection of an image capture trigger signal; and record a predetermined buffered portion of the acquired image upon detection of the image capture trigger signal. In certain embodiments, the buffered image comprises the most recent from about 2.0 seconds to about 30 seconds of the acquired image.

[0074] In still further embodiments of the present invention, the continuously acquired image may be streamed non-volatile storage for a predetermined period of time.

[0075] In some embodiments of the present invention, the system includes a quality-assessing module configured to figure of merit for the quality of an acquired image; trigger adjustment of the movable arm 106 path length and or focusing of at least one lens in the fixed arm 104 based on an assessed quality of the displayed image; and trigger the OCT system to initiate or continue acquisition of the image after adjustments are made.

[0076] In further embodiments of the present invention the OCT system may be configured to acquire an image from an aphakic subject that does not have an ocular lens in the eye being imaged.

[0077] In further embodiments of the present invention the OCT system may be configured to acquire an image of pathologies that are substantially anterior to the posterior pole, or retina of the subject, but still nominally within the anterior chamber of the eye of the subject. In still further embodiments of the present invention, the OCT system may be a pediatric OCT system.

[0078] Some embodiments of the present invention provide OCT imaging systems for imaging an eye including a source having an associated source arm path and a movable arm 106 having an associated movable arm 106 path coupled to the source path, the movable arm 106 path having an associated movable arm 106 path length. A sample having an associated fixed arm 104 path coupled to the source arm and movable arm 106 paths is provided. At least one lens is provided in the fixed arm 104 path, the at least one lens having a field curvature that matches a curvature of a retina of the eye of the subject.

[0079] Further embodiments of the present invention provide methods for imaging an eye in an optical coherence tomography (OCT) imaging system including setting a target movable arm 106 path length of the OCT system such that the movable arm 106 path length is matched to an eye length of a subject; obtaining additional information about the subject relevant to the target movable arm 106 path length; recalibrating the movable arm 106 path length based on the obtained information; and adjusting the movable arm 106 path length based on the recalibrated movable arm 106 path length.

[0080] In still further embodiments of the present invention, an image is acquired using the OCT system having the adjusted movable arm 106 path length. The method may further include accessing the image quality of the acquired image; determining if the adjusted movable arm 106 path length is optimum; further adjusting the movable arm 106 path length if it is determined that the adjusted movable arm 106 path length is not optimum; and reacquiring the image using the OCT system having the further adjusted movable arm 106 path length.

[0081] In still further embodiments of the present invention adjusting the movable arm 106 path length is accomplished manually or automatically based on feedback from an operator or an image quality metric on an acquired image.

[0082] In still further embodiments of the present invention the quality metric is the average or peak brightness of the image.

[0083] In some embodiments of the present invention, the steps of accessing, determining, further adjusting and reacquiring may be repeated until an image having a desired quality is obtained.

[0084] In further embodiments of the present invention, further adjusting is followed by determining if a focus of at least one objective lens of the OCT system is optimum; and adjusting focus position of the at least one objective lens of the OCT system if it is determined that the focus of the at least one objective lens is not optimum, wherein reacquiring the image further comprises reacquiring the image using the OCT system having the further adjusted movable arm 106 path length and the adjusted focus.

[0085] In still further embodiments of the present invention adjusting the focus is accomplished manually or automatically based on feedback from an operator or an image quality metric on an acquired image.

[0086] In still further embodiments of the present invention the quality metric is the average or peak brightness of the image.

[0087] Still further embodiments of the present invention provide computer program products for imaging an eye in OCT imaging systems including computer readable storage medium having computer readable program code embodied in said medium. The computer readable program code includes computer readable program code configured to set a target movable arm 106 path length of the OCT system such that the movable arm 106 path length is matched to an eye length of a subject; computer readable program code configured to obtain additional information about the subject relevant to the target movable arm 106 path length; computer readable program code configured to recalibrate the movable arm 106 path length based on the obtained information; computer readable program code configured to automatically adjust the movable arm 106 path length based on the recalibrated movable arm 106 path length; and computer readable program code configured to acquire an image using the OCT system having the adjusted movable arm 106 path length and display the acquired image on an electronic display associated with the OCT system.

[0088] Example embodiments are described above with reference to block diagrams and/or flowchart illustrations of methods, devices, systems and/or computer program products. It is understood that a block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. These computer program instructions may be provided to a image processing module 110 of a general purpose computer, special purpose computer, and/or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the image processing module 110 of the computer and/or other programmable data processing apparatus, create means (functionality) and/or structure for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.

[0089] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions/acts specified in the block diagrams and/or flowchart block or blocks.

[0090] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.

[0091] Accordingly, example embodiments may be implemented in hardware and/or in software (including firmware, resident software, micro-code, etc.). Furthermore, example embodiments may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in connection with an instruction execution system. In the context of this document, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0092] The computer-usable or computer-readable medium may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a random assess memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CD-ROM). Note that the computer-usable or computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0093] Computer program code for carrying out operations of data processing systems discussed herein may be written in a high-level programming language, such as Java, AJAX (Asynchronous JavaScript), C, and/or C++, for development convenience. In addition, computer program code for carrying out operations of example embodiments may also be written in other programming languages, such as, but not limited to, interpreted languages. Some modules or routines may be written in assembly language or even micro-code to enhance performance and/or memory usage. However, embodiments are not limited to a particular programming language. It will be further appreciated that the functionality of any or all of the program modules may also be implemented using discrete hardware components, one or more application specific integrated circuits (ASICs), or a programmed digital signal image processing module 110 or microcontroller.

[0094] The present invention described above, although described functionally or sensibly, may be configured to work in a network environment comprising a computer in communication with one or more devices. The present invention, may be implemented by computer programmable instructions stored on one or more computer readable media and executed by a image processing module 110 of the computer. The computer comprises the image processing module 110, a memory unit, an input/output (I/O) controller, and a display 104 communicating via a data bus. The computer may comprise multiple image processing module 110 s to increase a computing capability of the computer. The image processing module 110 is an electronic circuit which executes computer programs.

[0095] The memory unit, for example, comprises a read only memory (ROM) and a random access memory (RAM). The memory unit stores the instructions for execution by the image processing module 110 . In this invention, the one or more storage devices 114 is the memory unit. For instance, the memory unit stores the reference dataset and the reference ground- truth file. The memory unit may also store intermediate, static and temporary information required by the image processing module 110 during the execution of the instructions. The computer comprises one or more input devices, for example, a keyboard such as an alphanumeric keyboard, a mouse, a joystick, etc. The I/O controller controls the input and output actions performed by a user. The data bus allows communication between modules of the computer. The computer directly or indirectly communicates with the devices via an interface, for example, a local area network (LAN), a wide area network (WAN) or the Ethernet, the Internet, a token ring, or the like. Further, each of the devices adapted to communicate with the computer and may comprise computers with, for example, Sun® image processing modules 110, IBM® image processing modules 110, Intel® image processing module 110, AMD® image processing modules 110, etc.

[0096] The computer readable media comprises, for example, CDs, DVDs, floppy disks, optical disks, magnetic-optical disks, ROMs, RAMs, EEPROMs, magnetic cards, application specific integrated circuits (ASICs), or the like. Each of the computer readable media is coupled to the data bus.

[0097] The foregoing examples have been provided merely for the purpose of explanation and does not limit the present invention disclosed herein. While the invention has been described with reference to various embodiments, it is understood that the words are used for illustration and are not limiting. Those skilled in the art, may effect numerous modifications thereto and changes may be made without departing from the scope and spirit of the invention in its aspects.

[0098] It should also be noted that in some alternate implementations, the functions/acts noted in the blocks may occur out of the order noted in the flowcharts. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Moreover, the functionality of a given block of the flowcharts and/or block diagrams may be separated into multiple blocks and/or the functionality of two or more blocks of the flowcharts and/or block diagrams may be at least partially integrated.

[0099] In the drawings and specification, there have been disclosed exemplary embodiments of the invention. However, many variations and modifications can be made to these embodiments without substantially departing from the principles of the present invention. Accordingly, although specific terms are used, they are used in a generic and descriptive sense only and not for purposes of limitation, the scope of the invention being defined by the following claims.
, Claims:CLAIMS

What is claimed is:
1. An optical coherence tomography (OCT) imaging system for imaging an eye, the system comprising:
an image capturing device 102 having a fixed arm 104 and a movable arm 106, the movable arm 106 encasing a lens and configured for moving in a movable arm 106 path of a predetermined length, the movement of the movable arm 106 path being controlled by a movable arm 106 adjustment module coupled to the fixed arm 104 and wherein the predetermined length covered by the movable arm 106 path is set based on the age of a subject and wherein the movable arm 106 path is running parallel to the patient table;
a receiver adapted to receive an input from the image capturing device 102 based on a plurality of parameters of the image capturing device 102, wherein the input is the fundus image of the patient;
an image analyzing module 108 configured for selecting at least one image of a predetermined quality based on one or more predefined parameters, wherein the quality of each captured image being dynamically analyzed by the image analyzing module 108 based on the one or more predefined parameters;
an image processing module 110 adapted to process a selected image, the processing module configured to:
identify a plurality of indicators throughout the fundus image using a convolutional network;
detect a presence or absence of a retinal disease based the identified indicators using the convolutional network; and
classify a severity of the retinal disease based on the presence or absence of the retinal disease using the convolutional network.

2. The OCT imaging system of claim 1:
wherein a range of the movable arm 106 adjustment module is at least 10 mm;
wherein 10 mm defines an optical path length difference between an eye length of a infant eye and an eye length of an adult eye; and
wherein the movable arm 106 path length is adjusted to accommodate an eye length and an offset between a reference position and a focal plane within the sample of the at least one lens.

3. The OCT imaging system 1000 as claimed in claim 1, wherein the indicator is one of an abnormality, a retinal feature or the like.

4. The OCT imaging system 1000 as claimed in claim 3, wherein the abnormality is one of a lesion, a venous beading, a venous loop, an intra retinal microvascular abnormality, an intra retinal hemorrhage, a micro aneurysm, a soft exudate, a hard exudate, a vitreous/preretinal hemorrhage, neovascularization or the like.

5. The OCT imaging system 1000 as claimed in claim 1, wherein the retinal disease is one of diabetic retinopathy, diabetic macular edema, glaucoma, coloboma, retinal tear, retinal detachment or the like.

6. The OCT imaging system 1000 as claimed in claim 3, wherein the retinal feature is an optic disc, a macula, a blood vessel or the like.

7. The OCT imaging system of claim 1, wherein the movable arm 106 adjustment module is configured to set a target movable arm 106 path length based on additional information pertaining to the subject, the additional information comprising:
a refractive status of the eye of the subject;
measured axial eye length of the subject; and/or
any relevant test results.

8. The OCT system of claim 10, further comprises a fixation target for the subject configured to provide a comfort image to the subject during image acquisition and wherein the fixation target is configured to provide a continuously variable patient comfort image.

9. A method for acquiring and analyzing fundus image for detecting presence of retinal diseases, the method comprising steps of:
setting a target movable arm 106 path length of the OCT system such that the movable arm 106 path length is based on an eye length of a subject;
acquiring fundus image of patient by moving the movable arm 106 path along horizontal path; identifying a plurality of indicators throughout the fundus image using a convolutional network;
detecting a presence or absence of a retinal disease based the identified indicators using the convolutional network; and
classifying a severity of the retinal disease based on the presence or absence of the retinal disease using the convolutional network.

10. The method of claim 9, further comprising steps of:
accessing the image quality of the acquired image; determining if the adjusted movable arm 106 path length is optimum; further adjusting the movable arm 106 path length if it is determined that the adjusted movable arm 106 path length is not optimum; and reacquiring the image using the OCT system having the further adjusted movable arm 106 path length.

Dated this 12th Dec 2022
(Digitally signed)
SUMA K.B.(INPA-1753)
Agent for the Applicant
ARTIFICIAL LEARNING SYSTEMS INDIA PVT LTD.