The present disclosure relates to the field of diagnosis of diabetic foot disease. In particular, the present disclosure provides a system and method for screening and automatic diagnosis of diabetic foot disease.
BACKGROUND
[0002] Background description includes information that may be useful in understanding the present disclosure. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed disclosure, or that any publication specifically or implicitly referenced is prior art. [0003] Diabetes is a chronic condition caused by insulin insufficiency or excess and results in abnormalities of glucose, protein, and lipid metabolism. Diabetes is known to affect both old and the young and is commonly associated with symptoms like increased thirst, polyuria, blurred vision, and weight loss. There can also be serious symptoms such as stupor and coma in advanced stages, which if left untreated can lead to mortality. Besides, unregulated blood glucose level may yield cardiovascular illness, severe neuropathy, retinopathy, nephropathy, osteoporosis, and cancer. Diabetic foot disease is one of the most common consequences of Diabetes Mellitus (DM), and investigations have linked temperature variations of the plantar foot regions to diabetic foot disease. Amputation of the lower extremities can be avoided with early identification and effective treatment. In this context, thermography is a non-invasive imaging approach that enables qualitative analysis and prediction of the disease through visual verification of temperature variations in vascular tissues. [0004] Existing literatures describes a method for automatic detection of inflammation or in patients based on temperature asymmetry estimation by comparing body parts using thermograms and optical images. Another literature presents a method and apparatus for evaluating inflammation in foot of a patient utilizing temperature detection to generate two thermogram images of the sole, each representing continuous two-dimensional temperature profiles and a comparison between the two establishing patterns indicative of inflammation.

Another prior art presents a method and apparatus for diagnosis of abnormalities in the plantar surface of foot of a patient, describing an insole configured to capture thermographic reading of plantar surface of the patient's foot in contact with the insole. Discussions on diabetic foot disease, corresponding pathophysiology, conventional assessments methods, infrared thermography and the different infrared thermography-based CAD analysis methods have been reviewed in another literature. However, none of the disclosed articles present a system configured to perform automatic screening and diagnosis of diabetic foot disease using deep learning technology, the system being configured to be operated by a typical user of non-medical background.
[0005] Hence there is need in the art to develop a system enabled to screen and automatically diagnose diabetic foot disease, thereby generating assessment and prediction results that can be monitored in real-time as well as stored for future use. An automatic diagnosis mechanism of the system has been proposed, the mechanism being configured to be trained by datasets prepared from thermal images of plantar regions of a patient's feet.
OBJECTS OF THE PRESENT DISCLOSURE
[0006] Some of the objects of the present disclosure, which at least one
embodiment herein satisfies are as listed herein below.
[0007] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables one or
more image sensors to detect and capture a first set of images pertaining to left
and right feet of a patient.
[0008] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables
transmission of the first set of images from the one or more sensors to the one or
more processing units through one or more communication networks.
[0009] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that configures the first
set of images to be thermal images.

[0010] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to perform a set of functions and correspondingly generate
a second set of images.
[0011] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to extract a first set of features from the second set of
images.
[0012] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to classify the second set of images based on the first set of
features.
[0013] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to train and validate an automatic diagnosis generation
functionality using deep learning methods.
[0014] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to generate a second set of features corresponding to
detection, diagnosis, analysis and prediction of diabetic foot disease.
[0015] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to receive user inputs pertaining to selection of one or more
functionalities from the one or more input units through the one or more
communication networks.
[0016] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to transmit the received and generated information
pertaining to detection, diagnosis, analysis and prediction of diabetic foot disease
to the one or more output units and the one or more servers.

[0017] It is an object of the present disclosure to provide a method for screening and automatic diagnosis of diabetic foot disease that enables the one or more processing units to perform a sequence of functions pertaining to preprocessing of the received first set of plantar images, training and testing of an automatic diagnosis generation mechanism and performing deduction of severity of diabetic foot disease in a patient.
SUMMARY
[0018] The present disclosure relates to the field of diagnosis of diabetic foot
disease. In particular, the present disclosure provides a system and method for
screening and automatic diagnosis of diabetic foot disease.
[0019] An aspect of the present disclosure is to provide a system for screening
and automatic diagnosis of diabetic foot disease that may enable the system to
include one or more image sensors configured to detect and capture a first set of
images pertaining to left and right feet of a patient.
[0020] In an aspect the system may include one or more processing units
coupled to the one or more sensors through one or more communication networks.
[0021] In an aspect the system may enables transmission of the first set of
images from the one or more sensors to the one or more processing units through
one or more communication networks.
[0022] In an aspect the system may configure the first set of images to be
thermal images.
[0023] In an aspect the one or more processing units may be enabled to
perform a set of functions on the first set of images and correspondingly generate
a second set of images.
[0024] In an aspect the one or more processing units may be enabled to
extract a first set of features from the second set of images.
[0025] In an aspect the one or more processing units may be configured to
classify the second set of images based on the first set of features.

[0026] In an aspect the one or more processing units may be enabled to
perform training and validation of an automatic diagnosis generation functionality
using deep learning methods based on the first set of features.
[0027] In an aspect the one or more processing units may be enabled to
generate a second set of features corresponding to detection, diagnosis, analysis
and prediction of diabetic foot disease after training and validation.
[0028] In an aspect the system may include one or more output units, one or
more input units and one or more servers coupled to the one or more processing
units through the one or more networks.
[0029] In an aspect the one or more processing units may be enabled to
receive user inputs pertaining to selection of one or more functionalities from the
one or more input units.
[0030] In an aspect the one or more processing units may be enabled to
transmit the received and generated information pertaining to detection, diagnosis,
analysis and prediction of diabetic foot disease to the one or more output units and
the one or more servers.
[0031] An aspect of the present disclosure is to provide a method for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to perform a sequence of functions pertaining to
preprocessing of the received first set of plantar images, training and testing of an
automatic diagnosis generation mechanism and performing deduction of severity
of diabetic foot disease in a patient.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
[0032] The accompanying drawings are included to provide a further understanding of the present disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0033] The diagrams described herein are for illustration only, which thus are not limitations of the present disclosure, and wherein:

[0034] FIG. 1 illustrates exemplary network architecture of the proposed system for screening and automatic diagnosis of diabetic foot disease (100), to elaborate upon its working in accordance with an embodiment of the present disclosure.
[0035] FIG. 2 illustrates exemplary functional blocks (200) of the processing unit of the proposed system for screening and automatic diagnosis of diabetic foot disease (100), in accordance with an embodiment of the present disclosure. [0036] FIG. 3 illustrates exemplary dataflow (300) in the proposed system for screening and automatic diagnosis of diabetic foot disease (100), in accordance with an embodiment of the present disclosure.
[0037] FIG. 4 illustrates exemplary functional steps (400) of the proposed method for screening and automatic diagnosis of diabetic foot disease, in accordance with an embodiment of the present disclosure.
DETAILED DESCRIPTION
[0038] In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details. [0039] If the specification states a component or feature "may", "can", "could", or "might" be included or have a characteristic, that particular component or feature is not required to be included or have the characteristic. [0040] As used in the description herein and throughout the claims that follow, the meaning of "a," "an," and "the" includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of "in" includes "in" and "on" unless the context clearly dictates otherwise.
[0041] While embodiments of the present invention have been illustrated and described in the accompanying drawings, the embodiments are offered only in as much detail as to clearly communicate the disclosure and are not intended to limit the numerous equivalents, changes, variations, substitutions and modifications

falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0042] The present disclosure relates to the field of diagnosis of diabetic foot disease. In particular, the present disclosure provides a system and method for screening and automatic diagnosis of diabetic foot disease.
[0043] FIG. 1 illustrates exemplary network architecture of the proposed system for screening and automatic diagnosis of diabetic foot disease (100), to elaborate upon its working in accordance with an embodiment of the present disclosure.
[0044] In an embodiment, the system for screening and automatic diagnosis of diabetic foot disease (100) (interchangeably known as the system (100), herewith) may include one or more image sensors (102) configured to detect and capture images of plantar regions of patient's right and left foot. The one or more image sensors (102) may pertain to thermal cameras that may be configured to operate in the electromagnetic spectrum of infrared frequencies. The one or more image sensors (102) may pertain to any or a combination of short-wavelength, mid-wavelength and long-wavelength, active infrared, passive infrared, cryogenic, non-cryogenic cameras and the likes. The range of frequencies of operation may be predefined. The one or more image sensors (102) may be enabled to detect temperature variations in the vascular system of the plantar foot regions and correspondingly generate a first set of images. The first set of images may pertain to image formats such as, joint photographic experts' group format, portable graphics format, tag image file format, bitmap image file, encapsulated postscript and the like.
[0045] In an embodiment, the system (100) may include one or more processing units (104) that may be communicatively coupled to the one or more image sensors (102) The one or more processing units (104) may be configured to receive the first set of images from the one or more image sensors (102). The first set of images may pertain to a first set of features. By way of example the first set of features may include but not limited to resolution, color gradient, intensity, depth, texture, shapes, points, edges, luminance, contrast and the likes. The one or

more processing units (104) may be configured to perform a set of functions on the received first set of images.
[0046] In an embodiment, the set of functions may non-limitingly pertain to pre-processing of the first set of images, derivation of a second set of images from the first set of pre-processed images, extraction of the first set of features from the second set of images, classification of the second set of images based on the extracted features, training of an automatic diagnosis generation functionality by the second set of images and derivation of a second set of features from the second set of images after validating the trained automatic diagnosis generation functionality. The one or more processing units (104) may generate the diagnosis and transmit the diagnosis for real-time monitoring, storage, sharing and the likes. [0047] In an embodiment, the system (100) may include one or more output units (108) communicatively coupled to the one or more processing units (104). The one or more output units (1008) may be configured to receive information pertaining to the first and the second set of images, the first and the second set of features of the images, diagnosis, analysis and predictions about the detected diabetic foot disease determined by the one or more processing units (104) and correspondingly generate a set of output signals corresponding to the information in real-time. By way of example, the one or more output units (108) may include computer monitors, handheld PD devise, smart phones, Tablet Cs, liquid crystal displays, light emitting diode displays, flashing indicators, scrolling indicators, speakers, woofers, vibratory motors and the likes. In an exemplary embodiment, the output signals may pertain to any or a combination of visual, audible and vibratory responses. The one or more output units (108) may enable viewing, downloading, sharing, printing of the information by authorized personnel, the patient, medical professionals and the likes.
[0048] In an embodiment, the system (100) may include one or more input units (110) that may be communicatively coupled to the one or more processing units (104). The one or more input units (110) may be configured to receive user inputs pertaining to selection of one or more functionalities of the one or more processing units (104). The one or more functionalities of the one or more

processing units (104) that may be configured to be controlled by user inputs may correspond to any or a combination of detection, diagnosis, analysis, prediction, sharing, viewing and storage of the information received and generated by the one or more processing units (104). By way of example, the one or more input units (110) may include but may not be limited to tact keys, touch keys, keypads, touchpads, touch panels, joysticks, sliding switches, rotary switches, on-off switches and the likes.
[0049] The system (100) may include one or more servers (112) communicatively coupled to the one or more processing units (104), the one or more servers (112) being configured to receive the information received and generated by the one or more processing units (104) from the one or more processing units (104) and correspondingly store information for future use. The one or more servers may be accessed by authorized personnel, patients, medical professionals and researchers. Information stored in one or more servers (112) may be used for study and research of diabetic foot disease, referral of the patient for treatment, determination of statistics related to diabetic foot disease and the likes. By way of example, the one or more servers (112) may include computers, computing devices, smart phones, tablets, industrial assets, mainframes, and the likes.
[0050] In an embodiment, the system (100) may include one or more networks (106) coupled to the one or more sensors (102), the one or more processing units (104), the one or more output units (108), the one or more input units (110) and the one or more servers (112). The one or more networks (106) may be enabled to transmit one or more sets of data packets from the one or more processing units (104) to the one or more output units (108), the one or more processing units (104) to the one or more servers (112) and from the one or more sensors (102) and the one or more input units (110) to the one or more processing units (104). The one or more networks (112) may be configured to be unidirectional or bidirectional. In an exemplary embodiment, the one or more networks (112) may be a wireless network, a wired network or a combination thereof that can be implemented as any or a combination of the different types of

networks, such as Intranet, Local Area Network (LAN), Wide Area Network (WAN), Internet, GSM, 3G, 4G, 5G and the likes. Further, the one or more networks (112) may either be a dedicated network or a shared network. The shared network may represent an association of the different types of networks that may use variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like.
[0051] FIG. 2 illustrates exemplary functional blocks (200) of the processing unit of the proposed system for screening and automatic diagnosis of diabetic foot disease (100), in accordance with an embodiment of the present disclosure. [0052] As illustrated in an embodiment, the one or more processing units (104) may include one or more processor(s) (202). The one or more processor(s) (202) may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the one or more processor(s) (202) may be configured to fetch and execute computer-readable instructions stored in a memory (204) of the processing unit (108). The memory (204) may store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service. The memory (204) may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like.
[0053] In an embodiment, one or more processing units (104) may also include interface(s) (206). The interface(s) (206) may include a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) (206) may facilitate communication of the processing unit (104) with various devices including but not limited to networking hardware, one or more output units (108), one or more input units (110), one or more sensors (102), one or more servers (112) and portable mass storage devices and the likes coupled to the one or more processing

units (104). The interface(s) (206) may also provide a communication pathway for one or more components of the one or more processing units (104). Examples of such components include, but are not limited to, processing engine(s) (208), memory (204) and database (220).
[0054] In an embodiment, the processing engine(s) (208) may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) (208). In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) (208) may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine(s) (208) may include a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) (208). In such examples, the one or more processing units (104) can include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the one or more processing units (104) and the processing resource. In an embodiment, the processing engine may be implemented an Internet-of-things based engine. In other examples, the processing engine(s) (208) may be implemented by electronic circuitry. A database (222) may include information that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) (208).
[0055] In an embodiment, the processing engine (208) may include an image capturing unit (210) that may be configured to receive the first set of images from the one or more image sensors (102), the first set of images pertaining to plantar foot regions of the patient. The first set of images may be in digital format that may be computer readable. The one or more processors (202) may be configured

to perform image capturing using the one or more image sensors (102) pertaining to internet of things technology.
[0056] In an embodiment, the one or more processors (202) may include an image processing unit (212) that may be configured to process the received first set of images. The first set of images may be segmented into one or more polygonal sections, the one or more polygonal sections being used to separate one or more healthy and diabetic plantar foot regions. A second set of images may be generated by assembling the segmented first set of images using one or more predefined techniques. The second set of images may pertain to a first set of features that may be used in further processing of the second set of images and generation of a diagnosis.
[0057] In an embodiment, the one or more processors (202) may include a comparison unit (214) that may be enabled to extract the first set of features from the second set of images. The first set of features may be predetermined. The first set of features may be compared with a reference set of features by the one or more processors (202) and correspondingly the one or more processors (202) may be configured to generate a set of classifiers. The reference set of features may be stored in the database (22), operatively coupled to the one or more processors (202). The reference set of features may also be updated with generation of new second set of images from a variety of patients.
[0058] In an embodiment, the one or more processors (202) may include a classification unit (216) that may perform classification of the second set of images based on first set of features and correspondingly preparing datasets corresponding to training and testing of the automatic diagnosis generation functionality, pertaining to detection of presence and severity of diabetic foot disease.
[0059] In an embodiment, the one or more processors (202) may include an analysis unit (218) that may be enabled to perform training and testing of the automatic diagnosis generation functionality of the processing engine (208). Training and testing may be performed by deep learning techniques. Deep learning techniques may be implemented by any or a combination of supervised,

semi-supervised, unsupervised learning, neural networks, convolutional neural networks, recurrent networks, reinforcement learning and the likes. The training datasets may be used to train the automatic diagnosis generation functionality and he testing datasets prepared from the second set of images may be tested and validated against the training dataset using the automatic diagnosis generation functionality implemented by deep learning techniques. After validation, a second set of features may be derived that may indicate any or a combination of the diagnosis, analysis and predictions pertaining to the severity of the disease in the patient, progression, courses of treatment, expected timelines of recovery. The second set of features may include but not be limited to correlation between pixels, scaling, translation, rotation, corners, SIFT features, FAST features, distances between points of interest, cluster positions, geometry and the likes. [0060] In an embodiment, the processing engine (208) may include other units (218) that may be configured to that may be configured to implement functionalities that supplement actions performed by the one or more processors (202). In an exemplary embodiment, such actions may include transmission of the first and the second set of images, the first and the second set of features, training and he testing datasets, and the diagnosis, analysis and predictions from the one or more processors (202) to the one or more servers (112) and the one or more output units (08), user inputs from the one or more input units (110) to the one or more processors (202) and the first set of images from the one or more image sensors (102) to the one or more processors (202), auto calibration of the one or more image sensors (102) and the likes.
[0061] FIG. 3 illustrates exemplary dataflow (300) in the proposed system for screening and automatic diagnosis of diabetic foot disease (100), in accordance with an embodiment of the present disclosure.
[0062] In an embodiment, the system (100) may include one or more image sensors (102) configured to capture a set of images of plantar region of feet of a patient, the set of images being transmitted to one or more processing units (104) through one or more communication networks (not shown). The one or more processing units (104) may be enabled to perform training and testing of an

automatic diagnosis generation functionality pertaining to diabetic foot disease using the set of images. The one or more processing units (104) may be configured to transmit the diagnosis and analysis of the set of images and a set of features extracted from the set of images to one or more output units (108) and one or more servers (112) based on user inputs received by one or more input units (not shown).
[0063] FIG. 4 illustrates exemplary functional steps (400) of the proposed method for screening and automatic diagnosis of diabetic foot disease, in accordance with an embodiment of the present disclosure.
[0064] In an embodiment, the method (400) may include a step of (402) that may pertain to receiving at the one or more processors (202) a first set of images from the one or more image sensors (102), wherein the first set of images pertain to right and left feet of a patient and wherein the first set of images correspond to thermal images. Step (404) may pertain to performing at the one or more processors, segmentation of the received first set of images, the segmentation of the first set of images corresponding to one or more polygonal sections. The one or more polygonal sections may be used to separate one or more healthy and diabetic plantar foot regions. In step (406) the one or more processors (202) may perform assembling of the segmented first set of images into a second set of images, the second set of images pertaining to predetermined size. The assembled second set of images may be processed using one or more predefined techniques and the processed second set of images may be used to obtain a first set of features pertaining to detection of diabetic foot disease.
[0065] In an embodiment, step (408) may pertain to extracting and classifying the first set of features from the second set of images at the one or more processors (202), the first set of features being predefined in nature. Classification of the second set of images based on first set of features may pertain to preparation of one or more datasets. The one or more datasets may correspond to training and testing of an automatic diagnosis generation functionality pertaining to diagnosis of diabetic foot disease.

[0066] In an embodiment, training and testing the automatic diagnosis generation functionality at the one or more processors may be performed in step (410) using the prepared one or more datasets. The training datasets may be used to train the automatic diagnosis generation functionality which may be further used to validate the testing dataset of second set of images in comparison to the training datasets. Step (412) may pertain to determination at the one or more processors, a second set of features from the second set of images. The second set of features may be obtained after validating the testing dataset of the second set of images, the second set of features being predetermined in nature. The second set of features may be used to perform any or a combination of detection, diagnosis, analysis and prediction of diabetic foot disease of the patient. In step (414) the one or more processors may be enabled to transmit the information pertaining to the first and the second set of features, the first and the second set of images, the one or more datasets and the generated diagnosis, analysis and predictions corresponding to diabetic foot disease of the patient to one or more output units (108) and one or more servers (112) based on user inputs received by the one or more input units (110).
[0067] As used herein, and unless the context dictates otherwise, the term "coupled to" is intended to include both direct coupling (in which two elements that are coupled to each other contact each other) and indirect coupling (in which at least one additional element is located between the two elements). Therefore, the terms "coupled to" and "coupled with" are used synonymously. Within the context of this document terms "coupled to" and "coupled with" are also used euphemistically to mean "communicatively coupled with" over a network, where two or more devices are able to exchange data with each other over the network, possibly via one or more intermediary device.
[0068] The terms, descriptions and figures used herein are set forth by way of illustration only. Many variations are possible within the spirit and scope of the subject matter, which is intended to be defined by the following claims and their equivalents in which all terms are meant in their broadest reasonable sense unless otherwise indicated.

[0069] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
ADVANTAGES OF THE INVENTION
[0070] The present disclosure provides a system for screening and automatic
diagnosis of diabetic foot disease that enables one or more image sensors to detect
and capture a first set of images pertaining to left and right feet of a patient.
[0071] The present disclosure provides a system for screening and automatic
diagnosis of diabetic foot disease that enables transmission of the first set of
images from the one or more sensors to the one or more processing units through
one or more communication networks.
[0072] The present disclosure provides a system for screening and automatic
diagnosis of diabetic foot disease that configures the first set of images to be
thermal images.
[0073] The present disclosure provides a system for screening and automatic
diagnosis of diabetic foot disease that enables the one or more processing units to
perform a set of functions and correspondingly generate a second set of images.
[0074] It is an object of the present disclosure to provide a system for
screening and automatic diagnosis of diabetic foot disease that enables the one or
more processing units to extract a first set of features from the second set of
images.
[0075] The present disclosure provides a system for screening and automatic
diagnosis of diabetic foot disease that enables the one or more processing units to
classify the second set of images based on the first set of features.
[0076] The present disclosure provides a system for screening and automatic
diagnosis of diabetic foot disease that enables the one or more processing units to

train and validate an automatic diagnosis generation functionality using deep learning methods.
[0077] The present disclosure provides a system for screening and automatic diagnosis of diabetic foot disease that enables the one or more processing units to generate a second set of features corresponding to detection, diagnosis, analysis and prediction of diabetic foot disease.
[0078] The present disclosure provides a system for screening and automatic diagnosis of diabetic foot disease that enables the one or more processing units to receive user inputs pertaining to selection of one or more functionalities from the one or more input units through the one or more communication networks. [0079] The present disclosure provides a system for screening and automatic diagnosis of diabetic foot disease that enables the one or more processing units to transmit the received and generated information pertaining to detection, diagnosis, analysis and prediction of diabetic foot disease to the one or more output units and the one or more servers.
[0080] The present disclosure provides a system for screening and automatic diagnosis of diabetic foot disease that enables the one or more processing units to perform a sequence of functions pertaining to preprocessing of the received first set of plantar images, training and testing of an automatic diagnosis generation mechanism and performing deduction of severity of diabetic foot disease in a patient.

We Claim:

1. A system for screening and automatic diagnosis of diabetic foot disease, the system comprising:
one or more image sensors (102) configured to capture a first set of images corresponding to any or a combination of right and left feet of a patient, wherein the first set of images pertain to electromagnetic images, the electromagnetic images pertaining to infrared range of frequencies;
one or more processing units (104) communicatively coupled to the one or more image sensors (102), wherein the one or more processing units (108) comprise one or more processors associated with a memory, the memory storing instructions executable by the one or more processors and configured to:
receive the first set of images from the one or more image sensors (102);
perform segmentation of the first set of images; assemble the segmented first set of images into a second set of images, the second set of images pertaining to predetermined size;
extract and classify a first set of features from the second set of images, wherein the classification of the second set of images pertain to preparation of one or more datasets, wherein the one or more datasets correspond to training and testing datasets;
perform training and testing of an automatic diagnosis generation functionality using the prepared one or more datasets, wherein the training datasets are used to train the automatic diagnosis generation functionality and the testing datasets are used to validate the automatic

diagnosis generation functionality in comparison to the training datasets based on the first set of features;
determine a second set of features from the second set of images, wherein the second set of features are obtained after validating using the testing dataset of the second set of images, wherein the second set of features are predetermined in nature and wherein the second set of features are used to perform any or a combination of detection, diagnosis, determination of severity of diabetic foot disease;
transmit a set of data packets pertaining to the first and the second set of features, the first and the second set of images and the one or more datasets for monitoring, analysis and storage;
one or more output units (108) communicatively coupled to the one or more processing units (104), wherein the one or more output units are configured to receive the set of data packets from the one or more processing units (104) and correspondingly perform any or a combination of functions comprising viewing, downloading, printing and sharing of the set of data packets;
one or more input units (110) communicatively coupled to the one or more processing units (104), wherein the one or more input units are configured to receive user inputs pertaining to selection of one or more functionalities of the one or more processing units (104), wherein the user inputs are transmitted from the one or more input units to the one or more processing units;
one or more servers (112) communicatively coupled to the one or more processing units (104), wherein the one or more servers (112) are configured to receive the set of data packets from

the one or more processing units (104) and correspondingly store the set of data packets for future use;
one or more networks (106) coupled to the one or more sensors (102), the one or more processing units (104), the one or more output units (108) the one or more input units (110) and the one or more servers (112), wherein the one or more networks (106) are enabled to transmit the set of data packets from the one or more processing units (104) to the one or more output units (108) and the one or more servers (112) and from the one or more sensors (102) and the one or more input units (110) to the one or more processing units (104).
2. The system (100) as claimed in claim 1, wherein the segmentation of the first set of images correspond to one or more polygonal sections, the one or more polygonal sections being used to separate one or more healthy and diabetic plantar foot regions.
3. The system (100) as claimed in claim 1, wherein the warped second set of images are processed using one or more predefined techniques wherein processing pertains to extraction of predetermined nonlinear set of features facilitating detection of diabetic foot disease.
4. The system (100) as claimed in claim 1, wherein the classification of the second set of images is based on first set of features, wherein the first set of features are predefined in nature and wherein the prepared datasets correspond to training and testing of the automatic diagnosis generation functionality, wherein the automatic diagnosis generation functionality facilitates automatic diagnosis of presence and severity of diabetic foot disease.
5. The system (100) as claimed in claim 4, wherein the training datasets are used to train the automatic diagnosis generation functionality using deep learning methods.
6. The system (100) as claimed in claim 1, wherein the one or more output units are configured to The system (100) as claimed in claim 1, wherein

the one or more sensors (102) are enabled to detect the one or more networks (104), for communication, wherein the one or more networks (104) pertain to any or a combination of wired and wireless interfaces with the one or more sensors (102) and the one or more processing units (108).
7. The system (100) as claimed in claim 1, wherein the one or more functionalities of the one or more processing units (104) configured to be controlled by user inputs pertain to any or a combination of detection, diagnosis, analysis, prediction, sharing, viewing and storage of information received and generated by the one or more processing units (104).
8. A method for early screening of diabetic foot disease, the method comprising steps of:
receiving at the one or more processors a first set of images from the one or more image sensors (102), wherein the first set of images pertain to right and left feet of a patient and wherein the first set of images correspond to thermal images;
performing at the one or more processors segmentation of the received first set of images; wherein the segmentation of the first set of images correspond to one or more polygonal sections, the one or more polygonal sections being used to separate one or more healthy and diabetic plantar foot regions;
assembling the segmented first set of images into a second set of images, the second set of images pertaining to predetermined size, wherein the assembled second set of images are processed using one or more predefined techniques, and wherein the processed second set of images are used to obtain a set of features pertaining to detection of diabetic foot disease;
extracting and classifying a first set of features from the second set of images at the one or more processors, wherein the first set of features are predefined in nature and wherein the classification of the second set of images based on first set of

features pertain to preparation of one or more datasets, wherein the one or more datasets correspond to training and testing of an automatic diagnosis generation functionality pertaining to diagnosis of diabetic foot disease;
training and testing the automatic diagnosis generation functionality at the one or more processors using the prepared one or more datasets, wherein the training datasets are used to train the automatic diagnosis generation functionality and the testing datasets are used to validate in comparison to the training datasets;
determining at the one or more processors a second set of features from the second set of images, wherein the second set of features are obtained after validating the testing dataset of the second set of images, wherein the second set of features are predetermined in nature and wherein the second set of features are used to perform any or a combination of detection, diagnosis, analysis and prediction of diabetic foot disease of the patient;
transmitting by the one or more processors information pertaining to the first and the second set of features, the first and the second set of images and the one or more datasets to one or more output units (108) and one or more servers (112) based on user inputs received by the one or more input units (110), wherein the information are transmitted as digital data packets through the one or more networks (106).