FIELD OF THE INVENTION
The instant invention relates to the field of radiotherapy application. In particular, the current disclosure relates to a system and method for performing safety evaluation during radiotherapy delivery. The system employs artificial intelligence such as neural network rained module to identify/recognise, track exact location of target tissue region of a patient in more expedient, cost effective, reliable, and user-friendly manner.

BACKGROUND OF THE INVENTION
Radiotherapy (RT, RTx, or XRT) is a known medical procedure where one or more ionizing radiation doses are delivered on malignant cells (tumour like diseases). However, during this procedure the surrounding healthy cells are likely to be affected as the high radiation rays and the internal affected cells/tumour are not visible. Therefore, various modern medical devices such as CT scan, MRI scan are used to know/understand location of the malignant cells/tumours.

Conventionally, the anatomical images are acquired and compared with planned image of the patient. Then the patient’s position is aligned as per the planned image to know the exact location of target region. Still there the exact location of the target region may not always be traced due to internal organ movement or breathing of the patient. A list of prior arts as far as known to the applicants is elaborated herein below.

WO2022182681A2 elaborates a method for identifying a patient target region in which Positron emission tomography (PET) image of the patient are analysed. However, the risk of affecting the surrounding healthy cell cannot be fully avoided.

US9511243B2 elaborates a patient safety system using optical tracking (computed tomography treatment-simulation scan) in a linear accelerator treatment platform to prevent gross setup errors. However, there is no protection mechanism for the surrounding healthy cell.

JP2021522886A elaborates application of machine learning models integrated with radiography technique for the generation and optimization of radiotherapy dose. However, this method/system does not disclose how to trace exact location of the patients’ target region.

US20150306340A1 elaborates monitoring system and method for virtual reality medical application in which the patient is positioned for a predetermined medical mission. However, this machine fails show how to trace exact location for radiotherapy delivery.

In view of above limitations, there is a further need to develop an advance technique/mechanism for identifying exact location of the tumours or cancerous cells while delivering the d=radiation dose with the help of artificial intelligence such as neural network trained model so that the risk of damaging the surrounding tissues can be easily eliminated.

However, all the radiotherapy system and method have certain limitations with respect to target location tracing, a further desire arises to invent with an improved radiotherapy system and method which would in turn address variety of radiotherapy treatment issues including but not limited to, elimination of human assumption or manual inspection, identifying target tissues, delivering radiation beams exactly on the target regions in more reliable, cost effective, expedient, and user-friendly manner. Moreover, it is required to invent a system and method for performing safety evaluation during radiotherapy delivery, which will cover all the advantages/benefits of the conventional/existing techniques/methodologies and overcome the deficiencies/disadvantages of such techniques/methodologies.

OBJECT OF THE INVENTION
It is an objective of the proposed technology to automate target cell tracking/recognizing operation in radiotherapy delivery procedure.

It is another objective of the proposed technology to evaluate risk associated with the identified target.

It is one more objective of the proposed technology to minimize possibility of damaging the surrounding healthy tissue.

It is a further objective of the current invention to develop a system and method performing safety evaluation during radiotherapy delivery so that corrective measures/action can be taken before delivering radiotherapy.

SUMMARY OF THE INVENTION
In one embodiment or aspect, the present invention provides a system for performing safety evaluation during radiotherapy delivery on a patient body. The system comprises a radiation source; an image sensor; an image analysing control unit; and a cloud server. The radiation source is arranged around a patient be to deliver one or more type of rays on a target tissue region of the patient laying on the patient bed. The image sensor is adapted to acquire anatomical images of the target tissue region of the patient laying on the patient bed. The image analysing control unit is in wireless communication with the image sensor. The cloud server comprises a neural network trained module being in wireless communication with image analysing control unit. The neural network trained module embedded in the cloud server is configured to: define coordinates of the target tissue regions based on various health characteristics of the patient; acquire the anatomical images of the target tissue regions in one or more directions/orientations; deploy a deep neural trained model onto the anatomical images to find all possibilities of positioning of the target tissue regions; and compare the possible positioning of the target tissue regions with the defined coordinates of similar target tissue regions; compute a safety score associated with identified/traced positioning of the target tissue.

In other embodiment/aspect, the proposed invention provides method for performing safety evaluation during radiotherapy delivery on a patient body. The method comprising steps of: defining coordinates of target tissue regions based on various health characteristics of the patient; laying the patient on the patient bed around which a radiation source is arranged to deliver one or more type of rays on a target tissue region of the patient; acquiring, by an image sensor, anatomical images of the target tissue regions in one or more directions/orientations; deploying, by an image analysing control unit being in wireless communication with the image sensor, a deep neural trained model onto the anatomical images to find all possibilities of positioning of the target tissue regions, wherein a cloud server having embedded therein a neural network trained module being in wireless communication with image analysing control unit; comparing, by the image analysing control unit, the possible positioning of the target tissue regions with the defined coordinates of similar target tissue regions; computing a safety score associated with identified/traced positioning of the target tissue.

Other embodiment/aspect, benefits, and noticeable features of the proposed disclosure becomes clear to the skilled artisans from the following detailed description, that delineate the present invention in different embodiments.

BRIEF DESCRIPTION OF DRAWINGS
The multiple features, embodiments or aspects, and technical effects of the proposed system and method may become better understood when the following detailed description is read with reference to the accompanying figures or drawings.

Fig. 1 is a schematic diagram illustrating construction of the system for performing safety evaluation during radiotherapy delivery on a target patient body, according to an exemplary embodiment of the present disclosure.

Fig. 2 shows various method steps employed for performing safety evaluation during radiotherapy delivery on a target patient body, according to an exemplary embodiment of the present disclosure.

LIST OF REFERENCE NUMERALS
100 radiation source
102 radiation ray/beam shaping unit
200 patient bed
300 image sensor
400 image analysing control unit
500 cloud server

DETAILED DESCRIPTION OF THE INVENTION
Multiple embodiments discussed herein are intended only for explanatory purpose and subject to many variations. It may be noted that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient; however, are intended to include/cover the application or implementation without departing from the scope of the proposed system and method. Also, it is may be noted that the phraseology and terminology used herein is for the purpose of explanation and should not be considered as limiting.

The use of words “including,” “comprising,” or “having” and variations thereof herein are meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Moreover, the words “an” and “a” herein do not denote a limitation of quantity; however, rather indicate the presence of at least one of the referenced items. Furthermore, the words “at least one” and “one or more” herein are used to indicate one minimum number of components/features to be essentially proposed in the invention.

According to an aspect of the current disclosure, as shown in Fig. 1, system for performing safety evaluation during radiotherapy delivery on a patient body is depicted. The system comprises a radiation source (100); an image sensor (300); an image analysing control unit (400); and a cloud server (500). The radiation source (100) is arranged around a patient bed (200) to deliver one or more type of rays on a target tissue region of the patient laying on the patient bed (200). The image sensor (300) is adapted to acquire anatomical images of the target tissue region of the patient laying on the patient bed (200). The image analysing control unit (400) is in wireless communication with the image sensor (300). The cloud server (500) comprises a neural network trained module being in wireless communication with image analysing control unit (400).

According to an aspect of the current disclosure, the neural network trained module embedded in the cloud server (500) is configured to: defining coordinates of the target tissue regions based on various health characteristics of the patient; acquiring the anatomical images of the target tissue regions in one or more directions/orientations; deploying a deep neural trained model onto the anatomical images to find all possibilities of positioning of the target tissue regions; and comparing the possible positioning of the target tissue regions with the defined coordinates of similar target tissue regions; computing a safety score associated with identified/traced positioning of the target tissue.

According to an aspect of the current disclosure, the radiation source (100) comprises a ray/beam shaping unit (102).

According to an exemplary aspect of the current invention, the image sensor (300) is configured to capture all types rays such as alpha particles, gamma rays, beta particles, and neutron radiation.

According to an exemplary aspect of the current invention, the deep neural trained model is configured to update its database in synchronization with the cloud server.

According to an exemplary aspect of the current invention, the radiation source is adapted to kill tumour/cancerous cells.

According to an exemplary aspect of the current invention, the image analysing control unit (400) is a computing device having memory, processor, and display/screen.

According to an exemplary aspect of the current invention, the image sensor (300) is configured to acquire positron emission tomography images.

According to an exemplary aspect of the current invention, the system is designed to trace exact location of the target tumour/cancerous tissue.

According to an embodiment of the current invention, as shown in Fig. 2, the method system for performing safety evaluation during radiotherapy delivery on a patient body is depicted. The method employs a radiation source (100); an image sensor (300); an image analysing control unit (400); and a cloud server (500).

In an exemplary embodiment, the method comprises a step (S1) of defining coordinates of target tissue regions based on various health characteristics of the patient.

In an exemplary embodiment, the method comprises a step (S2) of laying the patient on the patient bed (200) around which a radiation source (100) is arranged to deliver one or more type of rays on a target tissue region of the patient.

In an exemplary embodiment, the method comprises a step (S3) of acquiring, by an image sensor (300), anatomical images of the target tissue regions in one or more directions/orientations.

In an exemplary embodiment, the method comprises a step (S4) of deploying, by an image analysing control unit (400) being in wireless communication with the image sensor (300), a deep neural trained model onto the anatomical images to find all possibilities of positioning of the target tissue regions, wherein a cloud server (500) having embedded therein a neural network trained module being in wireless communication with image analysing control unit (400).

In an exemplary embodiment, the method comprises a step (S5) of comparing, by the image analysing control unit (400), the possible positioning of the target tissue regions with the defined coordinates of similar target tissue regions.

In an exemplary embodiment, the step (S6) of computing a safety score associated with identified/traced positioning of the target tissue.

In an exemplary embodiment, the target coordinate defining step (S2) comprises sample database associated with positioning of various internal organs of healthy and unhealthy human body.

In an exemplary embodiment, the method comprises steps of the method comprises a step of predicting possibilities of damaging surrounding healthy cells.

The proposed invention (method and system) provides the following technical effects over the known/prior arts including but not limited to:

• Automates target locating/identifying/tracking steps in radiotherapy delivery procedure.
• Displaying safety score so that surgeons/doctors can take appropriate decision to trace the target tissue regions in the patient body.
• Minimizing risk associated with healthy tissue damage.
• Neural network trained module gets updated automatically to get improved results.
• Simple structure, user-friendly, and cost effective.

The aforesaid disclosure of exemplary aspects of the current disclosure have been elaborated for purpose of explanation and description. They are not intended to be exhaustive or to limit the proposed invention to the precise forms disclosed, and obviously many modifications and variations may be possible in light of the above teaching. The exemplary embodiments are selected and detailed in order to explain the underlying mechanism of the proposed invention and its practical application, to thereby enable the skilled artisans to best utilize the invention and various aspects with various improvements or modifications as are suited to the particular use contemplated.

We claim:

1. A system for performing safety evaluation during radiotherapy delivery on a patient body, the system comprising:
a radiation source (100) arranged around a patient bed (200) to deliver one or more type of rays on a target tissue region of the patient laying on the patient bed (200);
an image sensor (300) adapted to acquire anatomical images of the target tissue region of the patient laying on the patient bed (200);
an image analysing control unit (400) being in wireless communication with the image sensor (300); and
a cloud server (500) having embedded therein a neural network trained module being in wireless communication with image analysing control unit (400),
characterised in that
the neural network trained module embedded in the cloud server (500) is configured to:
define coordinates of the target tissue regions based on various health characteristics of the patient;
acquire the anatomical images of the target tissue regions in one or more directions/orientations;
deploy a deep neural trained model onto the anatomical images to find all possibilities of positioning of the target tissue regions; and
compare the possible positioning of the target tissue regions with the defined coordinates of similar target tissue regions;
compute a safety score associated with identified/traced positioning of the target tissue.

2. The system for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 1, wherein the radiation source (100) comprises a ray/beam shaping unit (102).

3. The system for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 1, wherein the image sensor (300) is configured to capture all types rays such as alpha particles, gamma rays, beta particles, and neutron radiation.

4. The system for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 1, wherein the deep neural trained model is configured to update its database in synchronization with the cloud server.

5. The system for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 1, wherein the radiation source is adapted to kill tumour/cancerous cells.

6. The system for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 1, wherein the image analysing control unit (400) is a computing device having memory, processor, and display/screen.

7. The system for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 1, wherein the image sensor (300) is configured to acquire positron emission tomography images.

8. A method system for performing safety evaluation during radiotherapy delivery on a patient body, the method comprising steps of:
defining (S1) coordinates of target tissue regions based on various health characteristics of the patient;
laying (S2) the patient on the patient bed (200) around which a radiation source (100) is arranged to deliver one or more type of rays on a target tissue region of the patient;
acquiring (S3), by an image sensor (300), anatomical images of the target tissue regions in one or more directions/orientations;
deploying (S4), by an image analysing control unit (400) being in wireless communication with the image sensor (300), a deep neural trained model onto the anatomical images to find all possibilities of positioning of the target tissue regions, wherein a cloud server (500) having embedded therein a neural network trained module being in wireless communication with image analysing control unit (400);
comparing (S5), by the image analysing control unit (400), the possible positioning of the target tissue regions with the defined coordinates of similar target tissue regions;
computing (S6) a safety score associated with identified/traced positioning of the target tissue.

9. The method for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 8, wherein the target coordinate defining step (S2) comprises sample database associated with positioning of various internal organs of healthy and unhealthy human body.

10. The method for performing safety evaluation during radiotherapy delivery on a patient body as claimed in claim 8, wherein the method comprises a step of predicting possibilities of damaging surrounding healthy cells.