WO2021250484A1

WO2021250484A1 - System and method to diagnose respiratory diseases in real-time

Info

Publication number: WO2021250484A1
Application number: PCT/IB2021/054208
Authority: WO
Inventors: Parth Chopra; Vimarsh Trehan; Varun Ramamohan; Karan MADAN
Original assignee: Parth Chopra
Priority date: 2020-06-10
Filing date: 2021-05-17
Publication date: 2021-12-16

Abstract

A system to diagnose respiratory disease(s) in real-time is provided. The system includes a data receiving subsystem which receives multiple radiogram images and annotation(s) of a lung area. The system also includes a radiogram-image processing subsystem which extracts a boundary of the lung area and compares with the annotation(s) of the lung area and then generates notification(s) upon detection of a mismatch between the boundary of the lung area and the annotation(s) of the lung area. Further, the system includes a diagnostic subsystem which extracts multiple features from the lung area. The multiple features include at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift, or a combination thereof of the lung area. The diagnostic subsystem also analyzes the multiple features and generates a diagnosis report for the patient(s) to diagnose the respiratory disease(s) in real-time.

Description

SYSTEM AND METHOD TO DIAGNOSE RESPIRATORY DISEASES IN

REAL-TIME

EARLIEST PRIORITY DATE: This Application claims priority from a Complete patent application filed in India having Patent Application No. 202011024378, filed on June 10, 2020 and titled “SYSTEM AND METHOD TO DIAGNOSE RESPIRATORY DISEASES IN REAL-TIME

FIELD OF INVENTION Embodiments of a present invention relate to diagnosing respiratory diseases, and more particularly, to a system and method to diagnose the respiratory diseases in real time.

BACKGROUND

Respiratory disease is a type of disease that affects the lungs and other parts of the respiratory system. The respiratory diseases are mostly related to the lungs of the human body such as asthma, chronic bronchitis, tuberculosis, and the like. There are multiple approaches to diagnose such respiratory diseases. One such approach is to take an X-ray of the chest area of the patient and then analyze the X-ray to check if the patient is suffering from any such respiratory diseases. Conventionally, the X-ray is observed by doctors to check for the respiratory diseases if any which the patient is suffering from.

In one approach, the X-ray of the chest area of the patient is fed to a sophisticated model that uses complex techniques to extract and analyze the multiple features of the X-ray and detect the respiratory diseases which the patient may be suffering from. However, such an approach requires a huge amount of memory and high processing power to store and execute the multiple instructions related to the corresponding complex techniques, thereby making the approach expensive and complex. Also, the doctors working in remote areas, distant villages, and the like where healthcare facilities are minimum cannot use such a sophisticated model to diagnose the respiratory diseases because of the high cost and complexity involved in the approach.

Hence, there is a need for an improved system and method to diagnose respiratory diseases in real-time which addresses the aforementioned issues.

BRIEF DESCRIPTION

In accordance with one embodiment of the disclosure, a system to diagnose one or more respiratory diseases in real-time is provided. The system includes one or more processors. The system also includes a data receiving subsystem operable by the one or more processors. The data receiving subsystem is configured to receive a plurality of radiogram images of a chest area of one or more patients captured via a radiogram image capturing device. The data receiving subsystem is also configured to receive one or more annotations of a lung area from the chest area on the plurality of radiogram images received. The system also includes a radiogram-image processing subsystem operable by the one or more processors. The radiogram-image processing subsystem is configured to extract a boundary of the lung area from the plurality of radiogram images received using a thresholding technique. The radiogram-image processing subsystem is also configured to compare the boundary of the lung area extracted from the plurality of radiogram images received with the one or more annotations of the lung area received. The radiogram-image processing subsystem is also configured to generate one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received. Further, the system includes a diagnostic subsystem operable by the one or more processors. The diagnostic subsystem is configured to extract a plurality of features from the lung area in the plurality of radiogram images processed by the radiogram- image processing subsystem. The plurality of features includes at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift, or a combination thereof of the lung area. The diagnostic subsystem is also configured to analyze the plurality of features using a diagnostic model. The diagnostic subsystem is also configured to generate a diagnosis report for the one or more patients based on an analysis of the plurality of features of the lung area to diagnose the one or more respiratory diseases in real-time. In accordance with another embodiment, a method for diagnosing one or more respiratory diseases in real-time is provided. The method includes receiving a plurality of radiogram images of a chest area of one or more patients captured via a radiogram image capturing device. The method also includes receiving one or more annotations of a lung area on the plurality of radiogram images received. The method also includes extracting a boundary of the lung area from the plurality of radiogram images received using a thresholding technique. Further, the method includes comparing the boundary of the lung area extracted from the plurality of radiogram images received with the one or more annotations of the lung area received. The method also includes generating one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received. Furthermore, the method includes extracting a plurality of features from the lung area in the plurality of radiogram images processed by the radiogram-image processing subsystem, wherein the plurality of features comprises at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift or a combination thereof of the lung area. Further, the method includes analyzing the plurality of features using a diagnostic model. The method also includes generating a diagnostic report for the one or more patients based on an analysis of the plurality of features of the lung area to diagnose the one or more respiratory diseases in real-time.

To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.

BRIEF DESCRIPTION OF THE DRAWINGS

The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which: FIG. 1 is a block diagram representation of a system to diagnose one or more respiratory diseases in real-time in accordance with an embodiment of the present disclosure;

FIG. 2 is a block diagram representation of an exemplary embodiment of the system to diagnose the one or more respiratory diseases in real-time of FIG. 1 in accordance with an embodiment of the present disclosure;

FIG. 3 is a block diagram of a respiratory disease diagnosing computer or a respiratory disease diagnosing server in accordance with an embodiment of the present disclosure; and FIG. 4 is a flow chart representing steps involved in a method for diagnosing one or more respiratory diseases in real-time in accordance with an embodiment of the present disclosure.

Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.

DETAILED DESCRIPTION

For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure. The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.

Embodiments of the present disclosure relate to a system to diagnose one or more respiratory diseases in real-time. The system includes one or more processors. The system also includes a data receiving subsystem operable by the one or more processors. The data receiving subsystem is configured to receive a plurality of radiogram images of a chest area of one or more patients captured via a radiogram image capturing device. The data receiving subsystem is also configured to receive one or more annotations of a lung area from the chest area on the plurality of radiogram images received. The system also includes a radiogram-image processing subsystem operable by the one or more processors. The radiogram-image processing subsystem is configured to extract a boundary of the lung area from the plurality of radiogram images received using a thresholding technique. The radiogram-image processing subsystem is also configured to compare the boundary of the lung area extracted from the plurality of radiogram images received with the one or more annotations of the lung area received. The radiogram-image processing subsystem is also configured to generate one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received. Further, the system includes a diagnostic subsystem operable by the one or more processors. The diagnostic subsystem is configured to extract a plurality of features from the lung area in the plurality of radiogram images processed by the radiogram- image processing subsystem. The plurality of features includes at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift, or a combination thereof of the lung area. The diagnostic subsystem is also configured to analyze the plurality of features using a diagnostic model. The diagnostic subsystem is also configured to generate a diagnosis report for the one or more patients based on an analysis of the plurality of features of the lung area to diagnose the one or more respiratory diseases in real-time.

FIG. 1 is a block diagram representation of a system (10) to diagnose one or more respiratory diseases in real-time in accordance with an embodiment of the present disclosure. The system (10) includes one or more processors (20). In an embodiment, the system (10) herein represents a centralized platform. The system (10) also includes a data receiving subsystem (30) operable by the one or more processors (20). The data receiving subsystem (30) receives multiple radiogram images of a chest area of one or more patients captured via a radiogram image capturing device (40). As used herein, the term “radiogram images” is defined as multiple photographic images produced on a radiosensitive surface by radiation other than visible light such as X-rays or Gamma rays. The multiple radiogram images of the chest area of the one or more patients include the multiple X-ray images. In one embodiment, the radiogram image capturing device (40) includes a portable X-ray apparatus, a mobile X-ray apparatus, a fixed X- ray apparatus, and the like.

In one embodiment, the data receiving subsystem (30) receives multiple radiogram images of a chest area of one or more patients from one or more clinicians upon registration on the centralized platform. In one embodiment, the data receiving subsystem (30) includes a registration subsystem (not shown in FIG. 1). In such embodiment, the registration subsystem registers the one or more clinicians on the centralized platform upon receiving multiple clinician details via a clinician device (50). In such embodiment, the multiple clinician details include a clinician name, a clinician contact number, a clinician email ID, and the like. In such another embodiment, the clinician device (50) includes a mobile phone, a laptop, a tablet, and the like. In one embodiment, the multiple clinician details are stored in a database (not shown in FIG. 1) of the system (10). In one embodiment, the one or more clinicians include one or more doctors, one or more physicians, one or more practitioners, or the like. In one embodiment, the database includes a local database or a cloud database.

The data receiving subsystem (30) also receives one or more annotations of a lung area from the chest area on the multiple radiogram images received. In one embodiment, the data receiving subsystem (30) receives the one or more annotations of the lung area on the multiple radiogram images received from the one or more clinicians. In such embodiment, the one or more annotations include one or more markings on the multiple radiogram images received of a boundary of the lung area.

The system (10) also includes a radiogram-image processing subsystem (60) operable by the one or more processors (20). The radiogram-image processing subsystem (60) is operatively coupled to the data receiving subsystem (30). The radiogram- image processing subsystem (60) extracts the boundary of the lung area from the multiple radiogram images received using a thresholding technique. As used herein, the term “thresholding” is defined as the simplest method of segmenting images in case of digital image processing. From a grayscale image, the thresholding technique can be used to create a binary image representing the segmentation of multiple objects of interest within the corresponding image. In one embodiment, the thresholding technique includes segmentation of the multiple radiogram images received on basis of multiple intensities in a foreground region and a background region of the multiple radiogram images received. In one embodiment, the thresholding technique includes an otsu’s method. As used herein, the term “otsu’s method” refers to a method that is used to perform automatic image thresholding. In one embodiment, the radiogram- image processing subsystem (60) reconstructs and refines the multiple radiogram images received while extracting the boundary of the lung area from the multiple radiogram images received.

The radiogram-image processing subsystem (60) also compares the boundary of the lung area extracted from the multiple radiogram images received with the one or more annotations of the lung area received. The radiogram-image processing subsystem (60) also generates one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received. In one embodiment, the one or more notifications generated include the one or more notifications for recapturing of the multiple radiogram images of the chest area of the one or more patients. In one embodiment, the one or more notifications generated are sent to the one or more clinicians for the one or more clinicians to recapture the multiple radiogram images of the chest area of the one or more patients. In such embodiment, the one or more notifications are sent in form of an email, a message, or the like.

Further, in one embodiment, the radiogram-image processing subsystem (60) includes a radiogram-image masking module (not shown in FIG. 1) which masks the lung area in the multiple radiogram images received using a masking technique based on the one or more annotations received. As used herein, the term “masking” is defined as a process of hiding some portions of an image and to reveal some other portions of the image. In such embodiment, the radiogram-image masking module masks the lung area in the multiple radiogram images received by reveling only a region within the boundary of the lung area and eliminating the region outside of the boundary of the lung area in the multiple radiogram images received using the masking technique.

Further, the system (10) includes a diagnostic subsystem (70) operable by the one or more processors (20). The diagnostic subsystem (70) is operatively coupled to the radiogram-image processing subsystem (60). The diagnostic subsystem (70) extracts multiple features from the lung area in the multiple radiogram images processed by the radiogram- image processing subsystem (60). The multiple features include at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift, or a combination thereof of the lung area. In one embodiment, the multiple features also include at least one of a bottom curvature, a volume, a ratio, an average intensity, a contrast, the average intensity, or a combination thereof of the lung area.

In one embodiment, the diagnostic subsystem (70) extracts the multiple features from the lung area in the multiple radiogram images received using a feature extracting technique. As used herein, the term “feature extracting technique” refers to a type of an image processing technique which is used to detect and isolate multiple desired portions or multiple desired shapes or multiple desired features of a digitized image or a video stream. The feature extracting technique includes an execution of multiple instructions to extract the multiple features from the lung area in the multiple radiogram images received.

The diagnostic subsystem (70) also analyzes the multiple features using a diagnostic model. In one embodiment, the diagnostic model is fed with multiple standardized features of the lung area which are used by the diagnostic model to analyze the multiple features extracted of the lung area in the multiple radiogram images received. In one embodiment, the diagnostic model includes a multistage classification model which executes the multiple instructions to analyze the multiple features extracted. In such embodiment, the diagnostic subsystem (70) classifies the one or more respiratory diseases according to the multiple features extracted. In one embodiment, the one or more respiratory diseases include tuberculosis (TB), pulmonary nodules, interstitial lung disease, cardiopulmonary arrest (CPA), and the like. In one embodiment, the diagnostic subsystem (70) detects for multiple abnormalities associated with the lung area in the multiple radiogram images received of the one or more patients upon analysis of the multiple features including detection of variation in a value associated with each of the multiple features.

The diagnostic subsystem (70) also generates a diagnosis report for the one or more patients based on an analysis of the multiple features of the lung area to diagnose the one or more respiratory diseases in real-time. In one embodiment, the diagnosis report includes a current health status of the one or more respiratory diseases of the one or more patients. In such embodiment, the current health status of the one or more respiratory diseases of the one or more patients includes a currently active status or a healed status. In one embodiment, the diagnostic subsystem (70) also receives a health-related history of the one or more patients, wherein the health-related history of the one or more patients includes information related to the one or more respiratory diseases which the one or more patients may be previously suffering from. In such embodiment, the information includes a severity level of the one or more respiratory diseases, multiple medications taken by the one or more patients, and the like. In one embodiment, the health-related history of the one or more patients is stored in the database of the system (10). Further, the diagnosis report for the one or more patients generated is also stored in the database. Furthermore, in one embodiment, the system (10) includes a health tracking subsystem (not shown in FIG. 1) operable by the one or more processors (20), wherein the health tracking subsystem tracks a respiratory condition of the one or more patients based on the diagnosis report generated over a period of time. In such embodiment, the health tracking subsystem uses a history of diagnosis of the one or more respiratory diseases of the one or more patients to track the respiratory condition of the corresponding one or more patients. In one embodiment, the history of diagnosis of the one or more respiratory diseases refers to the diagnosis report stored in the database over the period of time.

FIG. 2 is a block diagram representation of an exemplary embodiment of the system (10) to diagnose the one or more respiratory diseases in real-time of FIG. 1 in accordance with an embodiment of the present disclosure. The system (10) herein represents the centralized platform configured on the clinician device (50) of the one or more clinicians (80) wherein the clinician device (50) is the laptop. The one or more clinicians (80) have visited a village to diagnose for the one or more respiratory diseases in people of the village. The one or more clinicians (80) uses the system (10) upon registration on the centralized platform. The one or more clinicians (80) captures the multiple radiogram images (85) including the multiple X-ray images of the chest area of the one or more patients (90) visiting the one or more clinicians (80) using the radiogram image capturing device (40) including an X-ray machine.

Further, the one or more clinicians (80) feed the multiple X-ray images captured to the system (10) by scanning the multiple X-ray images via a scanner. The system (10) includes the data receiving subsystem (30) operable by the one or more processors (20). The data receiving subsystem (30) receives the multiple X-ray images. The data receiving subsystem (30) includes the registration subsystem (100) which registers the one or more clinicians (80) upon receiving the multiple clinician details via the clinician device (50). The system (10) includes the database (110) which stores the multiple clinician details. The data receiving subsystem (30) also receives the one or more annotations (115) of the lung area from the chest area on the multiple radiogram images (85) received. Further, the system (10) also includes the radiogram-image processing subsystem (60) operable by the one or more processors (20). The radiogram-image processing subsystem (60) extracts the boundary of the lung area from the multiple radiogram images (85) received using an intensity thresholding technique. The radiogram-image processing subsystem (60) compares the boundary of the lung area extracted from the multiple radiogram images (85) received with the one or more annotations (115) of the lung area received. Initially, the boundary of the lung area extracted from the multiple radiogram images (85) received mismatches with the one or more annotations (115) of the lung area received as the multiple radiogram images (85) received were lacking clarity. Hence, the radiogram-image processing subsystem (60) generated the one or more notifications to be sent to the one or more clinicians (80) to recapture the multiple radiogram images (85) of the chest area of the one or more patients (90).

Further, the multiple radiogram images (85) recaptured are processed again by the radiogram-image processing subsystem (60). The radiogram-image processing subsystem (60) includes the radiogram-image masking module (120) which masks the lung area in the multiple radiogram images (85) received using the masking technique based on the one or more annotations (115) received. Further, the system (10) includes the diagnostic subsystem (70) operable by the one or more processors (20). The diagnostic subsystem (70) extracts the multiple features from the lung area in the multiple radiogram images (115) processed and analyzes the multiple features using a diagnostic model. The diagnostic subsystem (70) generates the diagnosis report for the one or more patients (90) based on the analysis of the multiple features of the lung area to diagnose the one or more respiratory diseases in real-time. The diagnosis report generated is also stored in the database (110).

Further, the diagnostic subsystem (70) also receives the health-related history of the one or more patients (90), wherein the health-related history of the one or more patients (90) includes the information related to the one or more respiratory diseases which the one or more patients (90) may be previously suffering from. The health- related history of the one or more patients (90) is also stored in the database (110). Since the corresponding one or more patients (90) was suffering earlier from the TB and now is suffering from the CPA, the diagnosis report includes current health status for the TB as the healed status and the current health status for the CPA as the currently active status, thereby providing the diagnosis of the one or more respiratory diseases which the corresponding one or more patients (90) are suffering from. Furthermore, the system (10) also includes the health-tracking subsystem (125) operable by the one or more processors (20). The health-tracking subsystem (125) tracks the respiratory condition of the one or more patients (90) based on the diagnosis report generated over a period of time of multiple visits of the corresponding one or more patients (90) to the one or more clinicians (80) till a treatment for the corresponding one or more respiratory diseases is analyzed.

FIG. 3 is a block diagram of a respiratory disease diagnosing computer or a respiratory disease diagnosing server (130) in accordance with an embodiment of the present disclosure. The respiratory disease diagnosing server (130) includes a processor(s) (140), and a memory (150) coupled to a bus (160). As used herein, the processor(s) (140) and the memory (150) are substantially similar to the system (10) of FIG. 1. Here, the memory (150) is located in a local storage device.

The processor(s) (140), as used herein, means any type of computational circuit, such as but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.

Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s) (140).

The memory (150) includes a plurality of subsystems stored in the form of executable program which instructs the processor(s) (140) to perform method steps illustrated in FIG. 3. The memory (150) has following subsystems: a data receiving subsystem (30), a radiogram-image processing subsystem (60), and a diagnostic subsystem (70).

The data receiving subsystem (30) is configured to receive a plurality of radiogram images (85) of a chest area of one or more patients (90) captured via a radiogram image capturing device (40). The data receiving subsystem (30) is also configured to receive one or more annotations (115) of a lung area from the chest area on the plurality of radiogram images (85) received. The radiogram-image processing subsystem (60) is configured to extract a boundary of the lung area from the plurality of radiogram images (85) received using a thresholding technique. The radiogram- image processing subsystem (60) is also configured to compare the boundary of the lung area extracted from the plurality of radiogram images (85) received with the one or more annotations (115) of the lung area received. The radiogram-image processing subsystem (60) is also configured to generate one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations (115) of the lung area received

The diagnostic subsystem (70) is configured to extract a plurality of features from the lung area in the plurality of radiogram images (85) processed by the radiogram-image processing subsystem (60), wherein the plurality of features comprises at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift or a combination thereof of the lung area. The diagnostic subsystem (70) is also configured to analyze the plurality of features using a diagnostic model. The diagnostic subsystem (70) is also configured to generate a diagnosis report for the one or more patients (90) based on an analysis of the plurality of features of the lung area to diagnose the one or more respiratory diseases in real-time.

FIG. 4 is a flow chart representing steps involved in a method (170) for diagnosing one or more respiratory diseases in real-time in accordance with an embodiment of the present disclosure. The method (170) includes receiving multiple radiogram images of a chest area of one or more patients captured via a radiogram image capturing device in step 180. In one embodiment, receiving the multiple radiogram images of the chest area of the one or more patients includes receiving the multiple radiogram images of the chest area of the one or more patients by a data receiving subsystem. In one exemplary embodiment, receiving the multiple radiogram images of the chest area of the one or more patients includes receiving the multiple radiogram images of the chest area of the one or more patients from one or more clinicians upon registration on the centralized platform. In such embodiment, receiving the multiple radiogram images of the chest area of the one or more patients from the one or more clinicians includes the one or more clinicians including one or more doctors, one or more physicians, one or more practitioners or the like.

The method (170) also includes receiving one or more annotations of a lung area on the multiple radiogram images received in step 190. In one embodiment, receiving the one or more annotations of the lung area on the multiple radiogram images received includes receiving the one or more annotations of the lung area on the multiple radiogram images received by the data receiving subsystem. In such embodiment, receiving the one or more annotations of the lung area on the multiple radiogram images received includes receiving the one or more annotations from the one or more clinicians. In one exemplary embodiment, receiving the one or more annotations includes receiving the one or more annotations such as one or more markings on the multiple radiogram images received of a boundary of the lung area.

Furthermore, the method (170) includes extracting the boundary of the lung area from the multiple radiogram images received using a thresholding technique in step 200. In one embodiment, extracting the boundary of the lung area from the multiple radiogram images received includes extracting the boundary of the lung area from the multiple radiogram images received by a radiogram-image processing subsystem.

Furthermore, the method (170) also includes comparing the boundary of the lung area extracted from the multiple radiogram images received with the one or more annotations of the lung area received in step 210. In one embodiment, comparing the boundary of the lung area extracted from the multiple radiogram images received with the one or more annotations of the lung area received includes comparing the boundary of the lung area extracted from the multiple radiogram images received with the one or more annotations of the lung area received by the radiogram-image examination subsystem. Furthermore, the method (170) also includes generating one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received in step 220. In one embodiment, generating the one or more notifications upon detection of the mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received includes generating the one or more notifications upon detection of the mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received by the radiogram-image examination subsystem. In such embodiment, generating the one or more notifications includes generating the one or more notifications such as the one or more notifications for recapturing of the multiple radiogram images of the chest area of the one or more patients. In such another embodiment, generating the one or more notifications includes generating the one or more notifications which are sent to the one or more clinicians in form of an email, a message, or the like.

Furthermore, the method (170) also includes extracting multiple features from the lung area in the multiple radiogram images processed by the radiogram-image processing subsystem, wherein the multiple features comprises at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift or a combination thereof of the lung area in step 230. In one embodiment, extracting the multiple features from the lung area in the multiple radiogram images processed by the radiogram-image processing subsystem includes extracting the multiple features from the lung area in the multiple radiogram images processed by the radiogram-image processing subsystem by a diagnostic subsystem. In one exemplary embodiment, extracting the multiple features from the lung area includes extracting the multiple features from the lung area using a feature extracting technique.

Furthermore, the method (170) also includes analyzing the multiple features using a diagnostic model in step 240. In one embodiment, analyzing the multiple features includes analyzing the multiple features by the diagnostic subsystem. In such embodiment, analyzing the multiple features using the diagnostic model includes analyzing the multiple features using a diagnostic model, wherein the diagnostic model includes a multistage classification model which executes the multiple instructions to analyze the multiple features extracted. Furthermore, the method (170) also includes generating a diagnostic report for the one or more patients based on analysis of the multiple features of the lung area to diagnose the one or more respiratory diseases in real-time in step 250. In one embodiment, generating the diagnostic report for the one or more patients includes generating the diagnostic report for the one or more patients by the diagnostic subsystem. In one embodiment, generating the diagnostic report for the one or more patients includes generating the diagnostic report for the one or more patients, wherein the diagnostic report includes a current health status of the one or more respiratory diseases of the one or more patients. In such embodiment, generating the diagnostic report including the current health status of the one or more respiratory diseases of the one or more patients includes the current health status of the one or more respiratory diseases of the one or more patients including a currently active status or a healed status.

Various embodiments of the system and method to diagnose the one or more respiratory diseases in real-time helps the one or more clinicians to diagnose the one or more respiratory diseases easily without putting much effort. Also, the system enables the one or more patients in remote areas to quickly get the diagnosis the one or more respiratory diseases with the help of the one or more clinicians at a reasonable cost, thereby making the approach more reliable and more efficient.

While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

Claims

I/WE CLAIM:

1. A system (10) to diagnose one or more respiratory diseases in real-time, wherein the system (10) comprises: one or more processors (20); a data receiving subsystem (30) operable by the one or more processors (20), wherein the data receiving subsystem (30) is configured to: receive a plurality of radiogram images (85) of a chest area of one or more patients (90) captured via a radiogram image capturing device (40); and receive one or more annotations (115) of a lung area from the chest area on the plurality of radiogram images (85) received; a radiogram-image processing subsystem (60) operable by the one or more processors (20), wherein the radiogram-image processing subsystem (60) is configured to: extract a boundary of the lung area from the plurality of radiogram images (85) received using a thresholding technique; and compare the boundary of the lung area extracted from the plurality of radiogram images (85) received with the one or more annotations (115) of the lung area received; and generate one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations (115) of the lung area received; and a diagnostic subsystem (70) operable by the one or more processors (20), wherein the diagnostic subsystem (70) is configured to: extract a plurality of features from the lung area in the plurality of radiogram images (85) processed by the radiogram-image processing subsystem (60), wherein the plurality of features comprises at least one of entropy, a homogeneity, a standard deviation of average intensity, a bronchi angle, a tracheal shift or a combination thereof of the lung area. analyze the plurality of features using a diagnostic model; and generate a diagnosis report for the one or more patients (90) based on analysis of the plurality of features of the lung area to diagnose the one or more respiratory diseases in real-time.

2. The system (10) as claimed in claim 1, wherein the data receiving subsystem (30) is configured to receive the plurality of radiogram images (85) of the chest area of the one or more patients (90) from one or more clinicians upon registration on a centralized platform.

3. The system (10) as claimed in claim 1, wherein the radiogram-image processing subsystem (60) comprises a radiogram-image masking module (120) configured to mask the lung area in the plurality of radiogram images (85) received using a masking technique based on the one or more annotations (115) received.

4. The system (10) as claimed in claim 1, wherein the plurality of features comprises at least one of a bottom curvature, a volume, a ratio, an average intensity, a contrast, or a combination thereof of the lung area.

5. The system (10) as claimed in claim 1, wherein the diagnostic subsystem (70) is configured to extract the plurality of features from the lung area in the plurality of radiogram images (85) received using a feature extracting technique.

6. The system (10) as claimed in claim 1, wherein the diagnosis report generated comprises a current health status of the one or more respiratory diseases of the one or more patients (90).

7. The system (10) as claimed in claim 7, wherein the current health status of the one or more respiratory diseases of the one or more patients (90) comprises a currently active status or a healed status.

8. The system (10) as claimed in claim 1, comprises a health-tracking subsystem (125) operable by the one or more processors (20), wherein the health- tracking subsystem (125) is configured to track a respiratory condition of the one or more patients (90) based on the diagnosis report generated over a period of time.

9. A method (170) for diagnosing one or more respiratory diseases in real time, wherein the method (170) comprises: receiving, by a data receiving subsystem, a plurality of radiogram images of a chest area of one or more patients captured via a radiogram image capturing device; (180) receiving, by the data receiving subsystem, one or more annotations of a lung area on the plurality of radiogram images received; (190) extracting, by a radiogram-image processing subsystem, a boundary of the lung area from the plurality of radiogram images received using a thresholding technique; (200) comparing, by the radiogram-image examination subsystem, the boundary of the lung area extracted from the plurality of radiogram images received with the one or more annotations of the lung area received; (210) generating, by the radiogram-image examination subsystem, one or more notifications upon detection of a mismatch between the boundary of the lung area extracted and the one or more annotations of the lung area received; (220) extracting, by a diagnostic subsystem, a plurality of features from the lung area in the plurality of radiogram images processed by the radiogram-image processing subsystem, wherein the plurality of features comprises at least one of a lung entropy, a lung homogeneity, a standard deviation of an average lung intensity, a chest volume, a bronchi angle, a tracheal shift or a combination thereof; (230) analyzing, by the diagnostic subsystem, the plurality of features using a diagnostic model; (240) and generating, by the diagnostic subsystem, a diagnostic report for the one or more patients based on analysis of the plurality of features of the lung area to diagnose the one or more respiratory diseases in real-time (250).

10. The method (170) as claimed in claim 9, wherein receiving the plurality of radiogram images comprises receiving the plurality of radiogram images from one or more clinicians upon registration on a centralized platform.