A method and a system for performing medical diagnostic analysis

Abstract

A method for performing a medical diagnostic analysis may include capturing, by an imaging device, a plurality of images of an anatomical region of a subject, wherein the plurality of images is displayed on a User Interface (UI) of a display unit along with a plurality of pre-stored reference images, each reference image being assigned one or more diagnostic values associated with a plurality of characteristics and a classification score. Receiving, the one or more diagnostic values associated with the plurality of characteristics and the classification score for each image amongst the plurality of captured images based on a user comparison with the plurality of pre-stored reference images. Generating, by a generation engine, a summary output that indicates a severity classification. Displaying, by the display unit, one or more recommended actions based on the severity classification and the classification score.

Description

[0001] A METHOD AND A SYSTEM FOR PERFORMING MEDICAL DIAGNOSTIC ANALYSIS

[0002] FIELD

[0003] 1. The present invention relates generally to the medical field. More specifically, the present invention relates to a method and a system for performing a medical diagnostic analysis in various screen-and-treat or screen-triage-treat settings around the world for various types of pre-cancer, cancer, or any other type of medical abnormality, whereby the process is made more objective, efficient, reliable, and informative.

[0004] BACKGROUND

[0005] 2. Abnormal growth of potential precancerous cells in the cervix exhibits certain morphologic features that can be identified during a screening or triage exam, in which the cervix (as well as the vagina and vulva) is viewed, either with the naked eye, or through the magnified views of a colposcope / camera. Acetic acid (and, perhaps, iodine) solutions may be applied to the surface of the cervix to improve visualization of specific abnormal growths.

[0006] 3. Virtually all cervical pre-cancer lesions become a transient and opaque white color with the application of 3-5% acetic acid. The whitening process (also referred to as “aceto-whitening”) occurs over time and is visible to the naked eye (or with the assistance of a low-level magnification). Thus, the individual performing the exam is able to subjectively discriminate between abnormal and normal tissue.

[0007] 4. They are guided in this discrimination by using the Swede scoring system, which looks at five characteristics of the cervix noted during the procedure - 1 ) density of acetic acid uptake,

[0008] 2) margin and surface of the lesion,

[0009] 3) characteristics of blood vessels,

[0010] 4) size of the lesion, and

[0011] 5) result of the application of Lugol’s iodine. Each characteristic is given a score from 0 - 2 based on its nature. Considered a standard practice, International Agency For Research On Cancer (IARC) has published reference images on what the different cervical characteristics would look like. The final score, which is a sum of the scores from all five characteristics, can aid in the diagnosis of the cervix’s pathological state. However, it is advised that other factors, such as the patient’s age, screening results, etc. be taken into consideration in making the final diagnosis. Management of the treatment for cervical pre-cancer or cancer, which depends on the setting and resources available, involves either immediate treatment if there is concern the patient may not return for a follow-up visit, or biopsy to confirm the precancer. Treatment itself must consider important factors about the patient, her medical history, and state of cervical disease. Due to the subjective nature of the visual-based examination, however, the accuracy of the final assessment has been found to be highly dependent upon the medical personnel’s experience and expertise. The World Health Organization (WHO) and IARC have presented a set of guidelines by which management and treatment should be considered in various settings. This includes 7 potential approaches to screening and treating patients for cervical pre-cancer / cancer. These involve combinations of the use of human papillomavirus (HPV) testing, cytology, Visual Inspection with Acetic Acid (VIA), Visual Inspection with Lugol’s Iodine (VILI) and colposcopy.

[0012] 9. However, confidently making management decisions depends on a variety of factors that may not be duly considered in practice. This may lead to loss of valuable follow-up for a patient, as well as a lack of understanding on the reasons for a particular management decision when looking back at a patient case.

[0013] 10. This problem is only exacerbated when the examination takes place in a part of the world that has little medical training and may not have anyone other than a technician available to perform the procedure and make crucial management decisions.

[0014] SUMMARY

[0015] 11. Embodiments of the present invention disclose a method for performing a medical diagnostic analysis. According to some embodiments, the method includes the steps of: capturing, by an imaging device, a plurality of images of an anatomical region of a subject, wherein the plurality of images is displayed on a User Interface (UI) of a display unit along with a plurality of pre-stored reference images, each reference image being assigned one or more diagnostic values associated with a plurality of characteristics and a classification score; receiving, via an input means, the one or more diagnostic values associated with the plurality of characteristics and the classification score for each image amongst the plurality of captured images based on a user comparison with the plurality of pre-stored reference images; generating, by a generation engine, a summary output based on the received one or more diagnostic values, wherein the summary output indicates a severity classification; and displaying, by the display unit, one or more recommended actions based on the severity classification and the classification score. According to some embodiments, the method further includes receiving an input on the UI from the user to select a diagnostic protocol amongst a plurality of diagnostic protocols; and receiving on the UI, comprehensive patient information comprising demographic data, medical history data, risk factor data, previous diagnostic results, current medications and treatments, relevant physiological parameters, and contraindications for specific diagnostic procedures. According to some embodiments, the method further includes generating, by the generation engine, a summary comprising information associated with the subject, the one or more diagnostic values associated with each characteristic for each image, the classification score for each image and an associated description, and the summary output for displaying on the display unit. According to some embodiments, the medical diagnostic analysis is applicable to detection and classification of abnormalities in any anatomical region of the subject. According to some embodiments, the plurality of characteristics comprises one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed. According to some embodiments, the diagnostic values associated with each characteristic amongst the plurality of characteristics and the classification score comprises a standardized range of numerical values. According to some embodiments, generating the summary output includes applying a weighted scoring algorithm to the one or more diagnostic values to generate a weighted score; comparing the weighted score against a predetermined threshold for each characteristic; and determining the severity classification based on the comparison. According to some embodiments, the one or more recommended actions are displayed on the UI in the form of one or more interactive elements that display specific information associated with each action upon a user interaction. According to some embodiments, the method further includes analyzing the plurality of images using one or more computer vision techniques to generate the one or more diagnostic values; and displaying the one or more diagnostic values alongside the plurality of pre- stored reference images. According to some embodiments, the method further includes storing the plurality of images, the one or more received diagnostic values, and the summary output in a secure database; tracking changes in the one or more diagnostic values over a period of time; and generating a trend analysis report based on the tracked changes. According to some embodiments, the method further includes integrating data from a plurality of imaging modalities; correlating the integrated data with the plurality of pre-stored reference images; and generating a composite diagnostic score based on the correlation. According to some embodiments, the recommended actions are automatically generated based on the severity classification; the classification score; one or more patient-specific risk factors; and one or more standard medical protocols. Embodiments of the present invention disclose a system for performing medical diagnostic analysis. According to some embodiments, the system includes an imaging device configured to capture a plurality of images of an anatomical region of a subject, wherein the plurality of images is displayed on a UI of a display unit along with a plurality of pre-stored reference images, each reference image being assigned one or more diagnostic values associated with a plurality of characteristics and a classification score; an input means configured to receive the diagnostic values associated with the plurality of characteristics and the classification score for each image amongst the plurality of images based on user comparison with the plurality of pre- stored reference images; a generation engine configured to generate a summary output based on the received diagnostic values, wherein the output indicates a severity classification; and the display unit configured to display one or more recommended actions based on the severity classification and the classification score. The objects and advantages of the embodiments will be realized and achieved at least by the elements, features, and combinations particularly pointed out in the claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 25. Non-limiting examples of embodiments of the disclosure are described below with reference to figures attached hereto that are listed following this paragraph. Identical features that appear in more than one figure are generally labeled with the same label in all the figures in which they appear. A label indicating an icon representing a given feature of an embodiment of the disclosure in a figure may be used to reference the given feature. Dimensions of features shown in the figures are chosen for convenience and clarity of presentation and are not necessarily shown to scale.

[0017] 26. The subject matter regarded as the invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. The invention, however, both as to organization and method of operation, together with objects, features and advantages thereof, may best be understood by reference to the following detailed description when read with the accompanied drawings. Embodiments of the invention are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like reference numerals indicate corresponding, analogous or similar elements, and in which;

[0018] 27. FIG. 1A-1D are images of a number of pages for receiving comprehensive patient information, according to some embodiments;

[0019] 28. FIG. 2 is an image depicting a number of images being displayed along with a number of pre- stored reference images for a comparison, according to some embodiments; 29. FIG. 3 is an image depicting a summary page including a number of images that may previously be labeled with a score, according to some embodiments.

[0020] 30. FIG. 4 is a flow diagram of an algorithm selected by a user amongst a number of algorithms, according to some embodiments;

[0021] 31. FIG. 5 is a flow diagram, elaborating a process of performing a medical diagnostic analysis, according to some embodiments;

[0022] 32. FIG. 6 shows a high-level block diagram of a system configured to perform a medical diagnostic analysis, according to some embodiments; and

[0023] 33. FIG. 7 is a flow diagram of a method for performing a medical diagnostic analysis, according to some embodiments.

[0024] 34. It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn accurately or to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity, or several physical components may be included in one functional block or element. Further, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.

[0025] DETAILED DESCRIPTION

[0026] 35. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those skilled in the ail that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, and components, modules, units and / or circuits have not been described in detail so as not to obscure the invention. Some features or elements described with respect to one embodiment may be combined with features or elements described with respect to other embodiments. For the sake of clarity, discussion of same or similar features or elements may not be repeated. Although embodiments of the invention are not limited in this regard, discussions utilizing terms such as, for example, “processing”, “computing”, “calculating”, “determining”, “establishing”, “analyzing”, “checking”, or the like, may refer to operation(s) and / or process(es) of a computer, a computing platform, a computing system, or other electronic computing device, that manipulates and / or transforms data represented as physical (e.g., electronic) quantities within the computer's registers and / or memories into other data similarly represented as physical quantities within the computer's registers and / or memories or other information non-transitory storage medium that may store instructions to perform operations and / or processes. Although embodiments of the invention are not limited in this regard, the terms “number” and “a number” as used herein may include, for example, “multiple” or “two or more”. The terms “number” or “a number” may be used throughout the specification to describe two or more components, devices, elements, units, parameters, or the like. The term set when used herein may include one or more items. Unless explicitly stated, the method embodiments described herein are not constrained to a particular order or sequence. Additionally, some of the described method embodiments or elements thereof can occur or be performed simultaneously, at the same point in time, or concurrently. Embodiments of the present invention disclose a system and a method for performing medical diagnostic analysis. The present invention addresses a number of concerns regarding variabilities present in screening and treating pre-cancer and cancer (cervical, oral, etc.) as well as other types of medical abnormalities, in the form of a software-controlled tool to assist an individual or a user performing a procedure to not only follow a preferred set of process steps, but subsequently be guided through grading of a tissue lesion against a set of relevant reference images. The user may be better informed of a number of management options available and recommended based on procedural data captured, a controlled and guided assessment, and comprehensive patient information entered into the system, all backed by one or more most recent guidelines from an authoritative health organization such as the WHO. As mentioned above, a lack of guided flow and authoritative references readily available in practice and in a field have been found to lead to a lack of confidence in a final decision as well as a less accurate assessment of a tissue in question, which essentially may be any tissue for which abnormality may be discriminated via some form of detection (e.g., images, scans, spectra, etc.). Here, a case for images captured of a cervical tissue is described in more detail. A unique software and guided flow of the present invention, as described in detail below, enforces standardization, consistency, and presentation with a fuller context, encouraging a more holistic decision-making process in a highly user-friendly manner so that images that convey important diagnostic characteristics of tissue may be more accurately assessed and may be more reliably used to make crucial management and follow-up decisions. In particular, using the present invention, a user (which is a medical personnel) may be guided through recording comprehensive patient information about a patient related to the medical procedure. Examples of the comprehensive patient information may include, but are not limited to, demographic data, medical history data, risk factor data, previous diagnostic results, current medications and treatments, relevant physiological parameters, and contraindications for specific diagnostic procedures. In a specific embodiment, the comprehensive patient information may further include a previous history of screening / disease / treatment, any and all screening test results, an HIV status, a pregnancy status, parity, contraception methods, a LMP, a menstruation length and cycle, any medications, allergies as illustrated in FIG. 1A-1D. Further, FIG. 1A-1D illustrate a questionnaire to be filled by the user by providing the comprehensive patient information as the input. The questionnaire may be displayed on a screen including a number of fields to be answered by selecting the field and / or filling in the information in the field. In an embodiment, the user may choose to skip any screen by clicking “Next” without entering any information as not each field has to be answered in order to proceed. The user may enter one or more new questions in the form of new entries. The user may add new options for existing entries, for example, the user may add new fields pertaining to medication and / or allergies to input additional patient information. Furthermore, based on available facilities, the user or administrator may select the most appropriate set of algorithms, or workflows, recommended by the WHO (or any other authoritative health organization) that pertain to their setting. In a preferred embodiment, the user may select an algorithm amongst a number of algorithms, recommended by an authoritative health organization such as the WHO before the procedure. The workflows may be presented to the user on a display unit of the system, allowing the user to select the most relevant workflow(s) before starting procedures. In an exemplary embodiment, if a medical clinic / hospital routinely applies HPV tests, then the user may choose to follow WHO’s fifth algorithm, that involves an HPV DNA primary screen, followed by an enhanced visual inspection with the system disclosed in the present invention, followed by a treatment or an appropriate follow-up based on a severity of an abnormality or a lesion that is detected. Upon choosing the workflow, the system may present the workflow to the user after a procedure to aid in the user’s consideration of followup, as well as for record-keeping. In an embodiment, a workflow may be established for a given organization. Subsequently, the user may be guided through a defined image capture process that aligns with typical colposcopic procedures, (or typical oral cancer screening procedures, e.g., if an oral cancer screening is being carried out), with images specifically captured pre and post application of acetic acid as well as after an application of Lugol’s iodine, if available. Depending on the procedure, other kinds of medical data may otherwise be collected, such as spectral data. Upon a capturing of a number of images of an anatomical region of the patient, the user may be taken to an ‘impressions’ page whereby the user may be guided one- by-one through selecting individual attributes for each of a number of characteristics, as referred in FIG. 2. In a preferred embodiment, the number of characteristics may be five. Examples of the number of characteristics may include, but are not limited to, one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed. The one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed may relate to an acetic acid uptake, margins / surface of lesion, vasculature, lesion size, and Lugol’s iodine uptake. In order to make the scoring as accurate as possible, the user may be presented with the number of images captured during the procedure alongside a number of prestored reference images. The number of pre-stored reference images may be what a cervix would look like for each score. The score may be 0, 1, or 2 for each characteristic (acetic acid uptake, margins / surface of lesion, vasculature, lesion size, and Lugol’s iodine uptake). In an exemplary embodiment, when scoring for acetic acid uptake, the user is shown images captured by the system specifically at a step during which acetic acid is applied. Alongside the number of images, the user may see the number of pre-stored reference images of what a cervix with a particular’ score for acetic acid uptake may look like. When scoring for a vasculature, the user may be shown one or more images amongst the number of images captured by the system before an application of the acetic acid, in form of one or both of one or both of white light and green light (Narrow Band Imaging) images, of which a Narrow Band Imaging (NBI) image is known to give a better contrast for determining vasculature patterns.

[0027] Similarly, the user may enter a classification score that may pertain to a Transformation Zone (TZ) type where the TZ type refers to a visibility of the Transformation Zone in the cervix. The Transformation Zone of the cervix is the area where squamous and glandular cells meet. The TZ type may be a score from 1 - 3, against the number of images and the number of pre-stored reference images. In one embodiment, given a reference set of data, the system may automatically suggest to the user a severity grade based on the relevant procedural data captured. In one embodiment of the present invention, before scoring, the user may be asked for a general assessment. The general assessment may include at least one question. An example of the at least one question may include, but is not limited to, “is the exam adequate or inadequate? If the answer is “inadequate”, the user may enter why it’s inadequate.

[0028] The user may be taken to a ‘summary’ page, as shown in FIG. 3, which may show results of the Swede score as a final score, presented with an appealing and an intuitive visual that may be colored based on a severity of the individual characteristic scores. The summary page may include a number of images that may previously be labeled with a score. A total score may be provided along with a description that indicates the total score’s level of severity of a patient. In addition, the summary page may include a score and description of additional features such as the Transformation Zone type; The summary page may further display an observation associated with each characteristic amongst a number of characteristics, related to a score by the user for each image. The number of characteristics may include an acetic acid uptake, margins / surface of lesion, vasculature, lesion size, and Lugol’s iodine uptake. A clear presentation, such as a table may display the score for each characteristic, as well as a final score that may be a sum of the individual characteristics’ scores. Explanation of what the final score may mean pathologically may also be given. The TZ type along with the comprehensive patient information received earlier may be presented as well. In this way, the user may have a comprehensive view of the patient. Going through the flow and viewing a summary representation on the summary page may significantly assist the user diagnosing the severity and from this, to make a decision about the follow-up or the treatment. In one embodiment, the user may be allowed to select “Suspected Cancer” and if selected, it may appear in the summary page. While described for a cervical pre-cancer screening procedure, the system may be applied to other types of screening or triage procedures where medical data captured (at distinctly defined steps or at once) is referenced against a set of authoritative reference images (or spectra, etc.) representing different grades of abnormality related to the tissue and / or features of interest (at those distinctly defined steps if captured as such). In one embodiment, when considering an appropriate follow-up or treatment, the user may then be presented with the workflow selected earlier along with a number of management options as a flow diagram where the most appropriate portion of the flow is highlighted as referred in FIG. 4. The number of management options may be displayed on a separate page that may appear after the summary page. Subsequently, only one of a Negative, Positive, or Suspected cancer flow may be highlighted. In an exemplary embodiment, if the Swede score is high, the portion of the flow that shows one or more next steps when the case is determined to be “positive” may be highlighted. This may include making a decision about whether the patient is eligible for ablation or not as shown in Table 1 below, which may inform a kind of treatment to be applied. The portion of the flow that is automatically highlighted may be informed by a number of factors with the most important being the final calculated score. The portion of the flow may also be informed by a predicted score of severity from a machine learning model trained on a number of cervical images (or oral images, etc.) against a gold standard ground truth with known test characteristics.

[0029] Table 1 shows eligibility criteria for ablation Within the highlighted portion of the flow, subsequent “one or more interactive elements” may be clickable, which either present the user with more information about the one or more interactive elements or may serve to record in the system for the patient a decision made by the user for the treatment or the follow-up. The one or more interactive elements may be “bubbles” that the user is able to click. In an exemplary embodiment, the user may click on an interactive element amongst the one or more interactive elements. For example, the user may click on the interactive element “Eligible for treatment (ablation)”, which is also a decision that needs to be made if the test is positive. A pop-up may appear explaining one or more eligibility requirements to consider when using ablation as a method of treatment. To that understanding, if the user then decides to proceed with an ablative treatment, the user may click on “treatment” as another interactive element where the user may be provided with more information about the treatment, including instruments to use and how to perform the treatment. If the user confirms the treatment, by for example clicking on “Perform treatment” interactive element, this may automatically get recorded in a report for future reference. In an embodiment, upon clicking other interactive elements amongst the one or more interactive elements such as “Evaluation for further management”, the user may enter more information as free text that is saved in a final report. To that understanding, aside from eligibility information, information related to selections (e.g., clicks) made by the user may be recorded as part of a management decision in the final report, shown by highlighting that specific path in FIG. 4. The entire workflow including the highlighted portion, along with the summary, the number of images, and the final treatment or the follow-up decided on by the user may be recorded in the final report for the procedure. The report, along with the number of images, may be saved on a device as well as on a secure, HIPAA- compliant cloud storage base. Again, while described for cervical pre-cancer screening procedures, the above follow-up or treatment flow may be presented to the user based on the appropriate procedure carried out (e.g., oral cancer screening). The scoring flow described may be completed by the user either on the device at a point of care, or later, on a separate internet browser which the user is logged into with system credentials. In some embodiments, the user may be guided by one or more audio prompts in addition to a visual guidance that is provided. In particular, the one or more audio prompts may include feedback that is given to the user in real time, where depending on what the user clicks (or speaks to the software to perform), there is auditory feedback from the system confinning their selection and at appropriate times suggesting next steps. The entire summary presented visually to the user at the completion of a procedure may also be accompanied by a voice summarizing the information and suggesting the next steps. In another embodiment, the user may simply upload relevant medical data, that may have been captured previously with another device, to the system including the scoring flow with a set of reference images or data to help guide the user in assessing the degree of abnormality and subsequent recommended follow-up based on the set of uploaded medical data. The set of reference images may be the number of prestored reference images. The entire process of scoring against the number of pre-stored reference images and being presented with all relevant information may together serve to enable the user, especially if the user is less experienced, to become much more proficient, efficient, and accurate in grading the severity of the presented case and in determining the appropriate follow-up or treatment. The comprehensive nature of the information saved in the above flow may also assist in improving the accuracy of the final assessment that may be made by a remote user (e.g., doctor), who can also more easily understand the decisions made by the attending doctor given a fuller context. Reference is made to FIG. 5, showing a flow-diagram, elaborating on a process of performing a medical diagnostic analysis, according to some embodiments, including the following steps:

[0030] According to some embodiments, the input means of the system may be configured to receive an input on the UI from a user (5005). The input may be to select a diagnostic protocol amongst a number of diagnostic protocols. Upon a selection of the diagnostic protocol, the input means may be configured to receive comprehensive patient information related to the patient (5010). The input may be received on the UI. Examples of the comprehensive patient information may include, but are not limited to, demographic data, medical history data, risk factor data, previous diagnostic results, current medications and treatments, relevant physiological parameters, and contraindications for specific diagnostic procedures. Upon receiving the comprehensive patient information, the imaging device may be configured to capture a number of images of an anatomical region of a subject (5015). The subject may be a patient. The number of images may be utilized to determine the presence or absence of the pre-cancerous / cancerous cells in the patient. The number of images may be displayed on a User Interface (UI) of a display unit along with a number of pre- stored reference images (5020). Each reference image may be assigned one or more diagnostic values associated with a number of characteristics and a classification score. Examples of the number of characteristics may include, but are not limited to, one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed. The one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed may relate to an acetic acid uptake, margins / surface of lesion, vasculature, lesion size, and Lugol’s iodine uptake. Subsequently, the one or more diagnostic values associated with each characteristic amongst the number of characteristics and the classification score may include a standardized range of numerical values. In this example in which the reference is to a Swede Score system, the standardized range of numerical values may be 0, 1, or 2, for each characteristic in the Swede Score system. The total Swede Score may be in the range of 0 to 10. The classification score may be derived from a standard medical classification system specific to the anatomical region being analyzed. Furthermore, the classification score may be categorized into a number of categories. Examples of the number of categories may include, but are not limited to, a completely ectocervical (common under hormonal influence) category, an endocervical component but fully visible (common before puberty) category, and an endocervical component not fully visible (common after menopause) category. Each category may be referred to as a Transmission Zone (TZ) type category. The number of images may include images that may be characterized based on the one or more diagnostic values and images that may be ranked based on classification score.

[0031] In an embodiment, where the number of images is being analyzed to determine the presence or absence of the pre-cancerous / cancerous cells related to cervical cancer, the one or more diagnostic values may be the Swede Score which is a summation of the individual characteristic scores. The number of images may be compared to the number of pre- stored reference images for the medical diagnostic analysis.

[0032] Moving forward, the system may be configured to receive the diagnostic values associated with the number of characteristics and the classification score for each image amongst the number of images (5025). The diagnostic value and the classification score for each image may be based on a user comparison of the number of images with the number of pre-stored reference images. The system may be configured to prompt the user to compare each image with the number of prestored reference images. Based on the comparison, the system may be configured to provide a score for each image in terms of the one or more diagnostic values and the classification score.

[0033] In an embodiment, while comparing the number of patient images with the number of pre- stored reference images, the user determines that one of the number of patient images is similar to one of the number of pre-stored reference images. The diagnostic value associated with the pre-stored reference images is used. In another embodiment, the user selects a classification score which displays the number of pre-stored reference images associated with that classification score, which the user then compares to the patient images. If the user determines that the patient images are similar to the pre- stored reference image from the number of pre- stored reference images, the classification score is recorded. The user may continue to select classification score until the user determines that the pre-stored reference images from the number of pre- stored reference images is similar to the patient images. In an exemplary embodiment, upon comparing, the user may input the diagnostic value and the classification score for each image via an input means. The user may score each image based on a similarity between each image and at least one prestored reference image amongst the number of pre-stored reference images. In one embodiment, the controller may be configured to analyze the number of images using one or more computer vision techniques to generate the one or more diagnostic values. The display unit may display the one or more diagnostic values alongside the number of pre- stored reference images (5030). Subsequently, the system may be configured to generate a summary output based on the received diagnostic values (5035). The system may generate the summary output by applying a weighted scoring algorithm to the one or more diagnostic values to generate a weighted score. Upon applying the weighted scoring algorithm to the one or more diagnostic values, the system may be configured to compare the weighted score against a predetermined threshold for each characteristic. Upon comparing the weighted score against the predetermined threshold for each characteristic, the system may be configured to determine the severity classification based on the comparison. The output may indicate a severity classification. The severity classification may indicate the presence of the pre-cancerous / cancerous cells when the weighted score ranges between 5-10. The severity classification may indicate the absence of the pre-cancerous / cancerous cells when the weighted score is ranging between 0-4. The display unit may be configured to display one or more recommended actions based on the severity classification and the classification score (5040). The one or more recommended actions may be displayed on the UI in the form of one or more interactive elements that display specific information associated with each action upon a user interaction. The one or more recommended actions may be automatically generated based on the severity classification, the classification score, one or more patient-specific risk factors, and one or more standard medical protocols. The one or more recommended actions may be a rescreening in a number of years with an imaging test, an ablation treatment, or an evaluation, biopsy and further management. The rescreening may be recommended when the weighted score is between 0-4. The ablation treatment may be recommended when the weighted score is between 5-6. The evaluation, biopsy and further management may be recommended when the weighted score is between 7- 10. To that understanding, the system may further be configured to generate a summary (5045). The summary may include information associated with the patient, the diagnostic values associated with each characteristic for each image, the classification score for each image, and the summary output. The display unit may be configured to display the information associated with the patient, the diagnostic values associated with each characteristic for each image, the classification score for each image, and the summary output on the display unit (5050). In one embodiment, the summary may be displayed upon receiving a request for generating and displaying the summary via the input means. In another embodiment, the summary may be generated and displayed automatically once the one or more recommended actions are displayed on the display unit. Furthermore, the system may be configured to store the number of images, the one or more received diagnostic values, and the summary output in a secure database. Further, the system may be configured to track changes in the one or more diagnostic values over a period of time and generate a trend analysis report based on the tracked changes. In one embodiment where it is determined that the pre-cancerous / cancerous cells are present in the patient and the pre-cancerous / cancerous cells are related with cervical cancer, the system may be configured to integrate data from a number of imaging modalities including, but not limited to, visual imaging, spectroscopic analysis, fluorescence imaging, optical coherence tomography, ultrasound imaging, thermography, and confocal microscopy. The system may further correlate the integrated data with the plurality of pre-stored reference images using Bayesian fusion algorithms. To that understanding, the system may generate a composite diagnostic score based on the correlation, with modality- specific confidence weighting., Reference is made to FIG. 6, showing a high-level block diagram of a system 600 configured to perform a medical diagnostic analysis of a patient according to some embodiments of the present invention. The medical diagnostic analysis may be applicable to a detection and a classification of abnormalities in any anatomical region of the patient. Specifically, the medical diagnostic analysis may be performed to determine whether pre-cancerous / cancerous cells are present in the patient or not. The pre-cancerous / cancerous cells may be associated with at least one type of cancer from a number of types of cancers. Examples of the number of types of cancers, may include, but are not limited to, cervical cancer, oral cancer, and HPV. The system may be configured to utilize a number of images of an anatomical region of the patient to determine whether the pre-cancerous / cancerous cells are present in the patient or not. The system may be configured to further recommend one or more actions based on whether the one or more pre- cancerous / cancerous cells is present or not in the patient. As shown, the system may include a computing device 605, and an imaging device 650. The computing device 605 may include a controller 610, an operating system 615, a memory 620, an executable code 625, an input means 630, output devices 635, a generation engine 640, and a display unit 645. The computing device 605 may include a controller 610 that may be, for example, a central processing unit processor (CPU), a chip or any suitable computing or computational device. The controller 610 (or one or more controllers or processors, possibly across multiple units or devices) may be configured (e.g., by executing software or code) to carry out methods described herein, and / or to execute or act as the various modules, units, etc. More than one computing device 605 may be included in, and one or more computing devices may be, or act as the components of a system according to some embodiments of the invention.

[0034] The operating system 615 may be or may include any code segment (e.g., one similar to the executable code described herein) designed and / or configured to perform tasks involving coordination, scheduling, arbitration, supervising, controlling or otherwise managing operation of the computing device 605; for example, scheduling execution of software programs or enabling software programs or other modules or units to communicate. The operating system 615 may be a commercial operating system, e.g., Android or iOS.

[0035] The memory 620 may be or may include, for example, a Random- Access Memory (RAM), a read only memory (ROM), a Dynamic RAM (DRAM), a Synchronous DRAM (SD-RAM), a double data rate (DDR) memory chip, a Flash memory, a volatile memory, a non-volatile memory, a cache memory, a buffer, a short term memory unit, a long term memory unit, or other suitable memory units or storage units. The memory 620 may be or may include a number of, possibly different memory units. The memory 620 may be a computer or processor non-transitory readable medium, or a computer non-transitory storage medium, e.g., a RAM. Some embodiments may include a non-transitory storage medium having stored thereon instructions which when executed cause the processor to carry out methods disclosed herein.

[0036] The executable code 625 may be any executable code, e.g., an application (app), a program, a process, task or script. The executable code 625 may be executed by the controller 610 possibly under control of the operating system 615. Although, for the sake of clarity, a single item of executable code 625 is shown in FIG. 6, the system 600 according to some embodiments of the invention may include a number of executable code segments similar to the executable code 625 that may be loaded into the memory 620 and cause the controller 610 to carry out methods described herein. The input means 630 may be or may include a mouse, a keyboard, a touch screen or pad or any suitable input device. It will be recognized that any suitable number of input devices may be operatively connected to the computing device 605. The output devices 635 may include one or more monitors, speakers and / or any other suitable output devices. It will be recognized that any suitable number of output devices may be operatively connected to the computing device 605. Any applicable input / output (I / O) devices may be connected to the computing device 605. For example, the input means 630 and the output devices 635 may include a wireless network interface component (e.g., a WiFi system or component), a Bluetooth component and the like. To that understanding, in one embodiment, the display unit 645 may be one of the output devices 635. A system according to some embodiments of the invention may include components such as, but not limited to, a number of central processing units (CPU) or any other suitable multi-purpose or specific processors or controllers (e.g., controllers similar to the controller 610), a number of input units, a number of output units, a number of memory units, and a number of storage units. The input means 630 may be configured to receive an input on the UI from a user. The input may be to select a diagnostic protocol amongst a number of diagnostic protocols. Upon selection of the diagnostic protocol, the input means 630 may be configured to receive on the UI, comprehensive patient information related to the patient. Examples of the comprehensive patient information may include, but are not limited to, demographic data, medical history data, risk factor data, previous diagnostic results, current medications and treatments, relevant physiological parameters, and contraindications for specific diagnostic procedures.

[0037] Upon receiving the comprehensive patient information, the imaging device 650 may be configured to capture a number of images of an anatomical region of a patient. The imaging device 650 may be one of a camera, a video recorder, a smart phone, or the like. The number of images may be utilized to determine the presence or absence of the pre-cancerous / cancerous cells in the patient. In one embodiment, the imaging device 650 may be operated by the user. The number of images may be displayed on a UI of the display unit 645 along with a number of pre-stored reference images. The number of pre-stored reference images may be used to compare to the number of images for performing the medical diagnostic analysis. The comparison may be manually performed by a user such as a medical practitioner.

[0038] Each reference image may be assigned one or more diagnostic values associated with a number of characteristics and a classification score. Examples of the number of characteristics may include, but are not limited to, one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed. To that understanding, the diagnostic values associated with each characteristic amongst the number of characteristics and the classification score may include a standardized range of numerical values. The standardized range may be based on an established medical system. The number of images may be compared with the number of pre-stored reference images for a medical diagnostic analysis. Moving forward, the input means 630 may be configured to receive the diagnostic values associated with the number of characteristics and the classification score for each image amongst the number of images. The diagnostic value and the classification score for each image may be based on a user comparison of the number of images with the number of pre- stored reference images. In one embodiment, the controller 610 may be configured to analyze the number of images using one or more computer vision techniques to generate the one or more diagnostic values. The display unit 645 may display the one or more diagnostic values alongside the number of pre-stored reference images. Subsequently, the generation engine 640 may be configured to generate a summary output based on the received diagnostic values indicating a severity classification. The generation engine 640 may generate the summary output by applying a weighted scoring algorithm to the one or more diagnostic values to generate a weighted score. Upon applying the weighted scoring algorithm to the one or more diagnostic values, the generation engine 640 may be configured to compare the weighted score against a predetermined threshold for each characteristic. Upon comparing the weighted score against the predetermined threshold for each characteristic, the generation engine 640 may be configured to determine the severity classification based on the comparison. The display unit 645 may be configured to display one or more recommended actions based on the severity classification and the classification score. The one or more recommended actions may be displayed on the UI in the form of one or more interactive elements that display specific information associated with each action upon a user interaction. The one or more recommended actions may be automatically generated based on the severity classification, the classification score, one or more patient- specific risk factors, and / or one or more standard medical protocols. To that understanding, the generation engine 640 may further be configured to generate a summary. The summary may include information associated with the patient, the diagnostic values associated with each characteristic for each image, the classification score for each image, and the summary output. The display unit 645 may be configured to display the information associated with the patient, the diagnostic values associated with each characteristic for each image, the classification score for each image, and the summary output on the display unit 645. Furthermore, the controller 610 may be configured to store the number of images, the one or more received diagnostic values, and the summary output in a secure database. The secure database may be present in the memory. Further, the controller 610 may be configured to track changes in the one or more diagnostic values over a period of time and generate a trend analysis report based on the tracked changes. In one embodiment where it is determined that the pre-cancerous / cancerous cells are present in the patient and the pre-cancerous / cancerous cells are related with cervical cancer, the controller 610 may be configured to integrate data from a number of imaging modalities, correlate the integrated data with the number of prestored reference images. Upon correlating, the controller 610 may be configured to generate a composite diagnostic score based on the correlation. Reference is made to FIG. 7, depicting a flow diagram of a method for performing a medical diagnostic analysis, according to some embodiments. The method includes the steps of:

[0039] ■ capturing, by an imaging device, a plurality of images of an anatomical region of a subject, wherein the plurality of images is displayed on a User Interface (UI) of a display unit along with a plurality of pre-stored reference images, each reference image being assigned one or more diagnostic values associated with a plurality of characteristics and a classification score (7005);

[0040] ■ receiving, via an input means, the one or more diagnostic values associated with the plurality of characteristics and the classification score for each image amongst the plurality of captured images based on a user comparison with the plurality of pre-stored reference images (S7010);

[0041] ■ generating, by a generation engine, a summary output based on the received one or more diagnostic values, wherein the summary output indicates a severity classification (7015); and ■ displaying, by the display unit, one or more recommended actions based on the severity classification and the classification score (7020).

[0042] In the description and claims of the present application, each of the verbs, “comprise”, “include”, and “have”, and conjugates thereof, are used to indicate that the object or objects of the verb are not necessarily a complete listing of components, elements or parts of the subject or subjects of the verb. Unless otherwise stated, adjectives such as “substantially” and “about” modifying a condition or relationship characteristic of a feature or features of an embodiment of the disclosure, are understood to mean that the condition or characteristic is defined to within tolerances that are acceptable for operation of an embodiment as described. In addition, the word “or” is considered to be the inclusive “or” rather than the exclusive or, and indicates at least one of, or any combination of items it conjoins.

[0043] Descriptions of embodiments of the invention in the present application are provided by way of example and are not intended to limit the scope of the invention. The described embodiments comprise different features, not all of which are required in all embodiments. Some embodiments utilize only some of the features or possible combinations of the features. Variations of embodiments of the invention that arc described, and embodiments comprising different combinations of features noted in the described embodiments, will occur to a person having ordinary skill in the art. The scope of the invention is limited only by the claims.

[0044] Unless explicitly stated, the method embodiments described herein are not constrained to a particular order in time or chronological sequence. Additionally, some of the described method elements may be skipped, or they may be repeated, during a sequence of operations of a method.

[0045] While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents may occur to those skilled in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.

[0046] Various embodiments have been presented. Each of these embodiments may of course include features from other embodiments presented, and embodiments not specifically described may include various features described herein.

Claims

CLAIMS1. A method for performing a medical diagnostic analysis, comprising: capturing, by an imaging device, a plurality of images of an anatomical region of a subject, wherein the plurality of images is displayed on a User Interface (UI) of a display unit along with a plurality of pre-stored reference images, each reference image being assigned one or more diagnostic values associated with a plurality of characteristics and a classification score; receiving, via an input means, the one or more diagnostic values associated with the plurality of characteristics and the classification score for each image amongst the plurality of captured images based on a user comparison with the plurality of prestored reference images; generating, by a generation engine, a summary output based on the received one or more diagnostic values, wherein the summary output indicates a severity classification; and displaying, by the display unit, one or more recommended actions based on the severity classification and the classification score.

2. The method according to claim 1, further comprising: receiving an input on the UI from the user to select a diagnostic protocol amongst a plurality of diagnostic protocols; and receiving on the UI, comprehensive patient information comprising demographic data, medical history data, risk factor data, previous diagnostic results, current medications and treatments, relevant physiological parameters, and contraindications for specific diagnostic procedures.

3. The method according to claim 1 , further comprising: generating, by the generation engine, a summary comprising information associated with the subject, the one or more diagnostic values associated with each characteristic for each image, the classification score for each image and an associated description, and the summary output for displaying on the display unit.

4. The method according to claim 1, wherein the medical diagnostic analysis is applicable to detection and classification of abnormalities in any anatomical region of the subject.

5. The method according to claim 1, wherein the plurality of characteristics comprises one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed.

6. The method according to claim 1, wherein the one or more diagnostic values associated with each characteristic amongst the plurality of characteristics and the classification score comprises a standardized range of numerical values.

7. The method according to claim 1, wherein generating the summary output comprises: applying a weighted scoring algorithm to the one or more diagnostic values to generate a weighted score; comparing the weighted score against a predetermined threshold for each characteristic; and determining the severity classification based on the comparison.

8. The method according to claim 1 , wherein the one or more recommended actions are displayed on the UI in a form of one or more interactive elements that display specific information associated with each action upon a user interaction.

9. The method according to claim 1, wherein the method further comprises: analyzing the plurality of images using one or more computer vision techniques to generate the one or more diagnostic values; and displaying the one or more diagnostic values alongside the plurality of prestored reference images.

10. The method according to claim 1, further comprising: storing the plurality of images, the one or more received diagnostic values, and the summary output in a secure database; and tracking changes in the one or more diagnostic values over a period of time; and generating a trend analysis report based on the tracked changes.

11. The method according to claim 1, wherein the method further comprises: integrating data from a plurality of imaging modalities; correlating the integrated data with the plurality of pre-stored reference images; and generating a composite diagnostic score based on the correlation.

12. The method according to claim 1 , wherein the recommended actions are automatically generated based on: a. the severity classification; b. the classification score;c. one or more patient-specific risk factors; and d. one or more standard medical protocols.

13. A system for performing medical diagnostic analysis, comprising: an imaging device configured to capture a plurality of images of an anatomical region of a subject, wherein the plurality of images is displayed on a User Interface (UI) of a display unit along with a plurality of pre-stored reference images, each reference image being assigned one or more diagnostic values associated with a plurality of characteristics and a classification score; an input means configured to receive the diagnostic values associated with the plurality of characteristics and the classification score for each image amongst the plurality of images based on user comparison with the plurality of pre- stored reference images; a generation engine configured to generate a summary output based on the received diagnostic values, wherein the output indicates a severity classification; and the display unit configured to display one or more recommended actions based on the severity classification and the classification score.

14. The system according to claim 13, further comprising: the input means configured to: receive an input on the UI from the user to select a diagnostic protocol amongst a plurality of diagnostic protocols; and receive on the UI, comprehensive patient information comprising demographic data, medical history data, risk factor data, previous diagnostic results,current medications and treatments, relevant physiological parameters, and contraindications for specific diagnostic procedures.

15. The system according to claim 13, further comprising: the generation engine configured to generate a summary comprising information associated with the subject, the diagnostic values associated with each characteristic for each image, the classification score for each image, and the summary output for displaying on the display unit.

16. The system according to claim 13, wherein the diagnostic analysis is applicable to a detection and a classification of abnormalities in any anatomical region of the subject.

17. The system according to claim 13, wherein the plurality of characteristics comprises one or more quantitative and qualitative measurements of tissue properties, one or more structural features, and one or more responses to diagnostic agents specific to the anatomical region being analyzed.

18. The system according to claim 13, wherein the one or more diagnostic values associated with each characteristic amongst the plurality of characteristics and the classification score comprise standardized range of numerical values.

19. The system according to claim 13, wherein generating the summary output comprises: applying a weighted scoring algorithm to the one or more diagnostic values to generate a weighted score; comparing the weighted score against a predetermined threshold for each characteristic; and determining the severity classification based on the comparison.

0. The system according to claim 13, wherein the one or more recommended actions are displayed on the UI in a form of one or more interactive elements that display specific information associated with each action upon a user interaction.

Images