Joint inflammation

Abstract

A method for detecting inflammation in a body joint of a subject, including: providing at least one thermal image of at least one body joint, wherein the at least one thermal image includes indications of temperature of the at least one body joint; marking at least one region of interest (ROI) in the at least one thermal image, wherein the marked ROI is a region in the at least one thermal image which includes pixels representing elevated temperatures and less elevated temperatures in the at least one thermal image; extracting values of one or more parameters of distribution of the temperature indications in the at least marked ROI; detecting inflammation in the body joint based on the extracted values.

Description

[0001] JOINT INFLAMMATION

[0002] RELATED APPLICATION

[0003] This application claims the benefit of priority of Israeli Patent Application No. 310163 filed 15 January 2024, the content of which is incorporated herein by reference in its entirety.

[0004] FIELD AND BACKGROUND OF THE INVENTION

[0005] The present invention, in some embodiments thereof, relates to detection of inflammation and, more particularly, but not exclusively, to detection of inflammation in one or more body joints.

[0006] Isabel Morales-Ivorra et al. (2022) “a Thermographic Disease Activity Index for remote assessment of rheumatoid arthritis” describes, “objectives: Remote assessment of patients with rheumatoid arthritis (RA) has increased during recent years. However, telematic consultations preclude the possibility of carrying out a physical examination and obtaining objective inflammation. In this study, we developed and validated two novel composite disease activity indexes (Thermographic Disease Activity Index (ThermoDAI) and ThermoDALCRP) based on thermography of hands and machine learning, in order to assess disease activity easily, rapidly and without formal joint counts. Methods: ThermoDAI was developed as the sum of Thermographic Joint Inflammation Score (ThermoJIS), a novel joint inflammation score based on the analysis of thermal images of the hands by machine learning, the Patient Global Assessment (PGA) and, for ThermoDALCRP, the C reactive protein (CRP). Construct validity was tested in 146 patients with RA by using Spearman's correlation with ultrasound-determined grey-scale synovial hypertrophy (GS) and power Doppler (PD) scores, CDAI, SDAI and DAS28-CRP. Results: Correlations of ultrasound scores with ThermoDAI (GS=0.52; PD=0.56) and ThermoDALCRP (GS=0.58; PD=0.61) were moderate to strong, while the correlations of ultrasound scores with PGA (GS=0.35; PD=0.39) and PGA+CRP (GS=0.44; PD=0.46) were weak to moderate. ThermoDAI and ThermoDALCRP also showed strong correlations with Clinical Disease Activity Index (p>0.83), Simplified Disease Activity Index (p>0.85) and Disease Activity Score with 28-Joint Counts-CRP (p>0.81) and high sensitivity for detecting active synovitis using remission criteria. Conclusions: ThermoDAI and ThermoDALCRP showed stronger correlations with ultrasound- determined synovitis than PGA and PGA + CRP, thus presenting an opportunity to improve remote consultations with patients with RA” (abstract).

[0007] Isabel Morales-Ivorra et al. (2022) describes “assessment of inflammation in patients with rheumatoid arthritis using thermography and machine learning: a fast and automated technique” describes, Objectives: Sensitive detection of joint inflammation in rheumatoid arthritis (RA) is crucial to the success of the treat- to-target strategy. In this study, we characterise a novel machine learning-based computational method to automatically assess joint inflammation in RA using thermography of the hands, a fast and non-invasive imaging technique. Methods: We recruited 595 patients with arthritis and osteoarthritis (OA), as well as healthy subjects at two hospitals over 4 years. Machine learning was used to assess joint inflammation from the thermal images of the hands using ultrasound as the reference standard, obtaining a Thermographic Joint Inflammation Score (ThermoJIS). The machine learning model was trained and tuned using data from 449 participants with different types of arthritis, osteoarthritis or without rheumatic disease (development set). The performance of the method was evaluated based on 146 patients with RA (validation set) using Spearman's rank correlation coefficient, area under the receiver-operating curve (AUROC), average precision, sensitivity, specificity, positive and negative predictive value and Fl-score. Results: ThermoJIS correlated moderately with ultrasound scores (grey-scale synovial hypertrophy=0.49, p<0.001; and power Doppler=0.51, p<0.001). The AUROC for ThermoJIS for detecting active synovitis was 0.78 (95% CI, 0.71 to 0.86; p<0.001). In patients with RA in clinical remission, ThermoJIS values were significantly higher when active synovitis was detected by ultrasound. Conclusions: ThermoJIS was able to detect joint inflammation in patients with RA, even in those in clinical remission. These results open an opportunity to develop new tools for routine detection of joint inflammation” (abstract).

[0008] SUMMARY OF THE INVENTION

[0009] Some examples of some embodiments of the invention are listed below (it should be noted that one or more features of an example may be used in combination with one or more features of another example):

[0010] Example 1. A method for detecting inflammation in a body joint of a subject, comprising: providing at least one thermal image of at least one body joint, wherein the at least one thermal image includes indications of temperature of the at least one body joint; marking at least one region of interest (ROI) in the at least one thermal image, wherein the marked ROI is a region in the at least one thermal image which includes pixels representing elevated temperatures and less elevated temperatures in the at least one thermal image ; extracting values of one or more parameters of distribution of the temperature indications in the at least marked ROI; detecting inflammation in the body joint based on the extracted values. Example 2. A method according to example 1, wherein the marked ROI is a region in the at least one thermal image which includes pixels representing at least 50% of a range of temperature values in the at least one thermal image.

[0011] Example 3. A method according to any one of examples 1 or 2, wherein the at least one ROI comprises a single contiguous region in the at least one thermal image.

[0012] Example 4. A method according to any one of the previous examples, wherein the at least one ROI has an area of at least 0.16 cm2in the at least one thermal image.

[0013] Example 5. A method according to any one of the previous examples, wherein the at least one ROI includes pixels representing at least 25% of an area of the at least one body joint in the at least one thermal image.

[0014] Example 6. A method according to any one of the previous examples, comprising identifying an increase in non-uniformity of a distribution the temperature indications in the at least one ROI based on the extracted values, determining a relation between the identified increase in nonuniformity and a reference value, and wherein the detecting comprises detecting the inflammation based on the determined relation.

[0015] Example 7. A method according to example 6, wherein the detecting comprises detecting the inflammation if the identified increase in non-uniformity is larger than a the reference value.

[0016] Example 8. A method according to any one of the previous examples, wherein the one or more parameters comprise local entropy.

[0017] Example 9. A method according to example 8, wherein the extracting comprises extracting values of the local entropy from one or more regions having a size between 0.2 cm2and 0.9 cm2, in the selected ROI.

[0018] Example 10. A method according to example 8, wherein the extracting comprises extracting values of the local entropy from one or more regions having a size between 0.3 cm2and 0.5 cm2, in the selected ROI.

[0019] Example 11. A method according to any one of examples 9 or 10, wherein the extracting comprises extracting values of the local entropy from a plurality of regions having a size between 0.2 cm2and 0.9 cm2in the at least one ROI and calculating a value of a central tendency measure of the extracted local entropy values per the at least one ROI, and wherein the detecting comprises detecting the inflammation in the body joint based on the calculated central tendency value of the extracted local entropy values.

[0020] Example 12. A method according to any one of the previous examples, wherein the extracting comprises calculating a value of a central tendency measure of the one or more parameters per the at least one ROI, and wherein the detecting comprises detecting the inflammation based on the calculated central tendency measure.

[0021] Example 13. A method according to any one of examples 11 or 12, wherein the central tendency measure comprise mean, median, or mode, or any combination of the aforesaid.

[0022] Example 14. A method according to any one of the previous examples, wherein the one or more parameters comprise, skewness, entropy, or kurtosis, or any combination of the aforesaid.

[0023] Example 15. A method according to any one of the previous examples, wherein the extracting comprises extracting values of one or more temperature parameters and wherein the detecting comprises detecting the inflammation based on the extracted value of the one or more distribution parameters and based on the extracted values of the one or more temperature parameter.

[0024] Example 16. A method according to example 15, wherein the one or more temperature parameters comprise, mean temperature, minimum temperature ,or maximum temperature or any combination of the aforesaid.

[0025] Example 17. A method according to any one of the previous examples, wherein the detecting comprises determining inflammation type and / or severity.

[0026] Example 18. A method according to any one of the previous examples, wherein the at least one thermal image is at least one thermal image of at least two corresponding joints of a subject body. Example 19. A method according to example 18, wherein the marking comprises marking at least two regions of interest each in a different joint of the at least two corresponding joints, wherein the extracting comprises extracting the values of the one or more parameters or values of a central tendency measure thereof from each of the at least two regions of interest, and wherein the detecting comprises detecting the inflammation based on a difference in the extracted values or in the central tendency measure values, between the at least two corresponding joints.

[0027] Example 20. A method according to example 19, wherein the inflammation is detected if the difference in the extracted values between the at least two corresponding body joints is at least 5%. Example 21. A method according to any one of examples 19 or 20, wherein the at least two corresponding body joints are contralateral body joints.

[0028] Example 22. A method according to any one of the previous examples, wherein the at least one body joint comprises a knee, an ankle and / or a body joint of a hand.

[0029] Example 23. A method according to any one of the previous examples, comprising diagnosing the subject with an inflammation-related clinical state based on the detected inflammation.

[0030] Example 24. A method according to example 23, wherein the clinical state comprises latent asymptomatic inflammation, arthritis, and / or septic arthritis. Example 25. A method according to any one of the previous examples, wherein the temperature values indications comprise values of temperature measurements measured in a Celsius scale or in a Fahrenheit scale, or indications thereof.

[0031] Example 26. A method for detecting inflammation in a body joint, comprising: providing at least one thermal image of at least one body joint, wherein the at least one thermal image includes indications of temperature values of the at least one body joint; marking at least one region of interest (ROI) in the at least one thermal image extracting values of local entropy of the indications of temperature values from a region in the at least one thermal image which includes at least a portion of the at least one body joint; detecting inflammation in the at least one body joint based on the extracted local entropy values. Example 27. A method according to example 26, wherein the at least one ROI comprises a single contiguous region in the at least one thermal image.

[0032] Example 28. A method according to any one of examples 26 or 27, wherein the at least one ROI includes pixels representing at least 25% of an area of the at least one body joint in the at least one thermal image.

[0033] Example 29. A method according to any one of examples 26 to 28, wherein the region has a size between 0.2 cm2and 0.9 cm2.

[0034] Example 30. A method according to any one of examples 26 to 28, wherein the extracting comprises extracting values of the local entropy from one or more regions having a size between 0.3 cm2and 0.5 cm2.

[0035] Example 31. A method according to any one of examples 26 to 30, wherein the detecting comprises detecting the inflammation if the local entropy measurements are higher than a reference value.

[0036] Example 32. A method according to any one of examples 26 to 31, wherein the at least one thermal image is at least one thermal image of two or more corresponding body joints, wherein the extracting comprises extracting values of the local entropy from two region, each at a different body joint of the two or more corresponding body joints, and wherein the detecting comprises detecting the inflammation based on a difference in values of the local entropy between the two or more corresponding body joints.

[0037] Example 33. A method according to example 32, wherein the inflammation is detected if the difference in values of the local entropy between the two corresponding body joints is at least 5%. Example 34. A method according to any one of examples 32 or 33, wherein the two or more corresponding body joints are contralateral body joints. Example 35. A method according to any one of examples 26 to 34, wherein the at least one body joint comprises a knee, an ankle and / or a body joint of a hand.

[0038] Example 36. A method according to any one of the examples 26 to 35, comprising diagnosing the subject with an inflammation-related clinical state based on the detected inflammation.

[0039] Example 37. A method according to example 36, wherein the clinical state comprises latent asymptomatic inflammation, arthritis, and / or septic arthritis.

[0040] Example 38. A method according to any one of examples 26 to 37, wherein the temperature values indications comprise values of temperature measurements measured in a Celsius scale or in a Fahrenheit scale, or indications thereof.

[0041] Example 39. A method for monitoring an effect of a treatment for joint inflammation, comprising: providing at least one thermal image of at least one body joint acquired after initiating a treatment for inflammation in the at least one body joint, wherein the at least one thermal image includes indications of temperature values of the at least one body joint; processing the at least one thermal image; determining a state of the inflammation in the body joint, based on the results of the processing; generating an indication with information about the determined state.

[0042] Example 40. A method according to example 39, wherein the at least one thermal image is a thermal image acquired when the subject is outside a medical facility.

[0043] Example 41. A method according to any one of examples 39 or 40, comprising: determining an effect of the treatment on the joint inflammation based on the determined inflammation state, and wherein the generated indication includes information on the determined effect.

[0044] Example 42. A method according to example 41, wherein the generated indication comprises a suggestion to stop the treatment, to modify the treatment or to replace the treatment, if the determined effect is not a target effect.

[0045] Example 43. A method according to any one of examples 39 to 42, wherein the processing comprises extracting values indicating local entropy of temperatures distribution in a region of the at least one thermal image or a central tendency measure thereof, and wherein the determining comprises determining the state of the inflammation based on the extracted values.

[0046] Example 44. A method according to any one of examples 39 to 43, wherein the processing comprises marking at least one region of interest (ROI) in the at least one thermal image, wherein the marked ROI is a region which includes pixels representing elevated temperatures and less elevated temperatures in the at least one thermal image, and extracting values indicating one or more parameters of distribution of the temperatures in the at least marked ROI or a central tendency measure thereof, and wherein the determining comprises determining the state of the inflammation based on the extracted values.

[0047] Example 45. A method according to any one of examples 43 or 44, wherein the processing comprises determining a relation between the extracted values and previously extracted values or indications thereof, and wherein the state of the inflammation is determined based in the determined relation.

[0048] Example 46. A method according to any one of examples 43 to 45, wherein the at least one thermal image comprises at least one thermal image of two or more body joints, and wherein the processing comprises normalizing values extracted from at least one thermal image of at least one body joint of the two or more body joints to values extracted from the at least one thermal image or from at least one different thermal image of at least one different body joint, and wherein the inflammation state is determine using the normalized values.

[0049] Example 47. A method according to any one of examples 39 to 46, wherein the temperature values indications comprise values of temperature measurements measured in a Celsius scale or in a Fahrenheit scale, or indications thereof.

[0050] Example 48. A system, comprising: a memory circuitry, wherein the memory circuitry stores at least one thermal image of at least one body joint of a subject, wherein the at least one thermal image includes indications of different temperature values in the body joint; a user interface configured to generate and deliver at least one human detectable indications; a control circuitry configured to: extract values of one or more parameters of distribution of the temperatures from at least one region of interest (ROI) in the at least one thermal image which includes elevated temperatures and less elevated temperatures; detect inflammation in the body joint based on the extracted values; and signal the user interface to generate the human detectable indication with information about the detected inflammation.

[0051] Example 49. A system according to example 48, wherein the at least one ROI is a region in the at least one thermal image which includes pixels representing at least 50% of a range of temperature values in the at least one thermal image.

[0052] Example 50. A system according to any one of examples 48 or 49, wherein the at least one ROI comprises a single contiguous region in the at least one thermal image. Example 51. A system according to any one of examples 48 to 50, wherein the at least one ROI includes pixels representing at least 25% of an area of the at least one body joint in the at least one thermal image.

[0053] Example 52. A system according to any one of examples 48 to 51, comprising a communication circuitry configured to deliver a signal to a remote device, wherein the control circuitry signals the communication circuitry to deliver the signal to the remote device with information about the detected inflammation.

[0054] Example 53. A system according to any one of examples 48 to 52, wherein the control circuitry is configured to diagnose a clinical state based on the detected inflammation, and to signal the user interface to generate an indication with information about the clinical state.

[0055] Example 54. A system according to example 53, wherein the clinical state comprises latent asymptomatic inflammation, and / or arthritis.

[0056] Example 55. A system according to any one of examples 53 or 54, wherein the memory stores information about at least one treatment for the clinical state, and wherein the control circuitry signals the user interface to deliver a human detectable indication with information about the at least one treatment or with a suggestion to initiate the at least one treatment, if the inflammation is detected.

[0057] Example 56. A system according to any one of examples 48 to 55, wherein the control circuitry is configured to determine a relation between the extracted values and previously extracted values stored in the memory, and wherein the detect inflammation comprises determine a state of the inflammation in the subject based on the determined relation.

[0058] Example 57. A system according to example 56, wherein the memory stores information about at least one treatment provided to the subject, and wherein the control circuitry is configured to signal the user interface to generate an indication with at least one suggestion for stopping the treatment, modify the treatment and / or to combine the treatment with at least one different treatment, if the determined state is not a target state.

[0059] Example 58. A system according to any one of examples 48 to 57, wherein the user interface is configured to deliver a signal to the control circuitry with information about the at least one ROI. Example 59. A system according to any one of examples 48 to 57, wherein the control circuitry is configured to automatically determine the at least one ROI using an algorithm, a software program and / or a look-up table stored in the memory.

[0060] Example 60. A system according to any one of examples 48 to 59, wherein the temperature values indications comprise values of temperature measurements measured in a Celsius scale or in a Fahrenheit scale, or indications thereof. Provided below are some additional examples of some embodiments of the invention (it should be noted that one or more features of an example may be used in combination with one or more features of another example):

[0061] Example 1. A method for detecting inflammation in a body joint of a subject, comprising: providing at least one thermal image of at least one body joint, wherein the at least one thermal image includes indications of temperature of the at least one body joint; marking at least one region of interest (ROI) in the at least one thermal image, wherein the at least one ROI is a region in the at least one thermal image which includes pixels representing elevated temperatures and less elevated temperatures in the at least one thermal image; extracting values of one or more parameters of distribution of the temperature indications in the at least one ROI; detecting inflammation in the body joint based on the extracted values.

[0062] Example 2. A method according to example 1, wherein the providing comprises providing at least one thermal image of at least one body joint and adjacent tissue, wherein the at least one thermal image includes indication of temperature of the at least one body joint and of the adjacent tissue; wherein the marking comprises marking at least one ROI in the at least one thermal image which includes pixels indicating temperature of the body joint and of the adjacent tissue, wherein at least 1% of pixels in the at least one ROI indicate temperature of the adjacent tissue; wherein the extracting comprises extracting values of the one or more parameters of distribution of the temperature indications in the at least marked ROI, which includes temperature indications of the body joint and of the adjacent tissue.

[0063] Example 3. A method according to example 2, wherein the adjacent tissue comprises noninflamed tissue which is anatomically distinct from the at least one body joint.

[0064] Example 4. A method according to any one of the previous examples, wherein the marked ROI is a region in the at least one thermal image which includes pixels representing at least 50% of a range of temperature values in the at least one thermal image.

[0065] Example 5. A method according to any one of the previous examples, wherein the at least one ROI comprises a single contiguous region in the at least one thermal image.

[0066] Example 6. A method according to any one of the previous examples, wherein the at least one ROI has an area of at least 0.16 cm2in the at least one thermal image. Example 7. A method according to any one of the previous examples, wherein the at least one ROI includes pixels representing at least 25% of an area of the at least one body joint in the at least one thermal image.

[0067] Example 8. A method according to any one of the previous examples, comprising identifying an increase in non-uniformity of a distribution the temperature indications in the at least one ROI based on the extracted values, determining a relation between the identified increase in nonuniformity and a reference value, and wherein the detecting comprises detecting the inflammation based on the determined relation.

[0068] Example 9. A method according to example 8, wherein the detecting comprises detecting the inflammation if the identified increase in non-uniformity is larger than a the reference value.

[0069] Example 10. A method according to any one of the previous examples, wherein the one or more parameters comprise local entropy.

[0070] Example 11. A method according to example 10, wherein the extracting comprises extracting values of the local entropy from one or more regions having a size between 0.2 cm2and 0.9 cm2, in the selected ROI.

[0071] Example 12. A method according to example 10, wherein the extracting comprises extracting values of the local entropy from one or more regions having a size between 0.3 cm2and 0.5 cm2, in the selected ROI.

[0072] Example 13. A method according to example 11, wherein the extracting comprises extracting values of the local entropy from a plurality of regions having a size between 0.2 cm2and 0.9 cm2in the at least one ROI and calculating a value of a central tendency measure of the extracted local entropy values per the at least one ROI, and wherein the detecting comprises detecting the inflammation in the body joint based on the calculated central tendency value of the extracted local entropy values.

[0073] Example 14. A method according to any one of the previous examples, wherein the extracting comprises calculating a value of a central tendency measure of the one or more parameters per the at least one ROI, and wherein the detecting comprises detecting the inflammation base don the calculated central tendency measure.

[0074] Example 15. A method according to example 13, wherein the central tendency measure comprise mean, median, or mode, or any combination of the aforethe.

[0075] Example 16. A method according to any one of the previous examples, wherein the one or more parameters comprise, skewness, entropy, or kurtosis, or any combination of the aforethe. Example 17. A method according to any one of the previous examples, wherein the extracting comprises extracting values of one or more temperature parameters and wherein the detecting comprises detecting the inflammation based on the extracted value of the one or more distribution parameters and based on the extracted values of the one or more temperature parameter.

[0076] Example 18. A method according to example 17, wherein the one or more temperature parameters comprise, mean temperature, minimum temperature, or maximum temperature or any combination of the aforethe.

[0077] Example 19. A method according to any one of the previous examples, wherein the detecting comprises determining inflammation type and / or severity, and wherein the at least one body joint comprises a knee, an ankle and / or a body joint of a hand.

[0078] Example 20. A method according to any one of the previous examples, wherein the at least one thermal image is at least one thermal image of at least two corresponding joints of a subject body.

[0079] Example 21. A method according to example 20, wherein the marking comprises marking at least two regions of interest each in a different joint of the at least two corresponding joints, wherein the extracting comprises extracting the values of the one or more parameters or values of a central tendency measure thereof from each of the at least two regions of interest, and wherein the detecting comprises detecting the inflammation based on a difference in the extracted values or in the central tendency measure values, between the at least two corresponding joints.

[0080] Example 22. A method according to example 21, wherein the inflammation is detected if the difference in the extracted values between the at least two corresponding body joints is at least 5%, wherein the at least two corresponding body joints are contralateral body joints.

[0081] Example 23. A method according to any one of the previous examples, comprising diagnosing the subject with an inflammation-related clinical state based on the detected inflammation, wherein the clinical state comprises latent asymptomatic inflammation, arthritis, and / or septic arthritis.

[0082] Example 24. A method for detecting inflammation in a body joint, comprising: providing at least one thermal image of at least one body joint, wherein the at least one thermal image includes indications of temperature values of the at least one body joint; marking at least one region of interest (RO I) in the at least one thermal image which includes at least a portion of the at least one body joint; extracting values of local entropy of the indications of temperature values from the at least one ROI; detecting inflammation in the at least one body joint based on the extracted local entropy values. Example 25. A method according to example 24, wherein the providing comprises providing at least one thermal image of at least one body joint and adjacent tissue, wherein the at least one thermal image includes indication of temperature of the at least one body joint and of the adjacent tissue; wherein the marking comprises marking at least one ROI in the at least one thermal image which includes pixels indicating temperature of the body joint and of the adjacent tissue, wherein at least 1% of pixels in the at least one ROI indicate temperature of the adjacent tissue.

[0083] Example 26. A method according to example 25, wherein the adjacent tissue comprises noninflamed tissue which is anatomically distinct from the at least one body joint.

[0084] Example 27. A method according to any one of examples 24 or 25, wherein the at least one ROI comprises a single contiguous region in the at least one thermal image.

[0085] Example 28. A method according to any one of examples 24 to 27, wherein the at least one ROI includes pixels representing at least 25% of an area of the at least one body joint in the at least one thermal image.

[0086] Example 29. A method according to any one of examples 24 to 28, wherein the region has a size between 0.2 cm2and 0.9 cm2.

[0087] Example 30. A method according to any one of examples 24 to 29, wherein the detecting comprises detecting the inflammation if the local entropy measurements are higher than a reference value.

[0088] Example 31. A method according to any one of examples 24 to 30, wherein the at least one thermal image is at least one thermal image of two or more corresponding body joints, wherein the extracting comprises extracting values of the local entropy from two region, each at a different body joint of the two or more corresponding body joints, and wherein the detecting comprises detecting the inflammation based on a difference in values of the local entropy between the two or more corresponding body joints.

[0089] Example 32. A method according to example 31, wherein the inflammation is detected if the difference in values of the local entropy between the two corresponding body joints is at least 5%, and wherein the two or more corresponding body joints are contralateral body joints.

[0090] Example 33. A method according to any one of examples 24 to 32, wherein the at least one body joint comprises a knee, an ankle and / or a body joint of a hand.

[0091] Example 34. A method according to any one of examples 24 to 33, comprising diagnosing the subject with an inflammation-related clinical state based on the detected inflammation, wherein the clinical state comprises latent asymptomatic inflammation, arthritis, and / or septic arthritis. Example 35. A method for monitoring an effect of a treatment for joint inflammation, comprising: providing at least one thermal image of at least one body joint acquired after initiating a treatment for inflammation in the at least one body joint, wherein the at least one thermal image includes indications of temperature values of the at least one body joint; processing the at least one thermal image; determining a state of the inflammation in the body joint, based on the results of the processing; generating an indication with information about the determined state.

[0092] Example 36. A method according to example 35, wherein the providing comprises providing at least one thermal image of at least one body joint and adjacent tissue after initiating a treatment for inflammation in the at least one body joint.

[0093] Example 37. A method according to example 36, wherein the adjacent tissue comprises noninflamed tissue which is anatomically distinct from the at least one body joint.

[0094] 38. A method according to any one of examples 35 to 37, wherein the at least one thermal image is a thermal image acquired when the subject is outside a medical facility.

[0095] Example 39. A method according to any one of examples 35 to 38, comprising: determining an effect of the treatment on the joint inflammation based on the determined inflammation state, and wherein the generated indication includes information on the determined effect.

[0096] Example 40. A method according to example 39, wherein the generated indication comprises a suggestion to stop the treatment, to modify the treatment or to replace the treatment, if the determined effect is not a target effect.

[0097] Example 41. A method according to any one of examples 35 to 40, wherein the processing comprises extracting values indicating local entropy of temperatures distribution in a region of the at least one thermal image or a central tendency measure thereof, and wherein the determining comprises determining the state of the inflammation based on the extracted values.

[0098] Example 42. A method according to any one of examples 35 to 41, wherein the processing comprises marking at least one region of interest (RO I) in the at least one thermal image, wherein the marked ROI is a region which includes pixels representing elevated temperatures and less elevated temperatures in the at least one thermal image, and extracting values indicating one or more parameters of distribution of the temperatures in the at least marked ROI or a central tendency measure thereof, and wherein the determining comprises determining the state of the inflammation based on the extracted values. Example 43. A method according to example 42, wherein the at least one thermal image is a thermal image of the at least one body joint and of tissue adjacent to the at least one body joint, wherein the at least one ROI includes pixels indicating temperature of the body joint and of the adjacent tissue, wherein at least 1% of pixels in the at least one ROI indicate temperature of the adjacent tissue.

[0099] Example 44. A method according to example 41, wherein the processing comprises determining a relation between the extracted values and previously extracted values or indications thereof, and wherein the state of the inflammation is determined based in the determined relation.

[0100] Example 45. A method according to any one of examples 35 to 43, wherein the at least one thermal image comprises at least one thermal image of two or more body joints, and wherein the processing comprises normalizing values extracted from at least one thermal image of at least one body joint of the two or more body joints to values extracted from the at least one thermal image or from at least one different thermal image of at least one different body joint, and wherein the inflammation state is determined using the normalized values.

[0101] Example 46. A system, comprising: a memory circuitry, wherein the memory circuitry stores at least one thermal image of at least one body joint of a subject, wherein the at least one thermal image includes indications of different temperature values in the body joint; a user interface configured to generate and deliver at least one human detectable indications; a control circuitry configured to: extract values of one or more parameters of distribution of the temperatures from at least one region of interest (ROI) in the at least one thermal image which includes elevated temperatures and less elevated temperatures; detect inflammation in the body joint based on the extracted values; and signal the user interface to generate the human detectable indication with information about the detected inflammation.

[0102] Example 47. A system according to example 46, wherein the at least one thermal image stored in the memory is a thermal image of the at least one body joint and of tissue adjacent to the at least one body joint, wherein the at least one thermal image include indications of different temperature values in the body joint and in the adjacent tissue, and wherein the control circuitry is configured to: extract the values of the one or more parameters of distribution of the temperatures from at least one region of interest (ROI) in the at least one thermal image which includes elevated temperatures and less elevated temperatures and pixels indicating temperatures of the at least one body joint and of the adjacent tissue; detect inflammation in the body joint based on the extracted values; and signal the user interface to generate the human detectable indication with information about the detected inflammation.

[0103] Example 48. A system according to example 47, wherein at least 1 % of pixels in the at least one ROI indicate temperature of the adjacent tissue, and wherein the adjacent tissue comprises tissue which is anatomically distinct from the at least one body joint.

[0104] Example 49. A system according to any one of examples 46 to 48, wherein the at least one ROI is a region in the at least one thermal image which includes pixels representing at least 50% of a range of temperature values in the at least one thermal image.

[0105] Example 50. A system according to any one of examples 46 to 49, wherein the at least one ROI comprises a single contiguous region in the at least one thermal image.

[0106] Example 51. A system according to any one of examples 46 to 50, wherein the at least one ROI includes pixels representing at least 25% of an area of the at least one body joint in the at least one thermal image.

[0107] Example 52. A system according to any one of examples 46 to 51, comprising a communication circuitry configured to deliver a signal to a remote device, wherein the control circuitry signals the communication circuitry to deliver the signal to the remote device with information about the detected inflammation.

[0108] Example 53. A system according to any one of examples 46 to 52, wherein the control circuitry is configured to diagnose a clinical state based on the detected inflammation, and to signal the user interface to generate an indication with information about the clinical state.

[0109] Example 54. A system according to example 53, wherein the clinical state comprises latent asymptomatic inflammation, and / or arthritis.

[0110] Example 55. A system according to example 53, wherein the memory stores information about at least one treatment for the clinical state, and wherein the control circuitry signals the user interface to deliver a human detectable indication with information about the at least one treatment or with a suggestion to initiate the at least one treatment, if the inflammation is detected.

[0111] Example 56. A system according to any one of examples 46 to 55, wherein the control circuitry is configured to determine a relation between the extracted values and previously extracted values stored in the memory, and wherein the detect inflammation comprises determine a state of the inflammation in the subject based on the determined relation.

[0112] Example 57. A system according to example 56, wherein the memory stores information about at least one treatment provided to the subject, and wherein the control circuitry is configured to signal the user interface to generate an indication with at least one suggestion for stopping the treatment, modify the treatment and / or to combine the treatment with at least one different treatment, if the determined state is not a target state.

[0113] Example 58. A system according to any one of examples 46 to 57, wherein the user interface is configured to deliver a signal to the control circuitry with information about the at least one ROE

[0114] Example 59. A system according to any one of examples 46 to 58, wherein the control circuitry is configured to automatically determine the at least one ROI using an algorithm, a software program and / or a look-up table stored in the memory.

[0115] Unless otherwise defined, all technical and / or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention pertains. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of embodiments of the invention, exemplary methods and / or materials are described below. In case of conflict, the patent specification, including definitions, will control. In addition, the materials, methods, and examples are illustrative only and are not intended to be necessarily limiting.

[0116] As will be appreciated by one skilled in the art, some embodiments of the present invention may be embodied as a system, method or computer program product. Accordingly, some embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, some embodiments of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon. Implementation of the method and / or system of some embodiments of the invention can involve performing and / or completing selected tasks manually, automatically, or a combination thereof. Moreover, according to actual instrumentation and equipment of some embodiments of the method and / or system of the invention, several selected tasks could be implemented by hardware, by software or by firmware and / or by a combination thereof, e.g., using an operating system.

[0117] For example, hardware for performing selected tasks according to some embodiments of the invention could be implemented as a chip or a circuit. As software, selected tasks according to some embodiments of the invention could be implemented as a plurality of software instructions being executed by a computer using any suitable operating system. In an exemplary embodiment of the invention, one or more tasks according to some exemplary embodiments of method and / or system as described herein are performed by a data processor, such as a computing platform for executing a plurality of instructions. Optionally, the data processor includes a volatile memory for storing instructions and / or data and / or a non-volatile storage, for example, a magnetic hard-disk and / or removable media, for storing instructions and / or data. Optionally, a network connection is provided as well. A display and / or a user input device such as a keyboard or mouse are optionally provided as well.

[0118] Any combination of one or more computer readable medium(s) may be utilized for some embodiments of the invention. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0119] A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0120] Program code embodied on a computer readable medium and / or data used thereby may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0121] Computer program code for carrying out operations for some embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0122] Some embodiments of the present invention may be described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0123] These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0124] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0125] Some of the methods described herein are generally designed only for use by a computer, and may not be feasible or practical for performing purely manually, by a human expert. A human expert who wanted to manually perform similar tasks, such as extraction of textural parameter and calculation of textural parameter values, might be expected to use completely different methods, e.g., making use of expert knowledge and / or the pattern recognition capabilities of the human brain, which would be vastly more efficient than manually going through the steps of the methods described herein.

[0126] BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0127] The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

[0128] Some embodiments of the invention are herein described, by way of example only, with reference to the accompanying drawings and images. With specific reference now to the drawings and images in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of embodiments of the invention. In this regard, the description taken with the drawings and images makes apparent to those skilled in the art how embodiments of the invention may be practiced.

[0129] In the drawings:

[0130] FIG. 1A is a general flow chart of a process for detecting of inflammation of a body joint, according to some exemplary embodiments of the invention;

[0131] FIG. IB is a general flow chart of a process for detecting of inflammation of a body joint using thermal information on the body joint and on tissue adjacent to the body joint, according to some exemplary embodiments of the invention;

[0132] FIG. 1C is a schematic illustration showing a region or interest (ROI) of a thermal image which includes pixels indicating temperature of a body joint, and temperatures of tissue adjacent to the body joint, according to some exemplary embodiments of the invention;

[0133] FIG. 2A is a schematic illustration of a non-inflamed body joint, according to some exemplary embodiments of the invention;

[0134] FIG. 2B is a is a schematic illustration of an inflamed body joint, according to some exemplary embodiments of the invention;

[0135] FIG. 2C is a schematic illustration of a region of interest (ROI), according to some exemplary embodiments ;

[0136] FIG. 3A is a is a schematic illustration of system for analyzing thermal images of a joint and optionally for detection of inflammation of a body joint, according to some exemplary embodiments of the invention; FIG. 3B is a is a schematic illustration showing acquisition of thermal images and optionally detection of inflammation of a body joint using a personal device, for example when a patient is outside a clinic, according to some exemplary embodiments of the invention;

[0137] FIG. 4 is a flow chart of a detailed process for detecting of inflammation of a body joint, according to some exemplary embodiments of the invention;

[0138] FIG. 5 is a flow chart of a process for screening and / or diagnosing a patient with joint inflammation using data received from thermal images, according to some exemplary embodiments of the invention;

[0139] FIG. 6 is a flow chart of a process in which a device or a system is used for monitoring an effect of a treatment, according to some exemplary embodiments of the invention;

[0140] FIG. 7 A is a flow chart of a process used during a study;

[0141] FIGs. 7B-7G are thermal images acquired during the study;

[0142] FIGs. 7H and 71 are images showing selection, for example marking of a ROI in a thermal image of hands, as performed in the study, and according to some exemplary embodiments of the invention;

[0143] FIGs. 7J and 7K are images showing selection of a ROI in a thermal image of a knee (FIG. 7J), and a thermal image of an ankle (FIG. 7K), as performed in the study, and according to some exemplary embodiments of the invention;

[0144] FIG. 8 is a schematic illustration showing normalization of data as performed in the study, and according to some exemplary embodiments of the invention;

[0145] FIG. 9A is a graph showing differences in Entropy between a group of subjects having unilateral inflammation and a group of healthy subjects (control group);

[0146] FIG. 9B is a graph showing differences in mean temperature between a group of subjects having unilateral inflammation and a group of healthy subjects (control group);

[0147] FIG. 9C is a graph showing differences in maximum temperature between a group of subjects having unilateral inflammation and a group of healthy subjects (control group);

[0148] FIG. 9D is a graph showing differences in kurtosis between a group of subjects having unilateral inflammation and a group of healthy subjects (control group);

[0149] FIG. 9E is a graph showing differences in skewness between a group of subjects having unilateral inflammation and a group of healthy subjects (control group);

[0150] FIG. 9F is a graph showing differences in local entropy between a group of subjects having unilateral inflammation and a group of healthy subjects (control group);

[0151] FIGs. 10A-10F are confusion matrices showing an ability of an algorithm to detect inflammation; FIG. 11 is a thermal image of a hands of a human subject, as taken during a validation study, and according to some exemplary embodiments of the invention;

[0152] FIGs. 12A-12E are thermal images of knees of a human subject, taken prior to a treatment (FIG. 12A) and following the treatment (FIGs. 12B-12E) during a validation study, and according to some exemplary embodiments of the invention;

[0153] FIG. 13A is a graph showing changes in entropy and local entropy following a treatment;

[0154] FIG. 13B is a graph showing changes in mean temperature and maximal temperature following a treatment;

[0155] FIG. 14 is a thermal image of a human subject knees, taken during a validation study, and according to some exemplary embodiments of the invention; and

[0156] FIGs. 15A-15B are thermal images of a hand of a human subject acquired prior to a treatment (FIG. 15A) and following the treatment (FIG. 15B), taken during a validation study, and according to some exemplary embodiments of the invention.

[0157] DESCRIPTION OF SPECIFIC EMBODIMENTS OF THE INVENTION

[0158] The present invention, in some embodiments thereof, relates to detection of inflammation and, more particularly, but not exclusively, to detection of inflammation in one or more body joints.

[0159] An aspect of some embodiments of the invention relates to detecting inflammation of at least one body joint based on information from at least one thermal image of the body joint. In some embodiments, the inflammation is detected based on a distribution of temperature in at least one region of interest (RO I) defined in the thermal image that include pixels representing elevated temperatures and less elevated temperatures. In some embodiments, the temperatures are measured in a Celsius scale or in a Fahrenheit scale.

[0160] According to some embodiments, the distribution of the at least one ROI in the thermal image includes inflamed regions of the at least one joint and non-inflamed regions of the at least one joint. Alternatively, the at least one ROI includes inflamed regions and less inflamed regions of the joint.

[0161] In some embodiments, the pixels in the at least one ROI represent varying temperature values, for example pixels in the ROI representing temperatures that vary in at least 5%, in at least 10%, in at least 25% in at least 50% relative to other pixels in the ROI.

[0162] According to some embodiments, the at least one ROI is a contiguous, optionally a single, region in the at least one thermal image. In some embodiments, the at least one ROI is a region in the at least one thermal image which includes pixels representing at least 25% of a range of temperature values in the at least one thermal image, for example at least 50%, at least 60%, at least 70%, at least 80%, at least 90%, at least 95% or any intermediate, smaller or larger percentage value. In some embodiments, the at least one ROI has an area size of at least 1 cm2, for example an area size of at least 2 cm2, at least 5 cm2, at least 10 cm2, at least 20 cm2, or any intermediate, smaller or larger area size in the at least one thermal image. In some embodiments, the at least on ROI includes pixels representing at least 30%, at least 50%, at least 60%, at least 70%, at least 80%, at least 90%, at least 95%, of a body joint area in the thermal image.

[0163] According to some embodiments, the detection of inflammation is based on differences in temperatures and / or temperature distribution between corresponding, for example contralateral joints, optionally between temperatures and / or temperatures distribution in a first joint and temperatures and / or temperatures distribution in a second joint, or indications thereof. In some embodiments, when calculating a difference between the at least 2 corresponding joints, the temperature and / or temperature distribution in at least one first joint is used as a baseline or a reference value. It should be understood that in some embodiments calculating a value of a parameter, for example temperature and / or temperature distribution, means calculating a central tendency measure of the value, for example mean, meadian and / or mode, and using the calculated central tendency measure for further analysis, for example for determine a relation between the central tendency measure value and a baseline or a reference value.

[0164] According to some exemplary embodiments, values of at least one parameter of a texture of the temperature distribution in at least one ROI in a thermal image, are calculated. In some embodiments, the inflammation is detected based on the calculated values, based on a relation between the calculated values for a first joint and calculated values for a second corresponding joint or a central tendency measure value thereof, or based on a relation between the calculated values and an indication, for example an indication of a threshold value, a baseline value or a reference value.

[0165] According to some embodiments, detection of inflammation comprises classification of inflammation and / or determining inflammation severity. Optionally, detection of inflammation comprises detection of latent inflammation, latent asymptomatic inflammation, arthritis, and / or septic arthritis. In some embodiments, a body joint comprises a limb body joint, for example an ankle, a wrist, a knee.

[0166] According to some embodiments, the at least one parameter related to the distribution of temperature is a textural parameter, for example entropy, local entropy, skewness, kurtosis or a central tendency thereof. In some embodiments, the inflammation is detected based on the at least one distribution parameter and based on temperature value readings from the body joint, for example from the at least one ROI. In some embodiments, the inflammation is detected based on an increase in non-uniformity of temperature distribution, relative to a non-uniformity level of temperature distribution in a non-inflamed body joint. Alternatively, the inflammation is detected based on a decrease in uniformity of temperature distribution, relative to uniformity level of temperature distribution of in a non-inflamed body joint. Optionally, a level of non-uniformity or uniformity of temperature distribution indicates a level or severity of inflammation of the joint.

[0167] According to some embodiments, and without being bound by any theory, an inflammation process in a body joint may lead to vasodilation (widening of blood vessels), optionally resulting with an increase in blood volume at the body joint region. Additionally or optionally, the inflammation process leads to an increase in vascular permeability, resulting with leakage of fluid and other molecules out of the blood vessels and into the surrounding tissue of the joint. The increase in blood volume and / or the increase in vascular permeability, increase a temperature and changes temperature distribution at the joint area, relative to a non-inflamed joint area.

[0168] A potential advantage of detecting inflammation of a body joint based on at least one parameter of temperature distribution or changes thereof relative to using temperature values, may be that temperature distribution at the joint region is less affected by contact of the joint with a thermal energy source, for example a heat source or a cold source, compared to the effect of the thermal energy source on temperature values, and therefore may be more reliable.

[0169] A potential advantage of using a ROI which includes different temperatures, corresponding to tissue with different levels of inflammation may be that it allows internal data normalization per a specific joint of a specific subject, optionally leading to more reliable and accurate results.

[0170] A potential advantage of using a ROI that includes a large area of a joint in a thermal image may be that it allows to reduce noise in temperatures in the ROI coming from a change in temperatures of a body joint due to external environment, for example a thermal source located adjacent to the joint, relative to a change in temperature due to inflammation. Reducing the noise in temperature measurements which is a result of an external thermal source allows a system that uses the large area ROI, and / or one or more of the methods described herein, to be more suitable for thermal measurements and / or monitoring inflammation in an uncontrolled thermal environment such as at home or outside a clinic.

[0171] According to some embodiments, the detection of inflammation as described herein includes detection of at least one of, latent inflammation, Arthritis, Osteoarthritis, Rheumatoid arthritis, Psoriatic arthritis, Gout, Juvenile idiopathic arthritis (JIA), Infectious arthritis, Reactive arthritis, Septic arthritis, and / or Vasculitis. It should be understood that detection of inflammation based on different parameters, values or information extracted from thermal data, as described herein, includes detection of inflammation based on a central tendency thereof.

[0172] An aspect of some embodiments of the invention relates to detecting inflammation of a body joint, based on local entropy of temperatures in a thermal image of the body joint. In some embodiment, the inflammation is detected based on a relation between measurements of the local entropy and a reference value or indication thereof, for example when the local entropy measurements are lower or higher than the reference value. In some embodiments, the inflammation is detected based on differences between local entropy measurements of temperatures of a first body joint, and local entropy measurements of temperatures of a second corresponding body joint, for example a contralateral body joint.

[0173] According to some embodiments, the local entropy of temperatures is measured in at least one ROI which includes at least 30%, for example at least 50%, at least 6o5, at least 70%, or any intermediate, smaller or larger percentage of pixels of a body joint in at least one thermal image. In some embodiments, the at least one ROI include pixels that represent elevated and less elevated temperatures, for example temperature values. In some embodiments, a central tendency of the local entropy is measured, and the detection of inflammation is based on a relation between the measured central tendency of local entropy and at least one reference or a baseline value. In some embodiments, a relation between a central tendency measure of local entropy from a first joint and a central tendency measure of local entropy from a second joint is determined. In some embodiments, the detection of inflammation is based on the relation between the central tendency measures of local entropy of both joints.

[0174] According to some embodiments, detection of inflammation comprises classifying an inflammation and / or determining a severity of inflammation

[0175] Optionally, the term local entropy means a measure of a disorder or randomness, for example disorganization, at a specific location, volume and / or area. Optionally, the term local entropy means a measure of a disorder or randomness of a specific feature, for example temperature intensity or values thereof, at a specific volume or area. In some embodiments, local entropy is measured in an area having a size between 0.2 cm2and 0.9 cm2in a thermal image, for example an area having a size between 0.2 cm2and 0.5 cm2, an area having a size between 0.4 cm2and 0.6 cm2, an area having a size between 0.5 cm2and 0.9 cm2, an area having a size between 0.4 cm2and 0.7 cm2, or any intermediate, smaller or larger range of values. Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details set forth in the following description or exemplified by the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways.

[0176] Exemplary general process for inflammation detection

[0177] According to some exemplary embodiments, thermal data acquired from at least one body joint allows to detect an inflammatory process in the joint tissue and / or in tissue surrounding the joint. In some embodiments, the detection of the inflammatory process is based on thermal data from a ROI which includes a range of temperatures, optionally corresponding to tissue in different degrees of inflammation, for example both inflamed tissues and non- or less inflamed tissue.

[0178] According to some exemplary embodiments, inflammation is detected based on a distribution of temperatures in the ROI, or at least one parameter of the distribution, for example entropy, local entropy, skewness and / or kurtosis. Optionally, the joint inflammation is detected based on a combination between the distribution of temperatures and temperatures values in the ROI.

[0179] Reference is now made to fig. 1A, depicting a general process for detection of inflammation in a body joint, according to some exemplary embodiments of the invention.

[0180] According to some exemplary embodiments, at least one thermal image of a body joint is provided, at block 102. In some embodiments, at least one thermal image of a first joint and at least one thermal image of a second corresponding joint is provided. In some embodiments, at least one thermal image of both corresponding body joints is provided.

[0181] According to some exemplary embodiments, at least one ROI including different temperatures is selected at block 104. In some embodiments, the at least one ROI is selected for each joint. In some embodiments, the at least one ROI includes sub-regions of different temperatures, optionally corresponding to inflamed tissue and non- or less inflamed tissue of the joint.

[0182] According to some exemplary embodiments, values of at least one texture parameter of the temperatures distribution are extracted at block 106. In some embodiments, the values of the at least one texture parameter are extracted from the at least one ROI selected at block 104. In some embodiments, a central tendency value of the values is extracted. As used herein, the term values means also a single value.

[0183] According to some exemplary embodiments, inflammation of the body joint is detected at block 108. In some embodiments, the inflammation is detected based on the values extracted at block 106. In some embodiments, the inflammation is detected by determining a relation between the extracted values and one or more values or indications thereof. In some embodiments, the inflammation is detected based on a relation between the extracted values and previously calculated values, for example values of the parameter previously calculated for the same joint, or values of the parameter calculated for a corresponding joint or a contralateral joint.

[0184] According to some exemplary embodiments, inflammation of the body joint is detected at block 108, when a change in uniformity, for example an increase in uniformity, of the temperatures distribution is detected, compared to uniformity of temperatures distribution previously calculated for the same joint, or to uniformity of temperatures distribution of a corresponding joint.

[0185] Exemplary general process for inflammation detection based on information on body joint and adjacent tissue

[0186] Reference is now made to fig. IB, depicting a general process for detection of inflammation in a body joint based on thermal information about the body joint and about tissue adjacent to the body joint, according to some exemplary embodiments of the invention.

[0187] According to some exemplary embodiments, at least one thermal image of a body joint and of adjacent tissue is provided, at block 112. In some embodiments, at least one thermal image of a first joint and first adjacent tissue and at least one thermal image of a second corresponding joint and of second adjacent tissue is provided. In some embodiments, at least one thermal image of both corresponding body joints, with their adjacent tissues is provided.

[0188] According to some exemplary embodiments, at least one ROI including different temperatures is selected at block 114. In some embodiments, the at least one ROI is selected for each joint and its adjacent tissue. In some embodiments, the at least one ROI includes sub-regions of different temperatures, optionally corresponding to inflamed tissue and non- or less inflamed tissue of the joint, and of non-inflamed tissue in the adjacent tissue.

[0189] According to some exemplary embodiments, the at least one ROI includes pixels which indicate temperatures of the body joint and temperatures of tissue adjacent to the body joint. In some embodiments, at least 1%, at least 3%, at least 5%, at least 10%, at least 20%, or any intermediate, smaller or larger percentage value of the pixels, indicate temperatures of the adjacent tissue. In some embodiments, the adjacent tissue comprises tissue located outside anatomical borders of the body joint. In some embodiments, the adjacent tissue is at least partially in contact with tissue of the body joint, and have a distinctive border line with the body joint. In some embodiments, the at least one ROI comprises pixels indicating temperatures of the border line and / or tissue from both sides of the borderline. In some embodiments, the adjacent tissue comprises non-inflamed tissue.

[0190] According to some exemplary embodiments, the adjacent tissue is anatomically and / or physiologically distinct from the body joint.

[0191] According to some exemplary embodiments, values of at least one texture parameter of the temperatures distribution are extracted at block 116. In some embodiments, the values of the at least one texture parameter are extracted from the at least one ROI selected at block 114. In some embodiments, a central tendency value of the values is extracted. As used herein, the term values means also a single value.

[0192] According to some exemplary embodiments, inflammation of the body joint is detected at block 118. In some embodiments, the inflammation is detected based on the values extracted at block 116. In some embodiments, the inflammation is detected by determining a relation between the extracted values and one or more values or indications thereof. In some embodiments, the inflammation is detected based on a relation between the extracted values and previously calculated values, for example values of the parameter previously calculated for the same joint, or values of the parameter calculated for a corresponding joint or a contralateral joint. In some embodiments, the inflammation is detected based on a relation between values extracted from pixels indicating temperatures of the body joint, and values extracted from pixels indicating temperatures of the adjacent tissue.

[0193] According to some exemplary embodiments, inflammation of the body joint is detected at block 118, when a change in uniformity, for example an increase in uniformity, of the temperatures distribution is detected, compared to uniformity of temperatures distribution previously calculated for the same joint and adjacent tissue, or to uniformity of temperatures distribution of a corresponding joint and its adjacent tissue, or a relation thereof.

[0194] According to some exemplary embodiments, during processing of the ROI, a relation between values of one or more parameters, for example of temperature distribution texture parameter, calculated for pixels of the body joint and pixels of the adjacent tissue is determined. Optionally, parameter values calculated for the adjacent tissue are used as a reference, for example an internal reference of the ROI, optionally for normalizing parameter values calculated for the body joint.

[0195] According to some exemplary embodiments, inflammation in the body joint is detected based on changes in the determined relation, and / or based on changes in normalized values of the parameter calculated for the body joint. Exemplary ROI with information about body joint and adjacent tissue

[0196] Reference is now made to fig. 1C, depicting a ROI selected within a thermal image which corresponds to a body joint and to tissue adjacent to the body joint, according to some exemplary embodiments of the invention.

[0197] According to some exemplary embodiments, a thermal image 120 of at least one body joint 122 and of tissue 124 adjacent to the body joint 122, is acquired. In some embodiments, the thermal image is acquired from a distance between 0.5 meter to 2 meters, a distance between 1 meter and 2 meters, for example from a distance of about 1.5 meters, or any intermediate, smaller or larger distance, from the body joint and adjacent tissue.

[0198] According to some exemplary embodiments, a ROI 126 is selected, optionally marked, in the thermal image 120. In some embodiments, the ROI 126 includes pixels of the thermal image which indicate temperatures of the body joint 122 and of the adjacent tissue 124. In some embodiments, the ROI includes pixels of a border 128 between the body joint 122 and the adjacent tissue 124.

[0199] In some embodiments, a ROI, for example ROI 126 comprises at least one pixel indicating temperature of the tissue adjacent to the body joint, for example adjacent tissue 124.

[0200] Exemplary database

[0201] According to some exemplary embodiments, the extracted values of one or more temperature distribution texture parameters are stored in a database or are used to build a database, optionally instead of using the extracted values for detecting inflammation in a subject. In some embodiments, the database stores information on one or more subjects and thermal data from one or more joints of the one or more subjects. In some embodiments, the thermal data comprises at least one of, thermal image of at least one body joint of the subject, and extracted values of at least one parameter of temperatures distribution in the thermal image. In some embodiments, the at least one parameter comprises at least one of, entropy, local entropy, kurtosis, and / or skewness, of temperatures distribution. Additionally, the database includes values of temperature parameters comprising mean temperature, maximum temperature and minimum temperature.

[0202] According to some exemplary embodiments, the database is used to provide healthcare professionals information about patients and / or for improvement of thermal imaging processing techniques, for example for generating new protocols for processing of thermal images. Exemplary change in heat distribution

[0203] According to some exemplary embodiments, inflammation in a body joint is often characterized by vasodilation of blood vessels which increases blood volume in the joint region. Additionally or alternatively, inflammation is characterized in an increase in vascular permeability, leading to leakage of fluid out from the blood vessels. In some embodiments, the vasodilation and / or increase in permeability result with a change in the distribution of heat emitted from the joint region, compared to distribution of heat in a non-inflamed joint region. In some embodiments, the change in heat distribution comprises a change, for example an increases in non-uniformity of heat distribution. In some embodiments, the change in heat distribution and / or the inflammation leads to a change in textural parameters extracted from a ROI in a thermal image which includes an inflamed body joint or a portion thereof. In some embodiments, the heat distribution is shown in a thermal image by pixels representing different temperatures.

[0204] Reference is now made to figs. 2A and 2B depicting heat emission from a non-inflamed joint (fig. 2A), and from an inflamed body joint (fig. 2B), according to some exemplary embodiments of the invention.

[0205] According to some exemplary embodiments, for example as shown in fig. 2A, blood 202 flows within blood vessels 204 of a non-inflamed body joint, for example body joint 206. In fig. 2A, the body joint 206 is defined as a region between boundaries 208 and 210. In some embodiments, heat 212 emitted from tissue, for example blood vessels of the non-inflamed joint 206 is distributed relatively uniformly in the joint region, for example distributed with variations smaller than 10%, for example smaller than 5%, smaller than 2% or any intermediate, smaller or larger percentage value between regions of the body joint, having a size of at least 5 cm3, for example regions having a size of at least 10 cm3, at least 15 cm3, at least 25 cm3or any intermediate, smaller or larger size.

[0206] According to some exemplary embodiments, for example as shown in fig. 2B, in an inflamed body joint 216, at least some of the blood vessels, for example blood vessel 204, are dilated, resulting with an increase in flow of blood 202 into the joint region between boundaries 208 and 210. In some embodiments, the vasodilation changes the distribution of heat 212 emitted from the tissue. In some embodiments, vasodilation due to inflammation increases the nonuniformity of heat distribution within the joint.

[0207] According to some exemplary embodiments, the change in heat distribution due to inflammation related processes, for example the dilation of one or more blood vessels associated with the joint, for example blood vessels delivering blood to and / or from the joint, or one or more blood vessels adjacent to the joint, is shown in a thermal image of the joint as a change in distribution of temperatures represented by pixels in the thermal image, relative to at least one reference value, for example relative to distribution of temperatures in a corresponding joint.

[0208] Exemplary region of interest (ROI)

[0209] According to some exemplary embodiments, following the acquiring of a thermal image, at least one ROI is selected in the thermal image. Reference is now made to fig. 2C, depicting a ROI in a thermal image, according to some exemplary embodiments of the invention.

[0210] According to some exemplary embodiments, a thermal image of at least one body joint, is acquired by at least one infrared sensor, for example an infrared sensor of a thermal camera, optionally using Forward Looking Infrared (FLIR) technology. In some embodiments, the thermal image comprises a thermogram 230 showing differences in temperatures between different parts of the at least one joint. In some embodiments, the different parts include sub-regions 232, 234, 236, 238, and 240, each or at least some of the sub-regions include different temperatures.

[0211] According to some exemplary embodiments, a ROI, for example ROI 242 in the thermogram 230 is determined, optionally automatically by a control circuitry. In some embodiments, the ROI 242 is determined according to a size of the thermogram 230 and / or a size of the joint. Alternatively, the ROI 242 is manually selected. In some embodiments, a size of the ROI 242 is at least 0.16 cm2, for example at least 0.25 cm2, 0.36 cm2, 0.5 cm2, or any intermediate, smaller or larger area size. In some embodiments, the ROI 242 comprises two or more sub regions of the thermogram 230 that have different temperatures, for example sub-regions 236, 234 and 238. In some embodiments, the ROI 242 area is at least 50% of an area of a joint shown in the thermogram 230, for example at least 60%, at least 70%, at least 80% of a joint area, or any intermediate, smaller or larger area of the joint.

[0212] Exemplary system

[0213] According to some exemplary embodiments, a system for detection of an inflammation in a body joint is designed to be used in a clinic, in a medical facility, for example a hospital, and / or at home, for example a home of a patient.

[0214] Reference is now made to fig. 3A depicting a system for detection of inflammation, according to some exemplary embodiments of the invention.

[0215] According to some exemplary embodiments, a system, for example system 302 comprises a control unit 304, which is connectable to a thermal imager 306. Alternatively, the thermal imager 306 is an integral part of the control unit 304. In some embodiments, the thermal imager 306 comprises a thermal camera and / or a thermal sensor, and is configured to acquire a thermal image, for example an infrared image, of part of a body. In some embodiments, the thermal imager 306 is configured to acquire the thermal image using FLIR technology. In some embodiments, the control unit 304 comprises a control circuitry 308 is functionally connected to the thermal imager 306.

[0216] According to some exemplary embodiments, the thermal imager 306 is configured to acquire a thermal image of at least one joint 310 of a subject 312. In some embodiments, the control circuitry receives the thermal image from the thermal imager 306. In some embodiments, the control circuitry 308 is configured to process the received thermal image using one or more of a formula, an algorithm, a model, and / or a lookup table, stored in a memory 314 of the control unit 304.

[0217] According to some exemplary embodiments, processing of the thermal image by the control circuitry 308 comprises determining at least one ROI in the thermal image, extracting at least one parameter of a distribution of temperatures in the ROI, extracting of values of the at least one parameter, and detecting of inflammation in the ROI based on the extracted values or a central tendency thereof. In some embodiments, the control circuitry 308 is configured to detect inflammation in the ROI based on the extracted values, and based on temperatures in the ROI or a central tendency thereof.

[0218] According to some exemplary embodiments, the control unit 304 comprises a communication circuitry 316, configured to communicate, for example to receive and / or transmit signals, with a remote device 318. In some embodiments, the remote device 318 comprises a computer, a mobile device, a cellular device, a cloud storage, a cloud processing, a database, a server, or any device located at a distance of more than 1 meter from the control unit 304. In some embodiments, the communication circuitry 316 is configured to communicate with the remote device 318 using wireless signals, for example Bluetooth, Wi-Fi, Near Field Communication (NFC), and / or infrared. Alternatively or additionally, the communication circuitry 316 is configured to communicate with the remote device 318 using wired communication. In some embodiments, the system 302 comprises the remote device 318.

[0219] According to some exemplary embodiments, at least some of the processing of the thermal image and / or the detection of the inflammation is performed in the remote device 318. For example, the thermal image or temperatures and distribution in the ROI is transferred to the remote device 318 using the communication circuitry 316, and the remote device 318 transmits an indication to the control unit 304 about a detected inflammation, type of inflammation, severity of inflammation, instructions and / or suggestions how to modify a treatment, signal processing and / or acquisition of the thermal image. According to some exemplary embodiments, the remote device 318 is in communication with a physician 320, optionally delivering to the physician 320, or any health care provider, one or more indications regarding a state of the joint, results of the processing of thermal data, instructions and / or suggestions regarding a treatment. Optionally, the remote device 318 is configured to receive information from an external imaging device 322, for example an ultrasound device, a computed tomography (CT) device, a magnetic resonance imaging (MRI) device and / or a thermography device.

[0220] According to some exemplary embodiments, the remote device 318 is in communication with a device of the subject 312, for example a personal device 324. In some embodiments, the remote device 318 is configured to receive from the subject 312 input data using the device 324, for example input data regarding at least one symptom of an inflammation. Alternatively or additionally, the remote device 318 is configured to deliver to the subject 312 one or more indications using the device 324 regarding a detected inflammation, a treatment delivered to the subject, information from the physician. In some embodiments, the remote device communicates with the patient and / or physician using an application software installed in a device, for example device 324. In some embodiments, the remote device 318 delivers indication with instructions to the subject with instructions or suggestions how to modify a current treatment or instructions to stop the treatment, optionally using the device 324.

[0221] According to some exemplary embodiments, for example as shown in fig. 3B the system is a system that can use a thermal imager and a computer device of the patient, for example for home monitoring of a joint state and / or an inflammation state, according to some exemplary embodiments of the invention.

[0222] According to some exemplary embodiments, a device 330, for example a cellular device, comprises a thermal imager module 332, or is functionally connectable to a thermal imager module 332. In some embodiments, the thermal imager module 332 is configured to acquire a thermal image of joint 334 of subject 336. Optionally, the device 330 stores and operates a software that is configured to receive and process the acquired thermal image. In some embodiments, the device 330, optionally using the software installed in a memory of the device 330, detects inflammation in the joint based on the acquired thermal image, and generates an indication, for example a human detectable indication regarding the detection of inflammation or the processing of the thermal image.

[0223] According to some exemplary embodiments, the device 330 is in communication with a remote device 335, for example a device that is similar to remote device 318. In some embodiments, the device 330 is a cellular or a mobile device of the subject or a caregiver of the subject, which operates as control unit 304. In some embodiments, the device 330 interacts with the subject 336 or with a caregiver of the subject 336 using a user interface of the device. Additionally or optionally, the device 330 communicates with a physician 338, for example using a communication circuitry of the device 330. Optionally, the remote device 335 is configured to communicate with the physician 338, as described above in fig. 3A.

[0224] According to some exemplary embodiments, the control unit 304 comprises a user interface 315, which is configured to generate at least one indication, for example a human detectable indication, optionally in response to a signal from the control circuitry 308. In some embodiments, the human detectable indication comprises an audio indication and / or a visual indication.

[0225] Exemplary thermal image data processing

[0226] According to some exemplary embodiments, a system, optionally a control unit of the system, for example system 302 and control unit 304 shown in fig. 3A, is configured to process thermal data from a body joint, and to identify and / or to classify an inflammation in the joint.

[0227] Reference is now made to fig. 4, depicting a method for processing of thermal image data, according to some exemplary embodiments of the invention. In some embodiments, the method described herein is configured to be performed at least party or entirely by a system, a control unit, and / or a control circuitry.

[0228] According to some exemplary embodiments, at least one thermal image of a body joint is received, at block 402. In some embodiments, data from at least one thermal image is received at block 402. In some embodiments, the thermal image or data is received from a thermal imager, for example a thermal camera. Alternatively, the thermal image or data is received from a storage device, for example a cloud storage device or a physical storage device.

[0229] According to some exemplary embodiments, the system selects, optionally automatically, at least one ROI, at block 404. In some embodiments, the system selects at least one ROI in the at least one received thermal image. In some embodiments, the ROI is ROI 242 shown in fig. 2C. In some embodiments, the selected ROI includes sub-regions with different temperatures. In some embodiments, the ROI has a size that includes at least 60%, at least 70%, at least 80%, at least 90%, or any intermediate, smaller or larger percentage of a joint shown in the thermal image.

[0230] According to some exemplary embodiments, the ROI is selected based on pre-determined boundaries and / or a predetermined size of a ROI. In some embodiments, the system determines boundaries of a joint, as visualized in a thermal image, for example based on changes in temperatures in the thermal image. In some embodiments, the ROI is selected based on the determined boundaries. According to some exemplary embodiments, the system extracts values of at least one parameter of distribution of temperatures at block 406. In some embodiments, the at least one parameter of the distribution of temperatures comprises a textural parameter, for example entropy and local entropy. In some embodiments, the at least one textural parameter comprises skewness and / or kurtosis.

[0231] In some embodiments, the parameter values are extracted for the temperatures within the ROI selected at block 404. In some embodiments, extracting the values of the at least one parameter comprises extracting a central tendency of the parameter value, for example mean, median and / or mode, of the extracted values.

[0232] According to some exemplary embodiments, optionally the system determines a level of non-uniformity, at block 410. In some embodiments, the level of non-uniformity is determined based on the distribution of temperatures in the ROI. Alternatively or additionally, the level of non- uniformity is based on the parameter values extracted at block 406, or central tendency thereof.

[0233] According to some exemplary embodiments, high values of entropy, local entropy and / or kurtosis indicate high non-uniformity level of temperatures within the selected ROI, for example in comparison to previously extracted values, and / or in comparison to values extracted from at least one different ROI, for example a ROI in a thermal image of a corresponding joint.

[0234] According to some exemplary embodiments, optionally, values of at least one parameter of temperature intensity in the ROI, are extracted at block 412. In some embodiments, the at least one parameter comprises a central tendency of the temperatures in the selected ROI.

[0235] According to some exemplary embodiments, the system detects inflammation in the body joint, at block 414. In some embodiments, the body joint is the body joint included in the ROI selected at block 404. In some embodiments, the system detects the inflammation in the body joint, based on the values extracted at block 406 or a central tendency thereof. Alternatively or additionally, the system detects inflammation in the body joint based on the non-uniformity level, optionally determined at block 410. Alternatively or additionally, the system detects the inflammation based on the values of temperature intensity parameter, optionally extracted at block 412.

[0236] According to some exemplary embodiments, detecting of inflammation comprises generating a probability score that a subject has inflammation in the at least one joint.

[0237] According to some exemplary embodiments, the system optionally determines a type and / or severity of the detected inflammation, at block 416. In some embodiments, the system determines the type and / or severity by determining a relation between one or more of the values extracted at blocks 406 and 412 and the determined uniformity level, and one or more indications stored in a memory associated with the system, for example a memory of a control unit, or a memory of a remote device.

[0238] According to some exemplary embodiments, the system generates an indication. In some embodiments, the indication is generated according to at least one of, the detection of inflammation, the determined inflammation type and / or the determined inflammation severity. In some embodiments, the generated indication includes information on the detected inflammation, the determined type and / or the determined severity of the inflammation. In some embodiments, the generated indication includes suggestions whether or not to treat the inflammation, and / or a suggested treatment and a treatment regime for treating the inflammation.

[0239] According to some exemplary embodiments, the generated indication, is delivered to a patient, to a caregiver of the patient, to a physician, to a health care provider, and / or to a health maintenance organization (HMO), at block 420. In some embodiments, the generated indication is delivered by a remote device, for example the remote device 318 or the remote device 335. Alternatively or additionally, the generated indication is delivered using a user interface of a control unit, for example user interface 315 shown in fig. 3A. Alternatively or additionally, the generated indication is delivered using a user interface of the device 330 shown in fig. 3B. In some embodiments, the delivered indication comprises the probability score generated at block 414.

[0240] According to some exemplary embodiments, parameter values extracted at blocks 406 and / or blocks 412 are normalized relative to parameter values extracted from at least one different thermal image or from at least one different ROI. In some embodiments, the extracted parameter values are normalized to parameter values extracted from a corresponding joint, for example a contralateral joint. In some embodiments, the optionally determining of non-uniformity level at block 410, the detecting of inflammation at block 414, and / or the optional determining of inflammation type and / or severity at block 416, is based on the normalized parameter values.

[0241] Exemplary patient screening and / or diagnosis

[0242] Joint inflammation is currently diagnosed using imaging analysis devices, for example using a magnetic resonance imaging (MRI) device, which are expensive and large devices and therefore not common and available in every medical facility and cannot be used outside a medical facility, for example at home, due to their size. In some embodiments, thermography replaces the imaging analysis for diagnosing a subject with joint inflammation. Alternatively, thermography is used for screening of patients, for example to decide who is likely to suffer from joint inflammation, and therefore needs to undergo an imaging analysis. According to some exemplary embodiments, a decision whether or not to apply the methods described herein to detect inflammation in a body joint is based on input received from the subject, for example on pain sensation and feeling, and / or based on information about the subject, for example medical history, family history, profession, drug regime, and / or current and past clinical state and / or medical state. Alternatively or additionally, the decision is based on whether or not the subject experienced inflammation in at least one body joint in the past.

[0243] Reference is now made to fig. 5, depicting a process for screening and / or diagnosing a subject with joint inflammation, according to some exemplary embodiments of the invention.

[0244] According to some exemplary embodiments, a subject arrives to a clinic with one or more symptoms of joint inflammation, with regard to at least one joint, at block 502. In some embodiments, the one or more symptoms comprise at least one of, pain in a joint area, swelling of a joint area, stiffness, and / or a limited range of motion. In some embodiments, the one or more symptoms are accompanied by one or more general and systemic symptoms which include at least one of, fatigue, loss of appetite, fever, weight loss, and / or skin rash.

[0245] According to some exemplary embodiments, the subject is a subject that is in a high risk for developing joint inflammation, for example, an adult female, has a family history of rheumatic disease, and smoking.

[0246] According to some exemplary embodiments, thermography of the at least one joint is performed at block 506. In some embodiments, thermography is performed as described in fig. 4.

[0247] According to some exemplary embodiments, inflammation in the at least one joint is diagnosed at block 512, based on the thermography performed at block 506.

[0248] Alternatively, following thermography, an estimation of inflammation in the at least one joint is performed at block 508. In some embodiments, the estimation of inflammation is performed at block 508 based on the results of the thermography. In some embodiments, estimation of inflammation comprises receiving from a system a probability score that the subject suffers from inflammation in the at least one joint. In some embodiments, the score is received from the system as an indication, for example the indication delivered at block 420 of fig. 4.

[0249] According to some exemplary embodiments, the subject performs an imaging analysis of the joint, at block 510. In some embodiments, the subject performs the imaging analysis, for example MRI, based on the results of the estimation at block 508. In some embodiments, if a physician estimates that the subject has inflammation in the at least one joint, the subject is sent to perform the imaging analysis. In some embodiments, if a probability score for having inflammation is higher than a predetermined value, for example is higher than 50%, higher than 60%, higher than 70%, or higher than any intermediate, smaller or larger percentage, an indication is received from the system suggesting that the subject performs an imaging analysis of the at least one joint.

[0250] According to some exemplary embodiments, inflammation in the at least one joint is diagnosed at block 512 based on the results of the imaging analysis performed at block 510. Optionally, the inflammation is diagnosed based on the results of both the thermography performed at block 506 and the imaging analysis performed at block 510.

[0251] According to some exemplary embodiments, a treatment for the diagnosed inflammation is determined at block 514. In some embodiments, the treatment is determined by a health care professional, for example a physician or an expert. In some embodiments, the treatment is determined based on a suggestion from a system, for example system 302 shown in fig. 3A. In some embodiments, the determined treatment comprises at least one of, a pain reliever bioactive agent, for example drug, an anti-inflammatory bioactive agent, corticosteroids, Disease-modifying antirheumatic drugs (DMARDs), biologic drugs, physical therapy and / or surgery.

[0252] According to some exemplary embodiments, the determined treatment is delivered at block 516. In some embodiments, the treatment is delivered during a time period of at least one week, at least one month, at least 6 months, at least one year, or any intermediate, shorter or longer time duration.

[0253] According to some exemplary embodiments, a state of a joint is monitored using thermography, at block 518. In some embodiments, the joint is the at least one joint diagnosed with inflammation at block 512. In some embodiments, the joint state is monitored during the treatment, for example to determine an efficacy of the treatment. Alternatively or additionally, the joint state is monitored when completing the treatment, for example to determine if the provided treatment was effective.

[0254] Exemplary monitoring of treatment effect

[0255] According to some exemplary embodiments, thermography is used for monitoring an effect of a treatment provided to a subject already diagnosed with joint inflammation. In some embodiments, the monitoring is performed outside a clinic or a medical facility, for example at the subject home or workplace. In some embodiments, the thermography is performed using a mobile device, for example a cellular phone or a cellular device functionally coupled to a thermal imager, for example the device 330 shown in fig. 3B. In some embodiments, the monitoring is performed during a treatment period or after a completion of the treatment. Reference is now made to fig. 6 depicting a method for monitoring, optionally using a system, an effect of a treatment for joint inflammation, according to some exemplary embodiments of the invention.

[0256] According to some exemplary embodiments, a treatment program for treating joint inflammation is initiated, at block 602. In some embodiments, a system receives an indication about the initiation of the treatment program, for example using a software program installed in a memory of a device of a healthcare professional, or a software program installed in a memory of a device of the subject, for example a patient diagnosed with joint inflammation.

[0257] According to some exemplary embodiments, once the treatment program is initiated, the system initiates a monitoring program, automatically or in a response to an input signal from the healthcare professional, or in a response to an input signal from the patient.

[0258] According to some exemplary embodiments, the system delivers an alert signal to the patient to acquire at least one thermal image of the treated joint, at block 604. In some embodiments, the alert signal is delivered using a user interface of a device of the patient, for example device 330 shown in fig. 3B. In some embodiments, the delivered alert signal is a reminder to acquire a thermal image within a predetermined time window from the delivery of the alert signal, for example a time window of up to 10 minutes, up to 30 minutes, up to 60 minutes, up to 2 hours, up to 6 hours, up to 12 hours, up to 24 hours, or any intermediate, shorter or longer time period from the delivery of the alert signal.

[0259] According to some exemplary embodiments, the system optionally delivers instructions how to acquire a thermal image, at block 606. In some embodiments, the instructions include instructions how to position a thermal camera relative to a joint in order to acquire at least one thermal image with sufficient quality for further processing.

[0260] According to some exemplary embodiments, the system receives thermal data, at block 608. In some embodiments, the thermal data comprises at least one thermal image. Alternatively or additionally, the thermal data comprises information about temperatures and / or distribution thereof.

[0261] According to some exemplary embodiments, the system optionally determines if the received thermal data has sufficient quality, at block 610. In some embodiments, if the thermal data quality is not sufficient, then the system optionally transmits instructions how to acquire thermal data at block 606.

[0262] According to some exemplary embodiments, if the thermal data quality is sufficient, the system processes the thermal data, at block 612. In some embodiments, the processing of the thermal data, for example processing of at least one thermal image, is performed, for example, as described in fig. 4 at blocks 404, 406, 410, and 412.

[0263] According to some exemplary embodiments, the system estimates a state of the joint inflammation, at block 614. In some embodiments, the system estimates a state of joint inflammation, as described at block 414 in fig. 4. In some embodiments, estimating a state of joint inflammation comprises estimating a degree or level of the joint inflammation. Optionally, the system generates a score indicating the degree or state of joint inflammation. Optionally, estimating a state of joint inflammation comprises estimating a severity or type of inflammation, optionally estimating if the inflammation is in a latent state, in an active state or in a remission state.

[0264] According to some exemplary embodiments, an indication is delivered by the system, at block 616. In some embodiments, the indication is an indication regarding the joint inflammation state estimated at block 614. In some embodiments, the indication comprises information on the state of the joint inflammation and / or a score indicating the joint inflammation state. In some embodiments, the indication is delivered to a healthcare professional. Additionally, the indication is delivered to the subject, for example using device 330. In some embodiments, the indication includes a current state of joint inflammation and a previous state of joint inflammation.

[0265] According to some exemplary embodiments, the system determines an efficacy of a treatment, at block 618. In some embodiments, the treatment is the treatment initiated at block 602. In some embodiments, the system determines the efficacy by determining a relation between a current inflammation state and at least one previously estimated inflammation state. In some embodiments, the system determines that the treatment is efficacious if there is an improvement in inflammation state compared to at least one previous inflammation state.

[0266] According to some exemplary embodiments, if the treatment is sufficiently efficacious, then an indication, for example a positive indication, is optionally delivered to a healthcare professional at block 622. In some embodiments, the indication includes information on a current state of the joint inflammation and a positive indication that the treatment is efficacious.

[0267] According to some exemplary embodiments, if the treatment is not sufficiently efficacious, then a negative indication, is optionally delivered to the healthcare professional, at block 624. In some embodiments, the indication includes information that the treatment is not sufficiently efficacious, or that a current efficacy of the treatment is lower than a target efficacy.

[0268] According to some exemplary embodiments, the system optionally receives instructions from the healthcare professional how to modify the treatment program, at block 626. In some embodiments, the instructions include instructions to modify at least one parameter of the treatment program, for example to increase the efficacy of the treatment. In some embodiments, the instructions include at least one of, replacing an existing treatment program with a different treatment program, or with a different treatment, or combining the existing treatment with at least one additional treatment.

[0269] Alternatively, the system generates the instructions, for example using at least one algorithms, formula and / or a lookup table.

[0270] According to some exemplary embodiments, the system delivers the instructions, at block 628. In some embodiments, the system delivers the instructions to the subject and / or to the healthcare professional. In some embodiments, the system delivers the instructions optionally using a user interface of the device 330, and / or a user interface of a device, for example a computer, of the healthcare professional.

[0271] Study-detection of arthritis using thermal imaging

[0272] Study abstract

[0273] Accurate and rapid detection of arthritis is important to limit bone damage associated with the inflammatory condition. In this study, the use of a hand-held thermal imaging device and machine learning to create an innovative algorithm to detect arthritis, was investigated. The knees, hands and ankles of arthritic patients as well as healthy controls were thermographically imaged and processed. In an example, the knee images were processed on MATLAB to extract temperature and texture features from the thermal images. Unpaired t-tests were run on GraphPad on the temperature and textural data extracted from the images. It was seen that the features of the thermal images of the knees of patients with arthritis were significantly (p<0.05) different to those of healthy controls and patients in clinical remission. Additionally, using MATLAB, machine learning can accurately distinguish between the groups (accuracy >80%). In summary, the study showed that a hand-held thermal imaging device may be a non-invasive, non-intrusive, radiation- free, cheap and / or easy-to-use novel tool to detect inflammatory arthritis.

[0274] Study introduction and background

[0275] Thermal imaging, also known as thermography, involves the use of specialized cameras, for example to capture the infrared radiation emitted by the body's surface. This radiation is then used to create images that display the distribution of heat across the surface of the body, for example by displaying distribution of temperatures or indications thereof.

[0276] Arthritis is a chronic condition that affects the joints, causing pain, stiffness, and inflammation. Arthritis can lead to joint deformities and disability if left untreated. As such, early detection of arthritis is crucial for effective treatment and prevention of joint damage. Conventional methods of detecting arthritis such as physical examination, blood tests, and imaging techniques like X-rays, ultrasound imaging, and MRIs may not detect early arthritis which can delay the initiation of treatment. Additionally, all of the above-mentioned methods of detecting arthritis have limitations, particularly in detecting early- stage arthritis and monitoring clinical remission (where patients have subclinical synovitis instead of overt inflammation). In addition, some of the imaging techniques require expensive equipment, such as MRI devices, making these devices relatively rare and non or less accessible to a large part of the world population, especially in developing countries. Thermal imaging is much cheaper, and mobile, and therefore can be used to overcome these problems.

[0277] Thermal imaging has the potential to detect arthritis at an early stage by identifying changes in skin temperature associated with inflammation. Inflammatory cells release chemicals that increase blood flow to the affected area, leading to a localized increase in skin temperature. Thus, thermal imaging can detect these changes in skin temperature and provide an early warning sign of arthritis.

[0278] Study cohort

[0279] The study group included patients who were diagnosed with inflammatory arthritis - psoriatic arthritis (PSA), rheumatoid arthritis (RA), gout, familial Mediterranean fever (FMF) or calcium pyrophosphate deposition (CPPD). The control group included patients with osteoarthritis (OA) as well as healthy volunteers. All participants were over 18 years old and patients with nonspecific arthritis, who were pregnant or breastfeeding, patients with prominent varicose veins, patients with surface tissue injuries to the joints of interest and patients with deep tissue injuries to the joints of interest were excluded.

[0280] The final study cohort included 210 participants of whom 80 (38.10%) were healthy controls, 98 (46.67%) were patients with arthritis, 22 (10.48%) were patients with arthritis in their knee / s, 18 (8.57%) were patients in clinical remission, 5 (2.38%) were patients with OA in their knee / s, and 18 (8.57%) were patients with arthritis inflammation in their hand / s only. The mean age was 57.11 years, and 139 participants (66.7%) were women.

[0281] General data processing scheme

[0282] Reference is now made to fig. 7A, depicting a data processing procedure used in the study. At least some of the blocks shown in fig. 7A are used in some exemplary embodiments of the invention. Thermal images of patient joints were acquired at block 702. The thermal images were thermal images were images of knee joints, hand joints and ankle joints. The thermal image were thermal images of both corresponding, for example contralateral joints in the body of a subject participating in the study. Fig. 7B shows a thermal image of knees of a patient, with a right knee suspected to have inflammation compared to a thermal image of control knees in fig. 7C. Fig. 7D shows a thermal image of subject ankles with a right ankle suspected to have inflammation compared to a thermal image of control ankles in fig. 7E. Fig. 7F shows a thermal image of hands of a subject with a left hand suspected to have inflammation, compared to a thermal image of control hands in fig. 7G.

[0283] One or more ROIs were marked in the thermal images at block 704. The RO Is included regions with different temperatures. Additionally, the ROIs included a large portion of an examined joint, for example at least 50% of an anatomical region of the joint as shown in the thermal image. An example of ROIs markings is shown in fig. 7H showing ROI 720 of a wrist region marked in a thermal image of a hand, in fig. 71 showing a different ROI 722 of a wrist region, in fig. 7 J showing ROI 724 of a knee region, and in fig. 7K showing ROI 726 of an ankle region.

[0284] Values of one or more temperatures distribution textural parameters were extracted at block 706. In addition, values of temperatures were also extracted at block 706. The temperature parameters used in the analysis included maximum temperature, mean temperature and / or minimum temperature. The textural parameters used in the analysis included Entropy, Local entropy, Energy, Kurtosis, Skewness, Homogeneity, Contrast and / or Correlation.

[0285] The extracted values were normalized at block 708. Fig. 8 shows an exemplary normalization of knee joints. A similar normalization can and was applied in the study on other joints, for example ankle joints and hand joints. The normalization is a normalization of values extracted from joints of the same subject. For example, as shown in fig. 8, values extracted from a first joint, for example joints 2 and 4 were normalized to values extracted from joints 1 and 3, respectively.

[0286] A relation between normalized values of a subject from the study group, and normalized values of a subject from a control group, was determined at block 710. For example, as shown in fig. 8, a relation between a delta in the extracted values from a first subject and a delta in the extracted values from a second subject, was determined at block 710. Determining a relation included a comparison between a delta in values from the first subject and a delta in values from the second subject. In the study, and in some embodiments of the invention, a relation between non-normalized values, was also determined. For example, as shown in fig. 8, a relation between values extracted from different subjects, without first normalizing the values with respect to extracted values from a contralateral joint of the same subject.

[0287] Data collection

[0288] The study was a prospective study where patient data was collected between October 2022 and February of 2023. Patients who agreed to participate in the study were examined by a rheumatologist at the Rheumatology clinic at Meir Hospital in Kfar Saba Israel.

[0289] Once the participants received an explanation of the study and informed consent was obtained, the subject’s hands, ankles and knees were photographed using the FLIR ONE PRO or FLIR CX5 thermal camera. To maintain scientific integrity, data such as the subject’s age, room temperature (kept between 21-25°C) and humidity (kept between 37-55%) and subject temperature were recorded. Subjects were asked to remove clothes and jewelry covering the joints photographed. The camera was kept a uniform distance from the subject (50-80 cm) and kept perpendicular to the subject.

[0290] This analysis was performed on knee joints, hand joints (MCPs, radio-carpal, distal radioulnar and carpal-carpal joints) and ankle joints (the ankle mortise and tarsal joints). These analyses will include a comparison of MRI results to the thermal images obtained in this study.

[0291] Image processing

[0292] The obtained thermal images were analyzed using MATLAB software to extract temperature and textural data from the thermal. An emissivity of 0.98 was used as this is the established values for human skin. Temperature parameters of mean, maximum and minimum temperatures of the region of interest as well as textural parameters were assessed. Textural parameters measured included entropy, local entropy, skewness, kurtosis, temperature variance, contrast, correlation, homogeneity and energy. This data was analyzed using unpaired t-tests on GraphPad software to compare the thermal images of various study groups. A p-value<0.05 was considered significant.

[0293] Results of the analysis is shown in figs. 9A-9F. In these figures absolute values of normalized data are used. The values were obtained by normalized left and right knees and using the absolute value of that difference for analyses. Fig. 9A shows differences in entropy between subjects with unilateral inflammation 902 and healthy control subjects 904, fig. 9B shows differences in mean temperature between subjects with unilateral inflammation 906 and healthy control subjects 908, fig. 9C shows differences in maximal temperature between subjects with unilateral inflammation 910 and healthy control subjects 912, fig. 9D shows differences in kurtosis between subjects with unilateral inflammation 914 and healthy control subjects 916, fig. 9E shows differences in skewness between subjects with unilateral inflammation 918 and healthy control subjects 920, and fig. 9F shows differences in local entropy between subjects with unilateral inflammation 922 and healthy control subjects 924. The p values of the graphs can be seen in table 1 showing p values from unpaired t-tests comparing healthy controls and patients with unilateral knee inflammation: Machine learning

[0294] The temperature and textural parameters of the thermal images were used as input data for machine learning using MATLAB. Patients and controls were analyzed in a roughly 1 :1 or 3:2 ratio of healthy to sick or sick to healthy. An accuracy reading above 80% was considered significant. Most significant results were seen when comparing the absolute values of normalized data as seen in figures 10A-10F showing confusion matrices, for example tables that are used to define a performance of a classification algorithm. Results from the machine learning analysis are summarized in table 2:

[0295]

[0296] The results of the study show that the textural values of entropy (p=0.001), local entropy (p=0.0433), kurtosis (p-0.0044) and skewness (p-0.0017) are all higher in inflamed knees than those of healthy controls. This suggests that there is significantly less homogeneity in the pixels of inflamed knees which is consistent with the altered blood flow over the inflamed joint in comparison to that of a healthy joint.

[0297] The study about detecting inflammation in knees was repeated and expanded and included the following comparisons: inflamed vs control, inflammation in knees vs inflammation elsewhere, healthy control vs clinical remission, inflammatory arthritis with active inflammation in the knee vs Osteoarthritis (OA), temperature and texture vs temperature.

[0298] The findings of the comparison analysis are provided in Table 3 below:

[0299] Table 3

[0300] In addition, the study used the same processing and analysis techniques on thermal images of hands, and wrists, and included the following compari sons: posterior whole hand-inflammation in one hand vs healthy controls, Anterior wrist-inflammation in one hand vs healthy controls, and posterior wrist-inflammation in one hand vs healthy controls. Significant results are shown in Table 4 below:

[0301] Table 4 The study further used the same processing and analysis techniques on thermal images of ankles, and included the following comparisons: inflammation in one ankle vs healthy controls, and inflammation in ankle vs healthy controls. Significant results (values were normalized, comparison of anterior thermal images of ankles) are shown in Table 5 below:

[0302] Exemplary use cases

[0303] According to some exemplary embodiments, thermal imaging of the joints is used as a screening tool, for example to decide whether or not to send a patient to a more expensive imaging analysis, which is sometimes less accessible, for example a MRI analysis.

[0304] Below are validation studies and exemplary use cases /

[0305] Thermal images were acquired from a 73-year-old woman. Her doctor reported that she had Polymyalgia rheumatica in remission and OA in her hands (specifically the 2nd distal interphalangeal (DIP) joint. In both cases the patient would not be expected to present inflammation in the hands. The thermal images, for example the thermal image in fig. 11, showed that her right hand was visibly warmer than her left hand (fig. 11). The patient was sent for an MRI which confirmed that the patient had synovitis in her right hand. This use case shows how, thermal imaging can be used to detect synovitis, and / or to screen the patient prior to sending her to MRI.

[0306] Another case shoes how the thermal imaging can be used as a screening and as a monitoring tool.

[0307] Thermal images were acquired from a 72-year-old woman complaining on pain in her left knee. The thermal images showed that her left knee was significantly warmer than her right knee (fig. 12A). The patient was sent for an MRI which confirmed that the patient had synovitis / inflammatory OA.

[0308] The patient was injected with steroids and reported an improvement in pain that lasted 6 weeks. Additional thermal images were acquired it could be seen that her left knee was inflamed again (fig. 12B). The patient was injected with 2cc of Methylprednisolone and follow up images of her knees were taken every day to monitor the effects of the medication on her inflammation, for example fig. 12C (a day after injection), fig. 12D (two days after injection), and fig. 12E (3 days after injection). The patient reported significant improvement from Day 1.

[0309] Fig. 13A is a graph showing a change in normalized entropy 1302 and normalized local entropy 1304 parameters of temperature intensity between patient knees, from day 0 (prior to Methylprednisolone injection) to day 4 following the injection, in a selected ROI. The results show a marked decrease in entropy and local entropy between the two knees compared to day 0 in both measures at day 1 following injection, indicating an increase in homogeneity.

[0310] Fig. 13B is a graph showing a change in and normalized maximal temperature 1306 and normalized mean temperature 1308 from day 0 (prior to Methylprednisolone injection) to day 4 following the injection, in a selected ROI. The results show a marked decrease compared to day 0 in both measures.

[0311] In another use case, thermal images were acquired from a 71 -year-old womn with osteoarthritis. Her doctor reported that she had non-inflammatory OA which thermally should not show signs of significant heat asymmetry. However, her thermal images, for example the thermal image in fig. 14, showed signs of heat / possible inflammation in her left knee (specifically a medial section of the knee). The patient confirmed then that her medial left knee was the most painful section of her knees. The patient was sent for an MRI which confirmed that the patient had reactive synovitis in her left knee. In another use case, a 38 year old RA patient presented with active inflammation in his hands. The affected joints as described by his rheumatologist (and confirmed by thermal imaging - fig. 15A) were his third MCP in his left hand and 1stand 2nddigits on both hands. The patient was injected with steroids and thermal images were acquired after 3 days (fig. 15B). The patient reported improvement (incomplete) in his third MCP in his left hand and no pain in his 1st and 2nd digits on both hands. His reported improvement was confirmed by the acquired thermal image.

[0312] It is expected that during the life of a patent maturing from this application many relevant thermal images configured to acquire a thermal image of a body region will be developed; the scope of the term thermal imager is intended to include all such new technologies a priori.

[0313] As used herein with reference to quantity or value, the term “about” means “within ± 10 % of’.

[0314] The terms “comprises”, “comprising”, “includes”, “including”, “has”, “having” and their conjugates mean “including but not limited to”.

[0315] The term “consisting of’ means “including and limited to”.

[0316] The term “consisting essentially of’ means that the composition, method or structure may include additional ingredients, steps and / or parts, but only if the additional ingredients, steps and / or parts do not materially alter the basic and novel characteristics of the claimed composition, method or structure.

[0317] As used herein, the singular forms “a”, “an” and “the” include plural references unless the context clearly dictates otherwise. For example, the term “a compound” or “at least one compound” may include a plurality of compounds, including mixtures thereof.

[0318] Throughout this application, embodiments of this invention may be presented with reference to a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as “from 1 to 6” should be considered to have specifically disclosed subranges such as “from 1 to 3”, “from 1 to 4”, “from 1 to 5”, “from 2 to 4”, “from 2 to 6”, “from 3 to 6”, etc.; as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0319] Whenever a numerical range is indicated herein (for example “10-15”, “10 to 15”, or any pair of numbers linked by these another such range indication), it is meant to include any number (fractional or integral) within the indicated range limits, including the range limits, unless the context clearly dictates otherwise. The phrases “range / ranging / ranges between” a first indicate number and a second indicate number and “range / ranging / ranges from” a first indicate number “to”, “up to”, “until” or “through” (or another such range-indicating term) a second indicate number are used herein interchangeably and are meant to include the first and second indicated numbers and all the fractional and integral numbers therebetween.

[0320] Unless otherwise indicated, numbers used herein and any number ranges based thereon are approximations within the accuracy of reasonable measurement and rounding errors as understood by persons skilled in the art.

[0321] As used herein the term “method” refers to manners, means, techniques and procedures for accomplishing a given task including, but not limited to, those manners, means, techniques and procedures either known to, or readily developed from known manners, means, techniques and procedures by practitioners of the chemical, pharmacological, biological, biochemical and medical arts.

[0322] As used herein, the term “treating” includes abrogating, substantially inhibiting, slowing or reversing the progression of a condition, substantially ameliorating clinical or aesthetical symptoms of a condition or substantially preventing the appearance of clinical or aesthetical symptoms of a condition.

[0323] It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination or as suitable in any other described embodiment of the invention. Certain features described in the context of various embodiments are not to be considered essential features of those embodiments, unless the embodiment is inoperative without those elements.

[0324] Although the invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope of the appended claims.

[0325] All publications, patents and patent applications mentioned in this specification are herein incorporated in their entirety by reference into the specification, to the same extent as if each individual publication, patent or patent application was specifically and individually indicated to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the present invention. To the extent that section headings are used, they should not be construed as necessarily limiting. In addition, any priority document(s) of this application is / are hereby incorporated herein by reference in its / their entirety.

Claims

WHAT IS CLAIMED IS:

1. A method for detecting inflammation in a body joint of a subject, comprising: providing at least one thermal image of at least one body joint, wherein said at least one thermal image includes indications of temperature of the at least one body joint; marking at least one region of interest (ROI) in said at least one thermal image, wherein said at least one ROI is a region in said at least one thermal image which includes pixels representing elevated temperatures and less elevated temperatures in said at least one thermal image; extracting values of one or more parameters of distribution of said temperature indications in said at least one ROI; detecting inflammation in said body joint based on said extracted values.

2. A method according to claim 1, wherein said providing comprises providing at least one thermal image of at least one body joint and adjacent tissue, wherein said at least one thermal image includes indication of temperature of the at least one body joint and of said adjacent tissue; wherein said marking comprises marking at least one ROI in the at least one thermal image which includes pixels indicating temperature of said body joint and of said adjacent tissue, wherein at least 1% of pixels in said at least one ROI indicate temperature of said adjacent tissue; wherein said extracting comprises extracting values of said one or more parameters of distribution of said temperature indications in said at least marked ROI, which includes temperature indications of said body joint and of said adjacent tissue.

3. A method according to claim 2, wherein said adjacent tissue comprises non-inflamed tissue which is anatomically distinct from said at least one body joint.

4. A method according to claim 1, wherein said marked ROI is a region in said at least one thermal image which includes pixels representing at least 50% of a range of temperature values in said at least one thermal image.

5. A method according to claim 1, wherein said at least one ROI comprises a single contiguous region in said at least one thermal image.

6. A method according to claim 1, wherein said at least one ROI has an area of at least 0.16 cm2in said at least one thermal image.

7. A method according to claim 1, wherein said at least one ROI includes pixels representing at least 25% of an area of said at least one body joint in said at least one thermal image.

8. A method according to claim 1, comprising identifying an increase in non-uniformity of a distribution said temperature indications in said at least one ROI based on said extracted values, determining a relation between said identified increase in non-uniformity and a reference value, and wherein said detecting comprises detecting said inflammation based on said determined relation.

9. A method according to claim 8, wherein said detecting comprises detecting said inflammation if said identified increase in non-uniformity is larger than a said reference value.

10. A method according to claim 1, wherein said one or more parameters comprise local entropy.

11. A method according to claim 10, wherein said extracting comprises extracting values of said local entropy from one or more regions having a size between 0.2 cm2and 0.9 cm2, in said selected ROI.

12. A method according to claim 10, wherein said extracting comprises extracting values of said local entropy from one or more regions having a size between 0.3 cm2and 0.5 cm2, in said selected ROI.

13. A method according to claim 11, wherein said extracting comprises extracting values of said local entropy from a plurality of regions having a size between 0.2 cm2and 0.9 cm2in said at least one ROI and calculating a value of a central tendency measure of said extracted local entropy values per said at least one ROI, and wherein said detecting comprises detecting said inflammationin said body joint based on said calculated central tendency value of said extracted local entropy values.

14. A method according to claim 1, wherein said extracting comprises calculating a value of a central tendency measure of said one or more parameters per said at least one ROI, and wherein said detecting comprises detecting said inflammation base don said calculated central tendency measure.

15. A method according to claim 13, wherein said central tendency measure comprise mean, median, or mode, or any combination of the aforesaid.

16. A method according to claim 1, wherein said one or more parameters comprise, skewness, entropy, or kurtosis, or any combination of the aforesaid.

17. A method according to claim 1, wherein said extracting comprises extracting values of one or more temperature parameters and wherein said detecting comprises detecting said inflammation based on said extracted value of said one or more distribution parameters and based on said extracted values of said one or more temperature parameter.

18. A method according to claim 17, wherein said one or more temperature parameters comprise, mean temperature, minimum temperature ,or maximum temperature or any combination of the aforesaid.

19. A method according to claim 1, wherein said detecting comprises determining inflammation type and / or severity, and wherein said at least one body joint comprises a knee, an ankle and / or a body joint of a hand.

20. A method according to claim 1, wherein said at least one thermal image is at least one thermal image of at least two corresponding joints of a subject body.

21. A method according to claim 20, wherein said marking comprises marking at least two regions of interest each in a different joint of said at least two corresponding joints, wherein said extracting comprises extracting said values of said one or more parameters or values of a central tendency measure thereof from each of said at least two regions of interest, and wherein said detecting comprises detecting said inflammation based on a difference in said extracted values or in said central tendency measure values, between said at least two corresponding joints.

22. A method according to claim 21, wherein said inflammation is detected if said difference in said extracted values between said at least two corresponding body joints is at least 5%, wherein said at least two corresponding body joints are contralateral body joints.

23. A method according to claim 1, comprising diagnosing said subject with an inflammation- related clinical state based on said detected inflammation, wherein said clinical state comprises latent asymptomatic inflammation, arthritis, and / or septic arthritis.

24. A method for detecting inflammation in a body joint, comprising: providing at least one thermal image of at least one body joint, wherein said at least one thermal image includes indications of temperature values of the at least one body joint; marking at least one region of interest (RO I) in said at least one thermal image which includes at least a portion of said at least one body joint; extracting values of local entropy of said indications of temperature values from said at least one ROI; detecting inflammation in said at least one body joint based on said extracted local entropy values.

25. A method according to claim 24, wherein said providing comprises providing at least one thermal image of at least one body joint and adjacent tissue, wherein said at least one thermal image includes indication of temperature of the at least one body joint and of said adjacent tissue; wherein said marking comprises marking at least one ROI in the at least one thermal image which includes pixels indicating temperature of said body joint and of said adjacent tissue, wherein at least 1% of pixels in said at least one ROI indicate temperature of said adjacent tissue.

26. A method according to claim 25, wherein said adjacent tissue comprises non-inflamed tissue which is anatomically distinct from said at least one body joint.

27. A method according to claim 24, wherein said at least one ROI comprises a single contiguous region in said at least one thermal image.

28. A method according to claim 24, wherein said at least one ROI includes pixels representing at least 25% of an area of said at least one body joint in said at least one thermal image.

29. A method according to claim 24, wherein said region has a size between 0.2 cm2and 0.9 2 cm .

30. A method according to claim 24, wherein said detecting comprises detecting said inflammation if said local entropy measurements are higher than a reference value.

31. A method according to claim 24, wherein said at least one thermal image is at least one thermal image of two or more corresponding body joints, wherein said extracting comprises extracting values of said local entropy from two region, each at a different body joint of said two or more corresponding body joints, and wherein said detecting comprises detecting said inflammation based on a difference in values of said local entropy between the two or more corresponding body joints.

32. A method according to claim 31, wherein said inflammation is detected if said difference in values of said local entropy between the two corresponding body joints is at least 5%, and wherein said two or more corresponding body joints are contralateral body joints.

33. A method according to claim 24, wherein said at least one body joint comprises a knee, an ankle and / or a body joint of a hand.

34. A method according to claim 24, comprising diagnosing said subject with an inflammation- related clinical state based on said detected inflammation, wherein said clinical state comprises latent asymptomatic inflammation, arthritis, and / or septic arthritis.

35. A method for monitoring an effect of a treatment for joint inflammation, comprising: providing at least one thermal image of at least one body joint acquired after initiating a treatment for inflammation in the at least one body joint, wherein said at least one thermal image includes indications of temperature values of the at least one body joint; processing said at least one thermal image; determining a state of said inflammation in said body joint, based on the results of said processing; generating an indication with information about the determined state.

36. A method according to claim 35, wherein said providing comprises providing at least one thermal image of at least one body joint and adjacent tissue after initiating a treatment for inflammation in the at least one body joint.

37. A method according to claim 36, wherein said adjacent tissue comprises non-inflamed tissue which is anatomically distinct from said at least one body joint.

38. A method according to claim 35, wherein said at least one thermal image is a thermal image acquired when the subject is outside a medical facility.

39. A method according to claim 35, comprising: determining an effect of said treatment on said joint inflammation based on said determined inflammation state, and wherein said generated indication includes information on said determined effect.

40. A method according to claim 39, wherein said generated indication comprises a suggestion to stop said treatment, to modify said treatment or to replace said treatment, if said determined effect is not a target effect.

41. A method according to claim 35, wherein said processing comprises extracting values indicating local entropy of temperatures distribution in a region of said at least one thermal image or a central tendency measure thereof, and wherein said determining comprises determining said state of said inflammation based on said extracted values.

42. A method according to claim 35, wherein said processing comprises marking at least one region of interest (ROI) in said at least one thermal image, wherein said marked ROI is a region which includes pixels representing elevated temperatures and less elevated temperatures in said at least one thermal image, and extracting values indicating one or more parameters of distribution of said temperatures in said at least marked ROI or a central tendency measure thereof, and wherein said determining comprises determining said state of said inflammation based on said extracted values.

43. A method according to claim 41, wherein said processing comprises determining a relation between said extracted values and previously extracted values or indications thereof, and wherein said state of said inflammation is determined based in said determined relation.

44. A method according to claim 35, wherein said at least one thermal image comprises at least one thermal image of two or more body joints, and wherein said processing comprises normalizing values extracted from at least one thermal image of at least one body joint of said two or more body joints to values extracted from said at least one thermal image or from at least one different thermal image of at least one different body joint, and wherein said inflammation state is determined using said normalized values.

45. A system, comprising: a memory circuitry, wherein said memory circuitry stores at least one thermal image of at least one body joint of a subject, wherein said at least one thermal image includes indications of different temperature values in the body joint; a user interface configured to generate and deliver at least one human detectable indications; a control circuitry configured to: extract values of one or more parameters of distribution of said temperatures from at least one region of interest (ROI) in said at least one thermal image which includes elevated temperatures and less elevated temperatures; detect inflammation in said body joint based on said extracted values; and signal said user interface to generate said human detectable indication with information about said detected inflammation.

46. A system according to claim 45, wherein said at least one thermal image stored in said memory is a thermal image of said at least one body joint and of tissue adjacent to said at least one body joint, wherein said at least one thermal image include indications of different temperature values in said body joint and in said adjacent tissue, and wherein said control circuitry is configured to: extract said values of said one or more parameters of distribution of said temperatures from at least one region of interest (ROI) in said at least one thermal image which includes elevated temperatures and less elevated temperatures and pixels indicating temperatures of said at least one body joint and of said adjacent tissue; detect inflammation in said body joint based on said extracted values; and signal said user interface to generate said human detectable indication with information about said detected inflammation.

47. A system according to claim 46, wherein at least 1 % of pixels in said at least one ROI indicate temperature of said adjacent tissue, and wherein said adjacent tissue comprises tissue which is anatomically distinct from said at least one body joint.

48. A system according to claim 45, wherein said at least one ROI is a region in said at least one thermal image which includes pixels representing at least 50% of a range of temperature values in said at least one thermal image.

49. A system according to claim 45, wherein said at least one ROI comprises a single contiguous region in said at least one thermal image.

50. A system according to claim 45, wherein said at least one ROI includes pixels representing at least 25% of an area of said at least one body joint in said at least one thermal image.

51. A system according to claim 45, comprising a communication circuitry configured to deliver a signal to a remote device, wherein said control circuitry signals said communicationcircuitry to deliver said signal to said remote device with information about said detected inflammation.

52. A system according to claim 45, wherein said control circuitry is configured to diagnose a clinical state based on said detected inflammation, and to signal said user interface to generate an indication with information about said clinical state.

53. A system according to claim 52, wherein said clinical state comprises latent asymptomatic inflammation, and / or arthritis.

54. A system according to claim 52, wherein said memory stores information about at least one treatment for said clinical state, and wherein said control circuitry signals said user interface to deliver a human detectable indication with information about said at least one treatment or with a suggestion to initiate said at least one treatment, if said inflammation is detected.

55. A system according to claim 45, wherein said control circuitry is configured to determine a relation between said extracted values and previously extracted values stored in said memory, and wherein said detect inflammation comprises determine a state of said inflammation in said subject based on said determined relation.

56. A system according to claim 55, wherein said memory stores information about at least one treatment provided to said subject, and wherein said control circuitry is configured to signal said user interface to generate an indication with at least one suggestion for stopping said treatment, modify said treatment and / or to combine said treatment with at least one different treatment, if said determined state is not a target state.

57. A system according to claim 45, wherein said user interface is configured to deliver a signal to said control circuitry with information about said at least one ROI.

58. A system according to claim 45, wherein said control circuitry is configured to automatically determine said at least one ROI using an algorithm, a software program and / or a look-up table stored in said memory.

Images