# US 12,118,722 B2 · Compute system with eczema diagnostic mechanism and method of operation thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,722 B2 - Document ID: US12118722B2 - Status: Granted - Kind: B2 - Application number: 18/392,343 - Filed: 2023-12-21 - Published: 2024-04-25 - Granted: 2024-10-15 - Earliest claimed: 2022-08-23 - Assignees: BelleTorus Corporation - Applicants: BelleTorus Corporation - Inventors: Tien Dung Nguyen; Thi Thu Hang Nguyen; Paul Fricker; Léa Mathilde Gazeau; Matthew Gregory Gloss; Kavita Mariwalla; Emily Kathryn McAnelly; Megan M. Morbitzer; Duong Thuy Nguyen; Nga Thi Thuy Nguyen; Thang Duc Nguyen; Clifford Perlis; Christopher C. Szajna; Jonathan Wolfe - Web page: https://patentgrep.com/patent/US12118722B2 ## CPC - A61B 5/0077: {Devices for viewing the surface of the body, e.g. camera, magnifying lens} - G06T 7/0012: {Biomedical image inspection} - A61B 5/441: {Skin evaluation, e.g. for skin disorder diagnosis} - A61B 5/444: {Evaluating skin marks, e.g. mole, nevi, tumour, scar} - A61B 5/445: {Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore} - G06T 7/11: Region-based segmentation - G06T 7/136: involving thresholding - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/30: for calculating health indices; for individual health risk assessment - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/20132: Image cropping - G06T 2207/30088: Skin; Dermal - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A method of operation of a compute system includes: generating a skin segmentation including a non-skin region and a skin prediction based on a patient image; generating a body part segmentation based on the patient image; generating a cropped image based on the skin segmentation and the body part segmentation with the cropped image includes the non-skin region based on the skin prediction; generating a eczema segmentation based on the cropped image and the skin prediction; generating intermediate scores for erythema, papulation, lichenification, and excoriation for the cropped image; and generating a full body EASI score based on the eczema segmentation and the intermediate scores for displaying on a device to assist in diagnosis. ## Claims ### Claim 1 A method of operation of a compute system comprising: generating a skin segmentation including a non-skin region and a skin prediction based on a patient image; generating a body part segmentation based on the patient image; generating a cropped image based on the skin segmentation and the body part segmentation with the cropped image including the non-skin region based on the skin prediction; generating an eczema segmentation based on the cropped image and the skin prediction; generating intermediate scores for erythema, papulation, lichenification, and excoriation for the cropped image; and generating a full body EASI score based on the eczema segmentation and the intermediate scores for displaying on a device to assist in diagnosis. ### Claim 2 (depends on 1) The method as claimed in claim 1 further compromising accepting the patient image based on calculating, for the patient image, a non-skin score less than or equal to non- nominal threshold. ### Claim 3 (depends on 1) The method as claimed in claim 1 further compromising accepting the patient image based on calculating, for the patient image, a nominal metric greater than a nominal threshold. ### Claim 4 (depends on 1) The method as claimed in claim 1 further compromising accepting the patient image based on calculating, for the patient image, a blurry metric, a bad luminosity metric, or a combination thereof less than or equal to a blurry threshold, a bad luminosity threshold, respectively, or a combination thereof. ### Claim 5 (depends on 1) The method as claimed in claim 1 wherein: generating the cropped image includes generating one or more cropped images; and generating the full body EASI score includes aggregating the eczema segmentation and the intermediate scores for each of the cropped images. ### Claim 6 (depends on 1) The method as claimed in claim 1 wherein generating the full body EASI score include applying a conversion function (EQ4) to the eczema segmentation for the cropped image, including generating a heatmap for identifying erythema, papulation, lichenification, and excoriation. ### Claim 7 (depends on 1) The method as claimed in claim 1 further comprising checking a quality criteria for the patent image to meet or exceed a quality threshold prior to processing for the full body EASI score. ### Claim 8 A compute system comprising: a control circuit, including a processor, configured to: generate a skin segmentation including a non-skin region and a skin prediction based on a patient image, generate a body part segmentation based on the patient image, generate a cropped image based on the skin segmentation and the body part segmentation with the cropped image including the non-skin region based on the skin prediction, generate an eczema segmentation based on the cropped image and the skin prediction, generate intermediate scores for erythema, papulation, lichenification, and excoriation for the cropped image, and generate a full body EASI score based on eczema segmentation and the intermediate scores on the for displaying on a device to assist in diagnosis. ### Claim 9 (depends on 8) The system as claimed in claim 8 wherein the control circuit is further configured to accept the patient image based on calculating, for the patient image, a non-skin score less than or equal to non-nominal threshold. ### Claim 10 (depends on 8) The system as claimed in claim 8 wherein the control circuit is further configured to accept the patient image based on calculating, for the patient image, a nominal metric greater than a nominal threshold. ### Claim 11 (depends on 8) The system as claimed in claim 8 wherein the control circuit is further configured to accept the patient image based on calculating, for the patient image, a blurry metric, a bad luminosity metric, or a combination thereof less than or equal to a blurry threshold, a bad luminosity threshold, respectively, or a combination thereof. ### Claim 12 (depends on 8) The system as claimed in claim 8 wherein the control circuit is further configured to: generate the cropped image including generate one or more cropped images; and generate the full body EASI score including aggregate the eczema segmentation and the intermediate scores for each of the cropped images. ### Claim 13 (depends on 8) The system as claimed in claim 8 wherein the control circuit is further configured to generate the full body EASI score including apply a conversion function (EQ4) to the eczema segmentation for the cropped image, including a heatmap generated for identifying erythema, papulation, lichenification, and excoriation. ### Claim 14 (depends on 8) The system as claimed in claim 8 wherein the control circuit is further configured to check a quality criteria for the patent image to meet or exceed a quality threshold prior to processing for the full body EASI score. ### Claim 15 A non-transitory computer readable medium including instructions for a compute system comprising: generating a skin segmentation including a non-skin region and a skin prediction based on a patient image; generating a body part segmentation based on the patient image; generating a cropped image based on the skin segmentation and the body part segmentation with the cropped image including the non-skin region based on the skin prediction; generating an eczema segmentation based on the cropped image and the skin prediction; generating intermediate scores for erythema, papulation, lichenification, and excoriation for the cropped image; and generating a full body EASI score based on the eczema segmentation and the intermediate scores for displaying on a device to assist in diagnosis. ### Claim 16 (depends on 15) The non-transitory computer readable medium as claimed in claim 15 further compromising accepting the patient image based on calculating, for the patient image, a non-skin score less than or equal to non-nominal threshold. ### Claim 17 (depends on 15) The non-transitory computer readable medium as claimed in claim 15 further compromising accepting the patient image based on calculating, for the patient image, a nominal metric greater than a nominal threshold. ### Claim 18 (depends on 15) The non-transitory computer readable medium as claimed in claim 15 further compromising accepting the patient image based on calculating, for the patient image, a blurry metric, a bad luminosity metric, or a combination thereof less than or equal to a blurry threshold, a bad luminosity threshold, respectively, or a combination thereof. ### Claim 19 (depends on 15) The non-transitory computer readable medium as claimed in claim 15 wherein: generating the cropped image includes generating one or more cropped images; and generating the full body EASI score includes aggregating the eczema segmentation and the intermediate scores for each of the cropped images. ### Claim 20 (depends on 15) The non-transitory computer readable medium as claimed in claim 15 wherein generating the full body EASI score include applying a conversion function (EQ4) to the eczema segmentation for the cropped image, including generating a heatmap for identifying erythema, papulation, lichenification, and excoriation.