# US 12,119,118 B2 · Compute system with hidradenitis suppurativa severity 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 12,119,118 B2 - Document ID: US12119118B2 - Status: Granted - Kind: B2 - Application number: 18/535,627 - Filed: 2023-12-11 - Published: 2024-06-13 - Granted: 2024-10-15 - Earliest claimed: 2022-12-09 - Assignees: BelleTorus Corporation - Applicants: BelleTorus Corporation - Inventors: Tien Dung Nguyen; Thi Thu Hang Nguyen; Leá Mathilde Gazeau; Mariia Lebedeva; Nga Thi Thuy Nguyen; Jonathan Wolfe - Web page: https://patentgrep.com/patent/US12119118B2 ## CPC - G16H 50/30: for calculating health indices; for individual health risk assessment - G06T 7/0012: {Biomedical image inspection} - G06T 7/11: Region-based segmentation - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06T 2207/30088: Skin; Dermal - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method of operation of a compute system includes: verifying a patient image as an acceptable image; detecting a body part from the acceptable image; generating a skin segmentation for the body part including a non-skin region and a skin region based on the acceptable image; and generating a local Hidradenitis Suppurativa (HS) severity score based on the patient image for displaying on a device to assist in diagnosis. ## Claims ### Claim 1 A method of operation of a compute system comprising: verifying a patient image as an acceptable image; detecting a body part from the acceptable image; generating a skin segmentation for the body part including a non-skin region and a skin region based on the acceptable image; generating a normalized image with a rescale factor based on the skin segmentation and the patient image; identifying a type of an Hidradenitis Suppurativa (HS) lesion from among a nodule, an abscess, a fistula, a scar drainage, and a papule based on the normalized image; and generating a local HS severity score based on the patient type of the HS lesion for displaying on a device to assist in diagnosis. ### Claim 2 (depends on 1) The method as claimed in claim 1 further comprising generating a full body HS severity score including aggregating the local HS severity score and the body part area detected in the patient image. ### Claim 3 (depends on 1) The method as claimed in claim 1 wherein verifying the patient image includes detecting a skin region and a non-skin region to verify the skin region ratio greater than the non-skin region. ### Claim 4 (depends on 1) The method as claimed in claim 1 wherein verifying the acceptable image includes performing an image quality check to eliminate the patient image that is blurry, includes bad luminosity, or a combination thereof. ### Claim 5 (depends on 1) The method as claimed in claim 1 further comprising generating an accounting of HS lesions includes segmenting the HS instances of a cropped image and counting and classifying the HS lesions identified in the cropped image. ### Claim 6 (depends on 1) The method as claimed in claim 1 wherein generating the local HS severity score includes estimating the body area of the body part, counting and classifying the HS lesions, and calculating the affected area of the HS lesions in the cropped image. ### Claim 7 (depends on 1) The method as claimed in claim 1 wherein generating the normalized image includes cropping the acceptable image as a 512×512×3 pixel image. ### Claim 8 A compute system comprising: a control circuit, including a processor, configured to: verify an acceptable image from a patient image, detect a body part from the acceptable image, generate a skin segmentation for the body part including a non-skin region and a skin region based on the acceptable image, and generate a normalized image with a rescale factor based on the skin segmentation and the patient image; identify a type of an Hidradenitis Suppurativa (HS) lesion from among a nodule, an abscess, a fistula, a scar, drainage, and a papule based on the normalized image; and generate a local HS severity score based on the type of the HS lesion for displaying on a device to assist in diagnosis. ### Claim 9 (depends on 8) The compute system as claimed in claim 8, further comprising a full body HS severity score generated includes the local HS severity score and the body part area aggregated and detected in the patient image. ### Claim 10 (depends on 8) The compute system as claimed in claim 8, wherein the patient image verified includes a skin region and a non-skin region detected to verify the skin region ratio greater than the non-skin region. ### Claim 11 (depends on 8) The compute system as claimed in claim 8, wherein the acceptable image verified includes an image quality check performed to eliminate the patient image that is blurry, includes bad luminosity, or a combination thereof. ### Claim 12 (depends on 8) The compute system as claimed in claim 8, further comprising an accounting of HS lesions verified includes the HS instances of a cropped image segmented and counting and classifying the HS lesions identified in the cropped image. ### Claim 13 (depends on 8) The compute system as claimed in claim 8, wherein the local HS severity score generated includes the body area of the body part estimated, the HS lesions counted and classified, and the affected area of the HS lesions calculated in the cropped image. ### Claim 14 (depends on 8) The compute system as claimed in claim 8, wherein the normalized image generated includes the acceptable image cropped as a 512×512×3 pixel image. ### Claim 15 A non-transitory computer readable medium including instructions for a compute system comprising: verifying an acceptable image from a patient image; detecting a body part from the acceptable image; generating a skin segmentation for the body part including a non-skin region and a skin region based on the acceptable image; generating a normalized image with a rescale factor based on the skin segmentation and the patient image; identifying a type of an Hidradenitis Suppurativa (HS) lesion from among a nodule, an abscess, a fistula, a scar, drainage, and a papule based on the normalized image; and generating a local HS severity score based on the type of the HS lesion for displaying on a device to assist in diagnosis. ### Claim 16 (depends on 15) The non-transitory computer readable medium including instructions for a compute system, as claimed in claim 15, further comprising generating a full body HS severity score including aggregating the local HS severity score and the body part area detected in the patient image. ### Claim 17 (depends on 15) The non-transitory computer readable medium including instructions for a compute system, as claimed in claim 15, wherein verifying the patient image includes detecting a skin region and a non-skin region to verify the skin region ratio greater than the non-skin region. ### Claim 18 (depends on 15) The non-transitory computer readable medium including instructions for a compute system, as claimed in claim 15, wherein verifying the acceptable image includes performing an image quality check to eliminate the patient image that is blurry, includes bad luminosity, or a combination thereof. ### Claim 19 (depends on 15) The non-transitory computer readable medium including instructions for a compute system, as claimed in claim 15, further comprising generating an accounting of HS lesions includes segmenting the HS instances of a cropped image and counting and classifying the HS lesions identified in the cropped image. ### Claim 20 (depends on 15) The non-transitory computer readable medium including instructions for a compute system, as claimed in claim 15, wherein generating the local HS severity score includes estimating the body area of the body part, counting and classifying the HS lesions, and calculating the affected area of the HS lesions in the cropped image.