# US 12,118,723 B1 · Compute system with image based skin cancer detection 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 12,118,723 B1
- Document ID: US12118723B1
- Status: Granted
- Kind: B1
- Application number: 18/423,874
- Filed: 2024-01-26
- Granted: 2024-10-15
- Earliest claimed: 2023-06-21
- Assignees: BelleTorus Corporation
- Applicants: BelleTorus Corporation
- Inventors: Thi Thu Hang Nguyen; Tien Dung Nguyen; Thanh Thi Nguyen; Jean-Luc Perrot; Jonathan Wolfe
- Web page: https://patentgrep.com/patent/US12118723B1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06V 10/764: using classification, e.g. of video objects
- 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
- G06T 2207/20132: Image cropping
- G06T 2207/30088: Skin; Dermal
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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: receiving a patient image; segmenting a skin lesion in the patient image; constructing a normalized image by cropping the patient image and adding padding to position the skin lesion at the center of the normalized image; identifying, by a cancer artificial intelligence (AI) already trained, a skin cancer classification, a skin cancer sub-class, and a risk level assessment; and generating a skin cancer display including the normalized image, the skin cancer classification, the skin cancer sub-class, and the risk level assessment for displaying on a device.

## Claims

### Claim 1

A method of operation of a compute system comprising:
receiving a patient image;
segmenting a skin lesion in the patient image;
constructing a normalized image by cropping the patient image and adding padding to position the skin lesion at a center of the normalized image;
identifying, by a cancer artificial intelligence (AI) already trained, a skin cancer classification, a skin cancer sub-class, and a risk level assessment; and
generating a skin cancer display including the normalized image, the skin cancer classification, the skin cancer sub-class, and the risk level assessment for displaying on a device.

### Claim 2 (depends on 1)

The method as claimed in claim 1 wherein identifying the skin cancer sub-class includes submitting a class prediction and a sub-class prediction to a multiplier for calculating the skin cancer sub-class.

### Claim 3 (depends on 1)

The method as claimed in claim 1 wherein identifying the skin cancer classification includes identifying Melanoma (MEL), Basal Cell Carcinoma (BCC), Epidermal tumors (EPI), Malignant lesions (MALO), Melanocytic Nevus (NV), Dermatofibroma (DF), Benign Adnexal Lesions (BAL), Benign Keratinocytic Lesions (BKL), Benign Vascular lesions (VASC), or Benign Lesions (BENO).

### Claim 4 (depends on 1)

The method as claimed in claim 1 wherein identifying the risk level assessment by the cancer AI includes identifying a risk level zero through a risk level five.

### Claim 5 (depends on 1)

The method as claimed in claim 1 wherein the cancer artificial intelligence (AI) already trained includes the cancer artificial intelligence (AI) detecting the skin cancer classification and the skin cancer sub-class for displaying on the skin cancer display.

### Claim 6 (depends on 1)

The method as claimed in claim 1 wherein generating the skin cancer display includes identifying the risk level assessment as the risk level zero indicating low risk through the risk level five indicating high risk.

### Claim 7 (depends on 1)

The method as claimed in claim 1 further comprising screening the patient image to identify an oops score between 0.75 and 0.25 as an input to the normalized image.

### Claim 8

A compute system comprising:
a control circuit, including a processor, configured to:
receive a patient image;
segment a skin lesion in the patient image;
construct a normalized image by cropping the patient image and adding padding to position the skin lesion at the center of the normalized image;
identify, by a cancer artificial intelligence (AI) already trained, a skin cancer classification, a skin cancer sub-class, and a risk level assessment; and
generate a skin cancer display including the normalized image, the skin cancer classification, the skin cancer sub-class, and the risk level assessment for displaying on a device.

### Claim 9 (depends on 8)

The system as claimed in claim 8 wherein identifying the skin cancer sub-class includes submitting a class prediction and a sub-class prediction to a multiplier for calculating the skin cancer sub.

### Claim 10 (depends on 8)

The system as claimed in claim 8 wherein identifying the skin cancer classification includes identifying Melanoma (MEL), Basal Cell Carcinoma (BCC), Epidermal tumors (EPI), Malignant lesions (MALO), Melanocytic Nevus (NV), Dermatofibroma (DF), Benign Adnexal Lesions (BAL), Benign Keratinocytic Lesions (BKL), Benign Vascular lesions (VASC), or Benign Lesions (BENO).

### Claim 11 (depends on 8)

The system as claimed in claim 8 wherein identifying the risk level assessment by the cancer AI includes identifying a risk level zero through a risk level five.

### Claim 12 (depends on 8)

The system as claimed in claim 8 wherein the cancer artificial intelligence (AI) already trained includes the cancer artificial intelligence (AI) configured to detect the skin cancer classification and the skin cancer sub-class for displaying on the skin cancer display.

### Claim 13 (depends on 8)

The system as claimed in claim 8 wherein the skin cancer display generated includes the risk level assessment identified as the risk level zero indicating low risk through the risk level five indicating high risk.

### Claim 14 (depends on 8)

The system as claimed in claim 8 further comprising screen the patient image to identify an oops score between 0.75 and 0.25 as an input to the normalized image.

### Claim 15

A non-transitory computer readable medium including instructions for a compute system comprising:
receiving a patient image;
segmenting a skin lesion in the patient image;
constructing a normalized image by cropping the patient image and adding padding to position the skin lesion at the center of the normalized image;
identifying, by a cancer artificial intelligence (AI) already trained, a skin cancer classification, a skin cancer sub-class, and a risk level assessment; and
generating a skin cancer display including the normalized image, the skin cancer classification, the skin cancer sub-class, and the risk level assessment for displaying on a device.

### Claim 16 (depends on 15)

The non-transitory computer readable medium as claimed in claim 15 wherein identifying the skin cancer sub-class includes submitting a class prediction and a sub-class prediction to a multiplier for calculating the skin cancer sub-class.

### Claim 17 (depends on 15)

The non-transitory computer readable medium as claimed in claim 15 wherein identifying the skin cancer classification includes identifying Melanoma (MEL), Basal Cell Carcinoma (BCC), Epidermal tumors (EPI), Malignant lesions (MALO), Melanocytic Nevus (NV), Dermatofibroma (DF), Benign Adnexal Lesions (BAL), Benign Keratinocytic Lesions (BKL), Benign Vascular lesions (VASC), or Benign Lesions (BENO).

### Claim 18 (depends on 15)

The non-transitory computer readable medium as claimed in claim 15 wherein identifying the risk level assessment by the cancer AI includes identifying a risk level zero through a risk level five.

### Claim 19 (depends on 15)

The non-transitory computer readable medium as claimed in claim 15 wherein the cancer artificial intelligence (AI) already trained includes the cancer artificial intelligence (AI) detecting the skin cancer classification and the skin cancer sub-class for displaying on the skin cancer display.

### Claim 20 (depends on 15)

The non-transitory computer readable medium as claimed in claim 15 wherein generating the skin cancer display includes identifying the risk level assessment as the risk level zero indicating low risk through the risk level five indicating high risk.