# US 2022/0037025 A1 · Apparatus, systems, and methods for rapid cancer detection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0037025 A1
- Document ID: US20220037025A1
- Status: Published application
- Kind: A1
- Application number: 17/506,192
- Filed: 2021-10-20
- Published: 2022-02-03
- Earliest claimed: 2017-04-28
- Assignees: 4D Path Inc.
- Applicants: 4D Path Inc.
- Inventors: Satabhisa Mukhopadhyay; Tathagata Dasgupta; Supratim Guha Ray
- Web page: https://patentgrep.com/patent/US20220037025A1

## CPC

- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06V 20/695: {Preprocessing, e.g. image segmentation}
- G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06T 2207/10024: Color image
- G06T 2207/10048: Infrared image
- G06T 2207/30004: Biomedical image processing
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Presented herein are systems, methods, and apparatus that analyze molecular imprints for detecting cancerous cells. Embodiments of the present disclosure include systems, methods, and apparatus that analyze metabolic imprints of cells for cancer detection. In certain embodiments, the methods/systems comprise extracting thermal and thermodynamic quantities and properties from the molecular imprints. The thermal/thermodynamic quantities and/or further-processed quantities can be mapped on a universal cancer diagnostic scale for disease stratification, thereby providing/determining a normality status of the subject cells.

## Claims

### Claim 1

A method for detecting one or more types of cancers (e.g., deciding a normality status, e.g., subtle cases of cancers) from metabolic imprints of cells, the method comprising:
(i) accessing an image in a database;
(e.g., selecting an area to be analyzed in the image) (ii) identifying, by a processor of a computing device, one or more cells in the image;
(iii) segmenting, by the processor, each of the one more cells into a nucleus area and a cellular area;
(iv) for each of the one or more cells, extracting, by the processor, an information surface value associated with a nuclear contrast feature (e.g., temperature difference between the nucleus area and the cellular area, e.g., contrast difference between the nucleus area and the cellular area), and a nuclear area feature (e.g., a ratio of a nucleus area to a nuclear volume projection)
(e.g., wherein the nuclear contrast feature and/or the nuclear area feature are obtained at a wavelength corresponding to a maximal radiant power of the naturally emitted IR from one or more cells),
(e.g., wherein the nuclear contrast feature is an averaged value of one or more nuclear contrast features obtained at one or more wavelengths of naturally emitted IR from one or more cells),
(e.g., wherein the nuclear area feature is an averaged value of one or more nuclear area features obtained at one or more wavelengths of the naturally emitted IR from one or more cells);
(v) calculating, by the processor, a specificity index, a log thermal capacity and a diagnostic score from the information surface values; and
(vi) determining, by the processor, a normality status for at least a portion of the image by mapping the diagnostic score on a reference scale (e.g., identifying one or more portions of the cells in the image that are cancerous) (e.g., identifying one or more stages of cancer for one or more portions of the cells in the image).
