# US 2021/0240966 A1 · System for automatic tumor detection and classification

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

- Number: US 2021/0240966 A1
- Document ID: US20210240966A1
- Status: Published application
- Kind: A1
- Application number: 17/236,739
- Filed: 2021-04-21
- Published: 2021-08-05
- Earliest claimed: 2018-08-30
- Assignees: Applied Materials, Inc.
- Applicants: Applied Materials, Inc.
- Inventors: Parijat Prakash PRABHUDESAI; Ganesh Kumar MOHANUR RAGHUNATHAN; Sumit Kumar JHA; Aditya SISTA; Narasimha Murthy CHANDAN
- Web page: https://patentgrep.com/patent/US20210240966A1

## CPC

- G06V 20/698: {Matching; Classification}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06T 7/0012: {Biomedical image inspection}
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/7784: {based on feedback from supervisors}
- G06V 10/82: using neural networks
- G06V 10/987: {with the intervention of an operator}
- G06N 3/02: Neural networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06T 7/11: Region-based segmentation
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Certain aspects of the present disclosure provide techniques for automatically detecting and classifying tumor regions in a tissue slide. The method generally includes obtaining a digitized tissue slide from a tissue slide database and determining, based on output from a tissue classification module, a type of tissue of shown in the digitized tissue slide. The method further includes determining, based on output from a tumor classification model for the type of tissue, a region of interest (ROI) of the digitized tissue slide and generating a classified slide showing the ROI of the digitized tissue slide and an estimated diameter of the ROI. The method further includes displaying on an image display unit, the classified slide and user interface (UI) elements enabling a pathologist to enter input related to the classified slide.

## Claims

### Claim 1

A method for automatically detecting and classifying tumor regions in a tissue slide by a tumor classification module, comprising:
receiving from a pathologist assistance system, a digitized tissue slide;
generating a binary mask, wherein the binary mask indicates a region of interest (ROI) in the digitized tissue slide;
determining a diameter of the ROI based on an ellipse fitted to match the ROI;
sorting the ROI into a tumor class based on the diameter of the ROI, wherein the tumor class indicates a stage of tumors in the tumor class;
generating, based on the ROI, a classified slide, wherein the classified slide shows each ROI as color-coded based on the tumor class associated with each ROI; and
transmitting, to the pathologist assistance system, the classified slide.

### Claim 2 (depends on 1)

The method of claim 1, wherein the digitized tissue slide is analyzed by a tissue classification model to determine a class of tissue in the digitized tissue slide prior to detecting and classifying tumor regions therein.

### Claim 3 (depends on 1)

The method of claim 1, further comprising segmenting the ROI based on size.

### Claim 4 (depends on 1)

The method of claim 1, wherein the classified slide shows the ROI as an overlay.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving, from the pathologist assistance system, a correction to the classified slide made by a pathologist; and
updating a tumor classification model used to identify the ROI based on the correction to the classified slide.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
receiving, from the pathologist assistance system, an indication of a biomarker used to stain the digitized tissue slide; and
selecting a tumor classification model to analyze the digitized tissue slide based on the biomarker used.

### Claim 7 (depends on 1)

The method of claim 1, wherein the digitized tissue slide is obtained from a digitized tissue slide database.

### Claim 8 (depends on 1)

The method of claim 1, wherein the ROI is a region of continuous tumor cells.

### Claim 9

A system comprising:
a processor; and
a memory including instructions, which, when executed by the processor, cause the system to perform a method for automatically detecting and classifying tumor regions in a tissue slide by a tumor classification module, the method comprising:
receiving from a pathologist assistance system, a digitized tissue slide;
generating a binary mask, wherein the binary mask indicates a region of interest (ROI) in the digitized tissue slide;
determining a diameter of the ROI based on an ellipse fitted to match the ROI;
sorting the ROI into a tumor class based on the diameter of the ROI, wherein the tumor class indicates a stage of tumors in the tumor class;
generating, based on the ROI, a classified slide, wherein the classified slide shows each ROI as color-coded based on the tumor class associated with each ROI; and
transmitting, to the pathologist assistance system, the classified slide.

### Claim 10 (depends on 9)

The system of claim 9, the method further comprising:
segmenting the ROI based on size.

### Claim 11 (depends on 9)

The system of claim 9, wherein the classified slide shows the ROI as an overlay.

### Claim 12 (depends on 9)

The system of claim 9, the method further comprising:
receiving, from the pathologist assistance system, a correction to the classified slide made by a pathologist; and
updating a tumor classification model used to identify the ROI based on the correction to the classified slide.

### Claim 13 (depends on 9)

The system of claim 9, the method further comprising:
receiving, from the pathologist assistance system, an indication of a biomarker used to stain the digitized tissue slide; and
selecting a tumor classification model to analyze the digitized tissue slide based on the biomarker used.

### Claim 14 (depends on 9)

The system of claim 9, wherein the digitized tissue slide is obtained from a digitized tissue slide database.

### Claim 15 (depends on 9)

The system of claim 9, wherein the ROI is a region of continuous tumor cells.

### Claim 16

A method for automatically detecting and classifying tumor regions in a tissue slide by a tumor classification module, comprising:
receiving from a pathologist assistance system, a digitized tissue slide obtained from a digitized tissue slide database;
generating a binary mask, wherein the binary mask indicates a region of interest (ROI) in the digitized tissue slide, the ROI comprising a region of continuous tumor cells;
determining a diameter of the ROI based on an ellipse fitted to match the ROI, the diameter;
sorting the ROI into a tumor class based on the diameter of the ROI, wherein the tumor class indicates a stage of tumors in the tumor class;
generating, based on the ROI, a classified slide, wherein the classified slide shows the ROI as an overlay on the digitized tissue slide, and wherein the classified slide shows the ROI as color-coded based on the tumor class associated with the ROI; and
transmitting, to the pathologist assistance system, the classified slide.

### Claim 17 (depends on 16)

The method of claim 16, wherein the digitized tissue slide is analyzed by a tissue classification model to determine a class of tissue in the digitized tissue slide prior to detecting and classifying tumor regions therein.

### Claim 18 (depends on 16)

The method of claim 16, further comprising segmenting the ROI based on size.

### Claim 19 (depends on 16)

The method of claim 16, further comprising:
receiving, from the pathologist assistance system, a correction to the classified slide made by a pathologist; and
updating a tumor classification model used to identify the ROI based on the correction to the classified slide.

### Claim 20 (depends on 16)

The method of claim 16, further comprising:
receiving, from the pathologist assistance system, an indication of a biomarker used to stain the digitized tissue slide; and
selecting a tumor classification model to analyze the digitized tissue slide based on the biomarker used.