ConvPath software uses AI to identify cancer cells

UT Southwestern researchers have developed a software tool that uses artificial intelligence to recognize cancer cells from digital pathology images—giving clinicians a powerful way of predicting patient outcomes.

Photo
This illustration of the ConvPath software workflow shows how the AI algorithm automatically recognizes each cell in the pathology image (upper image) as a tumor cell (orange), stromal cell (green), or lymphocyte (blue), then converts the image into a spatial map (middle image). Clusters of tumor cells are further identified as tumor regions (orange areas in the bottom image).
Source: UT Southwestern Medical

The spatial distribution of different types of cells can reveal a cancer’s growth pattern, its relationship with the surrounding microenvironment, and the body’s immune response. But the process of manually identifying all the cells in a pathology slide is extremely labor intensive and error-prone. “As there are usually millions of cells in a tissue sample, a pathologist can only analyze so many slides in a day. To make a diagnosis, pathologists usually only examine several ‘representative’ regions in detail, rather than the whole slide. However, some important details could be missed by this approach,” said Dr. Guanghua “Andy” Xiao, corresponding author of a study published in EBioMedicine and Professor of Population and Data Sciences at UT Southwestern.

The human brain, Dr. Xiao added, is not good at picking up subtle morphological patterns. Therefore, a major technical challenge in systematically studying the tumor microenvironment is how to automatically classify different types of cells and quantify their spatial distributions, he said.

The AI algorithm that Dr. Xiao and his team developed, called ConvPath, overcomes these obstacles by using AI to classify cell types from lung cancer pathology images.

Here’s how it works: The ConvPath algorithm can “look” at cells and identify their types based on their appearance in the pathology images using an AI algorithm that learns from human pathologists. This algorithm effectively converts a pathology image into a “map” that displays the spatial distributions and interactions of tumor cells, stromal cells (i.e., the connective tissue cells), and lymphocytes (i.e., the white blood cells) in tumor tissue.

Whether tumor cells cluster well together or spread into stromal lymph nodes is a factor revealing the body’s immune response. So knowing that information can help doctors customize treatment plans and pinpoint the right immunotherapy.

Ultimately, the algorithm helps pathologists obtain the most accurate cancer cell analysis—in a much faster way. “It is time-consuming and difficult for pathologists to locate very small tumor regions in tissue images, so this could greatly reduce the time that pathologists need to spend on each image,” said Dr. Xiao, who also has an appointment in the Lyda Hill Department of Bioinformatics and is a member of both the Quantitative Biomedical Research Center (QBRC) and the Harold C. Simmons Comprehensive Cancer Center at UTSW.

Subscribe to our newsletter

Related articles

Algorithms for liver surgery make operations more safe

Algorithms for liver surgery make operations more safe

Researcher have developed algorithms that analyze patients‘ imaging data and calculate surgical risks. This makes liver cancer surgery safer and easier to plan.

AI finds patterns of mutations in tumour images

AI finds patterns of mutations in tumour images

Researchers have developed an AI algorithm that uses computer vision to analyze tissue samples from cancer patients.

Lung cancer: AI could predict risk of recurrence

Lung cancer: AI could predict risk of recurrence

Computer scientists working with pathologists have trained an AI tool to determine which patients with lung cancer have a higher risk of their disease coming back after treatment.

AI tracks down acute myeloid leukemia

AI tracks down acute myeloid leukemia

Artificial intelligence can detect one of the most common forms of blood cancer—acute myeloid leukemia (AML)—with high reliability.

AI detects even the smallest metastases

AI detects even the smallest metastases

Researchers have developed a new algorithm that enables automated detection of metastases at the level of single disseminated cancer cells in whole mice.

Deep learning identifies molecular patterns of cancer

Deep learning identifies molecular patterns of cancer

An AI platform can analyze genomic data extremely quickly, picking out key patterns to classify different types of colorectal tumors and improve the drug discovery process.

AI predicts effectiveness of immunotherapy

AI predicts effectiveness of immunotherapy

Scientists can determine which lung-cancer patients will benefit from expensive immunotherapy.

Deep learning assists in detecting malignant lung cancers

Deep learning assists in detecting malignant lung cancers

Radiologists assisted by deep learning based software were better able to detect malignant lung cancers on chest X-rays.

Using AI to predict risk of thyroid cancer on ultrasound

Using AI to predict risk of thyroid cancer on ultrasound

Researchers from Thomas Jefferson University use machine learning on ultrasound images of thyroid nodules to predict risk of malignancy.

Popular articles