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

Machine learning helps diagnose leukemia

Machine learning helps diagnose leukemia

Researchers at the University of Bonn show how artificial intelligence improves the evaluation of blood analysis data.

A pen to pin down the fringes of cancer

A pen to pin down the fringes of cancer

The MasSpec Pen has shown to accurately differentiate healthy and cancerous tissue from banked pancreas samples during surgery.

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.

Hydrogel improves method to diagnose cancer

Hydrogel improves method to diagnose cancer

Researchers tested the effectiveness of specialized hydrogels.

AI assesses metastatic potential in skin cancers

AI assesses metastatic potential in skin cancers

Using a deep learning algorithm, researchers have developed a way to accurately predict which skin cancers are highly metastatic.

Noninvasive test detects cancer cells

Noninvasive test detects cancer cells

Scientists at have shown that diagnostic nanoparticles could be used to monitor tumor recurrence after treatment or to perform routine cancer screenings.

Artificial intelligence shortcuts introduce bias in cancer treatment

Artificial intelligence shortcuts introduce bias in cancer treatment

AI tools models are a powerful tool in cancer treatment. However, unless these algorithms are properly calibrated, they can sometimes make inaccurate or biased predictions.

MasSpec Pen shows promise in pancreatic cancer surgery

MasSpec Pen shows promise in pancreatic cancer surgery

The MasSpec Pen has shown to accurately identify tissues and surgical margins directly in patients and differentiate healthy and cancerous tissue from banked pancreas samples.

Portable hybrid gamma camera should improve cancer diagnosis

Portable hybrid gamma camera should improve cancer diagnosis

Scientists have designed a portable 3D imaging device which will improve the treatment and diagnosis of cancer.

Popular articles

Subscribe to Newsletter