Artificial Intelligence (AI) has been a buzz word lately in the healthcare industry. As technology and healthcare continue to merge, applying AI to everyday tasks only seems logical. We have discussed how Google is getting involved with AI to help doctors better serve their clients and diagnose things like diabetes and kidney failure. Now, AI is getting into cancer diagnosis, according to a study by EBioMedicine.
This new AI program, appropriately named ConvPath, uses algorithms and machine learning to analyze the spatial distribution of different types of cells. These differences can reveal cancer cells' growth patterns and the body's immune response to these cancer cells. Pathologists have been doing this for years, but the process is very labor-intensive and time-consuming. Doctors would previously obtain a pathology slide then manually identify the patterns of the millions of cells on the slide. Choosing two or three uniquely identified sections to focus on, which can result in human error. Dr. Guanghua Xiao, the corresponding author of this study and Professor of Population and Data Sciences at UT Southwestern, stated,
"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."
ConvPath is designed to identify cell types from lung cancer pathology slides. They are identifying the cell types by their appearance in pathology slides then creating a map that shows their spatial distributions and interactions of tumor cells and lymphocytes in tumor tissues.
This process results in ConvPath, achieving a 90% accuracy rate. Not only this, but the program also tracks the body's immune response. Researchers think this information could help physicians determine whether the cancer cells cluster together or spread into stromal lymph nodes, drastically enhancing their ability to design personalized immunotherapies for patients.
Dr. Gauanghua Xiao is optimistic about ConvPath and he believes,
"This tool could help pathologists and clinicians to predict the patient prognosis and, therefore, to tailor the treatment plan of individual patients using readily available tissue images."
"Furthermore, this tool could be used to quantify cell to cell interactions and distributions of different types of cells, especially the spatial distribution for lymphocytes and their interaction with the tumor region, which could potentially provide information for patient response to immunotherapy."
Though this sounds like a breakthrough, which it is, we need to remember that this program still has a long road of learning ahead. ConvPath is only designed to identify three major cell types, which overlook the many subtypes that can also contribute to cancer growth. Researchers are already working on a distinct labeling system to help the AI learn to identify these cell subtypes better, but the process is not perfected yet.
Dr. Xiao and the research team concluded,
"The analysis pipeline developed in this study could convert the pathology image into a 'spatial map' of tumor cells, stromal cells, and lymphocytes. This could greatly facilitate and empower comprehensive analysis of the spatial organization of cells, as well as their roles in tumor progression and metastases."
Technology can certainly be surprising and complicated at the same time. That's why it's essential, now more than ever, for you to have the proper support for all your technological needs. Medicus IT is here to provide those Managed Services with efficiency, transparency, and compliance.
Contact us today and learn how we can help your healthcare organization.