According to the latest research, the Center for Computational Imaging and Personalized Diagnostics (CCIPD) at Case Western Reserve University and pharmaceutical companies have collaborated to create artificial intelligence (AI) tools that will help patients with non-small cell lung cancer (NSCLC) based on an analysis of typical tissue biopsy images.
Anant Madabhushi. Image Credit: Case Western Reserve University.
As per the American Society of Clinical Oncology, more than 236,000 adults in the United States will receive a lung cancer diagnosis this year, with non-small cell lung cancer accounting for around 82% of those cases.
To predict the efficacy of immunotherapy and clinical outcomes, such as survival, scientists at the CCIPD employed AI to extract biomarkers from biopsy pictures of patients with NSCLC and gynecologic tumors.
We have shown that the spatial interplay of features relating to the cancer nuclei and tumor-infiltrating lymphocytes drives a signal that allows us to identify which patients are going to respond to immunotherapy and which ones will not.
Anant Madabhushi, Director, Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University
Madabhushi was also a Donnell Institute Professor of Biomedical Engineering at Case Western Reserve.
In the journal Science Advances, the study was released this month.
As per the National Institutes of Health and other sources, studies on immunotherapy reveal that only 20–30% of patients benefit from the therapy. These results confirm that the CCIPD’s AI technologies can assist doctors in deciding how to treat patients with NSCLC and gynecologic cancers, such as cervical, endometrial, and ovarian cancer, according to Madabhushi.
A protein called PD-L1 that aids in preventing immune cells from attacking healthy cells in the body was also the subject of the study, which was based on a retrospective examination of data.
Patients with high PD-L1 frequently receive immunotherapy as part of their NSCLC therapy, whereas patients with low PD-L1 frequently obtain immunotherapy in combination with chemotherapy or are not provided it at all.
Our work has identified a subset of patients with low PD-L1 who respond very well to immunotherapy and may not require immunotherapy plus chemotherapy.
Anant Madabhushi, Director, Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University
“This could potentially help these patients avoid the toxicity associated with chemotherapy while also having a favorable response to immunotherapy.”
The multi-site, multi-institutional trial looked at atezolizumab, nivolumab, and pembrolizumab as three popular immunotherapy medications (known as checkpoint inhibitor treatments) that target PD-L1. For all three immunotherapies, the AI tools accurately predicted the response and clinical results.
The study is a component of larger research being done at CCIPD to create and implement novel AI and machine-learning approaches to diagnose and forecast the treatment response for a variety of diseases and cancers, such as breast, prostate, head and neck, brain, colorectal, gynecologic, and skin cancers.
The research comes at a time when Case Western Reserve and Picture Health have just signed a license deal for the commercialization of AI solutions for NSCLC and other cancer patients.
Journal Reference:
Wang, X., et al. (2022) Spatial interplay patterns of cancer nuclei and tumor-infiltrating lymphocytes (TILs) predict clinical benefit for immune checkpoint inhibitors. Science Advances. doi.org/10.1126/sciadv.abn3966.