Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images.

Autor: Patkar S; Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of Health, Bethesda, MD, USA. patkar.sushant@nih.gov., Chen A; Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of Health, Bethesda, MD, USA., Basnet A; Department of Hematology and Oncology, SUNY Upstate Medical University, Syracuse, NY, USA., Bixby A; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Rajendran R; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Chernet R; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Faso S; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Kumar PA; Department of Hematology and Oncology, SUNY Upstate Medical University, Syracuse, NY, USA., Desai D; Department of Hematology and Oncology, SUNY Upstate Medical University, Syracuse, NY, USA., El-Zammar O; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Curtiss C; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Carello SJ; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Nasr MR; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA., Choyke P; Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of Health, Bethesda, MD, USA., Harmon S; Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of Health, Bethesda, MD, USA., Turkbey B; Artificial Intelligence Resource (AIR), National Cancer Institute, National Institutes of Health, Bethesda, MD, USA., Jamaspishvili T; Department of Pathology and Laboratory Medicine, SUNY Upstate Medical University, Syracuse, NY, USA. jamaspit@upstate.edu.
Jazyk: angličtina
Zdroj: NPJ precision oncology [NPJ Precis Oncol] 2024 Dec 19; Vol. 8 (1), pp. 280. Date of Electronic Publication: 2024 Dec 19.
DOI: 10.1038/s41698-024-00765-w
Abstrakt: Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients. We show that HistoTME accurately predicts the expression of 30 distinct cell type-specific molecular signatures directly from whole slide images, achieving an average Pearson correlation of 0.5 with the ground truth on independent tumor cohorts. Furthermore, we find that HistoTME-predicted microenvironment signatures and their underlying interactions improve prognostication of lung cancer patients receiving immunotherapy, achieving an AUROC of 0.75 [95% CI: 0.61-0.88] for predicting treatment responses following first-line ICI treatment, utilizing an external clinical cohort of 652 patients. Collectively, HistoTME presents an effective approach for interrogating the TME and predicting ICI response, complementing PD-L1 expression, and bringing us closer to personalized immuno-oncology.
Competing Interests: Competing interests: The authors declare no competing interests.
(© 2024. This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.)
Databáze: MEDLINE
Externí odkaz: