Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images.

Autor: Huang Z; School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA.; Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA., Shao W; Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA., Han Z; Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.; Regenstrief Institute, Indianapolis, IN, 46202, USA.; Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, IN, 46202, USA., Alkashash AM; Department of Pathology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA., De la Sancha C; Department of Pathology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA., Parwani AV; Department of Pathology, The Ohio State University Wexner Medical Center, Columbus, OH, 43210, USA., Nitta H; Roche Tissue Diagnostics, 1910 E. Innovation Park Drive, Tucson, AZ, 85755, USA., Hou Y; University Hospitals Cleveland Medical Center, Case Western Reserve University, 11100 Euclid Avenue, Cleveland, OH, 44106, USA., Wang T; Department of Computer Science, Indiana University Bloomington, Bloomington, IN, 47408, USA., Salama P; Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA., Rizkalla M; Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA., Zhang J; Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA., Huang K; Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA. kunhuang@iu.edu.; Regenstrief Institute, Indianapolis, IN, 46202, USA. kunhuang@iu.edu.; Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, IN, 46202, USA. kunhuang@iu.edu., Li Z; Department of Pathology, The Ohio State University Wexner Medical Center, Columbus, OH, 43210, USA. Zaibo.Li@osumc.edu.
Jazyk: angličtina
Zdroj: NPJ precision oncology [NPJ Precis Oncol] 2023 Jan 27; Vol. 7 (1), pp. 14. Date of Electronic Publication: 2023 Jan 27.
DOI: 10.1038/s41698-023-00352-5
Abstrakt: Advances in computational algorithms and tools have made the prediction of cancer patient outcomes using computational pathology feasible. However, predicting clinical outcomes from pre-treatment histopathologic images remains a challenging task, limited by the poor understanding of tumor immune micro-environments. In this study, an automatic, accurate, comprehensive, interpretable, and reproducible whole slide image (WSI) feature extraction pipeline known as, IMage-based Pathological REgistration and Segmentation Statistics (IMPRESS), is described. We used both H&E and multiplex IHC (PD-L1, CD8+, and CD163+) images, investigated whether artificial intelligence (AI)-based algorithms using automatic feature extraction methods can predict neoadjuvant chemotherapy (NAC) outcomes in HER2-positive (HER2+) and triple-negative breast cancer (TNBC) patients. Features are derived from tumor immune micro-environment and clinical data and used to train machine learning models to accurately predict the response to NAC in breast cancer patients (HER2+ AUC = 0.8975; TNBC AUC = 0.7674). The results demonstrate that this method outperforms the results trained from features that were manually generated by pathologists. The developed image features and algorithms were further externally validated by independent cohorts, yielding encouraging results, especially for the HER2+ subtype.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz: