Pan-cancer integrative histology-genomic analysis via multimodal deep learning

• Published in: Cancer cell Vol. 40; no. 8; pp. 865 - 878.e6
• Main Authors: Chen, Richard J., Lu, Ming Y., Williamson, Drew F.K., Chen, Tiffany Y., Lipkova, Jana, Noor, Zahra, Shaban, Muhammad, Shady, Maha, Williams, Mane, Joo, Bumjin, Mahmood, Faisal
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 08.08.2022
• Subjects: Algorithms; artificial intelligence; biomarker discovery; cancer prognosis; computational pathology; data fusion; Deep Learning; digital pathology; Genomics - methods; Humans; multimodal integration; multimodal prognostic models; Neoplasms - genetics; Neoplasms - pathology; pan-cancer; Prognosis; data fusion; deep learning; pan-cancer; computational pathology; digital pathology; multimodal prognostic models; multimodal integration; cancer prognosis; biomarker discovery; artificial intelligence
• ISSN: 1535-6108; 1878-3686; 1878-3686
• DOI: 10.1016/j.ccell.2022.07.004

The rapidly emerging field of computational pathology has demonstrated promise in developing objective prognostic models from histology images. However, most prognostic models are either based on histology or genomics alone and do not address how these data sources can be integrated to develop joint image-omic prognostic models. Additionally, identifying explainable morphological and molecular descriptors from these models that govern such prognosis is of interest. We use multimodal deep learning to jointly examine pathology whole-slide images and molecular profile data from 14 cancer types. Our weakly supervised, multimodal deep-learning algorithm is able to fuse these heterogeneous modalities to predict outcomes and discover prognostic features that correlate with poor and favorable outcomes. We present all analyses for morphological and molecular correlates of patient prognosis across the 14 cancer types at both a disease and a patient level in an interactive open-access database to allow for further exploration, biomarker discovery, and feature assessment. [Display omitted] •Multimodal data fusion improves prognostic models for a majority of cancer types•Multimodal attribution elucidates the importance of individual modalities•Model interpretability elucidates morphologic and molecular correlates of prognosis Chen et al. present a pan-cancer analysis that uses deep learning to integrate whole-slide pathology images and molecular features to predict cancer prognosis, with multimodal interpretability used to elucidate morphologic and molecular correlates of prognosis.