Pan-cancer integrative histology-genomic analysis via multimodal deep learning
Панканцерный интегративный гистолого-геномный анализ с использованием мультимодального глубокого обучения
2022-08-01
SCID: 54.1/zn8rjxgz
Discuss with AI
computational pathologymolecular profilesmultimodal deep learningprognostic modelswhole-slide images
Figures from the paper
Abstract (AI)
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.
Key Findings
1
A weakly supervised multimodal deep-learning algorithm jointly analyzes whole-slide histology images and molecular profiles across 14 cancer types.
2
An interactive open-access database provides the analyses for exploration, biomarker discovery, and feature assessment.
3
Prognostic correlates are characterized at disease and patient levels across 14 cancers.
4
The method fuses heterogeneous image and genomic data to predict patient outcomes using joint image-omic prognostic models.
5
The models identify explainable morphological and molecular features associated with both poor and favorable prognosis.
Research Object
pathology whole-slide images and molecular profile data from 14 cancer types
Research Subject
integrated morphological and molecular prognostic features and their associations with patient outcomes across cancer types
Publication Details
Publication Date
2022-08-01
Journal
Publisher
ISSN
Cited by
714
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest