Discriminative Subtyping of Lung Cancers from Histopathology Images via Contextual Deep Learning
Lengerich, B. J.; Al-Shedivat, M.; Alavi, A.; Williams, J.; Labbaki, S.; Xing, E. P.
Show abstract
Summarizing multiple data modalities into a parsimonious cancer "subtype" is difficult because the most informative representation of each patients disease is not observed. We propose to model these latent summaries as discriminative subtypes: sample representations which induce accurate and interpretable sample-specific models for downstream predictions. In this way, discriminative subtypes, which are shared between data modalities, can be estimated from one data modality and optimized according to the predictions induced in another modality. We apply this approach to lung cancer by training a deep neural network to predict discriminative subtypes from histopathology images, and use these predicted subtypes to generate models which classify adenocarcinoma, squamous cell carcinoma, and healthy tissue based on transcriptomic signatures. In this way, we optimize the latent discriminative subtypes through induced prediction loss, and the discriminative subtypes are interpreted with standard interpretation of transcriptomic predictive models. Our framework achieves state-of-the-art classification accuracy (F1-score of 0.97) and identifies discriminative subtypes which link histopathology images to transcriptomic explanations without requiring pre-specification of morphological patterns or transcriptomic processes.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Highly Accurate Cancer Phenotype Prediction with AKLIMATE, a Stacked Kernel Learner Integrating Multimodal Genomic Data and Pathway Knowledge 96%
- Exploring tumor-normal cross-talk with TranNet: role of the environment in tumor progression 95%
- A variational autoencoder trained with priors from canonical pathways increases the interpretability of transcriptome data 94%
Similar papers in this journal
Similar papers in this journal
- ROSIE: AI generation of multiplex immunofluorescence staining from histopathology images 95%
- Uncovering interpretable potential confounders in electronic medical records 95%
- FastCCC: A permutation-free framework for scalable, robust, and reference-based cell-cell communication analysis in single cell transcriptomics studies 95%
Similar papers in this journal
- Spatial Transcriptomics Inferred from Pathology Whole-Slide Images Links Tumor Heterogeneity to Survival in Breast and Lung Cancer 97%
- Aggregation of Cohorts for Histopathological Diagnosis with Deep Morphological Analysis 95%
- Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.