Autonomous learning of pathologists' cancer grading rules
Nguyen, T. H.; Panwar, V.; Jarmale, V.; Perny, A.; Dusek, C.; Cai, Q.; Kapur, P. H.; Danuser, G.; Rajaram, S.
Show abstract
Deep learning has revealed that tissue morphology contains rich biological information beyond human understanding. However, approaches to convert these spatially distributed signals into precise subcellular insights informing disease mechanism are lacking. We introduce Delta-Marches, an interpretability-first approach that nominates distinguishing morphological features rather than explaining existing models decisions. Delta-Marches leverages a generative AI framework with latent-space traversals that simulate idealized morphological changes between classes. Comparing each image to its class-shifted counterpart allows downstream feature extractors to infer aspects most affected by the shift, reducing sample-to-sample variability and yielding interpretable morphological transformations at subcellular resolution. Prototyped in renal carcinoma histopathological grading, Delta-Marches generates realistic grade transitions and pinpoints tumor-cell nuclear phenotypes as key properties of tumor grades. It also reveals reduced vasculature associated with increasing grade, a pattern reported in studies but absent from standard grading rubrics. These results indicate Delta-Marchs ability to parse complex image phenotypes and catalyze hypothesis generation.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- STAIG: Spatial Transcriptomics Analysis via Image-Aided Graph Contrastive Learning for Domain Exploration and Alignment-Free Integration 97%
- Learning tissue representation by identification of persistent local patterns in spatial omics data 96%
- PHARAOH: A collaborative crowdsourcing platform for PHenotyping And Regional Analysis Of Histology 96%
Similar papers in this journal
- Predicting MammaPrint Recurrence Risk from Breast Cancer Pathological Images Using a Weakly Supervised Transformer 96%
- Unsupervised segmentation of 3D microvascular photoacoustic images using deep generative learning 96%
- Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity 96%
Similar papers in this journal
- AI for radiographic COVID-19 detection selects shortcuts over signal 96%
- Sagittarius: Extrapolating Heterogeneous Time-Series Gene Expression Data 95%
- Inferring spatial single-cell-level interactions through interpreting cell state and niche correlations learned by self-supervised graph transformer 95%
Similar papers in this journal
- Identifying perturbations that boost T-cell infiltration into tumours via counterfactual learning of their spatial proteomic profiles 96%
- Single-shot 3D photoacoustic tomography using a single-element detector for ultrafast imaging of hemodynamics 93%
- In vivo fluorescence imaging with a flat, lensless microscope 92%
"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.