Detecting Extrachromosomal DNA from Routine Histopathology
Khalid, M. A.; Gratius, M.; Brown, C.; Younis, R.; Ahmadi, Z.; Chavez, L.
Show abstract
Extrachromosomal DNA (ecDNA) is a major driver of oncogene amplification, tumour heterogeneity and poor clinical outcomes [1-3], yet its detection relies on specialised genomic assays that are not integrated into routine diagnostics. Here, we show that ecDNA status can be inferred directly from standard haematoxylin and eosin-stained whole-slide pathology images. We develop an end-to-end, weakly supervised deep learning framework that aggregates thousands of high-magnification patches per slide with slide-level augmentation and interpretable attention. Across twelve cancer types from The Cancer Genome Atlas, the approach identifies tumours with genomic amplifications and, critically, distinguishes ecDNA-amplified from chromosomally amplified or non-amplified tumours, with the strongest signal in glioblastoma. Attention maps localise regions enriched for nuclei with altered chromatin intensity and texture, and predicted ecDNA status recapitulates its adverse association with survival. These results indicate that ecDNA amplifications leave reproducible histomorphologic foot-prints detectable by routine pathology, enabling scalable screening to prioritise tumours for confirmatory molecular testing.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Machine learning-based tissue of origin classification for cancer of unknown primary diagnostics using genome-wide mutation features 95%
- Multiplexed RNA-FISH-guided Laser Capture Microdissection RNA Sequencing Improves Breast Cancer Molecular Subtyping, Prognostic Classification, and Predicts Response to Antibody Drug Conjugates 95%
- The mutational signatures of formalin fixation on the human genome 95%
Similar papers in this journal
- Image-Based Consensus Molecular Subtyping in Rectal Cancer Biopsies and Response to Neoadjuvant Chemoradiotherapy 95%
- Generalizing AI-driven Assessment of Immunohistochemistry across Immunostains and Cancer Types: A Universal Immunohistochemistry Analyzer 95%
- Predicting the Tumor Microenvironment Composition and Immunotherapy Response in Non-Small Cell Lung Cancer from Digital Histopathology Images 94%
Similar papers in this journal
- Disruption of metazoan gene regulatory networks in cancer alters the balance of co-expression between genes of unicellular and multicellular origins 94%
- RNA allelic frequencies of somatic mutations encode substantial functional information in cancers 93%
- Spatiotemporal modeling reveals high-resolution invasion states in glioblastoma 93%
Similar papers in this journal
"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.