mlsanityData to 7 Oct 2026

Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary

arXiv 2006.13932 ↗First posted 24 Jun 2020q-bio.TO cs.LG q-bio.QMcited by 89

Not on the map. Why?

Abstract (arXiv)

Cancer of unknown primary (CUP) is an enigmatic group of diagnoses where the primary anatomical site of tumor origin cannot be determined. This poses a significant challenge since modern therapeutics such as chemotherapy regimen and immune checkpoint inhibitors are specific to the primary tumor. Recent work has focused on using genomics and transcriptomics for identification of tumor origins. However, genomic testing is not conducted for every patient and lacks clinical penetration in low resource settings. Herein, to overcome these challenges, we present a deep learning-based computational pathology algorithm-TOAD-that can provide a differential diagnosis for CUP using routinely acquired histology slides. We used 17,486 gigapixel whole slide images with known primaries spread over 18 common origins to train a multi-task deep model to simultaneously identify the tumor as primary or metastatic and predict its site of origin. We tested our model on an internal test set of 4,932 cases with known primaries and achieved a top-1 accuracy of 0.84, a top-3 accuracy of 0.94 while on our external test set of 662 cases from 202 different hospitals, it achieved a top-1 and top-3 accuracy of 0.79 and 0.93 respectively. We further curated a dataset of 717 CUP cases from 151 different medical centers and identified a subset of 290 cases for which a differential diagnosis was assigned. Our model predictions resulted in concordance for 50% of cases (kappa=0.4 when adjusted for agreement by chance) and a top-3 agreement of 75%. Our proposed method can be used as an assistive tool to assign differential diagnosis to complicated metastatic and CUP cases and could be used in conjunction with or in lieu of immunohistochemical analysis and extensive diagnostic work-ups to reduce the occurrence of CUP.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 14; 2023: 23; 2024: 24; 2025: 11; 2026: 7.

89 papers.

Sort:

By area:

  1. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
  2. 2023Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Imagescited by 132
  3. 2021Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networkscited by 124
  4. 2023Artificial Intelligence for Digital and Computational Pathologycited by 106
  5. 2024HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysiscited by 104
  6. 2023Cross-Modal Translation and Alignment for Survival Analysiscited by 70
  7. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 58
  8. 2022Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potentialcited by 54
  9. 2024SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understandingcited by 54
  10. 2023Towards a Visual-Language Foundation Model for Computational Pathologycited by 52
  11. 2022Differentiable Zooming for Multiple Instance Learning on Whole-Slide Imagescited by 43
  12. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
38 more
  1. 2023The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classificationcited by 41
  2. 2022Deep Multi-modal Fusion of Image and Non-image Data in Disease Diagnosis and Prognosis: A Reviewcited by 37
  3. 2023CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Countingcited by 33
  4. 2025Evidence-based diagnostic reasoning with multi-agent copilot for human pathologycited by 26
  5. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Needcited by 21
  6. 2023A Foundational Multimodal Vision Language AI Assistant for Human Pathologycited by 19
  7. 2022Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalizationcited by 17
  8. 2024xMIL: Insightful Explanations for Multiple Instance Learning in Histopathologycited by 15
  9. 2024PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understandingcited by 15
  10. 2025Learning Optimal Multimodal Information Bottleneck Representationscited by 15
  11. 2023Hierarchical discriminative learning improves visual representations of biomedical microscopycited by 12
  12. 2024Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysiscited by 11
  13. 2022OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histologycited by 9
  14. 2023Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracycited by 9
  15. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teachercited by 9
  16. 2024Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imagingcited by 9
  17. 2022Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomicscited by 8
  18. 2023Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classificationcited by 8
  19. 2023A Generalizable Deep Learning System for Cardiac MRIcited by 8
  20. 2024AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnosticscited by 8
  21. 2021DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysiscited by 7
  22. 2023Large-scale pretraining on pathological images for fine-tuning of small pathological benchmarkscited by 7
  23. 2024Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directionscited by 7
  24. 2021PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learningcited by 6
  25. 2024A self-supervised framework for learning whole slide representationscited by 6
  26. 2024SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classificationcited by 6
  27. 2022REET: Robustness Evaluation and Enhancement Toolbox for Computational Pathologycited by 5
  28. 2022Embedding Space Augmentation for Weakly Supervised Learning in Whole-Slide Imagescited by 5
  29. 2021Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiologycited by 4
  30. 2021Rapid Automated Analysis of Skull Base Tumor Specimens Using Intraoperative Optical Imaging and Artificial Intelligencecited by 4
  31. 2022Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Imagescited by 4
  32. 2023From Whole-slide Image to Biomarker Prediction: A Protocol for End-to-End Deep Learning in Computational Pathologycited by 4
  33. 2024Hard Negative Sample Mining for Whole Slide Image Classificationcited by 4
  34. 2024Diagnostic Text-guided Representation Learning in Hierarchical Classification for Pathological Whole Slide Imagecited by 4
  35. 2024RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistencycited by 4
  36. 2021Pan-Cancer Integrative Histology-Genomic Analysis via Interpretable Multimodal Deep Learningcited by 3
  37. 2023AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Imagecited by 3
  38. 2023Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classificationcited by 3

50 most cited of 89 All 89 (JSON)