1
Signal
The recent window is materially active
636 eligible papers appear in the current 30-day evidence window, compared with 153 in the prior 30 days. The busiest visible day is 2026-04-21 with 69 eligible papers.
4.2x prior-window volumeWeekly Trend BriefEvidence window ending 2026-05-10
AI in cancer detection
Weekly trend brief
AI cancer-detection papers are concentrated in mammography, pathology slides, and deployment barriers. The current 30-day evidence window contains 636 eligible papers, 4.2x the prior 30-day window, with 633 abstract-backed papers available for a closer scan. Representative papers point to mammographic self-supervision, pathology foundation models, whole-slide metastasis detection, cytology classification, interpretable histopathology models, pathologist-AI interaction, and clinical implementation barriers.
636Recent papers
4.2xVs prior window
633Abstract-backed
6Representative sources
Current windowRecent eligible papers
ComparisonPrior eligible papers
Brief typeWeekly research trend
Evidence-backed signals
What's moving
2
Signal
The reviewable evidence is broad enough for commentary
633 recent papers include abstracts, about 100% of the eligible set. That gives the brief enough signal for topic-specific commentary while keeping claims limited to paper metadata and representative titles.
633 abstract-backed papers3
Signal
Representative titles show a clear topic shape
The selected papers point toward mammographic self-supervision, pathology foundation models, whole-slide metastasis detection, cytology classification, interpretable histopathology models, pathologist-AI interaction, and clinical implementation barriers. That gives the brief a visible research direction rather than only a ranked list of recent papers.
8 representative papers4
Signal
Source mix gives readers multiple entry points
8 representative papers span 6 sources, including 2 preprints that should be treated as preliminary.
6 representative sources
Topic shape
Theme clusters
Breast imaging and mammography models
Mammography and breast-cancer survival papers show the current evidence set is not just generic imaging AI.
8 representative papersPathology and slide-level classification
Whole-slide, cytology, histopathology, and foundation-model papers make digital pathology a central thread.
8 representative papersHuman workflow and deployment
Pathologist-AI interaction and implementation-barrier papers keep clinical workflow questions next to model-performance work.
8 representative papers
Evidence anchors
Representative papers
AI in cancer detection
MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in arXiv (Cornell University) (2026) and is matched to AI in cancer detection.
AI in cancer detection
Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in arXiv (Cornell University) (2026) and is matched to AI in cancer detection. Treat as preliminary because it is marked as a preprint.
AI in cancer detection
Detecting Breast Carcinoma Metastasis on Whole-Slide Images by Partially Subsampled Multiple Instance Learning
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in arXiv (Cornell University) (2026) and is matched to AI in cancer detection. Treat as preliminary because it is marked as a preprint.
AI in cancer detection
Explainable artificial intelligence with pyramid vision transformer model for multi-class malignant cell classification on cytology slides
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in Scientific Reports (2026) and is matched to AI in cancer detection.
AI in cancer detection
MSWA-ResNet: Multi-Scale Wavelet Attention for Patient-Level and Interpretable Breast Cancer Histopathology Classification
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in Journal of Imaging (2026) and is matched to AI in cancer detection.
AI in cancer detection
Examination of Pathologist–Artificial Intelligence Interactions and Their Impact on Pathologist Accuracy Using Artificial Intelligence–Assisted Scoring of Immunohistochemistry for Human Epidermal Growth Factor Receptor 2
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in Archives of Pathology & Laboratory Medicine (2026) and is matched to AI in cancer detection.
AI in cancer detection
Challenges and Barriers in Implementing AI for Clinical Applications in Anatomic Pathology
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in Advances in Anatomic Pathology (2026) and is matched to AI in cancer detection.
AI in cancer detection
A review of current imaging techniques for histopathology-based breast cancer diagnosis with comparative insights using machine learning and deep learning models and its challenges and future directions
Selected because it anchors a mammography, pathology, explainability, pathologist-workflow, or clinical-deployment question; this paper appears in PeerJ Computer Science (2026) and is matched to AI in cancer detection.