Radiomics and Machine Learning in Medical Imaging
Moving in Nature Medicine, bioRxiv, medRxiv, Cancer Research, Nature Communications, Nature Reviews Cancer, eLife and Frontiers in Genetics.
- Moved, week to 23 Oct 2026
- 0
- Papers in 60 days
- 23
Rebuilt
Moved this week
Nothing in this topic has moved yet this week.
Latest in Radiomics and Machine Learning in Medical Imaging
Newest first · last 60 days
Longitudinal clinicogenomic data from over 52,000 cancer patients reveal cachectic weight loss episodes cluster near disease progression and are linked to worse outcomes across cancer types.
- Open access
AI-driven multimodal models outperform single-modality approaches in predicting recurrence and survival in liver cancer patients.
- Open access
Emerging 3D multi-omics tumour atlases have the potential to reveal novel biomarkers and mechanisms of tumour evolution, advancing cancer diagnosis and treatment strategies.
EAGLE AI model detects early esophageal cancer with 90% sensitivity and 98.5% specificity from chest CT scans across multiple centers, enabling scalable screening.
- Open access
General-purpose multimodal large language models in histopathology exhibit errors and hallucinations in over 80% of outputs, impacting diagnostic safety and reliability.
- Open access
RADAR, a generalist AI trained on over 400,000 abdominal CTs, achieves expert-level diagnosis across 18 structures and 146 findings, with high accuracy and robustness.
Deep learning combined with label-free fluorescence lifetime imaging achieves a 0.966 accuracy in predicting EGFR mutations in lung adenocarcinoma tissues.
- Open access
CRISP, a clinically oriented foundation model trained on over 100,000 frozen sections, achieves 92.6% diagnostic accuracy in intraoperative pathology across diverse cases.
- Open access
Detection of tumor-specific HPV-human DNA junctions in serum predicts cervical cancer recurrence with higher accuracy than HPV type alone.
- Open access
Ultrasound radiomics combined with an immune-related gene signature predicts melanoma response to immune checkpoint inhibitors with 78-88% accuracy.
- Open access
Counterfactual diffusion models like MoPaDi enable interpretable explanations by revealing morphological features linked to AI predictions in pathology, with 4 datasets spanning multiple cancers.
- Open access
AI models using clinical and blood data achieved up to 0.77 AUC in NSCLC treatment prediction, outperforming traditional clinical scores in the largest real-world study to date.
- Open access
- 1 cites
Non-invasive imaging of cancer hallmarks enables real-time monitoring and stratification of tumors, with some techniques already impacting clinical treatment decisions.
Add Radiomics and Machine Learning in Medical Imaging as an interest in JClub
Browse JClub
Journals this month
- bioRxiv6131
- medRxiv1703
- PNAS447
- Sci Adv354
- JAMA262
- Environ Res230
- BMJ182
- Environ Pollution165
- Nat Commun161
- Science141
- Nature138
- Lancet128
- Cell Rep120
- NEJM119
- mBio107
- Plant Cell Environ107
- Curr Biol106
- J Exp Bot106
Topics moving, week to 23 Oct 2026
- Single-cell and spatial transcriptomics6
- Neuroinflammation and Neurodegeneration Mechanisms5
- Bacteriophages and microbial interactions5
- Gut microbiota and health5
- Genomics and Phylogenetic Studies4
- Cancer Genomics and Diagnostics4
- Cancer Immunotherapy and Biomarkers4
- Alzheimer's disease research and treatments3
- Inflammatory Bowel Disease3
- Influenza Virus Research Studies3