Causal Multiple Instance Learning Improves Weakly Supervised Tumor Slide Classification
A causal multiple instance learning framework reduces reliance on confounding slide variations to enhance weakly supervised tumor classification in whole ...
A causal multiple instance learning framework reduces reliance on confounding slide variations to enhance weakly supervised tumor classification in whole ...
A retrospective study demonstrates that a 2.5-dimensional Transformer fusion model using dynamic contrast-enhanced magnetic resonance imaging predicts breast cancer Ki-67 ...
A new study demonstrates that foundation model-based multiple instance learning can predict clinical outcomes in head and neck squamous cell ...
A systematic review examines how deep learning algorithms analyze gigapixel whole-slide images to classify tumors and predict transcriptomic profiles directly ...
A new text-driven multiple instance learning model, TedMIL, improved fine-grained melanoma classification and FISH status prediction from whole slide images ...
A multimodal transformer-based AI framework achieved an AUC of 0.727 on preoperative endoscopic biopsy slides for predicting lymph node metastasis ...
A new iScience study introduces CSCC-PAG, a deep learning framework that combines domain-specific pre-training with self-supervised domain adaptation to improve ...
A new study shows that AI models trained on routine pathology slides can predict BRAF mutation status in melanoma patients ...
A convolutional neural network trained with transfer learning can identify angiographic patterns of cystoid macular edema in retinal vasculitis patients, ...
A deep learning model trained exclusively on adult duodenal biopsy images has achieved pathologist-level accuracy in diagnosing coeliac disease in ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine