NSTL国家科技图书文献中心

1. Multi-task Learning Approach for Intracranial Hemorrhage Prognosis NSTL国家科技图书文献中心

Miriam Cobo | Amaia Perez del Barr...... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 12～21 - 共10页

摘要：Prognosis after intracranial hemorrhage (ICH | ) is influenced by a complex interplay between | imaging and tabular data. Rapid and reliable prognosis | are crucial for effective patient stratification and | informed treatment decision-making. In this study, we aim

关键词： Prognosis | Multi-task learning | Explainable AI

2. StoDIP: Efficient 3D MRF Image Reconstruction with Deep Image Priors and Stochastic Iterations NSTL国家科技图书文献中心

Perla Mayo | Matteo Cencini ... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 128～137 - 共10页

摘要：Magnetic Resonance Fingerprinting (MRF) is a | time-efficient approach to quantitative MRI for | multiparametric tissue mapping. The reconstruction of | quantitative maps requires tailored algorithms for removing | aliasing artefacts from the compressed sampled MRF

关键词： Magnetic resonance fingerprinting | Quantiative MRI | Compressed sensing | Deep image prior | Iterative algorithms

3. Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging NSTL国家科技图书文献中心

Sarah Muller | Louisa Fay ... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 53～62 - 共10页

摘要：Medical imaging cohorts are often confounded | by factors such as acquisition devices, hospital | sites, patient backgrounds, and many more. As a result | , deep learning models tend to learn spurious | correlations instead of causally related features, limiting

关键词： Shortcut learning | Domain shift | Disentanglement

4. Characterizing the Histology Spatial Intersections Between Tumor-Infiltrating Lymphocytes and Tumors for Survival Prediction of Cancers Via Graph Contrastive Learning NSTL国家科技图书文献中心

Yangyang Shi | Qi Zhu ... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 212～221 - 共10页

摘要：Tumor-infiltrating lymphocytes (TILs) and | their spatial interactions with tumors on whole-slide | images (WSIs) of histopathology sections can provide | valuable information about the immune response within the | tumor micro-environment that is closely associated

关键词： Graph contrastive learning | Survival analysis | Tumor-Infiltrating lymphocytes | Whole-Slide histopathological image

5. Arges: Spatio-Temporal Transformer for Ulcerative Colitis Severity Assessment in Endoscopy Videos NSTL国家科技图书文献中心

Krishna Chaitanya | Pablo F. Damasceno ... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 201～211 - 共11页

摘要：Accurate assessment of disease severity | from endoscopy videos in ulcerative colitis (UC) is | crucial for evaluating drug efficacy in clinical trials | . Severity is often measured by the Mayo Endoscopic | Subscore (MES) and Ulcerative Colitis Endoscopic Index of

关键词： Weakly-supervised learning | Ulcerative colitis | Endoscopy | Self-supervised learning | Transformers | UC disease severity assessment

6. Noise-Robust Conformal Prediction for Medical Image Classification NSTL国家科技图书文献中心

Coby Penso | Jacob Goldberger - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 159～168 - 共10页

摘要：Conformal Prediction (CP) quantifies network | uncertainty by building a small prediction set with a pre | -defined probability that the correct class is within | this set. In this study we tackle the problem of CP | calibration based on a validation set with noisy labels. We

关键词： Prediction set | Conformal prediction | Label noise | Conformal score

7. UniFed: A Universal Federation of a Mixture of Highly Heterogeneous Medical Image Classification Tasks NSTL国家科技图书文献中心

Atefe Hassani | Islem Rekik - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 32～42 - 共11页

摘要：A fundamental challenge in federated learning | lies in mixing heterogeneous datasets and | classification tasks while minimizing the high communication | cost caused by clients as well as the exchange of | weight updates with the server over a fixed number of

关键词： Multi-task federated learning | Heterogeneous data and model learning | Communication efficiency

8. Partially Supervised Unpaired Multi-modal Learning for Label-Efficient Medical Image Segmentation NSTL国家科技图书文献中心

Lei Zhu | Yanyu Xu ... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 85～94 - 共10页

摘要：Unpaired Multi-Modal Learning (UMML) which | leverages unpaired multi-modal data to boost model | performance on each individual modality has attracted a lot | of research interests in medical image analysis | . However, existing UMML methods require multi-modal

关键词： Unpaired multi-Modal learning | Partially supervised learning | Segmentation

9. Selective Classifier Based Search Space Shrinking for Radiographs Retrieval NSTL国家科技图书文献中心

Teo Manojlovic | Ivo Ipsic ... - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 63～73 - 共11页

摘要：We propose an image retrieval system which | reduces search space using the concept of selective | classification. The proposed system can partially annotate a | given medical radiology image, marking ambiguous parts | as undefined. For illustration, a model was built

关键词： Selective classification | Medical image retrieval | Search space shrinking

10. Probabilistic 3D Correspondence Prediction from Sparse Unsegmented Images NSTL国家科技图书文献中心

Krithika Iyer | Shireen Y. Elhabian - 《Machine Learning in Medical Imaging,Part II》 - International Workshop on Machine Learning in Medical Imaging | International Conference on Medical Image Computing and Computer-Assisted Intervention - 2025, - 117～127 - 共11页

摘要：The study of physiology demonstrates that the | form (shape) of anatomical structures dictates their | functions, and analyzing the form of anatomies plays a | crucial role in clinical research. Statistical shape | modeling (SSM) is a widely used tool for quantitative

摘要：Prognosis after intracranial hemorrhage (ICH | ) is influenced by a complex interplay between | imaging and tabular data. Rapid and reliable prognosis | are crucial for effective patient stratification and | informed treatment decision-making. In this study, we aim

关键词： Prognosis | Multi-task learning | Explainable AI

摘要：Magnetic Resonance Fingerprinting (MRF) is a | time-efficient approach to quantitative MRI for | multiparametric tissue mapping. The reconstruction of | quantitative maps requires tailored algorithms for removing | aliasing artefacts from the compressed sampled MRF

关键词： Magnetic resonance fingerprinting | Quantiative MRI | Compressed sensing | Deep image prior | Iterative algorithms

摘要：Medical imaging cohorts are often confounded | by factors such as acquisition devices, hospital | sites, patient backgrounds, and many more. As a result | , deep learning models tend to learn spurious | correlations instead of causally related features, limiting

关键词： Shortcut learning | Domain shift | Disentanglement

摘要：Tumor-infiltrating lymphocytes (TILs) and | their spatial interactions with tumors on whole-slide | images (WSIs) of histopathology sections can provide | valuable information about the immune response within the | tumor micro-environment that is closely associated

关键词： Graph contrastive learning | Survival analysis | Tumor-Infiltrating lymphocytes | Whole-Slide histopathological image

摘要：Accurate assessment of disease severity | from endoscopy videos in ulcerative colitis (UC) is | crucial for evaluating drug efficacy in clinical trials | . Severity is often measured by the Mayo Endoscopic | Subscore (MES) and Ulcerative Colitis Endoscopic Index of

关键词： Weakly-supervised learning | Ulcerative colitis | Endoscopy | Self-supervised learning | Transformers | UC disease severity assessment

摘要：Conformal Prediction (CP) quantifies network | uncertainty by building a small prediction set with a pre | -defined probability that the correct class is within | this set. In this study we tackle the problem of CP | calibration based on a validation set with noisy labels. We

关键词： Prediction set | Conformal prediction | Label noise | Conformal score

摘要：A fundamental challenge in federated learning | lies in mixing heterogeneous datasets and | classification tasks while minimizing the high communication | cost caused by clients as well as the exchange of | weight updates with the server over a fixed number of

关键词： Multi-task federated learning | Heterogeneous data and model learning | Communication efficiency

摘要：Unpaired Multi-Modal Learning (UMML) which | leverages unpaired multi-modal data to boost model | performance on each individual modality has attracted a lot | of research interests in medical image analysis | . However, existing UMML methods require multi-modal

关键词： Unpaired multi-Modal learning | Partially supervised learning | Segmentation

摘要：We propose an image retrieval system which | reduces search space using the concept of selective | classification. The proposed system can partially annotate a | given medical radiology image, marking ambiguous parts | as undefined. For illustration, a model was built

关键词： Selective classification | Medical image retrieval | Search space shrinking

摘要：The study of physiology demonstrates that the | form (shape) of anatomical structures dictates their | functions, and analyzing the form of anatomies plays a | crucial role in clinical research. Statistical shape | modeling (SSM) is a widely used tool for quantitative

关键词： Dense correspondence prediction | Aleatoric uncertainty | Sparse unsegmented images

4008-161-200 800-990-8900

国家科技图书文献中心