aiqbench analysis
This research presents a novel machine learning framework for breast cancer classification using DCE-MRI, addressing critical challenges like protocol heterogeneity and small lesion detection. By dynamically analyzing latent representations and leveraging large-scale pretraining, the method significantly outperforms existing radiology foundation models in robustness and accuracy. The work represents a substantive advance in applying AI to medical imaging, offering improved diagnostic reliability across diverse clinical environments.
Feature Space Guidance for Breast Cancer Classification in DCE-MRI
arXiv:2609.32555v1 Announce Type: cross Abstract: Dynamic contrast enhanced breast MRI (DCE-MRI) is a powerful clinical tool for breast cancer detection, providing high resolution anatomical detail together with rich temporal contrast information. However, high dimensional 4D inputs, small lesions, and heterogeneous acquisition protocols across clinical sites hinder robust automated classification of healthy, benign, and malignant cases. To address these challenges, we propose a framework that dynamically analyzes latent representations to adapt to protocol-specific characteristics. Spatial variability is mitigated by reducing confounding background uptake and compensating for misalignment caused by deformable soft tissue. Additionally, relationships in the latent space across phases are leveraged to select the most informative temporal features, improving robustness to protocol-specific temporal variability. Finally, task specific discriminative features are promoted through large scale supervised lesion segmentation pretraining, which substantially enhances downstream finetuning. Evaluated under leave-one-center-out validation on the ODELIA dataset and the held-out AMBL cohort, the proposed framework substantially outperforms finetuned radiology foundation models and prior methods, improving mean AUROC by nearly 8 points and balanced accuracy by 4 points over the strongest baseline. Additionally, our method achieved first place in the MICCAI ODELIA Breast MRI Challenge 2025, further demonstrating its effectiveness for robust breast cancer classification. We publicly release our codebase under https://github.com/MIC-DKFZ/CURIAtor.
Abstract:Dynamic contrast enhanced breast MRI (DCE-MRI) is a powerful clinical tool for breast cancer detection, providing high resolution anatomical detail together with rich temporal contrast information. However, high dimensional 4D inputs, small lesions, and heterogeneous acquisition protocols across clinical sites hinder robust automated classification of healthy, benign, and malignant cases. To address these challenges, we propose a framework that dynamically analyzes latent representations to adapt to protocol-specific characteristics. Spatial variability is mitigated by reducing confounding background uptake and compensating for misalignment caused by deformable soft tissue. Additionally, relationships in the latent space across phases are leveraged to select the most informative temporal features, improving robustness to protocol-specific temporal variability. Finally, task specific discriminative features are promoted through large scale supervised lesion segmentation pretraining, which substantially enhances downstream finetuning. Evaluated under leave-one-center-out validation on the ODELIA dataset and the held-out AMBL cohort, the proposed framework substantially outperforms finetuned radiology foundation models and prior methods, improving mean AUROC by nearly 8 points and balanced accuracy by 4 points over the strongest baseline. Additionally, our method achieved first place in the MICCAI ODELIA Breast MRI Challenge 2025, further demonstrating its effectiveness for robust breast cancer classification. We publicly release our codebase under this https URL.
11 pages, 2 figures, 2 tables. Code: this https URL
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.32555 [cs.CV]
(or arXiv:2609.32555v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.32555 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 312 words
Related coverage
AI in healthcare: applications and best practices
Databricks · Jul 24, 2026
ProtoCAM: Interpretable Few-Shot Mask-Guided Prototypical Learning for Breast Lesion Classification in Ultrasound Imaging
arXiv · Sep 16, 2026
Re-thinking Mammography Transfer Learning: The Dataset-Informed Transfer Learning (DITL) Framework for Breast Cancer Screening and Lesion Diagnosis
arXiv · Jul 29, 2026
XtrAIn: Training-Guided Occlusion for Feature Attribution
arXiv · Jun 10, 2026