Cross-Dataset Generalization in Breast MRI Tumor Classification via Class-Wise Dataset Mixing

• URL: http://arxiv.org/abs/2607.18678v1
• Date: Tue, 21 Jul 2026 03:51:53 GMT
• Title: Cross-Dataset Generalization in Breast MRI Tumor Classification via Class-Wise Dataset Mixing
• Abstract summary: Deep learning models often perform well on internal splits but can fail across institutions because of domain shift and dataset-origin bias.<n>We study this failure mode for binary breast MRI tumor classification.<n>In a deliberately confounded setup, where label is perfectly correlated with dataset origin, external accuracy is near chance.<n>On MAMA-MIA, dataset mixing improves accuracy/F1 to 0.8463/0.8625 for WaveViT-Small and 0.8884/0.8994 for EfficientNet-B3.
• Score: 1.160208922584163
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Breast MRI is highly sensitive for detecting breast tumors, but exams contain many slices and require substantial reading time. Deep learning models often perform well on internal splits but can fail across institutions because of domain shift and dataset-origin bias. We study this failure mode for binary breast MRI tumor classification. EfficientNet-B3 and WaveViT-Small are trained using Duke Breast Cancer MRI and fastMRI, and evaluated only on the independent multi-center MAMA-MIA cohort. In a deliberately confounded setup, where label is perfectly correlated with dataset origin, external accuracy is near chance (0.5048--0.5265), despite very high recall. We then construct a mixed training set in which each class contains samples from both Duke and fastMRI, while preserving patient-level splitting, augmentation, and leakage controls. On MAMA-MIA, dataset mixing improves accuracy/F1 to 0.8463/0.8625 for WaveViT-Small and 0.8884/0.8994 for EfficientNet-B3. These results show that controlling dataset-origin bias is important for reliable breast MRI classification.

Related papers

• Dataset-Origin Signatures and Shortcut Learning in Screening Mammography AI: A Cross-Dataset Case Study [0.0]
  We examined whether supplementing such data with biopsy-confirmed cases from abnormal-enriched external datasets improves performance.<n>We evaluated an EfficientNet-B5 encoder with Mammo-CLIP weights as a frozen linear probe under consistent preprocessing.
  arXiv  Detail & Related papers  (2026-07-16T19:41:48Z)
• CoMNeT: A MedNeXt-CorrDiff Framework for Volumetric Brain Tumor Segmentation [1.2048008992808203]
  We show that combining a modern 3D convolutional segmentation model with corrective diffusion-based refinement and ensembling improves volumetric glioma segmentation.<n>We propose CoMNeT, a MedNeXt-CorrDiff framework that uses four MRI modalities as input and predicts ET, TC, and whole tumor.<n>Using five-fold cross-validation, CoMNeT achieved the highest Dice score for most tumor regions, with ET, TC, WT, and average Dice scores of 0.7543 +/- 0.0261, 0.6806 +/- 0.0166, 0.9049 +/- 0.0128, and 0.7798 +/- 0.0184
  arXiv  Detail & Related papers  (2026-06-13T13:51:10Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [49.1574468325115]
  This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset.<n>The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer)
  arXiv  Detail & Related papers  (2025-05-23T14:06:42Z)
• SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms [60.35639972035727]
  The lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. Dice scores reached up to 0.838 $pm$ 0.066 and 0.716 $pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $pm$ 0.15.
  arXiv  Detail & Related papers  (2024-11-14T17:06:00Z)
• Brain Tumor Classification on MRI in Light of Molecular Markers [56.99710477905796]
  Co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas.<n>This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection.
  arXiv  Detail & Related papers  (2024-09-29T07:04:26Z)
• Domain Transfer Through Image-to-Image Translation for Uncertainty-Aware Prostate Cancer Classification [42.75911994044675]
  We present a novel approach for unpaired image-to-image translation of prostate MRIs and an uncertainty-aware training approach for classifying clinically significant PCa. Our approach involves a novel pipeline for translating unpaired 3.0T multi-parametric prostate MRIs to 1.5T, thereby augmenting the available training data. Our experiments demonstrate that the proposed method significantly improves the Area Under ROC Curve (AUC) by over 20% compared to the previous work.
  arXiv  Detail & Related papers  (2023-07-02T05:26:54Z)
• Motion-related Artefact Classification Using Patch-based Ensemble and Transfer Learning in Cardiac MRI [5.186000805926489]
  We propose an automatic cardiac MRI quality estimation framework using ensemble and transfer learning. Multiple pre-trained models were initialised and fine-tuned on 2-dimensional image patches sampled from the training data. It achieved a classification accuracy of 78.8% and 70.0% on the training set and validation set, respectively.
  arXiv  Detail & Related papers  (2022-10-14T11:31:40Z)
• Weakly-supervised Biomechanically-constrained CT/MRI Registration of the Spine [72.85011943179894]
  We propose a weakly-supervised deep learning framework that preserves the rigidity and the volume of each vertebra while maximizing the accuracy of the registration. We specifically design these losses to depend only on the CT label maps since automatic vertebra segmentation in CT gives more accurate results contrary to MRI. Our results show that adding the anatomy-aware losses increases the plausibility of the inferred transformation while keeping the accuracy untouched.
  arXiv  Detail & Related papers  (2022-05-16T10:59:55Z)
• Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity [77.78624443410216]
  We propose improved FDAM algorithms for detecting heterogeneous chest data. A result of this paper is that the communication of the proposed algorithm is strongly independent of the number of machines and also independent of the accuracy level. Experiments have demonstrated the effectiveness of our FDAM algorithm on benchmark datasets and on medical chest Xray images from different organizations.
  arXiv  Detail & Related papers  (2021-02-09T04:05:19Z)
• How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning? [2.330464988780586]
  Planning the optimal time of intervention for pulmonary valve replacement surgery in patients with the congenital heart disease Tetralogy of Fallot (TOF) is mainly based on ventricular volume and function according to current guidelines. In several grand challenges in the last years, U-Net architectures have shown impressive results on the provided data. However, in clinical practice, data sets are more diverse considering individual pathologies and image properties derived from different scanner properties.
  arXiv  Detail & Related papers  (2020-02-10T08:50:51Z)
• Handling Missing MRI Input Data in Deep Learning Segmentation of Brain Metastases: A Multi-Center Study [1.4463443378902883]
  A deep learning based segmentation model for automatic segmentation of brain metastases, named DropOut, was trained on multi-sequence MRI. The segmentation results were compared with the performance of a state-of-the-art DeepLabV3 model. The DropOut model showed a significantly higher score compared to the DeepLabV3 model.
  arXiv  Detail & Related papers  (2019-12-27T02:49:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.