{"slug": "cross-dataset-generalization-in-breast-mri-tumor-classification-via-class-wise", "title": "Cross-Dataset Generalization in Breast MRI Tumor Classification via Class-Wise Dataset Mixing", "summary": "Deep learning models for breast MRI tumor classification suffer near-chance external accuracy (0.5048–0.5265) when dataset origin is perfectly correlated with label, but a class-wise dataset mixing method using Duke Breast Cancer MRI and fastMRI training data improves accuracy to 0.8884 for EfficientNet-B3 and 0.8463 for WaveViT-Small on the independent MAMA-MIA cohort, according to a new arXiv preprint (2607.18678v1). The study demonstrates that controlling dataset-origin bias is critical for reliable cross-institution generalization.", "body_md": "arXiv:2607.18678v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/cross-dataset-generalization-in-breast-mri-tumor-classification-via-class-wise", "canonical_source": "https://arxiv.org/abs/2607.18678", "published_at": "2026-07-22 04:00:00+00:00", "updated_at": "2026-07-22 04:14:26.812488+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision"], "entities": ["EfficientNet-B3", "WaveViT-Small", "Duke Breast Cancer MRI", "fastMRI", "MAMA-MIA", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/cross-dataset-generalization-in-breast-mri-tumor-classification-via-class-wise", "markdown": "https://wpnews.pro/news/cross-dataset-generalization-in-breast-mri-tumor-classification-via-class-wise.md", "text": "https://wpnews.pro/news/cross-dataset-generalization-in-breast-mri-tumor-classification-via-class-wise.txt", "jsonld": "https://wpnews.pro/news/cross-dataset-generalization-in-breast-mri-tumor-classification-via-class-wise.jsonld"}}