EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Breast Ultrasound Classification Under Cross-Dataset Shift: A Multi-Seed Benchmark of Convolutional Networks, a Vision Transformer, and a Self-Supervised Foundation Model

Ervin Ramollari, Narasimha Rao Vajjhala, Rajesh Kumar, Komal Ramchandani, Ranjeeta Mahraj, Khalid Hussain

Algorithms · 18.11.2026 · 19 (11) · 1011

DOI: 10.3390/a19111011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 18.11.2026. Verfasst von Ervin Ramollari und 5 weiteren Autor:innen. Die Arbeit nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep-learning classifiers for breast ultrasound are usually evaluated on images from their training institution, and self-supervised foundation models are increasingly proposed as more transferable than supervised networks; whether ranking ability, decision thresholds, and probability calibration survive a change in institution has rarely been tested under leakage-controlled conditions. We fine-tuned ResNet-50, EfficientNet-B0, a supervised Vision Transformer (ViT-B/16), and self-supervised DINOv2 under one shared protocol on the official BUS-BRA five-fold partitions, each fold with three seeds, and on three case-grouped hold-out splits, and evaluated every trained model unchanged on the Breast Ultrasound Images (BUSI) dataset. The supervised models largely retained their discrimination externally. ResNet-50 had the highest mean area under the receiver operating characteristic curve under the official folds, but no criterion separated it from ViT-B/16, whose small hold-out advantage at the decision threshold did not recur. In every official-fold run, both models labeled a larger share of BUSI than of BUS-BRA images malignant, although prevalence was the same—a shift that temperature scaling cannot correct. Top-label calibration error also understated malignant-class miscalibration. Full-frame DINOv2 did not fit its training data in any run, although exploratory lesion cropping produced good discrimination. External evaluations should report operating-point transport and class-wise calibration alongside discrimination.

Zitieren

APA

Ramollari, E., Vajjhala, N. R., Kumar, R., Ramchandani, K., Mahraj, R., & Hussain, K. (2026). Breast Ultrasound Classification Under Cross-Dataset Shift: A Multi-Seed Benchmark of Convolutional Networks, a Vision Transformer, and a Self-Supervised Foundation Model. Algorithms, 19(11), 1011. https://doi.org/10.3390/a19111011

Vancouver

Ramollari E, Vajjhala NR, Kumar R, Ramchandani K, Mahraj R, Hussain K. Breast Ultrasound Classification Under Cross-Dataset Shift: A Multi-Seed Benchmark of Convolutional Networks, a Vision Transformer, and a Self-Supervised Foundation Model. Algorithms. 2026;19(11):1011. doi:10.3390/a19111011

BibTeX
@article{Ramollari2026,
  author = {Ramollari, Ervin and Vajjhala, Narasimha Rao and Kumar, Rajesh and Ramchandani, Komal and Mahraj, Ranjeeta and Hussain, Khalid},
  title = {Breast Ultrasound Classification Under Cross-Dataset Shift: A Multi-Seed Benchmark of Convolutional Networks, a Vision Transformer, and a Self-Supervised Foundation Model},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {11},
  pages = {1011},
  doi = {10.3390/a19111011}
}
Kostenlos starten →