EUVIMEDEUVIMED entdecken
Crossref

Segmentation-Guided Lesion-Centric Deep Learning Framework for Interpretable Breast Ultrasound Classification

Ishita Rana, Jaimeel Shah, Hardik Variya

International Journal of Drug Delivery Technology · 15.04.2026 · 16 (12s)

DOI: 10.25258/ijddt.16.12s.35 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 15.04.2026. Verfasst von Ishita Rana und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast ultrasound imaging is commonly employed for the assessment of breast lesions, especially in women with dense breast tissue and in circumstances where mammography sensitivity is constrained. Nonetheless, interpreting ultrasound images continues to be difficult because of speckle noise, uneven backgrounds, and differences between operators. This study proposes a segmentation-guided, lesion-centric deep learning framework for the automated classification of breast ultrasound images. The framework combines U-Net-based lesion segmentation, region-of-interest (ROI) extraction, EfficientNetB0-based classification, and Gradient-weighted Class Activation Mapping (Grad-CAM) to make the model easier to understand. We tested the method on the Breast Ultrasound Images (BUSI) dataset, which had normal, benign, and malignant images. The training dataset went through preprocessing that included bilateral filtering, uniform resizing, and class-balanced augmentation. Before classification, segmentation outputs were used to find the areas of lesions. This reduced background noise and made it easier to learn features. The EfficientNetB0 classifier got an overall classification accuracy of 79.6% on the independent test set, with performance that was balanced across classes. Grad-CAM visualizations showed that the network's predictions were mostly based on lesion-relevant areas and not on artifacts in the surrounding tissue. The results show that segmentation-guided lesion-centric pipelines make it easier to understand and more reliable to diagnose breast cancer using ultrasound. They also lay the groundwork for computer-aided diagnostic systems that can be used in real life.

Zitieren

APA

Rana, I., Shah, J., & Variya, H. (2026). Segmentation-Guided Lesion-Centric Deep Learning Framework for Interpretable Breast Ultrasound Classification. International Journal of Drug Delivery Technology, 16(12s). https://doi.org/10.25258/ijddt.16.12s.35

Vancouver

Rana I, Shah J, Variya H. Segmentation-Guided Lesion-Centric Deep Learning Framework for Interpretable Breast Ultrasound Classification. International Journal of Drug Delivery Technology. 2026;16(12s). doi:10.25258/ijddt.16.12s.35

BibTeX
@article{Rana2026,
  author = {Rana, Ishita and Shah, Jaimeel and Variya, Hardik},
  title = {Segmentation-Guided Lesion-Centric Deep Learning Framework for Interpretable Breast Ultrasound Classification},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {12s},
  doi = {10.25258/ijddt.16.12s.35}
}
Kostenlos starten →