Oct 2026· iScience· Vol 29· 0 citations· 39 references
Medicine
Abstract
Summary Accurate discrimination of benign and malignant breast lesions is essential for early diagnosis, yet remains challenging due to lesion heterogeneity and interobserver variability in ultrasound assessment. We developed a deep learning (DL) framework integrating dual inverted bottleneck blocks (Dual-IB), adaptive hierarchical feature fusion, and knowledge distillation (KD) for breast ultrasound lesion classification. The model was trained and evaluated on public datasets and validated on an independent external cohort to assess its generalizability. Results demonstrated superior performance compared with baseline methods and resident radiologists, while maintaining robust performance across diverse datasets and imaging conditions. On the external validation dataset, the model achieved the best performance, with an accuracy (Acc) of 92.64% and an F1-score of 92.37%. Furthermore, class activation mapping (CAM) visualizations revealed focused and anatomically plausible attention patterns within lesion regions, aiding interpretation and suggesting its potential to assist in breast ultrasound lesion classification.
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, further demonstrating its effectiveness for robust breast cancer classification.
Benjamin Hamm, Y. Kirchhoff, M. Rokuss et al.· International Conference on...· 1 citation
The high mortality rate from breast cancer drives the need for objective and precise diagnostic methods to increase the chance of patient recovery. Ultrasound (US) is a commonly used screening modality due to its accessibility, but it is susceptible to speckle noise and high visual variability, which can complicate les...
Salsabila Rahayu Putri, Gena Darma, Muhammad Rakha et al.· 2026 International Conferenc...· 0 citations
Breast cancer diagnosis from histopathology images is accurate but labor-intensive and subject to interobserver variability. Deep learning has shown strong performance on digital pathology benchmarks; however, limited transparency, magnification variability, and patient-level data leakage can reduce clinical trust and...
Sittichat Mekwan, Buntueng Yana, Ratsada Praphasawat et al.· ECTI Transactions on Compute...· 0 citations
Breast cancer is one of the leading causes of cancers among patients around the world, where the early diagnosis of the disease by diagnostic ultrasound imaging technique becomes vital in achieving low mortality rates. Nevertheless, class imbalance continues to remain a problem in computer-aided automated diagnosis of...
M. N. Babitha, Raviram V, S. Abirami et al.· Journal of Artificial Intell...· 0 citations
An enhanced deep learning framework for lung nodule segmentation and detection is proposed that combines an improved preprocessing pipeline, an attention-guided U-Net architecture, and a lightweight convolutional neural network (CNN) for classification.
B. Rajani, D. Reddy· International Conference on...· 0 citations
Breast ultrasound is a crucial imaging modality for early breast cancer screening and benign-malignant lesion differentiation. Accurate lesion segmentation serves as an essential prerequisite for clinical quantitative evaluation and intelligent diagnosis and treatment. The residual attention fused U-Net is constructed...
Bo-Yang Kang, Si-Jia Wang, Xiao-Fen Gao· The International Conference...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.