A Mask-Guided, Explainable Deep-Learning Framework with Verifiable Attention for Benign–Malignant Classification of Breast Ultrasound Images
Preprint
- 22 October 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Background/Objectives: Breast cancer is one of the most common cancer types in women, and reading a breast ultrasound is still very much dependent on the individual radiologist, creating inter-observer variability. Deep-learning classifiers can achieve accuracy comparable to that of experts, but there are two challenges for their use in routine practice: they rarely explain their predictions, and a model can reach the right label for the wrong reason, by attending to tissue unrelated to the lesion. This study addresses both of these. Methods: On the BUS-BRA dataset, we used the lesion segmentation mask as an additional input channel to the network, along with the RGB image, so two backbones (EfficientNet-B3 and EfficientNet-B4) were directed towards the lesion from the first layer, while only the initial convolution layer was modified, keeping the ImageNet-pretrained weights unchanged. To ensure a fair evaluation, the data were split at the patient level rather than the image level, preventing leakage. Training was performed with focal loss, heavy augmentation and test-time augmentation, with the decision threshold set on the validation set. Grad-CAM, SHAP, and Occlusion Sensitivity explained each prediction, and were scored for fidelity, stability, and overlap with the true lesion. Results: During the controlled ablation, the mask channel improved accuracy by more than eight points over an region-of-interest (ROI)-only baseline. The average of the two backbone models yielded 86.7% accuracy and 0.911 AUC on the held-out test set, and when applied to the independent BUSI dataset, without any modification, with the threshold frozen, it achieved 90.4% accuracy and 0.972 AUC, with Grad-CAM maps landing on the annotated lesions. Conclusions: The accuracy of mask guidance using an imbalance-aware design is competitive, and the accuracy can be transferred to an external dataset, providing a credible basis for decision support that can be verified by the clinician with the image.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- A review of explainable AI techniques and their evaluation in mammography for breast cancer screeningClinical Imaging, 2025
- Improving breast cancer classification in fine-grain ultrasound images through feature discrimination and a transfer learning approachBiomedical Signal Processing and Control, 2025
- Review of AI & XAI-based breast cancer diagnosis methods using various imaging modalitiesMultimedia Tools and Applications, 2024
- BUS‐BRA: A breast ultrasound dataset for assessing computer‐aided diagnosis systemsMedical Physics, 2023
- An efficient deep learning scheme to detect breast cancer using mammogram and ultrasound breast imagesBiomedical Signal Processing and Control, 2023
- XML‐LightGBMDroid: A self‐driven interactive mobile application utilizing explainable machine learning for breast cancer diagnosisEngineering Reports, 2023
- Computer‐aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networksComputer Methods and Programs in Biomedicine, 2020
- Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversionMedical Physics, 2018
- Visualizing and Understanding Convolutional Networks2014
- Combined Screening With Ultrasound and Mammography vs Mammography Alone in Women at Elevated Risk of Breast CancerJAMA, 2008