EMT-NET: Efficient multitask network for computer-aided diagnosis of breast cancer
This work addresses the need for efficient computer-aided diagnosis tools for breast cancer detection, enabling broader real-world deployment, but it is incremental as it builds on existing multitask learning approaches.
The paper tackled the problem of computationally intensive deep learning for breast cancer diagnosis by proposing an efficient multitask network that simultaneously classifies and segments tumors, achieving 88.6% accuracy, 94.1% sensitivity, and 85.3% specificity with an inference time of 0.35 seconds per image.
Deep learning-based computer-aided diagnosis has achieved unprecedented performance in breast cancer detection. However, most approaches are computationally intensive, which impedes their broader dissemination in real-world applications. In this work, we propose an efficient and light-weighted multitask learning architecture to classify and segment breast tumors simultaneously. We incorporate a segmentation task into a tumor classification network, which makes the backbone network learn representations focused on tumor regions. Moreover, we propose a new numerically stable loss function that easily controls the balance between the sensitivity and specificity of cancer detection. The proposed approach is evaluated using a breast ultrasound dataset with 1,511 images. The accuracy, sensitivity, and specificity of tumor classification is 88.6%, 94.1%, and 85.3%, respectively. We validate the model using a virtual mobile device, and the average inference time is 0.35 seconds per image.