DeepAI AI Chat
Log In Sign Up

EMT-NET: Efficient multitask network for computer-aided diagnosis of breast cancer

by   Jiaqiao Shi, et al.

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 We validate the model using a virtual mobile device, and the average inference time is 0.35 seconds per image.


page 2

page 4


Two-Dimensional ARMA Modeling for Breast Cancer Detection and Classification

We propose a new model-based computer-aided diagnosis (CAD) system for t...

ESTAN: Enhanced Small Tumor-Aware Network for Breast Ultrasound Image Segmentation

Breast tumor segmentation is a critical task in computer-aided diagnosis...

Stan: Small tumor-aware network for breast ultrasound image segmentation

Breast tumor segmentation provides accurate tumor boundary, and serves a...

Local image registration a comparison for bilateral registration mammography

Early tumor detection is key in reducing the number of breast cancer dea...

Regression Concept Vectors for Bidirectional Explanations in Histopathology

Explanations for deep neural network predictions in terms of domain-rela...

Why I'm not Answering

Safe deployment of deep learning systems in critical real world applicat...