Incorporating Tumor Edge Information for Fine-Grained BI-RADS Classification of Breast Ultrasound Images
Open Access
- 12 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 38732-38744
Abstract
Breast Ultrasound (BUS) imaging is an essential tool for the early detection of breast cancer. The Breast Imaging Reporting and Data System (BI-RADS) in BUS images helps standardize the interpretation and reporting process by categorizing breast tumors into multiple classes, which enables radiologists to make more accurate diagnoses and treatment plans. However, most existing classification methods distinguish only between benign and malignant categories. In addition, features extracted by classic convolutional neural networks tend to be insufficient when subdividing BUS images into fine-grained BI-RADS classes, as they typically do not consider prior knowledge in medical applications, such as foreground shape. To address the above problems, we propose a novel fine-grained BI-RADS classification approach that integrates tumor edges to provide more efficient discriminative features. Firstly, weakly supervised pseudo-label generation: we detect coarse tumor edge regions utilizing a pre-trained PiDiNet and two novel loss functions based on prior knowledge from our dataset. The detected tumor edges are subsequently used as pseudo-labels for the next step. Secondly, co-training a tumor edge detection network and a BI-RADS classification network: edge images generated by the edge detection network are used as weight masks to highlight tumor edge regions as discriminative parts for better classification results, especially for categories with high similarities. The proposed method is evaluated on a BUS image dataset of 1061 images with BI-RADS categories. Experimental results indicate that the proposed method significantly improves over the baseline model by 4.73% in terms of top-1 accuracy.Keywords
Funding Information
- National Natural Science Foundation of China (82071930)
This publication has 57 references indexed in Scilit:
- Weakly Supervised Deep Learning Approach to Breast MRI AssessmentAcademic Radiology, 2022
- FMRNet: A fused network of multiple tumoral regions for breast tumor classification with ultrasound imagesMedical Physics, 2021
- Breast cancer early detection: A phased approach to implementationCancer, 2020
- Breast Cancer Detection Techniques: Issues and ChallengesJournal of The Institution of Engineers (India): Series B, 2019
- Learning to Navigate for Fine-Grained Classification2018
- A computer-aided diagnosis system for breast ultrasound based on weighted BI-RADS classesComputer Methods and Programs in Biomedicine, 2018
- Part-Based R-CNNs for Fine-Grained Category Detection2014
- Computer-aided diagnosis of breast masses using quantified BI-RADS findingsComputer Methods and Programs in Biomedicine, 2013
- Indoor Segmentation and Support Inference from RGBD Images2012
- Computer-Aided Diagnosis of Digital Mammography and Ultrasound Images of Breast Mass Lesions1998