TY - JOUR
T1 - Multi-Task/Single-Task Joint Learning of Ultrasound BI-RADS Features
AU - Huang, Qinghua
AU - Ye, Liping
N1 - Publisher Copyright:
1525-8955 © 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
PY - 2022/2/1
Y1 - 2022/2/1
N2 - Breast cancer is one of the most common cancers among women in the world. The breast imaging reporting and data system (BI-RADS) features effectively improve the accuracy and sensitivity of breast tumors. Based on the description of signs in BI-RADS, a quantitative scoring scheme is proposed based on ultrasound (US) data. This scheme includes feature extraction of high-level semantic, that is, an intermediate step interpreting the subsequent diagnosis. However, the scheme requires doctors to score the features of breast data, which is labor-intensive. To reduce the burden of doctors, we design a multi-task learning (MTL) framework, which can directly output the scores of different BI-RADS features from the raw US images. The MTL framework consists of a shared network that learns global features and {K} soft attention networks for different BI-RADS features. Thus, it enables the network not only to learn the potential correlation among different BI-RADS features, but also learn the unique specificity of each feature, which can assist each other and jointly improve the scoring accuracy. In addition, we group different BI-RADS features according to the correlation among tasks and build a multi-task/single-task joint framework. Experimental results on the US breast tumor dataset collected from 1859 patients with 4458 US images show that the proposed BI-RADS feature scoring framework achieves an average scoring accuracy of 84.91% for 11 BI-RADS features on the test dataset, which is helpful for the subsequent diagnosis of breast tumors.
AB - Breast cancer is one of the most common cancers among women in the world. The breast imaging reporting and data system (BI-RADS) features effectively improve the accuracy and sensitivity of breast tumors. Based on the description of signs in BI-RADS, a quantitative scoring scheme is proposed based on ultrasound (US) data. This scheme includes feature extraction of high-level semantic, that is, an intermediate step interpreting the subsequent diagnosis. However, the scheme requires doctors to score the features of breast data, which is labor-intensive. To reduce the burden of doctors, we design a multi-task learning (MTL) framework, which can directly output the scores of different BI-RADS features from the raw US images. The MTL framework consists of a shared network that learns global features and {K} soft attention networks for different BI-RADS features. Thus, it enables the network not only to learn the potential correlation among different BI-RADS features, but also learn the unique specificity of each feature, which can assist each other and jointly improve the scoring accuracy. In addition, we group different BI-RADS features according to the correlation among tasks and build a multi-task/single-task joint framework. Experimental results on the US breast tumor dataset collected from 1859 patients with 4458 US images show that the proposed BI-RADS feature scoring framework achieves an average scoring accuracy of 84.91% for 11 BI-RADS features on the test dataset, which is helpful for the subsequent diagnosis of breast tumors.
KW - Breast cancer
KW - Breast tumors
KW - Feature extraction
KW - Malignant tumors
KW - Medical services
KW - Multitasking
KW - Tumors
UR - http://www.scopus.com/inward/record.url?scp=85121343787&partnerID=8YFLogxK
U2 - 10.1109/TUFFC.2021.3132933
DO - 10.1109/TUFFC.2021.3132933
M3 - 文章
C2 - 34871170
AN - SCOPUS:85121343787
SN - 0885-3010
VL - 69
SP - 691
EP - 701
JO - IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
JF - IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
IS - 2
ER -