Share Email Print
cover

Proceedings Paper

Weakly-supervised US breast tumor characterization and localization with a box convolution network
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In US breast tumor diagnosis, machine learning approaches for the malignancy classification and the mass localization have been attracting many researchers to improve the diagnostic sensitivity and specificity while reducing the image interpretation time. Recently, fully-supervised deep learning methods showed their promising results in those tasks. However, the full supervision for the localization requires human efforts and time to annotate ground truth regions. In this paper, we present a weakly-supervised deep network which can localize breast masses in US images from only diagnostic labels (i.e., malignant and benign). Specifically, we exploit a flexible convolution method, which learns the size and offset of the convolution kernel, in the classification network to detect more relevant regions of breast masses against their various size and shape. Experimental results show that the proposed network outperform conventional CNN models, such as VGG-16 and VGG-16 with dilated convolution. The proposed model achieved 89.03% in the binary classification accuracy. To evaluate the localization performance with weakly-supervised manners, we also compared class activation maps for each instance with manual masks of breast mass in terms of the Dice similarity coefficient and localization recall. The experimental results also demonstrate that the deep network with the adjustable convolution layers can clinically relevant features of breast mass and its surrounding area for both benign and malignant cases.

Paper Details

Date Published: 16 March 2020
PDF: 7 pages
Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided Diagnosis, 1131419 (16 March 2020); doi: 10.1117/12.2549203
Show Author Affiliations
Chanho Kim, Kyungpook National Univ. (Korea, Republic of)
Won Hwa Kim, Kyungpook National Univ. (Korea, Republic of)
Hye Jung Kim, Kyungpook National Univ. (Korea, Republic of)
Jaeil Kim, Kyungpook National Univ. (Korea, Republic of)


Published in SPIE Proceedings Vol. 11314:
Medical Imaging 2020: Computer-Aided Diagnosis
Horst K. Hahn; Maciej A. Mazurowski, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray