Title | Compare and contrast: Detecting mammographic soft-tissue lesions with C-2-Net |
Authors | Li, Yuhan Zhou, Changsheng Zhang, Fandong Zhang, Qianyi Wang, Siwen Zhou, Juan Sheng, Fugeng Wang, Xiaoqi Liu, Wanhua Wang, Yizhou Yu, Yizhou Lu, Guangming |
Affiliation | Deepwise Healthcare, AI Lab, Beijing 100080, Peoples R China Peking Univ, Adv Inst Informat Technol, Dept Comp Sci & Technol, Ctr Frontiers Comp Studies, Beijing, Peoples R China Nanjing Univ, Coll Med, Nanjing Jinling Hosp Clin Sch, Med Imaging Ctr, Nanjing 210002, Peoples R China Chinese Peoples Liberat Army Gen Hosp, Med Ctr 5, Dept Radiol, Beijing 100071, Peoples R China Gansu Prov Canc Hosp, Dept Radiol, Lanzhou 730050, Peoples R China Southeast Univ, Zhongda Hosp, Dept Radiol, Nanjing 210009, Peoples R China Univ Hong Kong, Dept Comp Sci, Pokfulam, Hong Kong, Peoples R China |
Keywords | COMPUTER-AIDED DETECTION FALSE-POSITIVE REDUCTION MASS DETECTION BREAST MASSES AUTOMATED DETECTION INFORMATION FUSION ENHANCEMENT MODEL CLASSIFICATION FRAMEWORK |
Issue Date | Jul-2021 |
Publisher | MEDICAL IMAGE ANALYSIS |
Abstract | Detecting breast soft-tissue lesions including masses, structural distortions and asymmetries is of great importance due to the high risk leading to breast cancer. Most existing deep learning based approaches detect lesions with only unilateral images. However, multi-view mammogram images provide highly related and complementary information which helps to make the clinical analysis more comprehensive and reliable. In this paper, we propose a multi-view network for breast soft-tissue lesion detection called C-2-Net (Compare and Contrast, C-2) that fuses information across different views. The proposed model contains the following three modules. The spatial context enhancing (SCE) module compares ipsilateral views and extracts complementary features to model lesion inherent 3D structure. The multi-scale kernel pooling (MKP) module contrasts contralateral views with added misalignment tolerance. Finally, the logic guided fusion (LGF) module fuses multi-view features by enhancing logic modeling capacity. Experimental results on both the public DDSM dataset and the in-house multi-center dataset demonstrate that the proposed method has achieved state-of-the-art performance. (C) 2021 Elsevier B.V. All rights reserved. |
URI | http://hdl.handle.net/20.500.11897/618045 |
ISSN | 1361-8415 |
DOI | 10.1016/j.media.2021.101999 |
Indexed | SCI(E) |
Appears in Collections: | 信息科学技术学院 |