期刊
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
卷 -, 期 -, 页码 91-95出版社
IEEE
DOI: 10.1109/ICIP42928.2021.9506563
关键词
computed tomography; two-stream framework; composite context fusion; inter-slice attention; lesion detection
类别
资金
- National Key Research and Development Program of China [2019YFC0118101]
- National Natural Science Foundation of China [81971616, 82072005, 62076218]
- Beijing Municipal Science and Technology Planning Project [Z201100005620002, Z201100005620008, Z211100003521009]
This paper presents a novel Composite Context Fusion Network (CCF-Net) to jointly model intra-slice and inter-slice features, achieving state-of-the-art detection performance on multi-disease CT lesion detection task by excavating and exchanging information between texture-aware and context-aware features through stage-by-stage feature fusion.
Detecting lesions from computed tomography (CT) scans relies on two aspects of the input: intra-slice texture information from the key slice and inter-slice structural context information from the adjacent slices. However, most existing methods ignore the correlation and complementarity between texture and structural information resulting in unexpected loss of performance. In this paper, a novel Composite Context Fusion Network (CCF-Net) is proposed to jointly model intra-slice and inter-slice features so as to prove the effectiveness of the two-steam framework. To extract both texture and structural information, two streams of 2D and 3D convolutional modules are employed in each stage. Moreover, a Composite Fusion architecture equipped with Inter-slice Correlative Fusion (ICF) modules is proposed to achieve stage-by-stage feature fusion in order to excavate and exchange information between texture-aware and context-aware features. Extensive experiments show that the proposed CCF-Net is able to achieve state-of-the-art detection performance on the multi-disease CT lesion detection task and significantly surpass the baseline methods.(1)
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据