PMID- 33836449
OWN - NLM
STAT- MEDLINE
DCOM- 20210625
LR  - 20210625
IS  - 1879-0534 (Electronic)
IS  - 0010-4825 (Linking)
VI  - 133
DP  - 2021 Jun
TI  - Attention-embedded complementary-stream CNN for false positive reduction in 
      pulmonary nodule detection.
PG  - 104357
LID - S0010-4825(21)00151-7 [pii]
LID - 10.1016/j.compbiomed.2021.104357 [doi]
AB  - False positive reduction plays a key role in computer-aided detection systems for 
      pulmonary nodule detection in computed tomography (CT) scans. However, this 
      remains a challenge owing to the heterogeneity and similarity of anisotropic 
      pulmonary nodules. In this study, a novel attention-embedded complementary-stream 
      convolutional neural network (AECS-CNN) is proposed to obtain more representative 
      features of nodules for false positive reduction. The proposed network comprises 
      three function blocks: 1) attention-guided multi-scale feature extraction, 2) 
      complementary-stream block with an attention module for feature integration, and 
      3) classification block. The inputs of the network are multi-scale 3D CT volumes 
      due to variations in nodule sizes. Subsequently, a gradual multi-scale feature 
      extraction block with an attention module was applied to acquire more contextual 
      information regarding the nodules. A subsequent complementary-stream integration 
      block with an attention module was utilized to learn the significantly 
      complementary features. Finally, the candidates were classified using a fully 
      connected layer block. An exhaustive experiment on the LUNA16 challenge dataset 
      was conducted to verify the effectiveness and performance of the proposed 
      network. The AECS-CNN achieved a sensitivity of 0.92 with 4 false positives per 
      scan. The results indicate that the attention mechanism can improve the network 
      performance in false positive reduction, the proposed AECS-CNN can learn more 
      representative features, and the attention module can guide the network to learn 
      the discriminated feature channels and the crucial information embedded in the 
      data, thereby effectively enhancing the performance of the detection system.
CI  - Copyright (c) 2021 Elsevier Ltd. All rights reserved.
FAU - Sun, Lingma
AU  - Sun L
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu, Sichuan, 610054, China; Laboratory of 
      Imaging Detection and Intelligent Perception, University of Electronic Science 
      and Technology of China, Chengdu, 611731, China.
FAU - Wang, Zhuoran
AU  - Wang Z
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu, Sichuan, 610054, China; Laboratory of 
      Imaging Detection and Intelligent Perception, University of Electronic Science 
      and Technology of China, Chengdu, 611731, China.
FAU - Pu, Hong
AU  - Pu H
AD  - Sichuan Provincial People's Hospital, Chengdu, Sichuan, 610072, China; School of 
      Medicine, University of Electronic Science and Technology of China, Chengdu, 
      Sichuan, 610054, China.
FAU - Yuan, Guohui
AU  - Yuan G
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu, Sichuan, 610054, China; Laboratory of 
      Imaging Detection and Intelligent Perception, University of Electronic Science 
      and Technology of China, Chengdu, 611731, China.
FAU - Guo, Lu
AU  - Guo L
AD  - Sichuan Provincial People's Hospital, Chengdu, Sichuan, 610072, China; School of 
      Medicine, University of Electronic Science and Technology of China, Chengdu, 
      Sichuan, 610054, China.
FAU - Pu, Tian
AU  - Pu T
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu, Sichuan, 610054, China; Laboratory of 
      Imaging Detection and Intelligent Perception, University of Electronic Science 
      and Technology of China, Chengdu, 611731, China.
FAU - Peng, Zhenming
AU  - Peng Z
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu, Sichuan, 610054, China; Laboratory of 
      Imaging Detection and Intelligent Perception, University of Electronic Science 
      and Technology of China, Chengdu, 611731, China. Electronic address: 
      zmpeng@uestc.edu.cn.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20210330
PL  - United States
TA  - Comput Biol Med
JT  - Computers in biology and medicine
JID - 1250250
SB  - IM
MH  - Humans
MH  - *Lung Neoplasms/diagnostic imaging
MH  - Neural Networks, Computer
MH  - Radiographic Image Interpretation, Computer-Assisted
MH  - *Solitary Pulmonary Nodule/diagnostic imaging
MH  - Tomography, X-Ray Computed
OTO - NOTNLM
OT  - Attention mechanism
OT  - Convolutional neural network
OT  - False positive reduction
OT  - Multi-scale features
OT  - Pulmonary nodule detection
EDAT- 2021/04/10 06:00
MHDA- 2021/06/29 06:00
CRDT- 2021/04/09 20:18
PHST- 2021/01/19 00:00 [received]
PHST- 2021/03/22 00:00 [revised]
PHST- 2021/03/22 00:00 [accepted]
PHST- 2021/04/10 06:00 [pubmed]
PHST- 2021/06/29 06:00 [medline]
PHST- 2021/04/09 20:18 [entrez]
AID - S0010-4825(21)00151-7 [pii]
AID - 10.1016/j.compbiomed.2021.104357 [doi]
PST - ppublish
SO  - Comput Biol Med. 2021 Jun;133:104357. doi: 10.1016/j.compbiomed.2021.104357. Epub 
      2021 Mar 30.