Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification

doi:10.1016/j.patcog.2016.05.029

	Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification
	Shen, Wei1,2 ; Zhou, Mu 3; Yang, Feng 4; Yu, Dongdong1,2 ; Dong, Di1,2 ; Yang, Caiyun1,2 ; Zang, Yali1,2 ; Tian, Jie 1,2; Feng Yang, Jie Tian
发表期刊	PATTERN RECOGNITION
	2017
卷号	61 期号:61 页码:663-673
文章类型	Article
摘要	We investigate the problem of lung nodule malignancy suspiciousness (the likelihood of nodule malignancy) classification using thoracic Computed Tomography (CT) images. Unlike traditional studies primarily relying on cautious nodule segmentation and time-consuming feature extraction, we tackle a more challenging task on directly modeling raw nodule patches and building an end-to-end machine-learning architecture for classifying lung nodule malignancy suspiciousness. We present a Multi-crop Convolutional Neural Network (MC-CNN) to automatically extract nodule salient information by employing a novel multi-crop pooling strategy which crops different regions from convolutional feature maps and then applies max-pooling different times. Extensive experimental results show that the proposed method not only achieves state-of-the-art nodule suspiciousness classification performance, but also effectively characterizes nodule semantic attributes (subtlety and margin) and nodule diameter which are potentially helpful in modeling nodule malignancy; We investigate the problem of lung nodule malignancy suspiciousness (the likelihood of nodule malignancy) classification using thoracic Computed Tomography (CT) images. Unlike traditional studies primarily relying on cautious nodule segmentation and time-consuming feature extraction, we tackle a more challenging task on directly modeling raw nodule patches and building an end-to-end machine learning architecture for classifying lung nodule malignancy suspiciousness. We present a Multi-crop Convolutional Neural Network (MC-CNN) to automatically extract nodule salient information by employing a novel multi-crop pooling strategy which crops different regions from convolutional feature maps and then applies max-pooling different times. Extensive experimental results show that the proposed method not only achieves state-of-the-art nodule suspiciousness classification performance, but also effectively characterizes nodule semantic attributes (subtlety and margin) and nodule diameter which are potentially helpful in modeling nodule malignancy. (C) 2016 Elsevier Ltd. All rights reserved.
关键词	Lung Nodule Malignancy Suspiciousness Convolutional Neural Network Multi-crop Pooling
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.patcog.2016.05.029
关键词[WOS]	IMAGE DATABASE CONSORTIUM ; COMPUTER-AIDED DIAGNOSIS ; PULMONARY NODULES ; CT IMAGES ; SEGMENTATION ; CANCER ; REPRESENTATION ; INFORMATION ; ENSEMBLE ; SCANS
收录类别	SCI
语种	英语
项目资助者	Chinese Academy of Sciences Key Deployment Program(KGZD-EW-T03) ; National Natural Science Foundation of China(81227901 ; Beijing Natural Science Foundation(4132080) ; Fundamental Research Funds for the Central Universities(2013JBZ014 ; Scientific Research and Equipment Development Project of Chinese Academy of Sciences(YZ201457) ; NVIDIA Corporation ; 81527805 ; 2016JBM018) ; 61231004 ; 81370035 ; 81230030 ; 61301002 ; 61302025 ; 81301346 ; 81501616)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000385899400051
引用统计	被引频次：390[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12244
专题	中国科学院分子影像重点实验室
通讯作者	Feng Yang, Jie Tian
作者单位	1.Chinese Acad Sci, Inst Automat, Key Lab Mol Imaging, Beijing 100190, Peoples R China 2.Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China 3.Stanford Univ, Stanford Ctr Biomed Informat Res, Stanford, CA 94305 USA 4.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China
第一作者单位	中国科学院自动化研究所; 中国科学院分子影像重点实验室
推荐引用方式 GB/T 7714	Shen, Wei,Zhou, Mu,Yang, Feng,et al. Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification[J]. PATTERN RECOGNITION,2017,61(61):663-673.
APA	Shen, Wei.,Zhou, Mu.,Yang, Feng.,Yu, Dongdong.,Dong, Di.,...&Feng Yang, Jie Tian.(2017).Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification.PATTERN RECOGNITION,61(61),663-673.
MLA	Shen, Wei,et al."Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification".PATTERN RECOGNITION 61.61(2017):663-673.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2017.沈伟PR.pdf（1358KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载