Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study

doi:10.1093/neuonc/noac025

	Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study
	Yin, Shaohan 1,2; Luo, Xiao 1,2; Yang, Yadi 1,2; Shao, Ying 1,3; Ma, Lidi 1,2; Lin, Cuiping 1,2; Yang, Qiuxia 1,2; Wang, Deling 1,2; Luo, Yingwei 1,2; Mai, Zhijun 1,2; Fan, Weixiong 4; Zheng, Dechun 5; Li, Jianpeng 6; Cheng, Fengyan 4; Zhang, Yuhui 4; Zhong, Xinwei 4; Shen, Fangmin 5; Shao, Guohua 6; Wu, Jiahao 6; Sun, Ying 1,7; Luo, Huiyan 1,8; Li, Chaofeng 1,9; Gao, Yaozong 3; Shen, Dinggang3,10 ; Zhang, Rong 1,2; Xie, Chuanmiao 1,2
	2022-09-01
发表期刊	NEURO-ONCOLOGY
ISSN	1522-8517
EISSN	1523-5866
发表状态	已发表
DOI	10.1093/neuonc/noac025
摘要	Background Accurate detection is essential for brain metastasis (BM) management, but manual identification is laborious. This study developed, validated, and evaluated a BM detection (BMD) system. Methods Five hundred seventy-three consecutive patients (10 448 lesions) with newly diagnosed BMs and 377 patients without BMs were retrospectively enrolled to develop a multi-scale cascaded convolutional network using 3D-enhanced T1-weighted MR images. BMD was validated using a prospective validation set comprising an internal set (46 patients with 349 lesions; 44 patients without BMs) and three external sets (102 patients with 717 lesions; 108 patients without BMs). The lesion-based detection sensitivity and the number of false positives (FPs) per patient were analyzed. The detection sensitivity and reading time of three trainees and three experienced radiologists from three hospitals were evaluated using the validation set. Results The detection sensitivity and FPs were 95.8% and 0.39 in the test set, 96.0% and 0.27 in the internal validation set, and ranged from 88.9% to 95.5% and 0.29 to 0.66 in the external sets. The BMD system achieved higher detection sensitivity (93.2% [95% CI, 91.6-94.7%]) than all radiologists without BMD (ranging from 68.5% [95% CI, 65.7-71.3%] to 80.4% [95% CI, 78.0-82.8%], all P < .001). Radiologist detection sensitivity improved with BMD, reaching 92.7% to 95.0%. The mean reading time was reduced by 47% for trainees and 32% for experienced radiologists assisted by BMD relative to that without BMD. Conclusions BMD enables accurate BM detection. Reading with BMD improves radiologists' detection sensitivity and reduces their reading times.
关键词	automatic detection brain metastases cascaded convolutional network MRI
URL	查看原文
收录类别	SCI ; SCIE
语种	英语
WOS研究方向	Oncology ; Neurosciences & Neurology
WOS类目	Oncology ; Clinical Neurology
WOS记录号	WOS:000767431900001
出版者	OXFORD UNIV PRESS INC
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/162924
专题	生物医学工程学院_PI研究组_沈定刚组
通讯作者	Zhang, Rong; Xie, Chuanmiao
作者单位	1.Sun Yat Sen Univ, Collaborat Innovat Ctr Canc Med, State Key Lab Oncol South China, Canc Ctr, Guangzhou, Guangdong, Peoples R China 2.Sun Yat Sen Univ, Dept Radiol, Canc Ctr, Guangzhou, Guangdong, Peoples R China 3.Shanghai United Imaging Intelligence Co Ltd, R&D Dept, Shanghai, Peoples R China 4.Meizhou Peoples Hosp, Dept Magnet Resonance, Guangdong Prov Key Lab Precis Med & Clin Translat, Meizhou, Peoples R China 5.Fujian Med Univ, Fujian Canc Hosp, Dept Radiol, Canc Hosp, Fuzhou, Fujian, Peoples R China 6.Southern Med Univ, Affiliated Dongguan Hosp, Dept Radiol, Dongguan, Peoples R China 7.Sun Yat Sen Univ, Dept Radiat Oncol, Canc Ctr, Guangzhou, Peoples R China 8.Sun Yat Sen Univ, Dept Med Oncol, Canc Ctr, Guangzhou, Guangdong, Peoples R China 9.Sun Yat Sen Univ, Dept Artificial Intelligence Lab, Canc Ctr, Guangzhou, Peoples R China 10.ShanghaiTech Univ, Sch Biomed Engn, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Yin, Shaohan,Luo, Xiao,Yang, Yadi,et al. Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study[J]. NEURO-ONCOLOGY,2022.
APA	Yin, Shaohan.,Luo, Xiao.,Yang, Yadi.,Shao, Ying.,Ma, Lidi.,...&Xie, Chuanmiao.(2022).Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study.NEURO-ONCOLOGY.
MLA	Yin, Shaohan,et al."Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study".NEURO-ONCOLOGY (2022).