利用深度学习自动分割脑转移瘤:一项多中心、随机交叉、多阅读器评估研究。

IF 16.4 1区 医学 Q1 CLINICAL NEUROLOGY
Xiao Luo, Yadi Yang, Shaohan Yin, Hui Li, Ying Shao, Dechun Zheng, Xinchun Li, Jianpeng Li, Weixiong Fan, Jing Li, Xiaohua Ban, Shanshan Lian, Yun Zhang, Qiuxia Yang, Weijing Zhang, Cheng Zhang, Lidi Ma, Yingwei Luo, Fan Zhou, Shiyuan Wang, Cuiping Lin, Jiao Li, Ma Luo, Jianxun He, Guixiao Xu, Yaozong Gao, Dinggang Shen, Ying Sun, Yonggao Mou, Rong Zhang, Chuanmiao Xie
{"title":"利用深度学习自动分割脑转移瘤:一项多中心、随机交叉、多阅读器评估研究。","authors":"Xiao Luo, Yadi Yang, Shaohan Yin, Hui Li, Ying Shao, Dechun Zheng, Xinchun Li, Jianpeng Li, Weixiong Fan, Jing Li, Xiaohua Ban, Shanshan Lian, Yun Zhang, Qiuxia Yang, Weijing Zhang, Cheng Zhang, Lidi Ma, Yingwei Luo, Fan Zhou, Shiyuan Wang, Cuiping Lin, Jiao Li, Ma Luo, Jianxun He, Guixiao Xu, Yaozong Gao, Dinggang Shen, Ying Sun, Yonggao Mou, Rong Zhang, Chuanmiao Xie","doi":"10.1093/neuonc/noae113","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence has been proposed for brain metastasis (BM) segmentation but it has not been fully clinically validated. The aim of this study was to develop and evaluate a system for BM segmentation.</p><p><strong>Methods: </strong>A deep-learning-based BM segmentation system (BMSS) was developed using contrast-enhanced MR images from 488 patients with 10338 brain metastases. A randomized crossover, multi-reader study was then conducted to evaluate the performance of the BMSS for BM segmentation using data prospectively collected from 50 patients with 203 metastases at 5 centers. Five radiology residents and 5 attending radiologists were randomly assigned to contour the same prospective set in assisted and unassisted modes. Aided and unaided Dice similarity coefficients (DSCs) and contouring times per lesion were compared.</p><p><strong>Results: </strong>The BMSS alone yielded a median DSC of 0.91 (95% confidence interval, 0.90-0.92) in the multi-center set and showed comparable performance between the internal and external sets (P = .67). With BMSS assistance, the readers increased the median DSC from 0.87 (0.87-0.88) to 0.92 (0.92-0.92) (P < .001) with a median time saving of 42% (40-45%) per lesion. Resident readers showed a greater improvement than attending readers in contouring accuracy (improved median DSC, 0.05 [0.05-0.05] vs 0.03 [0.03-0.03]; P < .001), but a similar time reduction (reduced median time, 44% [40-47%] vs 40% [37-44%]; P = .92) with BMSS assistance.</p><p><strong>Conclusions: </strong>The BMSS can be optimally applied to improve the efficiency of brain metastasis delineation in clinical practice.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":"2140-2151"},"PeriodicalIF":16.4000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automated segmentation of brain metastases with deep learning: A multi-center, randomized crossover, multi-reader evaluation study.\",\"authors\":\"Xiao Luo, Yadi Yang, Shaohan Yin, Hui Li, Ying Shao, Dechun Zheng, Xinchun Li, Jianpeng Li, Weixiong Fan, Jing Li, Xiaohua Ban, Shanshan Lian, Yun Zhang, Qiuxia Yang, Weijing Zhang, Cheng Zhang, Lidi Ma, Yingwei Luo, Fan Zhou, Shiyuan Wang, Cuiping Lin, Jiao Li, Ma Luo, Jianxun He, Guixiao Xu, Yaozong Gao, Dinggang Shen, Ying Sun, Yonggao Mou, Rong Zhang, Chuanmiao Xie\",\"doi\":\"10.1093/neuonc/noae113\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Artificial intelligence has been proposed for brain metastasis (BM) segmentation but it has not been fully clinically validated. The aim of this study was to develop and evaluate a system for BM segmentation.</p><p><strong>Methods: </strong>A deep-learning-based BM segmentation system (BMSS) was developed using contrast-enhanced MR images from 488 patients with 10338 brain metastases. A randomized crossover, multi-reader study was then conducted to evaluate the performance of the BMSS for BM segmentation using data prospectively collected from 50 patients with 203 metastases at 5 centers. Five radiology residents and 5 attending radiologists were randomly assigned to contour the same prospective set in assisted and unassisted modes. Aided and unaided Dice similarity coefficients (DSCs) and contouring times per lesion were compared.</p><p><strong>Results: </strong>The BMSS alone yielded a median DSC of 0.91 (95% confidence interval, 0.90-0.92) in the multi-center set and showed comparable performance between the internal and external sets (P = .67). With BMSS assistance, the readers increased the median DSC from 0.87 (0.87-0.88) to 0.92 (0.92-0.92) (P < .001) with a median time saving of 42% (40-45%) per lesion. Resident readers showed a greater improvement than attending readers in contouring accuracy (improved median DSC, 0.05 [0.05-0.05] vs 0.03 [0.03-0.03]; P < .001), but a similar time reduction (reduced median time, 44% [40-47%] vs 40% [37-44%]; P = .92) with BMSS assistance.</p><p><strong>Conclusions: </strong>The BMSS can be optimally applied to improve the efficiency of brain metastasis delineation in clinical practice.</p>\",\"PeriodicalId\":19377,\"journal\":{\"name\":\"Neuro-oncology\",\"volume\":\" \",\"pages\":\"2140-2151\"},\"PeriodicalIF\":16.4000,\"publicationDate\":\"2024-11-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neuro-oncology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/neuonc/noae113\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuro-oncology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/neuonc/noae113","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

摘要

背景:人工智能已被提出用于脑转移瘤(BM)的分割,但尚未得到充分的临床验证。本研究旨在开发和评估一种用于脑转移瘤分割的系统:方法:利用来自 488 例 10,338 例脑转移瘤患者的对比增强 MR 图像,开发了基于深度学习的脑转移瘤分割系统(BMSS)。然后进行了一项随机交叉、多阅片机研究,利用从五个中心的 50 名 203 例转移瘤患者中收集的数据,评估了 BMSS 在 BM 分割方面的性能。五名放射科住院医师和五名放射科主治医师被随机分配,分别在辅助和非辅助模式下对同一前瞻集进行轮廓分析。比较了辅助和非辅助的骰子相似系数(DSC)和每个病灶的轮廓绘制时间:单独使用 BMSS 时,多中心数据集的中位 DSC 为 0.91(95% 置信区间,0.90-0.92),内部数据集和外部数据集的性能相当(p = 0.67)。在 BMSS 的协助下,读者的 DSC 中位数从 0.87(0.87-0.88)提高到了 0.92(0.92-0.92)(p < 0.001),每个病灶的中位时间节省了 42% (40-45%)。与主治医生相比,住院医生在轮廓绘制的准确性方面有更大的提高(DSC中位数提高了0.05 [0.05-0.05] vs. 0.03 [0.03-0.03];p < 0.001),但在BMSS的帮助下,时间减少的情况相似(时间中位数减少了44% [40-47%] vs. 40% [37-44%];p = 0.92):结论:在临床实践中,BMSS 可以优化应用,以提高脑转移灶划分的效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automated segmentation of brain metastases with deep learning: A multi-center, randomized crossover, multi-reader evaluation study.

Background: Artificial intelligence has been proposed for brain metastasis (BM) segmentation but it has not been fully clinically validated. The aim of this study was to develop and evaluate a system for BM segmentation.

Methods: A deep-learning-based BM segmentation system (BMSS) was developed using contrast-enhanced MR images from 488 patients with 10338 brain metastases. A randomized crossover, multi-reader study was then conducted to evaluate the performance of the BMSS for BM segmentation using data prospectively collected from 50 patients with 203 metastases at 5 centers. Five radiology residents and 5 attending radiologists were randomly assigned to contour the same prospective set in assisted and unassisted modes. Aided and unaided Dice similarity coefficients (DSCs) and contouring times per lesion were compared.

Results: The BMSS alone yielded a median DSC of 0.91 (95% confidence interval, 0.90-0.92) in the multi-center set and showed comparable performance between the internal and external sets (P = .67). With BMSS assistance, the readers increased the median DSC from 0.87 (0.87-0.88) to 0.92 (0.92-0.92) (P < .001) with a median time saving of 42% (40-45%) per lesion. Resident readers showed a greater improvement than attending readers in contouring accuracy (improved median DSC, 0.05 [0.05-0.05] vs 0.03 [0.03-0.03]; P < .001), but a similar time reduction (reduced median time, 44% [40-47%] vs 40% [37-44%]; P = .92) with BMSS assistance.

Conclusions: The BMSS can be optimally applied to improve the efficiency of brain metastasis delineation in clinical practice.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Neuro-oncology
Neuro-oncology 医学-临床神经学
CiteScore
27.20
自引率
6.30%
发文量
1434
审稿时长
3-8 weeks
期刊介绍: Neuro-Oncology, the official journal of the Society for Neuro-Oncology, has been published monthly since January 2010. Affiliated with the Japan Society for Neuro-Oncology and the European Association of Neuro-Oncology, it is a global leader in the field. The journal is committed to swiftly disseminating high-quality information across all areas of neuro-oncology. It features peer-reviewed articles, reviews, symposia on various topics, abstracts from annual meetings, and updates from neuro-oncology societies worldwide.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信