利用深度学习自动分割脑转移瘤：一项多中心、随机交叉、多读者评估研究。
Automated segmentation of brain metastases with deep learning: a multi-center, randomized crossover, multi-reader evaluation study.
发表日期：2024 Jul 11
作者：
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
来源：
Brain Structure & Function
摘要：
人工智能已被提议用于脑转移（BM）分割，但尚未得到充分的临床验证。本研究的目的是开发和评估 BM 分割系统。使用来自 488 名患有 10,338 个脑转移瘤的患者的对比增强 MR 图像，开发了基于深度学习的 BM 分割系统 (BMSS)。然后进行了一项随机交叉、多读者研究，使用从五个中心的 50 名患有 203 个转移灶的患者前瞻性收集的数据来评估 BMSS 在 BM 分割方面的性能。五名放射科住院医师和五名主治放射科医生被随机分配到辅助和非辅助模式下的同一预期组中。比较了有辅助和无辅助的 Dice 相似系数 (DSC) 和每个病变的轮廓绘制时间。在多中心组中，仅 BMSS 产生的中值 DSC 为 0.91（95% 置信区间，0.90-0.92），并且在内部和内部组之间显示出可比的性能。外部组（p = 0.67）。在 BMSS 的帮助下，读者将中位 DSC 从 0.87 (0.87-0.88) 提高到 0.92 (0.92-0.92) (p < 0.001)，每个病变的中位时间节省了 42% (40-45%)。常驻读者在轮廓绘制准确度方面比出席读者表现出更大的改进（中位 DSC 提高 0.05 [0.05-0.05] 对比 0.03 [0.03-0.03]；p < 0.001），但时间也减少了类似（中位时间缩短了 44% [ 40-47%] vs. 40% [37-44%]；p = 0.92），使用 BMSS 辅助。BMSS 可以最佳地应用于临床实践中提高脑转移描绘的效率。© 作者 2024。由牛津大学出版社代表神经肿瘤学会出版。
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.A deep-learning-based BM segmentation system (BMSS) was developed using contrast-enhanced MR images from 488 patients with 10,338 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 five centers. Five radiology residents and five 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.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 = 0.67). With BMSS assistance, the readers increased the median DSC from 0.87 (0.87-0.88) to 0.92 (0.92-0.92) (p < 0.001) 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 < 0.001), but a similar time reduction (reduced median time, 44% [40-47%] vs. 40% [37-44%]; p = 0.92) with BMSS assistance.The BMSS can be optimally applied to improve the efficiency of brain metastasis delineation in clinical practice.© The Author(s) 2024. Published by Oxford University Press on behalf of the Society for Neuro-Oncology.