Artificial intelligence assists identifying malignant versus benign liver lesions using contrast-enhanced ultrasound.
Artificial intelligence assists identifying malignant versus benign liver lesions using contrast-enhanced ultrasound.
复制标题
DOI：
10.1111/jgh.15522
复制
发表时间：
2021-10
影响因子：
4.1
通讯作者：
Kuang M
中科院分区：
文献类型：
--
作者：
Hu HT;Wang W;Chen LD;Ruan SM;Chen SL;Li X;Lu MD;Xie XY;Kuang M
本研究旨在构建一种使用人工智能（AI）辅助的策略，以帮助放射科医生使用对比增强超声（CEUS）识别恶性与良性局灶性肝脏病变（FLL）。从我们的研究所收集了一个训练集（患者= 363）和一个测试集（患者= 211）。在训练集中的四相CEUS图像上，训练并调整复合深度学习架构以区分恶性和良性FLL。在测试数据集中，通过与具有不同经验水平的放射科医生进行比较来评估AI性能。基于比较，构建了AI辅助策略，并进一步测试了其在减少CEUS观察者间异质性方面的有效性。在测试集中，为了识别恶性与良性FLL，AI的曲线下面积为0.934（95% CI 0.890-0.978），准确度为91.0%。与放射科医生审查视频沿着补充患者信息相比，AI优于居民（82.9- 84.4%，P = 0.038），与专家的表现（87.2- 88.2%，P = 0.438）相匹配。由于较高的阳性预测值（PPV）（AI：95.6% vs居民：88.6- 89.7%，P = 0.056），定义了AI策略以提高恶性诊断。在AI的辅助下，放射科医生的敏感性提高了97.0-99.4%（P < 0.05），准确性提高了91.0-92.9%（P = 0.008-0.189），与专家的准确性相当（P = 0.904）。基于CEUS的AI策略改善了住院医师的表现，并降低了CEUS在区分良性和恶性FLL方面的观察者间异质性。
This study aims to construct a strategy that uses assistance from artificial intelligence (AI) to assist radiologists in the identification of malignant versus benign focal liver lesions (FLLs) using contrast‐enhanced ultrasound (CEUS). A training set (patients = 363) and a testing set (patients = 211) were collected from our institute. On four‐phase CEUS images in the training set, a composite deep learning architecture was trained and tuned for differentiating malignant and benign FLLs. In the test dataset, AI performance was evaluated by comparison with radiologists with varied levels of experience. Based on the comparison, an AI assistance strategy was constructed, and its usefulness in reducing CEUS interobserver heterogeneity was further tested. In the test set, to identify malignant versus benign FLLs, AI achieved an area under the curve of 0.934 (95% CI 0.890–0.978) with an accuracy of 91.0%. Comparing with radiologists reviewing videos along with complementary patient information, AI outperformed residents (82.9–84.4%, P = 0.038) and matched the performance of experts (87.2–88.2%, P = 0.438). Due to the higher positive predictive value (PPV) (AI: 95.6% vs residents: 88.6–89.7%, P = 0.056), an AI strategy was defined to improve the malignant diagnosis. With the assistance of AI, radiologists exhibited a sensitivity improvement of 97.0–99.4% (P < 0.05) and an accuracy of 91.0–92.9% (P = 0.008–0.189), which was comparable with that of the experts (P = 0.904). The CEUS‐based AI strategy improved the performance of residents and reduced CEUS's interobserver heterogeneity in the differentiation of benign and malignant FLLs.
登录
查看更多内容
影响因子：
29.4
作者：
Ilyas SI;Gores GJ
通讯作者：
Gores GJ
非典型肝细胞癌与局灶性结节性增生的鉴别：对比增强超声和微流成像的诊断性能。
影响因子：
19.7
作者：
Li, Wei;Wang, Wei;Lu, Ming-De
通讯作者：
Lu, Ming-De
影响因子：
19.7
作者：
Lakhani, Paras;Sundaram, Baskaran
通讯作者：
Sundaram, Baskaran
影响因子：
5.9
作者：
Hamm, Charlie A.;Wang, Clinton J.;Letzen, Brian
通讯作者：
Letzen, Brian
基于两阶段多视图学习框架的超声造影计算机辅助诊断肝脏肿瘤
影响因子：
2.1
作者：
Guo, Le-Hang;Wang, Dan;Xu, Hui-Xiong
通讯作者：
Xu, Hui-Xiong