School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel.
Dept of Radiology, Hadassah Medical Center, Faculty of Medicine, The Hebrew University of Jerusalem, POB 12000, 91120, Jerusalem, Israel.
Eur Radiol. 2023 Dec;33(12):9320-9327. doi: 10.1007/s00330-023-09926-0. Epub 2023 Jul 22.
To compare liver metastases changes in CT assessed by radiologists using RECIST 1.1 and with aided simultaneous deep learning-based volumetric lesion changes analysis.
A total of 86 abdominal CT studies from 43 patients (prior and current scans) of abdominal CT scans of patients with 1041 liver metastases (mean = 12.1, std = 11.9, range 1-49) were analyzed. Two radiologists performed readings of all pairs; conventional with RECIST 1.1 and with computer-aided assessment. For computer-aided reading, we used a novel simultaneous multi-channel 3D R2U-Net classifier trained and validated on other scans. The reference was established by having an expert radiologist validate the computed lesion detection and segmentation. The results were then verified and modified as needed by another independent radiologist. The primary outcome measure was the disease status assessment with the conventional and the computer-aided readings with respect to the reference.
For conventional and computer-aided reading, there was a difference in disease status classification in 40 out of 86 (46.51%) and 10 out of 86 (27.9%) CT studies with respect to the reference, respectively. Computer-aided reading improved conventional reading in 30 CT studies by 34.5% for two readers (23.2% and 46.51%) with respect to the reference standard. The main reason for the difference between the two readings was lesion volume differences (p = 0.01).
AI-based computer-aided analysis of liver metastases may improve the accuracy of the evaluation of neoplastic liver disease status.
AI may aid radiologists to improve the accuracy of evaluating changes over time in metastasis of the liver.
• Classification of liver metastasis changes improved significantly in one-third of the cases with an automatically generated comprehensive lesion and lesion changes report. • Simultaneous deep learning changes detection and volumetric assessment may improve the evaluation of liver metastases temporal changes potentially improving disease management.
比较使用 RECIST 1.1 评估的放射科医师和使用辅助同时进行的深度学习容积病变变化分析评估的肝转移瘤的变化。
共分析了 43 例患者（之前和当前扫描）的 86 例腹部 CT 研究，共 1041 个肝转移瘤（平均值=12.1，标准差=11.9，范围 1-49）。两名放射科医师对所有配对进行了阅读；常规使用 RECIST 1.1 和计算机辅助评估。对于计算机辅助阅读，我们使用了一种新颖的同时多通道 3D R2U-Net 分类器，该分类器在其他扫描上进行了训练和验证。参考标准是由一位专家放射科医师验证计算出的病变检测和分割。然后，另一位独立的放射科医师根据需要对结果进行核实和修改。主要观察指标是常规阅读和计算机辅助阅读相对于参考标准的疾病状态评估。
对于常规阅读和计算机辅助阅读，分别有 40 项（46.51%）和 10 项（27.9%）CT 研究与参考标准相比，疾病状态分类不同。与参考标准相比，计算机辅助阅读提高了两位读者的 30 项 CT 研究的常规阅读准确性，分别提高了 34.5%和 46.51%。两次阅读结果不同的主要原因是病变体积差异（p=0.01）。
基于人工智能的肝转移瘤计算机辅助分析可能提高评价肿瘤性肝病状态的准确性。
人工智能可以帮助放射科医师提高评估肝脏转移瘤随时间变化的准确性。
•在三分之一的病例中，自动生成全面的病变和病变变化报告，显著改善了肝转移瘤变化的分类。•同时进行深度学习的变化检测和容积评估可能改善对肝脏转移瘤时间变化的评估，从而有可能改善疾病管理。
