Hong Sungho, Hwang Eui Jin, Kim Soojin, Song Jiyoung, Lee Taehee, Jo Gyeong Deok, Choi Yelim, Park Chang Min, Goo Jin Mo
Department of Radiology, Seoul National University Hospital, Seoul 03082, Republic of Korea.
Department of Radiology, Seoul National University College of Medicine, Seoul 03082, Republic of Korea.
Diagnostics (Basel). 2023 Mar 13;13(6):1089. doi: 10.3390/diagnostics13061089.
It is unclear whether the visualization methods for artificial-intelligence-based computer-aided detection (AI-CAD) of chest radiographs influence the accuracy of readers' interpretation. We aimed to evaluate the accuracy of radiologists' interpretations of chest radiographs using different visualization methods for the same AI-CAD. Initial chest radiographs of patients with acute respiratory symptoms were retrospectively collected. A commercialized AI-CAD using three different methods of visualizing was applied: (a) closed-line method, (b) heat map method, and (c) combined method. A reader test was conducted with five trainee radiologists over three interpretation sessions. In each session, the chest radiographs were interpreted using AI-CAD with one of the three visualization methods in random order. Examination-level sensitivity and accuracy, and lesion-level detection rates for clinically significant abnormalities were evaluated for the three visualization methods. The sensitivity ( = 0.007) and accuracy ( = 0.037) of the combined method are significantly higher than that of the closed-line method. Detection rates using the heat map method ( = 0.043) and the combined method ( = 0.004) are significantly higher than those using the closed-line method. The methods for visualizing AI-CAD results for chest radiographs influenced the performance of radiologists' interpretations. Combining the closed-line and heat map methods for visualizing AI-CAD results led to the highest sensitivity and accuracy of radiologists.
基于人工智能的胸部X光片计算机辅助检测（AI-CAD）的可视化方法是否会影响阅片者解读的准确性尚不清楚。我们旨在评估放射科医生使用相同AI-CAD的不同可视化方法对胸部X光片解读的准确性。回顾性收集有急性呼吸道症状患者的初始胸部X光片。应用了一种商业化的采用三种不同可视化方法的AI-CAD：（a）封闭线法，（b）热图法，以及（c）联合法。对五名放射科实习医生进行了三次解读环节的阅片测试。在每个环节中，使用三种可视化方法之一的AI-CAD以随机顺序对胸部X光片进行解读。对三种可视化方法评估了检查级别的敏感性和准确性，以及对具有临床意义异常的病灶级检测率。联合法的敏感性（P = 0.007）和准确性（P = 0.037）显著高于封闭线法。使用热图法（P = 0.043）和联合法（P = 0.004）的检测率显著高于使用封闭线法的检测率。胸部X光片AI-CAD结果的可视化方法影响了放射科医生解读的表现。将封闭线法和热图法结合用于AI-CAD结果的可视化可使放射科医生的敏感性和准确性最高。
