Cho Hye Soo, Hwang Eui Jin, Yi Jaeyoun, Choi Boorym, Park Chang Min
Seoul National University Hospital, Seoul National University College of Medicine, Department of Radiology, Seoul, Republic of Korea.
Seoul National University College of Medicine, Department of Radiology, Seoul, Republic of Korea.
Diagn Interv Radiol. 2025 Mar 3;31(2):102-110. doi: 10.4274/dir.2024.242835. Epub 2024 Sep 9.
This study aimed to evaluate whether an artificial intelligence (AI) system can identify basal lung metastatic nodules examined using abdominopelvic computed tomography (CT) that were initially overlooked by radiologists.
We retrospectively included abdominopelvic CT images with the following inclusion criteria: a) CT images from patients with solid organ malignancies between March 1 and March 31, 2019, in a single institution; and b) abdominal CT images interpreted as negative for basal lung metastases. Reference standards for diagnosis of lung metastases were confirmed by reviewing medical records and subsequent CT images. An AI system that could automatically detect lung nodules on CT images was applied retrospectively. A radiologist reviewed the AI detection results to classify them as lesions with the possibility of metastasis or clearly benign. The performance of the initial AI results and the radiologist's review of the AI results were evaluated using patient-level and lesion-level sensitivities, false-positive rates, and the number of false-positive lesions per patient.
A total of 878 patients (580 men; mean age, 63 years) were included, with overlooked basal lung metastases confirmed in 13 patients (1.5%). The AI exhibited an area under the receiver operating characteristic curve value of 0.911 for the identification of overlooked basal lung metastases. Patient- and lesion-level sensitivities of the AI system ranged from 69.2% to 92.3% and 46.2% to 92.3%, respectively. After a radiologist reviewed the AI results, the sensitivity remained unchanged. The false-positive rate and number of false-positive lesions per patient ranged from 5.8% to 27.6% and 0.1% to 0.5%, respectively. Radiologist reviews significantly reduced the false-positive rate (2.4%-12.6%; all values < 0.001) and the number of false-positive lesions detected per patient (0.03-0.20, respectively).
The AI system could accurately identify basal lung metastases detected in abdominopelvic CT images that were overlooked by radiologists, suggesting its potential as a tool for radiologist interpretation.
The AI system can identify missed basal lung lesions in abdominopelvic CT scans in patients with malignancy, providing feedback to radiologists, which can reduce the risk of missing basal lung metastasis.
本研究旨在评估人工智能（AI）系统能否识别出在腹部盆腔计算机断层扫描（CT）检查中被放射科医生最初遗漏的肺部基底转移结节。
我们回顾性纳入了符合以下纳入标准的腹部盆腔CT图像：a）2019年3月1日至3月31日期间，来自单一机构的实体器官恶性肿瘤患者的CT图像；b）腹部CT图像被解读为肺部基底转移阴性。通过查阅病历和后续的CT图像来确定肺转移诊断的参考标准。回顾性应用了一种能够自动检测CT图像上肺结节的AI系统。一名放射科医生对AI检测结果进行审查，将其分类为可能转移的病变或明确良性的病变。使用患者层面和病变层面的敏感性、假阳性率以及每位患者的假阳性病变数量来评估最初的AI结果和放射科医生对AI结果审查的性能。
共纳入878例患者（580例男性；平均年龄63岁），其中13例（1.5%）患者存在被遗漏的肺部基底转移。AI在识别被遗漏的肺部基底转移方面，受试者工作特征曲线下面积值为0.911。AI系统在患者层面和病变层面的敏感性分别为69.2%至92.3%和46.2%至92.3%。在放射科医生审查AI结果后，敏感性保持不变。每位患者的假阳性率和假阳性病变数量分别为5.8%至27.6%和0.1%至0.5%。放射科医生的审查显著降低了假阳性率（2.4% - 12.6%；所有值<0.001）以及每位患者检测到的假阳性病变数量（分别为0.03 - 0.20）。
AI系统能够准确识别在腹部盆腔CT图像中被放射科医生遗漏的肺部基底转移，表明其作为放射科医生解读工具的潜力。
AI系统能够识别恶性肿瘤患者腹部盆腔CT扫描中遗漏的肺部基底病变，为放射科医生提供反馈，从而降低遗漏肺部基底转移的风险。
