Artificial intelligence system for identification of overlooked lung metastasis in abdominopelvic computed tomography scans of patients with malignancy

Hye Soo Cho, Eui Jin Hwang, and colleagues conducted a study to evaluate the effectiveness of an AI system in identifying basal lung metastases that were initially overlooked by radiologists in abdominopelvic CT scans. The AI system used was the AVIEW Lung Nodule CAD, a deep-learning-based tool designed for detecting pulmonary nodules. The study retrospectively analyzed 878 CT scans from patients with solid organ malignancies. AI detected overlooked metastases in 13 patients (1.5% of cases), with a sensitivity range of 69.2% to 92.3%. Although the AI initially produced false-positive results, radiologist review significantly reduced the false-positive rate, while maintaining the same sensitivity levels. The study concludes that AI systems like AVIEW could serve as valuable second readers for radiologists, improving diagnostic accuracy by identifying metastases that may be missed in routine evaluations. Future research is recommended to explore the integration of AI into clinical workflows and its impact on patient outcomes.