Related Experiment Video
Updated: Aug 30, 2025
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
Automated Computer-Aided Detection of Lung Nodules in Metastatic Colorectal Cancer Patients for the Identification of
Jason Joon Bock Lee1, Young Joo Suh2, Caleb Oh3
1Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul, Korea; Department of Radiation Oncology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea.
Purpose:
This study aimed to explore the possibility and clinical utility of existing artificial intelligence (AI)-based computer-aided detection (CAD) of lung nodules to identify pulmonary oligometastases.
Patients And Methods:
The chest computed tomography (CT) scans of patients with lung metastasis from colorectal cancer between March 2006 and November 2018 were analyzed. The patients were selected from a database of 1395 patients and studied in 2 cohorts. The first cohort included 50 patients, and the CT scans of these patients were independently evaluated for lung-nodule (≥3 mm) detection by a CAD-assisted radiation oncologist (CAD-RO) as well as by an expert radiologist. Interobserver variability by 2 additional radiation oncologists and 2 thoracic surgeons were also measured. In the second cohort of 305 patients, survival outcomes were evaluated based on the number of CAD-RO-detected nodules.
Results:
In the first cohort, the sensitivity and specificity of the CAD-RO for identifying oligometastatic disease (OMD) from varying criteria by ≤2 nodules, ≤3 nodules, ≤4 nodules, and ≤5 nodules were 71.9% and 88.9%, 82.9% and 93.3%, 97.1% and 73.3%, and 97.5% and 90.0%, respectively. The sensitivity of the CAD-RO in the nodule detection compared with the radiologist was 81.6%. The average (standard deviation) sensitivity in interobserver variability analysis was 80.0% (3.7%). In the second cohort, the 5-year survival rates of patients with 1, 2, 3, 4, or ≥5 metastatic nodules were 75.2%, 52.9%, 45.7%, 29.1%, and 22.7%, respectively.
Conclusions:
Proper identification of the pulmonary OMD and the correlation between the number of CAD-RO-detected nodules and survival suggest the potential practicality of AI in OMD recognition. Developing a deep learning-based model specific to the metastatic setting, which enables a quick estimation of disease burden and identification of OMD, is underway.
