Evidence
Performance of AI for Preoperative CT Assessment of Lung Metastases: Retrospective Analysis of 167 Patients
European Journal of Radiology
Masci et al. Oct 2024
The performance of artificial intelligence (AI) in the preoperative detection of lung metastases on CT was evaluated. Patients who underwent lung metastasectomy were enrolled. Their preoperative CT scans were retrospectively processed by AI. The results indicated that AI significantly increases the sensitivity of preoperative detection of lung metastases and enables earlier detection, with a significant potential benefit for patient management.
Early experiences of integrating an artificial intelligence-based diagnostic decision support system into radiology settings: a qualitative study
Nuša Farič, PhD, Sue Hinder, PhD, Robin Williams, PhD, Rishi Ramaesh, MD, Miguel O Bernabeu, PhD, Edwin van Beek, PhD, Kathrin Cresswell, PhD
Higher Agreement Between Readers with Deep Learning CAD Software for Reporting Pulmonary Nodules on CT
European Journal of Radiology Open
Hempel et al. Aug 2022
This retrospective study evaluated the impact of CAD software on the pulmonary nodule management recommendations of radiologists in a cohort of patients with incidentally detected nodules on CT. Two radiologists independently assessed 50 chest CT cases twice, unaided and aided by CAD. Readers showed a better agreement with the aid of CAD with and a significant reduction of reading time, suggesting that a dedicated CAD system for aiding in pulmonary nodule reporting may help improve the uniformity of management recommendations.
Validation of a Deep Learning Computer Aided System for CT Based Lung Nodule Detection, Classification, and Growth Rate Estimation in a Routine Clinical Population
PLoS One
Murchison et al. May 2022
The deep learning algorithm of a commercially available computer assisted diagnosis system (CAD) was trained with a lung cancer screening cohort and developed for detection, classification, quantification, and growth of actionable pulmonary nodules on chest CT scans. In a retrospective cohort of a routine clinical population, the applied CAD significantly increased radiologist’s detection of actionable nodules while minimally increasing the false positive rate, suggesting it can assist in pulmonary nodule detection and management.
Validation, Comparison, and Combination of Algorithms for Automatic Detection of Pulmonary Nodules in Computed Tomography Images: The LUNA16 Challenge
Medical Image Analysis
Setio et al. Dec 2017
The LUNA16 challenge is an objective evaluation framework for automatic nodule detection algorithms using the largest publicly available reference database of chest CT scans. Participants developed algorithms focused on 1) the complete nodule detection track or 2) the false positive reduction track. The impact of combined systems was also investigated. The combination of these solutions achieved a sensitivity of over 95% at fewer than 1.0 false positives per scan, highlighting the potential to improve detection performance.