The Development of an Intelligent Agent to Detect and Non-Invasively Characterize Lung Lesions on CT Scans: Ready for the “Real World”?

SIMPLE SUMMARY: An “intelligent agent” based on deep learning solutions is proposed to detect and non-invasively characterize lung lesions on computed tomography (CT) scans. Our retrospective study aimed to assess the effectiveness of Retina U-Net and the convolutional neural network for computer-aided detection (CADe) and computer-aided diagnosis (CADx) purposes. CADe and CADx were trained, validated, and tested on the publicly available LUNA challenge dataset and two local low-dose CT datasets from the IRCCS Humanitas Research Hospital. ABSTRACT: (1) Background: Once lung lesions are identified on CT scans, they must be characterized by assessing the risk of malignancy. Despite the promising performance of computer-aided systems, some limitations related to the study design and technical issues undermine these tools’ efficiency; an “intelligent agent” to detect and non-invasively characterize lung lesions on CT scans is proposed. (2) Methods: Two main modules tackled the detection of lung nodules on CT scans and the diagnosis of each nodule into benign and malignant categories. Computer-aided detection (CADe) and computer aided-diagnosis (CADx) modules relied on deep learning techniques such as Retina U-Net and the convolutional neural network; (3) Results: Tests were conducted on one publicly available dataset and two local datasets featuring CT scans acquired with different devices to reveal deep learning performances in “real-world” clinical scenarios. The CADe module reached an accuracy rate of 78%, while the CADx’s accuracy, specificity, and sensitivity stand at 80%, 73%, and 85.7%, respectively; (4) Conclusions: Two different deep learning techniques have been adapted for CADe and CADx purposes in both publicly available and private CT scan datasets. Experiments have shown adequate performance in both detection and diagnosis tasks. Nevertheless, some drawbacks still characterize the supervised learning paradigm employed in networks such as CNN and Retina U-Net in real-world clinical scenarios, with CT scans from different devices with different sensors’ fingerprints and spatial resolution. Continuous reassessment of CADe and CADx’s performance is needed during their implementation in clinical practice.