Improved unsupervised 3D lung lesion detection and localization by fusing global and local features: Validation in 3D low-dose computed tomography.
Authors
Affiliations (6)
Affiliations (6)
- Medical AI Research Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Republic of Korea; Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, Republic of Korea.
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea.
- School of Transdisciplinary Innovations, Artificial Intelligence Institute, Interdisciplinary Program in Bioengineering, and Interdisciplinary Program in Artificial Intelligence, Seoul, Republic of Korea; Department of Biomedical Science, Medical Research Center, SNUH Institute of Convergence Medicine with Innovative Technology, SNUH Institute of Healthcare AI Research, Seoul, Republic of Korea. Electronic address: [email protected].
- Medical AI Research Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Republic of Korea; Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul, Republic of Korea.
- School of Transdisciplinary Innovations, Interdisciplinary Program in Bioengineering, and Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea; Department of Radiology, Department of Biomedical Science and Medical Research Center, Seoul National University, Seoul, Republic of Korea.
- Medical AI Research Center, Research Institute for Future Medicine, Samsung Medical Center, Seoul, Republic of Korea; Department of Data Convergence and Future Medicine, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea; Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea. Electronic address: [email protected].
Abstract
Unsupervised anomaly detection (UAD) is crucial in low-dose computed tomography (LDCT). Recent AI technologies, leveraging global features, have enabled effective UAD with minimal training data of normal patients. However, this approach, devoid of utilizing local features, exhibits vulnerability in detecting deep lesions within the lungs. In other words, while the conventional use of global features can achieve high specificity, it often comes with limited sensitivity. Developing a UAD AI model with high sensitivity is essential to prevent false negatives, especially in screening patients with diseases demonstrating high mortality rates. We have successfully pioneered a new LDCT UAD AI model that leverages local features, achieving a previously unattainable increase in sensitivity compared to global methods (17.5% improvement). Furthermore, by integrating this approach with conventional global-based techniques, we have successfully consolidated the advantages of each model - high sensitivity from the local model and high specificity from the global model - into a single, unified, trained model (17.6% and 33.5% improvement, respectively). Without the need for additional training, we anticipate achieving significant diagnostic efficacy in various LDCT applications, where both high sensitivity and specificity are essential, using our fixed model. Code is available at https://github.com/kskim-phd/Fusion-UADL.