DECTGoutSys: Reducing False Positive Gout Diagnoses via a Machine Vision Pipeline for Crystal Tophi Identification+Classification in Dual-Energy Computed Tomography (DECT).
Authors
Affiliations (8)
Affiliations (8)
- Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, SK, S7N 5A9, Canada.
- Research Institute of Clinical Medicine, Jeonbuk National University-Biomedical Research Institute, Jeonbuk National University Hospital, 54907, Jeonju, Jeollabuk-do, Republic of Korea.
- Department of Internal Medicine, Division of Rheumatology, Jeonbuk National University Medical School, 54896, Jeonju, Jeollabuk-do, South Korea.
- Department of Obstetrics and Gynecology, Jeonbuk National University-Biomedical Research Institute, Jeonbuk National University Hospital, 54907, Jeonju, Republic of Korea.
- Department of Radiology, Jeonbuk National University-Biomedical Research Institute, Jeonbuk National University Hospital, 54907, Jeonju, Republic of Korea.
- Research Institute of Clinical Medicine, Jeonbuk National University-Biomedical Research Institute, Jeonbuk National University Hospital, 54907, Jeonju, Jeollabuk-do, Republic of Korea. [email protected].
- Department of Radiology, Jeonbuk National University-Biomedical Research Institute, Jeonbuk National University Hospital, 54907, Jeonju, Republic of Korea. [email protected].
- Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, SK, S7N 5A9, Canada. [email protected].
Abstract
Gout is the world's foremost chronic inflammatory arthritis. Dual-energy computed tomography (DECT) images tophi-monosodium urate (MSU) crystal deposits that indicate gout-as an easily recognizable green color, facilitating high sensitivity. However, tophi-like regions ("artifacts") may be found in healthy controls, degrading specificity. To mitigate false positives, we propose the first automated system to localize MSU-presenting crystal deposits from DECT and classify them as gouty tophi or artifacts. Our solution, developed using 47 gout and 27 control patient scans, is three-stage. First, a computer vision algorithm crops green regions of interest (RoIs) from a patient's DECT scan frames and filters obvious false positives. Next, extracted RoIs are classified as tophi or artifact via one of three fine-tuned deep learning models; one model is trained to predict "small" RoIs, another "medium," and the third predicts "large" RoIs. Size thresholds are based on pixel area quartile statistics. Patient-level gout versus control classification is made via a machine learning system trained using a suite of features calculated from the outcomes of the RoI classifiers. Using 6-fold cross-validation, the proposed pipeline achieved a patient-level diagnostic accuracy, sensitivity, and specificity of 91.89%, 87.23%, and 100.00%. Using confidence values derived from the majority vote of RoI predictions, the best area under the receiver operator characteristics curve (ROC AUC) is 97.16%. The best RoI-level classifiers achieved mean tophus versus artifact accuracy, sensitivity, specificity, and ROC AUC of 89.61%, 85.42%, 93.70%, and 92.72%. Results demonstrate that machine/deep learning facilitates high-specificity gout diagnoses while maintaining respectable sensitivity.