Development of a deep learning model for the automated detection of green pixels indicative of gout on dual energy CT scan

• Published in: Research in Diagnostic and Interventional Imaging (Online) Vol. 9; p. 100044
• Main Authors: Faghani, Shahriar, Nicholas, Rhodes G., Patel, Soham, Baffour, Francis I., Moassefi, Mana, Rouzrokh, Pouria, Khosravi, Bardia, Powell, Garret M., Leng, Shuai, Glazebrook, Katrina N., Erickson, Bradley J., Tiegs-Heiden, Christin A.
• Format: Journal Article
• Language: English
• Published: France Elsevier Masson SAS 01.03.2024; Elsevier
• Subjects: Convolutional neural network; Deep learning; Dual-energy CT; Gout; Original; Segmentation; Vision transformers; Deep learning; digital imaging and communications in medicine; Segmentation; monosodium urate; Gout; Convolutional neural network; dice similarity score; Dual-energy CT; convolutional neural networks; Vision transformers; neuroimaging informatics technology initiative; standard deviation
• ISSN: 2772-6525; 2772-6525
• DOI: 10.1016/j.redii.2024.100044

Dual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Most software labels MSU as green and calcium as blue. There are limitations in the current image processing methods of segmenting green-encoded pixels. Additionally, identifying green foci is tedious, and automated detection would improve workflow. This study aimed to determine the optimal deep learning (DL) algorithm for segmenting green-encoded pixels of MSU crystals on DECTs. DECT images of positive and negative gout cases were retrospectively collected. The dataset was split into train (N = 28) and held-out test (N = 30) sets. To perform cross-validation, the train set was split into seven folds. The images were presented to two musculoskeletal radiologists, who independently identified green-encoded voxels. Two 3D Unet-based DL models, Segresnet and SwinUNETR, were trained, and the Dice similarity coefficient (DSC), sensitivity, and specificity were reported as the segmentation metrics. Segresnet showed superior performance, achieving a DSC of 0.9999 for the background pixels, 0.7868 for the green pixels, and an average DSC of 0.8934 for both types of pixels, respectively. According to the post-processed results, the Segresnet reached voxel-level sensitivity and specificity of 98.72 % and 99.98 %, respectively. In this study, we compared two DL-based segmentation approaches for detecting MSU deposits in a DECT dataset. The Segresnet resulted in superior performance metrics. The developed algorithm provides a potential fast, consistent, highly sensitive and specific computer-aided diagnosis tool. Ultimately, such an algorithm could be used by radiologists to streamline DECT workflow and improve accuracy in the detection of gout.