Coupled Contour Regression for Efficient Delineation of Lumen and External Elastic Lamina in Intravascular Ultrasound Images

• Published in: IEEE journal of biomedical and health informatics 2023-12, Vol.27 (12), p.5883-5894
• Main Authors: Yang, Yuan, Yu, Wei, Du, Haiyan, Ling, Li, Feng, Qianjin, Tu, Shengxian, Yang, Wei
• Format: Article
• Language: English
• Subjects: contour regression; Contours; Cross-Sectional Studies; Decoding; deep learning; Delineation; Elastic limit; Feature extraction; Humans; Image reconstruction; Intravascular ultrasound; Lumen; Metric space; segmentation; Shape; Signatures; Task analysis; Ultrasonic imaging; Ultrasonography; Ultrasonography, Interventional - methods; Ultrasound
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2023.3321788

Automatic delineation of the lumen and vessel contours in intravascular ultrasound (IVUS) images is crucial for the subsequent IVUS-based analysis. Existing methods usually address this task through mask-based segmentation, which cannot effectively handle the anatomical plausibility of the lumen and external elastic lamina (EEL) contours and thus limits their performance. In this article, we propose a contour encoding based method called coupled contour regression network (CCRNet) to directly predict the lumen and EEL contour pairs. The lumen and EEL contours are resampled, coupled, and embedded into a low-dimensional space to learn a compact contour representation. Then, we employ a convolutional network backbone to predict the coupled contour signatures and reconstruct the signatures to the object contours by a linear decoder. Assisted by the implicit anatomical prior of the paired lumen and EEL contours in the signature space and contour decoder, CCRNet has the potential to avoid producing unreasonable results. We evaluated our proposed method on a large IVUS dataset consisting of 7204 cross-sectional frames from 185 pullbacks. The CCRNet can rapidly extract the contours at 100 fps. Without any post-processing, all produced contours are anatomically reasonable in the test 19 pullbacks. The mean Dice similarity coefficients of our CCRNet for the lumen and EEL are 0.940 and 0.958, which are comparable to the mask-based models. In terms of the contour metric Hausdorff distance, our CCRNet achieves 0.258 mm for lumen and 0.268 mm for EEL, which outperforms the mask-based models.