期刊
JOURNAL OF MAGNETIC RESONANCE IMAGING
卷 49, 期 6, 页码 1565-1576出版社
WILEY
DOI: 10.1002/jmri.26330
关键词
Crohn's disease; convolutional neural network (CNN); curved planar reformatting (CPR); MRI
资金
- NIH [R01 NS079788, R01 EB019483, R01 DK100404, R44 MH086984, IDDRC U54 HD090255]
- Boston Children's Hospital Translational Research Program
- Crohn's and Colitis Foundation of America's Career Development Award
- AGA-Boston Scientific Technology & Innovation Pilot Research Award
- National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) of the NIH [R01DK100404]
Background Contrast-enhanced MRI of the small bowel is an effective imaging sequence for the detection and characterization of disease burden in pediatric Crohn's disease (CD). However, visualization and quantification of disease burden requires scrolling back and forth through 3D images to follow the anatomy of the bowel, and it can be difficult to fully appreciate the extent of disease. Purpose To develop and evaluate a method that offers better visualization and quantitative assessment of CD from MRI. Study Type Retrospective. Population Twenty-three pediatric patients with CD. Field Strength/Sequence 1.5T MRI system and T-1-weighted postcontrast VIBE sequence. Assessment The convolutional neural network (CNN) segmentation of the bowel's lumen, wall, and background was compared with manual boundary delineation. We assessed the reproducibility and the capability of the extracted markers to differentiate between different levels of disease defined after a consensus review by two experienced radiologists. Statistical Tests The segmentation algorithm was assessed using the Dice similarity coefficient (DSC) and boundary distances between the CNN and manual boundary delineations. The capability of the extracted markers to differentiate between different disease levels was determined using a t-test. The reproducibility of the extracted markers was assessed using the mean relative difference (MRD), Pearson correlation, and Bland-Altman analysis. Results Our CNN exhibited DSCs of 75 +/- 18%, 81 +/- 8%, and 97 +/- 2% for the lumen, wall, and background, respectively. The extracted markers of wall thickness at the location of min radius (P = 0.0013) and the median value of relative contrast enhancement (P = 0.0033) could differentiate active and nonactive disease segments. Other extracted markers could differentiate between segments with strictures and segments without strictures (P < 0.05). The observers' agreement in measuring stricture length was >3 times superior when computed on curved planar reformatting images compared with the conventional scheme. Data Conclusion The results of this study show that the newly developed method is efficient for visualization and assessment of CD.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据