Journal
JOURNAL OF ORTHOPAEDIC RESEARCH
Volume 41, Issue 3, Pages 649-656Publisher
WILEY
DOI: 10.1002/jor.25390
Keywords
ACL; automated; deep learning; segmentation; T-2* relaxometry
Categories
Ask authors/readers for more resources
The study applies transfer learning to automate the segmentation and evaluation of collagen organization in ACL using T-2* mapping. Results show that the performance of T-2* segmentation is comparable to CISS, and the automated segmentation outperforms independent manual segmentation and performs equally well as retest segmentation.
Collagen organization of the anterior cruciate ligament (ACL) can be evaluated using T-2* relaxometry. However, T-2* mapping requires manual image segmentation, which is a time-consuming process and prone to inter- and intra- segmenter variability. Automating segmentation would address these challenges. A model previously trained using Constructive Interference in Steady State (CISS) scans was applied to T-2* segmentation via transfer learning. It was hypothesized that there would be no significant differences in the model's segmentation performance between T-2* and CISS, structural measures versus ground truth manual segmentation, and reliability versus independent and retest manual segmentation. Transfer learning was conducted using 54 T-2* scans of the ACL. Segmentation performance was assessed with Dice coefficient, precision, and sensitivity, and structurally with T-2* value, volume, subvolume proportions, and cross-sectional area. Model performance relative to independent manual segmentation and repeated segmentation by the ground truth segmenter (retest) were evaluated on a random subset. Segmentation performance was analyzed with Mann-Whitney U tests, structural measures with Wilcoxon signed-rank tests, and performance relative to manual segmentation with repeated-measures analysis of variance/Tukey tests (alpha = 0.05). T-2* segmentation performance was not significantly different from CISS on all measures (p > 0.35). No significant differences were detected in structural measures (p > 0.50). Automatic segmentation performed as well as the retest on all segmentation measures, whereas independent segmentations were lower than retest and/or automatic segmentation (p < 0.023). Structural measures were not significantly different between segmenters. The automatic segmentation model performed as well on the T-2* sequence as on CISS and outperformed independent manual segmentation while performing as well as retest segmentation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available