Automated Magnetic Resonance Image Segmentation of the Anterior Cruciate Ligament.

Researchers

Journal

Modalities

Models

Abstract

The objective of this work was to develop an automated segmentation method for the anterior cruciate ligament that is capable of facilitating quantitative assessments of ligament in clinical and research settings. A modified U-Net fully convolutional network model was trained, validated, and tested on 246 Constructive Interference in Steady State magnetic resonance images of intact anterior cruciate ligaments. Overall model performance was assessed on the image set relative to an experienced (>5 years) “ground truth” segmenter in two domains: anatomical similarity and the accuracy of quantitative measurements (i.e. signal intensity and volume) obtained from the automated segmentation. To establish model reliability relative to manual segmentation, a subset of the imaging data was re-segmented by the ground truth segmenter and two additional segmenters (A: 6 months, B: 2 years of experience), with their performance evaluated relative to the ground truth. The final model scored well on anatomical performance metrics (Dice coefficient=.84, precision=.82, sensitivity=.85). The median signal intensities and volumes of the automated segmentations were not significantly different from ground truth (0.3% difference, p=.9; 2.3% difference, p=.08, respectively). When the model results were compared to the independent segmenters, the model predictions demonstrated greater median Dice coefficient (A=.73, p=.001; B=.77, p=NS) and sensitivity (A=.68, p=.001; B=.72, p=.003). The model performed equivalently well to re-test segmentation by the ground truth segmenter on all measures. The quantitative measures extracted from the automated segmentation model did not differ from those of manual segmentation, enabling their use in quantitative MRI pipelines to evaluate the anterior cruciate ligament. This article is protected by copyright. All rights reserved.
This article is protected by copyright. All rights reserved.