4.7 Article

Deep learning for standardized, MRI-based quantification of subcutaneous and subfascial tissue volume for patients with lipedema and lymphedema

Journal

EUROPEAN RADIOLOGY
Volume 33, Issue 2, Pages 884-892

Publisher

SPRINGER
DOI: 10.1007/s00330-022-09047-0

Keywords

Deep learning; Magnetic resonance imaging; Lymphography; Leg; Subcutaneous tissue

Ask authors/readers for more resources

A deep learning pipeline using MR imaging data for assessing shape, volume, and asymmetry of the lower extremities in patients with lipedema or lymphedema is proposed. The pipeline includes localization of anatomical landmarks and quality-assured tissue segmentation. The results show excellent performance in landmark detection and segmentation, allowing for standardized analysis of tissue volume and distribution.
Objectives To contribute to a more in-depth assessment of shape, volume, and asymmetry of the lower extremities in patients with lipedema or lymphedema utilizing volume information from MR imaging. Methods A deep learning (DL) pipeline was developed including (i) localization of anatomical landmarks (femoral heads, symphysis, knees, ankles) and (ii) quality-assured tissue segmentation to enable standardized quantification of subcutaneous (SCT) and subfascial tissue (SFT) volumes. The retrospectively derived dataset for method development consisted of 45 patients (42 female, 44.2 +/- 14.8 years) who underwent clinical 3D DIXON MR-lymphangiography examinations of the lower extremities. Five-fold cross-validated training was performed on 16,573 axial slices from 40 patients and testing on 2187 axial slices from 5 patients. For landmark detection, two EfficientNet-B1 convolutional neural networks (CNNs) were applied in an ensemble. One determines the relative foot-head position of each axial slice with respect to the landmarks by regression, the other identifies all landmarks in coronal reconstructed slices using keypoint detection. After landmark detection, segmentation of SCT and SFT was performed on axial slices employing a U-Net architecture with EfficientNet-B1 as encoder. Finally, the determined landmarks were used for standardized analysis and visualization of tissue volume, distribution, and symmetry, independent of leg length, slice thickness, and patient position. Results Excellent test results were observed for landmark detection (z-deviation = 4.5 +/- 3.1 mm) and segmentation (Dice score: SCT = 0.989 +/- 0.004, SFT = 0.994 +/- 0.002). Conclusions The proposed DL pipeline allows for standardized analysis of tissue volume and distribution and may assist in diagnosis of lipedema and lymphedema or monitoring of conservative and surgical treatments.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available