The Impact of Fatty Infiltration on MRI Segmentation of Lower Limb Muscles in Neuromuscular Diseases: A Comparative Study of Deep Learning Approaches
Open Access
- 6 April 2023
- journal article
- research article
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 58 (6) , 1826-1835
Abstract
Background: Deep learning methods have been shown to be useful for segmentation of lower limb muscle MRIs of healthy subjects but, have not been sufficiently evaluated on neuromuscular disease (NDM) patients.Purpose: Evaluate the influence of fat infiltration on convolutional neural network (CNN) segmentation of MRIs from NMD patients.Study Type: Retrospective study.Subjects: Data were collected from a hospital database of 67 patients with NMDs and 14 controls (age: 53 ± 17 years, sex: 48 M, 33 F). Ten individual muscles were segmented from the thigh and six from the calf (20 slices, 200 cm section).Field Strength/Sequence: A 1.5 T. Sequences: 2D T1‐weighted fast spin echo. Fat fraction (FF): three‐point Dixon 3D GRE, magnetization transfer ratio (MTR): 3D MT‐prepared GRE, T2: 2D multispin‐echo sequence.Assessment: U‐Net 2D, U‐Net 3D, TransUNet, and HRNet were trained to segment thigh and leg muscles (101/11 and 95/11 training/validation images, 10‐fold cross‐validation). Automatic and manual segmentations were compared based on geometric criteria (Dice coefficient [DSC], outlier rate, absence rate) and reliability of measured MRI quantities (FF, MTR, T2, volume).Statistical Tests: Bland–Altman plots were chosen to describe agreement between manual vs. automatic estimated FF, MTR, T2 and volume. Comparisons were made between muscle populations with an FF greater than 20% (G20+) and lower than 20% (G20−).Results: The CNNs achieved equivalent results, yet only HRNet recognized every muscle in the database, with a DSC of 0.91 ± 0.08, and measurement biases reaching −0.32% ± 0.92% for FF, 0.19 ± 0.77 for MTR, −0.55 ± 1.95 msec for T2, and − 0.38 ± 3.67 cm3 for volume. The performances of HRNet, between G20− and G20+ decreased significantly.Data Conclusion: HRNet was the most appropriate network, as it did not omit any muscle. The accuracy obtained shows that CNNs could provide fully automated methods for studying NMDs. However, the accuracy of the methods may be degraded on the most infiltrated muscles (>20%).Evidence Level: 4.Technical Efficacy: Stage 1.Keywords
This publication has 33 references indexed in Scilit:
- Muscle Quantitative MR Imaging and Clustering Analysis in Patients with Facioscapulohumeral Muscular Dystrophy Type 1PLOS ONE, 2015
- Longitudinal measurements of MRI-T2 in boys with Duchenne muscular dystrophy: Effects of age and disease progressionNeuromuscular Disorders, 2014
- Distinct Disease Phases in Muscles of Facioscapulohumeral Dystrophy Patients Identified by MR Detected Fat InfiltrationPLOS ONE, 2014
- Manual segmentation of individual muscles of the quadriceps femoris using MRI: A reappraisalJournal of Magnetic Resonance Imaging, 2013
- MRI findings, patterns of disease distribution, and muscle fat fraction calculation in five patients with Charcot-Marie-Tooth type 2 F diseaseSkeletal Radiology, 2011
- Skeletal muscle MRI magnetisation transfer ratio reflects clinical severity in peripheral neuropathiesJournal of Neurology, Neurosurgery & Psychiatry, 2011
- European Federation of Neurological Societies/Peripheral Nerve Society Guideline on management of chronic inflammatory demyelinating polyradiculoneuropathy: Report of a joint task force of the European Federation of Neurological Societies and the Peripheral Nerve Society – First RevisionJournal of the Peripheral Nervous System, 2010
- Different clinical and magnetic resonance imaging features between Charcot–Marie–Tooth disease type 1A and 2ANeuromuscular Disorders, 2008
- Muscle MRI in inherited neuromuscular disorders: Past, present, and futureJournal of Magnetic Resonance Imaging, 2007
- Transthyretin-Related Familial Amyloidotic PolyneuropathyArchives of Neurology, 2005