EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The Impact of Fatty Infiltration on MRI Segmentation of Lower Limb Muscles in Neuromuscular Diseases: A Comparative Study of Deep Learning Approaches

Marc-Adrien Hostin iD, Augustin C Ogier, Constance P Michel, Yann Le Fur, Maxime Guye, Shahram Attarian, Etienne Fortanier, Marc-Emmanuel Bellemare, David Bendahan iD

Journal of Magnetic Resonance Imaging · 2023

DOI: 10.1002/jmri.28708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2023. Verfasst von Marc-Adrien Hostin und 8 weiteren Autor:innen. Beteiligte Einrichtung: Aix Marseille University, CNRS, CRMBM, Marseille, France. Hauptthemen laut MEDLINE: Deep Learning, Neuromuscular Diseases. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 T 1 ‐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 cm 3 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningNeuromuscular DiseasesHumansAdultMiddle AgedAgedRetrospective StudiesReproducibility of ResultsMagnetic Resonance ImagingThighMusclesImage Processing, Computer-Assisted

Stichwörter der Autor:innen

deep learningfat infiltrationmuscle segmentationneuromuscular diseasequantitative MRI

Autor:innen und Institutionen

  • Aix Marseille University, CNRS, CRMBM, Marseille, France.
  • Aix Marseille University, CNRS, LIS, Marseille, France.
  • Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.
  • APHM, Hopital Universitaire Timone, CEMEREM, Marseille, France.
  • Reference Center for Neuromuscular Diseases and ALS, APHM, University Hospital of Marseille/Timone University Hospital, Marseille, France.

ORCID-Profile: Marc-Adrien Hostin, David Bendahan

Zitieren

APA

Hostin, M. A., Ogier, A. C., Michel, C. P., Le Fur, Y., Guye, M., Attarian, S., Fortanier, E., Bellemare, M. E., & Bendahan, D. (2023). The Impact of Fatty Infiltration on MRI Segmentation of Lower Limb Muscles in Neuromuscular Diseases: A Comparative Study of Deep Learning Approaches. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.28708

Vancouver

Hostin MA, Ogier AC, Michel CP, Le Fur Y, Guye M, Attarian S, et al. The Impact of Fatty Infiltration on MRI Segmentation of Lower Limb Muscles in Neuromuscular Diseases: A Comparative Study of Deep Learning Approaches. Journal of Magnetic Resonance Imaging. 2023. doi:10.1002/jmri.28708

BibTeX
@article{Hostin2023,
  author = {Hostin, Marc-Adrien and Ogier, Augustin C and Michel, Constance P and Le Fur, Yann and Guye, Maxime and Attarian, Shahram and Fortanier, Etienne and Bellemare, Marc-Emmanuel and Bendahan, David},
  title = {The Impact of Fatty Infiltration on MRI Segmentation of Lower Limb Muscles in Neuromuscular Diseases: A Comparative Study of Deep Learning Approaches},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2023},
  doi = {10.1002/jmri.28708}
}
Kostenlos starten →