Přístupnostní navigace
E-application
Search Search Close
Bachelor's Thesis
Author of thesis: Apolena Přikrylová
Acad. year: 2025/2026
Supervisor: doc. Mgr. Ing. Marek Dostál, Ph.D.
Reviewer: Ing. et Ing. Michal Nohel
This bachelor’s thesis addresses the automatic segmentation of thigh muscles from magnetic resonance images in patients with type 2 myotonic dystrophy. The theoretical section includes a literature review of the anatomy of the thigh muscles, the principles of MRI, fat fraction quantification, and automatic segmentation methods. The thesis describes methods ranging from traditional approaches through machine learning to current deep learning architectures based on U-Net. The practical part involves testing three segmentation algorithms (MuscleMap, TotalSegmentator, and Dafne) on a dataset of 9 patients with type 2 myotonic dystrophy and 9 healthy volunteers. The accuracy of the algorithms was evaluated using the Dice coefficient and Hausdorff distance in comparison with manual segmentation as the gold standard. The MuscleMap and TotalSegmentator methods achieved the best results with an average Dice coefficient of approximately 0.80–0.83, while the Dafne method showed significantly lower spatial agreement (Dice ~ 0.47–0.53). Furthermore, the fat fraction of the thigh muscles was quantified from Dixon sequences. In patients with MD2, statistically significant differences in fat fraction values were observed between segmentation methods, particularly in the quadriceps femoris and medial thigh compartment. The results confirm that the choice of segmentation method can influence the quantitative parameters of clinically relevant biomarkers.
magnetic resonance imaging, automatic segmentation, thigh muscles, type 2 myotonic dystrophy, fat fraction, evaluation metrics, MuscleMap, TotalSegmenator, Dafne
Date of defence
16.06.2026
Result of the defence
Defended (thesis was successfully defended)
Grading
C
Process of defence
Studentka prezentovala výsledky své práce a komise byla seznámena s posudky. Ing. Nohel položil otázku: Proč jste nepoužila jiné metriky? Jak se počítala tuková frakce? Studentka obhájila bakalářskou práci s výhradami a odpověděla na otázky členů komise a oponenta.
Language of thesis
Czech
Faculty
Fakulta elektrotechniky a komunikačních technologií
Department
Department of Biomedical Engineering
Study programme
Biomedical Technology and Bioinformatics (BPC-BTB)
Composition of Committee
Doc. MUDr. Jaromír Gumulec, Ph.D. (předseda) doc. Mgr. Ing. Karel Sedlář, Ph.D. (místopředseda) Ing. Kateřina Šabatová (člen) Ing. Lucie Šaclová, Ph.D. (člen) Ing. Jan Odstrčilík, Ph.D. (člen) Ing. et Ing. Michal Nohel (člen)
Supervisor’s reportdoc. Mgr. Ing. Marek Dostál, Ph.D.
Grade proposed by supervisor: B
Reviewer’s reportIng. et Ing. Michal Nohel
Grade proposed by reviewer: C
Responsibility: Mgr. et Mgr. Hana Odstrčilová