Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network
Computer Methods and Programs in Biomedicine · 2024-11 · 256 · 108398
DOI: 10.1016/j.cmpb.2024.108398 ↗At a glance
Journal article in Computer Methods and Programs in Biomedicine, 2024-11. Written by Zakia Khatun and 7 co-authors. Institution: Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Salerno, Italy; Institute of Biomedical and Neur…. Major MEDLINE topics: Magnetic Resonance Imaging, Machine Learning, Support Vector Machine, Achilles Tendon. Cited 9 times so far (Crossref); 48 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
BACKGROUND AND OBJECTIVE: Tendon segmentation is crucial for studying tendon-related pathologies like tendinopathy, tendinosis, etc. This step further enables detailed analysis of specific tendon regions using automated or semi-automated methods. This study specifically aims at the segmentation of Achilles tendon, the largest tendon in the human body. METHODS: This study proposes a comprehensive end-to-end tendon segmentation module composed of a preliminary superpixel-based coarse segmentation preceding the final segmentation task. The final segmentation results are obtained through two distinct approaches. In the first approach, the coarsely generated superpixels are subjected to classification using Random Forest (RF) and Support Vector Machine (SVM) classifiers to classify whether each superpixel belongs to a tendon class or not (resulting in tendon segmentation). In the second approach, the arrangements of superpixels are converted to graphs instead of being treated as conventional image grids. This classification process uses a graph-based convolutional network (GCN) to determine whether each superpixel corresponds to a tendon class or not. RESULTS: All experiments are conducted on a custom-made ankle MRI dataset. The dataset comprises 76 subjects and is divided into two sets: one for training (Dataset 1, trained and evaluated using leave-one-group-out cross-validation) and the other as unseen test data (Dataset 2). Using our first approach, the final test AUC (Area Under the ROC Curve) scores using RF and SVM classifiers on the test data (Dataset 2) are 0.992 and 0.987, respectively, with sensitivities of 0.904 and 0.966. On the other hand, using our second approach (GCN-based node classification), the AUC score for the test set is 0.933 with a sensitivity of 0.899. CONCLUSIONS: Our proposed pipeline demonstrates the efficacy of employing superpixel generation as a coarse segmentation technique for the final tendon segmentation. Whether utilizing RF, SVM-based superpixel classification, or GCN-based classification for tendon segmentation, our system consistently achieves commendable AUC scores, especially the non-graph-based approach. Given the limited dataset, our graph-based method did not perform as well as non-graph-based superpixel classifications; however, the results obtained provide valuable insights into how well the models can distinguish between tendons and non-tendons. This opens up opportunities for further exploration and improvement.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Salerno, Italy; Institute of Biomedical and Neural Engineering, Department of Engineering, Reykjavik University, Reykj…
- Department of Orthopaedics, Landspitali University Hospital, Reykjavik, Iceland.
- Department of Radiology, Landspitali University Hospital, Reykjavik, Iceland.
- Department of Trauma and Orthopaedic Surgery, Faculty of Medicine and Psychology, University Hospital Sant'Andrea, University La Sapienza, Rome, Italy; School of Pharmacy and Bioengineering, Faculty of Medicine, Keele U…
- Department of Human Sciences and Promotion of the Quality of Life, San Raffaele Roma Open University, Rome, Italy.
- Biomedical Department, École Polytechnique Universitaire d'Aix-Marseille, Marseille, France.
Cite
APA
Khatun, Z., Jónsson, H., Tsirilaki, M., Maffulli, N., Oliva, F., Daval, P., Tortorella, F., & Gargiulo, P. (2024). Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network. Computer Methods and Programs in Biomedicine, 256, 108398. https://doi.org/10.1016/j.cmpb.2024.108398
Vancouver
Khatun Z, Jónsson H, Tsirilaki M, Maffulli N, Oliva F, Daval P, et al. Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network. Computer Methods and Programs in Biomedicine. 2024;256:108398. doi:10.1016/j.cmpb.2024.108398
BibTeX
@article{Khatun2024,
author = {Khatun, Zakia and Jónsson, Halldór and Tsirilaki, Mariella and Maffulli, Nicola and Oliva, Francesco and Daval, Pauline and Tortorella, Francesco and Gargiulo, Paolo},
title = {Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network},
journal = {Computer Methods and Programs in Biomedicine},
year = {2024},
volume = {256},
pages = {108398},
doi = {10.1016/j.cmpb.2024.108398}
}
EUVIMED