Comparison of Different Deep Learning Frameworks for Hippocampus Body and Head Segmentation
,
Abstract
Purpose: The hippocampus is a crucial brain region responsible for memory, spatial navigation, and emotion regulation. Precise hippocampus segmentation from Magnetic Resonance Imaging (MRI) scans is vital in diagnosing various neurological disorders. Traditional segmentation methods face challenges due to the hippocampus's complex structure, leading to the adoption of deep learning algorithms. This study compares four deep learning frameworks to segment hippocampal parts, including concurrent, separated, ordinal, and attention-based strategies.
Materials and Methods: This research utilized 3D T1-weighted MR images with manually delineated hippocampus head and body labels from 260 participants. The images were randomly split into five folds for experimentation, each time one of those designated as the test set and the rest as the training set.
Results: The findings indicate that both the concurrent and separated frameworks perform better than the ordinal and attention-based frameworks regarding the Dice and Jaccard coefficients. In head segmentation, the separated framework had a Dice similarity of 0.8748, a Jaccard similarity of 0.7794, and a Hausdorff distance of 5.4160. In body segmentation, the concurrent framework had a Dice similarity of 0.8616, a Jaccard similarity of 0.7591, and a sensitivity of 0.8437. Statistical results from the one-way ANOVA test showed a significant difference in performance for the body part (P-value=0.008), but not for the head region (P-value=0.652) between concurrent and separated frameworks. Comparing the concurrent with ordinal and attention-based frameworks showed a significant difference in both body and head regions (P-value<0.001 for both comparisons).
Conclusion: Researchers must consider the differences between various frameworks while selecting a segmentation method for their specific task. Understanding the strengths and weaknesses of every framework is essential for deciding on the top-rated segmentation approach for precise applications.
2- S. Yazdani, R. Yusof, A. Karimian, A. H. Riazi, and M. Bennamoun, "A Unified Framework for Brain Segmentation in MR Images." Computational and Mathematical Methods in Medicine, Vol. 2015 (No. 1), p. 829893, 2015/01/01 (2015).
3- Sarah Atwi, Dallan McMahon, Helen Scharfman, and Neil J MacLusky, "Androgen modulation of hippocampal structure and function." The Neuroscientist, Vol. 22 (No. 1), pp. 46-60, (2016).
4- A. Basher et al., "Hippocampus Localization Using a Two-Stage Ensemble Hough Convolutional Neural Network." IEEE Access, Vol. 7pp. 73436-47, (2019).
5- Vanderson Dill, Alexandre Rosa Franco, and Márcio Sarroglia Pinho, "Automated methods for hippocampus segmentation: the evolution and a review of the state of the art." Neuroinformatics, Vol. 13pp. 133-50, (2015).
6- Reza Karimzadeh, Emad Fatemizadeh, and Hossein Arabi, "Attention-based deep learning segmentation: Application to brain tumor delineation." in 2021 28th National and 6th International Iranian Conference on Biomedical Engineering (ICBME), (2021): IEEE, pp. 248-52.
7- P Sharifian, A Karimian, H Arabi, and H Zaidi, "Anatomical brain regions segmentation from MR images using global and local deep learning networks." in 2023 IEEE Nuclear Science Symposium, Medical Imaging Conference and International Symposium on Room Temperature Semiconductor Detectors (NSS MIC RTSD), (2023): IEEE, pp. 1-1.
8- Frauke Nees and Sebastian T Pohlack, "Functional MRI studies of the hippocampus." The Hippocampus in Clinical Neuroscience, Vol. 34pp. 85-94, (2014).
9- Hossein Arabi and Habib Zaidi, "Recent advances in positron emission tomography/magnetic resonance imaging technology." Magnetic Resonance Imaging Clinics, Vol. 31 (No. 4), pp. 503-15, (2023). 10- Sandra González-Villà, Arnau Oliver, Sergi Valverde, Liping Wang, Reyer Zwiggelaar, and Xavier Lladó, "A review on brain structures segmentation in magnetic resonance imaging." Artificial Intelligence in Medicine, Vol. 73pp. 45-69, 2016/10/01/ (2016).
11- Hossein Arabi and Habib Zaidi, "Single annotator versus multi-annotator: Challenge of segmenting two neighboring hippocampus head and body with high precision." Biomedical Signal Processing and Control, Vol. 97p. 106667, (2024).
12- Jia-Ni Li, Shao-Wu Zhang, Yan-Rui Qiang, and Qin-Yi Zhou, "A novel cross-layer dual encoding-shared decoding network framework with spatial self-attention mechanism for hippocampus segmentation." Computers in Biology and Medicine, Vol. 167p. 107584, (2023).
13- Hossein Arabi and Habib Zaidi, "Segmentation of the Hippocampus Head and Body: Comparison of Single Annotator and Multi-annotator." in 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), (2021): IEEE, pp. 1-3.
14- H. Arabi and H. Zaidi, "Whole-body bone segmentation from MRI for PET/MRI attenuation correction using shape-based averaging." (in eng), Med Phys, Vol. 43 (No. 11), p. 5848, Nov (2016).
15- Carlos E Cardenas, Jinzhong Yang, Brian M Anderson, Laurence E Court, and Kristy B Brock, "Advances in auto-segmentation." in Seminars in radiation oncology, (2019), Vol. 29 (No. 3): Elsevier, pp. 185-97.
16- Hossein Arabi, Azadeh AkhavanAllaf, Amirhossein Sanaat, Isaac Shiri, and Habib Zaidi, "The promise of artificial intelligence and deep learning in PET and SPECT imaging." Physica Medica, Vol. 83pp. 122-37, (2021).
17- Hossein Arabi and Habib Zaidi, "Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy." European Journal of Hybrid Imaging, Vol. 4 (No. 1), p. 17, (2020).
18- Seyed Reza Seif, Alireza Karimian, Hossein Arabi, and Habib Zaidi, "Impact of Attention Modules in Deep Learning-based Semantic Segmentation: Evaluation for Liver Lesion Segmentation from CT Images." in 2022 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), (2022): IEEE, pp. 1-3.
19- Parisa Talebi, Elham Saeedzadeh, Mohsen Bakhshandeh, and Hossein Arabi, "A Novel Attention based Neural Network for Automated Lung Lesion Delineation from 4DCT Images." in 2022 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), (2022): IEEE, pp. 1-3.
20- H. Arabi and H. Zaidi, "Contrastive Learning vs. Self Learning vs. Deformable Data Augmentation in Semantic Segmentation of Medical Images." J Imaging Inform Med, pp. 1-14, Jun 10 (2024).
21- Maged Goubran et al., "Hippocampal segmentation for brains with extensive atrophy using three-dimensional convolutional neural networks." Human Brain Mapping, Vol. 41 (No. 2), pp. 291-308, (2020).
22- Dimitrios Ataloglou, Anastasios Dimou, Dimitrios Zarpalas, and Petros Daras, "Fast and precise hippocampus segmentation through deep convolutional neural network ensembles and transfer learning." Neuroinformatics, Vol. 17pp. 563-82, (2019).
23- A. Basher, B. C. Kim, K. H. Lee, and H. Y. Jung, "Automatic Localization and Discrete Volume Measurements of Hippocampi From MRI Data Using a Convolutional Neural Network." IEEE Access, Vol. 8pp. 91725-39, (2020).
24- Manhua Liu et al., "A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer’s disease." Neuroimage, Vol. 208p. 116459, (2020).
25- Hanieh Arabian, Alireza Karimian, Reza Rasti, Hossein Arabi, and Habib Zaidi, "Deep Attention-based Seminal Segmentation: A Practical Deep Learning Framework for Accurate Segmentation of the Hippocampus from Magnetic Resonance Images." in 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), (2021): IEEE, pp. 1-3.
26- Michela Antonelli et al., "The medical segmentation decathlon." Nature communications, Vol. 13 (No. 1), p. 4128, (2022).
27- Amber L Simpson et al., "A large annotated medical image dataset for the development and evaluation of segmentation algorithms." arXiv:1902.09063, (2019). arXiv preprint
28- Eli Gibson et al., "NiftyNet: a deep-learning platform for medical imaging." Computer Methods and Programs in Biomedicine, Vol. 158pp. 113-22, 2018/05/01/ (2018).
29- Abdel Aziz Taha and Allan Hanbury, "Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool." BMC Medical Imaging, Vol. 15 (No. 1), p. 29, 2015/08/12 (2015).
| Files | ||
| Issue | Vol 13 No 3 (2026) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/fbt.v13i3.22748 | |
| Keywords | ||
| Deep learning MRI Segmentation Concurrent framewor | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
