Few-Shot Learning for Medical Image Segmentation Using 3D U-Net and Model-Agnostic Meta-Learning (MAML)
Diagnostics · 07.06.2024 · 14 (12) · 1213
DOI: 10.3390/diagnostics14121213 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 07.06.2024. Verfasst von Aqilah M Alsaleh und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Information Technology, King Faisal University, Al Hofuf 400-31982, AlAhsa, Saudi Arabia. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Faisal University, Deanship of Scientific Research, King Faisal University.
Abstract (Originalsprache)
Deep learning has attained state-of-the-art results in general image segmentation problems; however, it requires a substantial number of annotated images to achieve the desired outcomes. In the medical field, the availability of annotated images is often limited. To address this challenge, few-shot learning techniques have been successfully adapted to rapidly generalize to new tasks with only a few samples, leveraging prior knowledge. In this paper, we employ a gradient-based method known as Model-Agnostic Meta-Learning (MAML) for medical image segmentation. MAML is a meta-learning algorithm that quickly adapts to new tasks by updating a model’s parameters based on a limited set of training samples. Additionally, we use an enhanced 3D U-Net as the foundational network for our models. The enhanced 3D U-Net is a convolutional neural network specifically designed for medical image segmentation. We evaluate our approach on the TotalSegmentator dataset, considering a few annotated images for four tasks: liver, spleen, right kidney, and left kidney. The results demonstrate that our approach facilitates rapid adaptation to new tasks using only a few annotated images. In 10-shot settings, our approach achieved mean dice coefficients of 93.70%, 85.98%, 81.20%, and 89.58% for liver, spleen, right kidney, and left kidney segmentation, respectively. In five-shot sittings, the approach attained mean Dice coefficients of 90.27%, 83.89%, 77.53%, and 87.01% for liver, spleen, right kidney, and left kidney segmentation, respectively. Finally, we assess the effectiveness of our proposed approach on a dataset collected from a local hospital. Employing five-shot sittings, we achieve mean Dice coefficients of 90.62%, 79.86%, 79.87%, and 78.21% for liver, spleen, right kidney, and left kidney segmentation, respectively.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Information Technology, King Faisal University, Al Hofuf 400-31982, AlAhsa, Saudi Arabia.
- Department of Information Technology, AlAhsa Health Cluster, Al Hofuf 3158-36421, AlAhsa, Saudi Arabia.
- Department of Radiology, King Faisal General Hospital, Al Hofuf 36361, AlAhsa, Saudi Arabia.
- Department of Data Science, School of Science Engineering and Environment, University of Salford, Manchester M5 4WT, UK.
- Department of Electrical and Computer Engineering, Lebanese American University, Byblos P.O. Box 13-5053, Lebanon.
ORCID-Profile: Aqilah M Alsaleh, Eid Albalawi, Abdulelah Algosaibi, Salman S Albakheet
Förderung
- King Faisal University
- Deanship of Scientific Research, King Faisal University
Zitieren
APA
Alsaleh, A. M., Albalawi, E., Algosaibi, A., Albakheet, S. S., & Khan, S. B. (2024). Few-Shot Learning for Medical Image Segmentation Using 3D U-Net and Model-Agnostic Meta-Learning (MAML). Diagnostics, 14(12), 1213. https://doi.org/10.3390/diagnostics14121213
Vancouver
Alsaleh AM, Albalawi E, Algosaibi A, Albakheet SS, Khan SB. Few-Shot Learning for Medical Image Segmentation Using 3D U-Net and Model-Agnostic Meta-Learning (MAML). Diagnostics. 2024;14(12):1213. doi:10.3390/diagnostics14121213
BibTeX
@article{Alsaleh2024,
author = {Alsaleh, Aqilah M and Albalawi, Eid and Algosaibi, Abdulelah and Albakheet, Salman S and Khan, Surbhi Bhatia},
title = {Few-Shot Learning for Medical Image Segmentation Using 3D U-Net and Model-Agnostic Meta-Learning (MAML)},
journal = {Diagnostics},
year = {2024},
volume = {14},
number = {12},
pages = {1213},
doi = {10.3390/diagnostics14121213}
}
EUVIMED