Few-Shot Learning for Medical Image Segmentation Using 3D U-Net and Model-Agnostic Meta-Learning (MAML)

• Published in: Diagnostics (Basel) Vol. 14; no. 12; p. 1213
• Main Authors: Alsaleh, Aqilah M., Albalawi, Eid, Algosaibi, Abdulelah, Albakheet, Salman S., Khan, Surbhi Bhatia
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.06.2024; MDPI
• Subjects: Algorithms; Artificial intelligence; Automation; Brain research; Data mining; Datasets; Disease; few-shot learning; Image processing; Magnetic resonance imaging; MAML; medical image segmentation; Medical imaging; meta-learning; Neural networks; Software; Tomography; Tumors; U-Net; Ultrasonic imaging; X-rays; MAML; medical image segmentation; U-Net; meta-learning; few-shot learning
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics14121213

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.