Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learning

2023-08-31 · Yiming Zhang, Tianang Leng, Kun Han, Xiaohui Xie

While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical images in its training dataset. Nonetheless, gathering comprehensive datasets and training models that are universally applicable is particularly challenging due to the long-tail problem common in medical images. To address this gap, here we present a Self-Sampling Meta SAM (SSM-SAM) framework for few-shot medical image segmentation. Our innovation lies in the design of three key modules: 1) An online fast gradient descent optimizer, further optimized by a meta-learner, which ensures swift and robust adaptation to new tasks. 2) A Self-Sampling module designed to provide well-aligned visual prompts for improved attention allocation; and 3) A robust attention-based decoder specifically designed for medical few-shot learning to capture relationship between different slices. Extensive experiments on a popular abdominal CT dataset and an MRI dataset demonstrate that the proposed method achieves significant improvements over state-of-the-art methods in few-shot segmentation, with an average improvements of 10.21% and 1.80% in terms of DSC, respectively. In conclusion, we present a novel approach for rapid online adaptation in interactive image segmentation, adapting to a new organ in just 0.83 minutes. Code is publicly available on GitHub upon acceptance.

📄 PDF Abstract BibTeX arXiv:2308.16466

Code (1)

dragondescentzerotsu/ssm-sam 공식 구현 pytorch

Tasks

Decoder Few-Shot Learning Image Segmentation Medical Image Segmentation Meta-Learning Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Meta-hallucinator: Towards Few-Shot Cross-Modality Cardiac Image Segmentation

2023-05-11 · Ziyuan Zhao, Fangcheng Zhou, Zeng Zeng, Cuntai Guan 외

Domain shift and label scarcity heavily limit deep learning applications to various medical image analysis tasks. Unsupervised domain adaptation (UDA) techniques have recently achieved promising cross-modality medical im…

Cardiac Segmentation Domain Adaptation Hallucination Image Segmentation+7

Adaptive Task Sampling for Meta-Learning

2020-07-17 · ECCV 2020 8 · Chenghao Liu, Zhihao Wang, Doyen Sahoo, Yuan Fang 외

Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situati…

Classification General Classification Meta-Learning

CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection

2024-10-15 · Sin Chee Chin, Xuan Zhang, Lee Yeong Khang, Wenming Yang

Artificial intelligence aids in brain tumor detection via MRI scans, enhancing the accuracy and reducing the workload of medical professionals. However, in scenarios with extremely limited medical images, traditional dee…

Anomaly Detection Contrastive Learning Self-Supervised Learning Synthetic Data Generation

Learn To Learn More Precisely

2024-08-08 · Runxi Cheng, Yongxian Wei, Xianglong He, Wanyun Zhu 외

Meta-learning has been extensively applied in the domains of few-shot learning and fast adaptation, achieving remarkable performance. While Meta-learning methods like Model-Agnostic Meta-Learning (MAML) and its variants …

Few-Shot Learning Meta-Learning

Meta Episodic learning with Dynamic Task Sampling for CLIP-based Point Cloud Classification

2024-04-01 · Shuvozit Ghose, Yang Wang

Point cloud classification refers to the process of assigning semantic labels or categories to individual points within a point cloud data structure. Recent works have explored the extension of pre-trained CLIP to 3D rec…

Point Cloud Classification