How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model
- URL: http://arxiv.org/abs/2404.09957v2
- Date: Mon, 13 May 2024 04:29:48 GMT
- Title: How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model
- Authors: Hanxue Gu, Haoyu Dong, Jichen Yang, Maciej A. Mazurowski,
- Abstract summary: This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning algorithms across 18 combinations.
We evaluate them on 17 datasets covering all common radiology modalities.
We release our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM.
- Score: 12.051904886550956
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning. While foundation models have been useful in natural language processing and some vision tasks for some time, the foundation model developed with image segmentation in mind - Segment Anything Model (SAM) - has been developed only recently and has shown similar promise. However, there are still no systematic analyses or "best-practice" guidelines for optimal fine-tuning of SAM for medical image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning algorithms across 18 combinations, and evaluates them on 17 datasets covering all common radiology modalities. Our study reveals that (1) fine-tuning SAM leads to slightly better performance than previous segmentation methods, (2) fine-tuning strategies that use parameter-efficient learning in both the encoder and decoder are superior to other strategies, (3) network architecture has a small impact on final performance, (4) further training SAM with self-supervised learning can improve final model performance. We also demonstrate the ineffectiveness of some methods popular in the literature and further expand our experiments into few-shot and prompt-based settings. Lastly, we released our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM, at https://github.com/mazurowski-lab/finetune-SAM.
Related papers
- ASPS: Augmented Segment Anything Model for Polyp Segmentation [77.25557224490075]
The Segment Anything Model (SAM) has introduced unprecedented potential for polyp segmentation.
SAM's Transformer-based structure prioritizes global and low-frequency information.
CFA integrates a trainable CNN encoder branch with a frozen ViT encoder, enabling the integration of domain-specific knowledge.
arXiv Detail & Related papers (2024-06-30T14:55:32Z) - Improving Segment Anything on the Fly: Auxiliary Online Learning and Adaptive Fusion for Medical Image Segmentation [52.172885882728174]
In medical imaging contexts, it is not uncommon for human experts to rectify segmentations of specific test samples after SAM generates its segmentation predictions.
We introduce a novel approach that leverages the advantages of online machine learning to enhance Segment Anything (SA) during test time.
We employ rectified annotations to perform online learning, with the aim of improving the segmentation quality of SA on medical images.
arXiv Detail & Related papers (2024-06-03T03:16:25Z) - MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation [2.2585213273821716]
We propose a novel framework, called MedCLIP-SAM, that combines CLIP and SAM models to generate segmentation of clinical scans.
By extensively testing three diverse segmentation tasks and medical image modalities, our proposed framework has demonstrated excellent accuracy.
arXiv Detail & Related papers (2024-03-29T15:59:11Z) - Diagonal Hierarchical Consistency Learning for Semi-supervised Medical Image Segmentation [0.0]
We propose a novel framework for robust semi-supervised medical image segmentation using diagonal hierarchical consistency learning (DiHC-Net)
It is composed of multiple sub-models with identical multi-scale architecture but with distinct sub-layers, such as up-sampling and normalisation layers.
A series of experiments verifies the efficacy of our simple framework, outperforming all previous approaches on public benchmark dataset covering organ and tumour.
arXiv Detail & Related papers (2023-11-10T12:38:16Z) - nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance [12.169801149021566]
The Segment Anything Model (SAM) has emerged as a versatile tool for image segmentation without specific domain training.
Traditional models like nnUNet perform automatic segmentation during inference but need extensive domain-specific training.
We propose nnSAM, integrating SAM's robust feature extraction with nnUNet's automatic configuration to enhance segmentation accuracy on small datasets.
arXiv Detail & Related papers (2023-09-29T04:26:25Z) - MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image
Segmentation [58.53672866662472]
We introduce a modality-agnostic SAM adaptation framework, named as MA-SAM.
Our method roots in the parameter-efficient fine-tuning strategy to update only a small portion of weight increments.
By injecting a series of 3D adapters into the transformer blocks of the image encoder, our method enables the pre-trained 2D backbone to extract third-dimensional information from input data.
arXiv Detail & Related papers (2023-09-16T02:41:53Z) - Cheap Lunch for Medical Image Segmentation by Fine-tuning SAM on Few
Exemplars [19.725817146049707]
The Segment Anything Model (SAM) has demonstrated remarkable capabilities of scaled-up segmentation models.
However, the adoption of foundational models in the medical domain presents a challenge due to the difficulty and expense of labeling sufficient data.
This paper introduces an efficient and practical approach for fine-tuning SAM using a limited number of exemplars.
arXiv Detail & Related papers (2023-08-27T15:21:25Z) - Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
We propose a learnable weight-based hybrid medical image segmentation approach.
Our approach is easy to integrate into any hybrid model and requires no external training data.
Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2023-06-15T17:55:05Z) - Zero-shot performance of the Segment Anything Model (SAM) in 2D medical
imaging: A comprehensive evaluation and practical guidelines [0.13854111346209866]
Segment Anything Model (SAM) harnesses a massive training dataset to segment nearly any object.
Our findings reveal that SAM's zero-shot performance is not only comparable, but in certain cases, surpasses the current state-of-the-art.
We propose practical guidelines that require minimal interaction while consistently yielding robust outcomes.
arXiv Detail & Related papers (2023-04-28T22:07:24Z) - Understanding the Tricks of Deep Learning in Medical Image Segmentation:
Challenges and Future Directions [66.40971096248946]
In this paper, we collect a series of MedISeg tricks for different model implementation phases.
We experimentally explore the effectiveness of these tricks on consistent baselines.
We also open-sourced a strong MedISeg repository, where each component has the advantage of plug-and-play.
arXiv Detail & Related papers (2022-09-21T12:30:05Z) - Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based
Action Recognition [88.34182299496074]
Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage.
We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets.
By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
arXiv Detail & Related papers (2022-07-17T07:05:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.