Saved in:
Bibliographic Details
Main Authors: Shi, Ruohua, Pang, Qiufan, Ma, Lei, Duan, Lingyu, Huang, Tiejun, Jiang, Tingting
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.14114
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914923891654656
author Shi, Ruohua
Pang, Qiufan
Ma, Lei
Duan, Lingyu
Huang, Tiejun
Jiang, Tingting
author_facet Shi, Ruohua
Pang, Qiufan
Ma, Lei
Duan, Lingyu
Huang, Tiejun
Jiang, Tingting
contents Electron microscopy (EM) imaging offers unparalleled resolution for analyzing neural tissues, crucial for uncovering the intricacies of synaptic connections and neural processes fundamental to understanding behavioral mechanisms. Recently, the foundation models have demonstrated impressive performance across numerous natural and medical image segmentation tasks. However, applying these foundation models to EM segmentation faces significant challenges due to domain disparities. This paper presents ShapeMamba-EM, a specialized fine-tuning method for 3D EM segmentation, which employs adapters for long-range dependency modeling and an encoder for local shape description within the original foundation model. This approach effectively addresses the unique volumetric and morphological complexities of EM data. Tested over a wide range of EM images, covering five segmentation tasks and 10 datasets, ShapeMamba-EM outperforms existing methods, establishing a new standard in EM image segmentation and enhancing the understanding of neural tissue architecture.
format Preprint
id arxiv_https___arxiv_org_abs_2408_14114
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation
Shi, Ruohua
Pang, Qiufan
Ma, Lei
Duan, Lingyu
Huang, Tiejun
Jiang, Tingting
Computer Vision and Pattern Recognition
Electron microscopy (EM) imaging offers unparalleled resolution for analyzing neural tissues, crucial for uncovering the intricacies of synaptic connections and neural processes fundamental to understanding behavioral mechanisms. Recently, the foundation models have demonstrated impressive performance across numerous natural and medical image segmentation tasks. However, applying these foundation models to EM segmentation faces significant challenges due to domain disparities. This paper presents ShapeMamba-EM, a specialized fine-tuning method for 3D EM segmentation, which employs adapters for long-range dependency modeling and an encoder for local shape description within the original foundation model. This approach effectively addresses the unique volumetric and morphological complexities of EM data. Tested over a wide range of EM images, covering five segmentation tasks and 10 datasets, ShapeMamba-EM outperforms existing methods, establishing a new standard in EM image segmentation and enhancing the understanding of neural tissue architecture.
title ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.14114