SAM-I2I: Unleash the Power of Segment Anything Model for Medical Image Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huo, Jiayu, Ourselin, Sebastien, Sparks, Rachel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909396280279040
author Huo, Jiayu
Ourselin, Sebastien
Sparks, Rachel
author_facet Huo, Jiayu
Ourselin, Sebastien
Sparks, Rachel
contents Medical image translation is crucial for reducing the need for redundant and expensive multi-modal imaging in clinical field. However, current approaches based on Convolutional Neural Networks (CNNs) and Transformers often fail to capture fine-grain semantic features, resulting in suboptimal image quality. To address this challenge, we propose SAM-I2I, a novel image-to-image translation framework based on the Segment Anything Model 2 (SAM2). SAM-I2I utilizes a pre-trained image encoder to extract multiscale semantic features from the source image and a decoder, based on the mask unit attention module, to synthesize target modality images. Our experiments on multi-contrast MRI datasets demonstrate that SAM-I2I outperforms state-of-the-art methods, offering more efficient and accurate medical image translation.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12755
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAM-I2I: Unleash the Power of Segment Anything Model for Medical Image Translation
Huo, Jiayu
Ourselin, Sebastien
Sparks, Rachel
Image and Video Processing
Computer Vision and Pattern Recognition
Medical image translation is crucial for reducing the need for redundant and expensive multi-modal imaging in clinical field. However, current approaches based on Convolutional Neural Networks (CNNs) and Transformers often fail to capture fine-grain semantic features, resulting in suboptimal image quality. To address this challenge, we propose SAM-I2I, a novel image-to-image translation framework based on the Segment Anything Model 2 (SAM2). SAM-I2I utilizes a pre-trained image encoder to extract multiscale semantic features from the source image and a decoder, based on the mask unit attention module, to synthesize target modality images. Our experiments on multi-contrast MRI datasets demonstrate that SAM-I2I outperforms state-of-the-art methods, offering more efficient and accurate medical image translation.
title SAM-I2I: Unleash the Power of Segment Anything Model for Medical Image Translation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.12755