Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yuwen, Yildiz, Zafer, Li, Qihang, Chen, Yaqian, Dong, Haoyu, Gu, Hanxue, Konz, Nicholas, Mazurowski, Maciej A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911245118996480
author Chen, Yuwen
Yildiz, Zafer
Li, Qihang
Chen, Yaqian
Dong, Haoyu
Gu, Hanxue
Konz, Nicholas
Mazurowski, Maciej A.
author_facet Chen, Yuwen
Yildiz, Zafer
Li, Qihang
Chen, Yaqian
Dong, Haoyu
Gu, Hanxue
Konz, Nicholas
Mazurowski, Maciej A.
contents Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation, such as Segment Anything Model 2 (SAM 2), offer a potential opportunity to significantly speed up the annotation process by manually annotating one or a few slices and then propagating target masks across the entire volume. However, the performance of SAM 2 in this context varies. Our experiments show that relying on a single memory bank and attention module is prone to error propagation, particularly at boundary regions where the target is present in the previous slice but absent in the current one. To address this problem, we propose Short-Long Memory SAM 2 (SLM-SAM 2), a novel architecture that integrates distinct short-term and long-term memory banks with separate attention modules to improve segmentation accuracy. We evaluate SLM-SAM 2 on four public datasets covering organs, bones, and muscles across MRI, CT, and ultrasound videos. We show that the proposed method markedly outperforms the default SAM 2, achieving an average Dice Similarity Coefficient improvement of 0.14 and 0.10 in the scenarios when 5 volumes and 1 volume are available for the initial adaptation, respectively. SLM-SAM 2 also exhibits stronger resistance to over-propagation, reducing the time required to correct propagated masks by 60.575% per volume compared to SAM 2, making a notable step toward more accurate automated annotation of medical images for segmentation model development.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
Chen, Yuwen
Yildiz, Zafer
Li, Qihang
Chen, Yaqian
Dong, Haoyu
Gu, Hanxue
Konz, Nicholas
Mazurowski, Maciej A.
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation, such as Segment Anything Model 2 (SAM 2), offer a potential opportunity to significantly speed up the annotation process by manually annotating one or a few slices and then propagating target masks across the entire volume. However, the performance of SAM 2 in this context varies. Our experiments show that relying on a single memory bank and attention module is prone to error propagation, particularly at boundary regions where the target is present in the previous slice but absent in the current one. To address this problem, we propose Short-Long Memory SAM 2 (SLM-SAM 2), a novel architecture that integrates distinct short-term and long-term memory banks with separate attention modules to improve segmentation accuracy. We evaluate SLM-SAM 2 on four public datasets covering organs, bones, and muscles across MRI, CT, and ultrasound videos. We show that the proposed method markedly outperforms the default SAM 2, achieving an average Dice Similarity Coefficient improvement of 0.14 and 0.10 in the scenarios when 5 volumes and 1 volume are available for the initial adaptation, respectively. SLM-SAM 2 also exhibits stronger resistance to over-propagation, reducing the time required to correct propagated masks by 60.575% per volume compared to SAM 2, making a notable step toward more accurate automated annotation of medical images for segmentation model development.
title Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.01854