Saved in:
Bibliographic Details
Main Authors: Zeng, Zixue, Zhao, Xiaoyan, Cartier, Matthew, Yu, Tong, Wang, Jing, Meng, Xin, Sheng, Zhiyu, Satarpour, Maryam, Cormack, John M, Bean, Allison, Nussbaum, Ryan, Maurer, Maya, Landis-Walkenhorst, Emily, Kumbhare, Dinesh, Kim, Kang, Wasan, Ajay, Pu, Jiantao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.17690
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909923276750848
author Zeng, Zixue
Zhao, Xiaoyan
Cartier, Matthew
Yu, Tong
Wang, Jing
Meng, Xin
Sheng, Zhiyu
Satarpour, Maryam
Cormack, John M
Bean, Allison
Nussbaum, Ryan
Maurer, Maya
Landis-Walkenhorst, Emily
Kumbhare, Dinesh
Kim, Kang
Wasan, Ajay
Pu, Jiantao
author_facet Zeng, Zixue
Zhao, Xiaoyan
Cartier, Matthew
Yu, Tong
Wang, Jing
Meng, Xin
Sheng, Zhiyu
Satarpour, Maryam
Cormack, John M
Bean, Allison
Nussbaum, Ryan
Maurer, Maya
Landis-Walkenhorst, Emily
Kumbhare, Dinesh
Kim, Kang
Wasan, Ajay
Pu, Jiantao
contents We introduce a novel segmentation-aware joint training framework called generative reinforcement network (GRN) that integrates segmentation loss feedback to optimize both image generation and segmentation performance in a single stage. An image enhancement technique called segmentation-guided enhancement (SGE) is also developed, where the generator produces images tailored specifically for the segmentation model. Two variants of GRN were also developed, including GRN for sample-efficient learning (GRN-SEL) and GRN for semi-supervised learning (GRN-SSL). GRN's performance was evaluated using a dataset of 69 fully annotated 3D ultrasound scans from 29 subjects. The annotations included six anatomical structures: dermis, superficial fat, superficial fascial membrane (SFM), deep fat, deep fascial membrane (DFM), and muscle. Our results show that GRN-SEL with SGE reduces labeling efforts by up to 70% while achieving a 1.98% improvement in the Dice Similarity Coefficient (DSC) compared to models trained on fully labeled datasets. GRN-SEL alone reduces labeling efforts by 60%, GRN-SSL with SGE decreases labeling requirements by 70%, and GRN-SSL alone by 60%, all while maintaining performance comparable to fully supervised models. These findings suggest the effectiveness of the GRN framework in optimizing segmentation performance with significantly less labeled data, offering a scalable and efficient solution for ultrasound image analysis and reducing the burdens associated with data annotation.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17690
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Segmentation-Aware Generative Reinforcement Network (GRN) for Tissue Layer Segmentation in 3-D Ultrasound Images for Chronic Low-back Pain (cLBP) Assessment
Zeng, Zixue
Zhao, Xiaoyan
Cartier, Matthew
Yu, Tong
Wang, Jing
Meng, Xin
Sheng, Zhiyu
Satarpour, Maryam
Cormack, John M
Bean, Allison
Nussbaum, Ryan
Maurer, Maya
Landis-Walkenhorst, Emily
Kumbhare, Dinesh
Kim, Kang
Wasan, Ajay
Pu, Jiantao
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We introduce a novel segmentation-aware joint training framework called generative reinforcement network (GRN) that integrates segmentation loss feedback to optimize both image generation and segmentation performance in a single stage. An image enhancement technique called segmentation-guided enhancement (SGE) is also developed, where the generator produces images tailored specifically for the segmentation model. Two variants of GRN were also developed, including GRN for sample-efficient learning (GRN-SEL) and GRN for semi-supervised learning (GRN-SSL). GRN's performance was evaluated using a dataset of 69 fully annotated 3D ultrasound scans from 29 subjects. The annotations included six anatomical structures: dermis, superficial fat, superficial fascial membrane (SFM), deep fat, deep fascial membrane (DFM), and muscle. Our results show that GRN-SEL with SGE reduces labeling efforts by up to 70% while achieving a 1.98% improvement in the Dice Similarity Coefficient (DSC) compared to models trained on fully labeled datasets. GRN-SEL alone reduces labeling efforts by 60%, GRN-SSL with SGE decreases labeling requirements by 70%, and GRN-SSL alone by 60%, all while maintaining performance comparable to fully supervised models. These findings suggest the effectiveness of the GRN framework in optimizing segmentation performance with significantly less labeled data, offering a scalable and efficient solution for ultrasound image analysis and reducing the burdens associated with data annotation.
title Segmentation-Aware Generative Reinforcement Network (GRN) for Tissue Layer Segmentation in 3-D Ultrasound Images for Chronic Low-back Pain (cLBP) Assessment
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2501.17690