Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation

Automatic segmentation of skin lesions from dermoscopy images is crucial for the early diagnosis and treatment of skin cancer. However, this task presents significant challenges, including complex lesion shapes, indistinct boundaries, and variations in size and color. This study aims to enhance segm...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuwan Feng, Xiaowei Chen, Shengzhi Li
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10759664/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258303411552256
author Shuwan Feng
Xiaowei Chen
Shengzhi Li
author_facet Shuwan Feng
Xiaowei Chen
Shengzhi Li
author_sort Shuwan Feng
collection DOAJ
description Automatic segmentation of skin lesions from dermoscopy images is crucial for the early diagnosis and treatment of skin cancer. However, this task presents significant challenges, including complex lesion shapes, indistinct boundaries, and variations in size and color. This study aims to enhance segmentation accuracy and robustness by integrating the Wavelet Guided Visual State Space (WGVSS) Block and Resampling Semantic Information Fusion (RSIF) into the segmentation process. Our proposed framework incorporates the WGVSS Block and RSIF within a U-shaped architecture specifically designed for skin lesion segmentation. The WGVSS Block addresses the challenge of effectively capturing multi-scale features, which are essential for accurately delineating irregular lesion boundaries. By employing discrete wavelet transform, this module decomposes features into low and high-frequency components. It utilizes selective scanning to learn frequency and spatial features that guide the extraction of relevant characteristics from the original image, thereby improving feature representation and enhancing the model’s ability to distinguish complex lesion shapes. On the other hand, RSIF tackles the issue of information loss that often occurs during the upsampling process, which can result in blurred or missing fine-grained details critical for accurate segmentation. By employing Resample Patch Resize, RSIF selectively preserves important features, ensuring that crucial details are maintained. This approach effectively mitigates the loss of resolution that typically occurs in conventional upsampling methods, thereby improving segmentation accuracy. Experimental validation on diverse medical datasets demonstrates that our approach significantly outperforms existing methods, such as VMUNet, H-vmunet and VMUNetv2, on the ISIC2017, ISIC2018, and PH2 datasets. The proposed architecture effectively addresses the challenges posed by irregular lesion shapes, varied sizes, and blurred boundaries, resulting in superior segmentation accuracy and robustness.
format Article
id doaj-art-478ba05869ad45cfb139e730d2b52dff
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-478ba05869ad45cfb139e730d2b52dff2025-08-20T01:56:13ZengIEEEIEEE Access2169-35362024-01-011218152118153210.1109/ACCESS.2024.350429710759664Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion SegmentationShuwan Feng0https://orcid.org/0009-0000-6994-0111Xiaowei Chen1Shengzhi Li2https://orcid.org/0009-0008-5320-8792School of Information, University of Michigan, Ann Arbor, MI, USAThe First Affiliated Hospital of China Medical University, Shenyang, ChinaAI Research of TIFIN, Mountain View, CA, USAAutomatic segmentation of skin lesions from dermoscopy images is crucial for the early diagnosis and treatment of skin cancer. However, this task presents significant challenges, including complex lesion shapes, indistinct boundaries, and variations in size and color. This study aims to enhance segmentation accuracy and robustness by integrating the Wavelet Guided Visual State Space (WGVSS) Block and Resampling Semantic Information Fusion (RSIF) into the segmentation process. Our proposed framework incorporates the WGVSS Block and RSIF within a U-shaped architecture specifically designed for skin lesion segmentation. The WGVSS Block addresses the challenge of effectively capturing multi-scale features, which are essential for accurately delineating irregular lesion boundaries. By employing discrete wavelet transform, this module decomposes features into low and high-frequency components. It utilizes selective scanning to learn frequency and spatial features that guide the extraction of relevant characteristics from the original image, thereby improving feature representation and enhancing the model’s ability to distinguish complex lesion shapes. On the other hand, RSIF tackles the issue of information loss that often occurs during the upsampling process, which can result in blurred or missing fine-grained details critical for accurate segmentation. By employing Resample Patch Resize, RSIF selectively preserves important features, ensuring that crucial details are maintained. This approach effectively mitigates the loss of resolution that typically occurs in conventional upsampling methods, thereby improving segmentation accuracy. Experimental validation on diverse medical datasets demonstrates that our approach significantly outperforms existing methods, such as VMUNet, H-vmunet and VMUNetv2, on the ISIC2017, ISIC2018, and PH2 datasets. The proposed architecture effectively addresses the challenges posed by irregular lesion shapes, varied sizes, and blurred boundaries, resulting in superior segmentation accuracy and robustness.https://ieeexplore.ieee.org/document/10759664/Medical image segmentationstate space modelwavelet transformresampling
spellingShingle Shuwan Feng
Xiaowei Chen
Shengzhi Li
Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation
IEEE Access
Medical image segmentation
state space model
wavelet transform
resampling
title Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation
title_full Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation
title_fullStr Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation
title_full_unstemmed Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation
title_short Wavelet Guided Visual State Space Model and Patch Resampling Enhanced U-Shaped Structure for Skin Lesion Segmentation
title_sort wavelet guided visual state space model and patch resampling enhanced u shaped structure for skin lesion segmentation
topic Medical image segmentation
state space model
wavelet transform
resampling
url https://ieeexplore.ieee.org/document/10759664/
work_keys_str_mv AT shuwanfeng waveletguidedvisualstatespacemodelandpatchresamplingenhancedushapedstructureforskinlesionsegmentation
AT xiaoweichen waveletguidedvisualstatespacemodelandpatchresamplingenhancedushapedstructureforskinlesionsegmentation
AT shengzhili waveletguidedvisualstatespacemodelandpatchresamplingenhancedushapedstructureforskinlesionsegmentation