Few-Shot Medical Image Segmentation with Large Kernel Attention

Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image segmentation. To address this issue, few-shot segmentation method...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Xiaoxiao, Chen, Xiaowei, Gao, Zhenguo, Qu, Shulei, Qiu, Yuanyuan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Wu, Xiaoxiao
Chen, Xiaowei
Gao, Zhenguo
Qu, Shulei
Qiu, Yuanyuan
description Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image segmentation. To address this issue, few-shot segmentation methods based on meta-learning have been employed. Presently, the methods primarily focus on aligning the support set and query set to enhance performance, but this approach hinders further improvement of the model's effectiveness. In this paper, our objective is to propose a few-shot medical segmentation model that acquire comprehensive feature representation capabilities, which will boost segmentation accuracy by capturing both local and long-range features. To achieve this, we introduce a plug-and-play attention module that dynamically enhances both query and support features, thereby improving the representativeness of the extracted features. Our model comprises four key modules: a dual-path feature extractor, an attention module, an adaptive prototype prediction module, and a multi-scale prediction fusion module. Specifically, the dual-path feature extractor acquires multi-scale features by obtaining features of 32{\times}32 size and 64{\times}64 size. The attention module follows the feature extractor and captures local and long-range information. The adaptive prototype prediction module automatically adjusts the anomaly score threshold to predict prototypes, while the multi-scale fusion prediction module integrates prediction masks of various scales to produce the final segmentation result. We conducted experiments on publicly available MRI datasets, namely CHAOS and CMR, and compared our method with other advanced techniques. The results demonstrate that our method achieves state-of-the-art performance.
doi_str_mv 10.48550/arxiv.2407.19148
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_19148</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_19148</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_191483</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zO0NDSx4GSwd0st1w3OyC9R8E1NyUxOzFHwzE1MT1UITk3PTc0rSSzJzM9TKM8syVDwSSwCinunFuWl5ig4lpQAZYFyPAysaYk5xam8UJqbQd7NNcTZQxdsVXxBUWZuYlFlPMjKeLCVxoRVAAB1fTXq</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Few-Shot Medical Image Segmentation with Large Kernel Attention</title><source>arXiv.org</source><creator>Wu, Xiaoxiao ; Chen, Xiaowei ; Gao, Zhenguo ; Qu, Shulei ; Qiu, Yuanyuan</creator><creatorcontrib>Wu, Xiaoxiao ; Chen, Xiaowei ; Gao, Zhenguo ; Qu, Shulei ; Qiu, Yuanyuan</creatorcontrib><description>Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image segmentation. To address this issue, few-shot segmentation methods based on meta-learning have been employed. Presently, the methods primarily focus on aligning the support set and query set to enhance performance, but this approach hinders further improvement of the model's effectiveness. In this paper, our objective is to propose a few-shot medical segmentation model that acquire comprehensive feature representation capabilities, which will boost segmentation accuracy by capturing both local and long-range features. To achieve this, we introduce a plug-and-play attention module that dynamically enhances both query and support features, thereby improving the representativeness of the extracted features. Our model comprises four key modules: a dual-path feature extractor, an attention module, an adaptive prototype prediction module, and a multi-scale prediction fusion module. Specifically, the dual-path feature extractor acquires multi-scale features by obtaining features of 32{\times}32 size and 64{\times}64 size. The attention module follows the feature extractor and captures local and long-range information. The adaptive prototype prediction module automatically adjusts the anomaly score threshold to predict prototypes, while the multi-scale fusion prediction module integrates prediction masks of various scales to produce the final segmentation result. We conducted experiments on publicly available MRI datasets, namely CHAOS and CMR, and compared our method with other advanced techniques. The results demonstrate that our method achieves state-of-the-art performance.</description><identifier>DOI: 10.48550/arxiv.2407.19148</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2024-07</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2407.19148$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.19148$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wu, Xiaoxiao</creatorcontrib><creatorcontrib>Chen, Xiaowei</creatorcontrib><creatorcontrib>Gao, Zhenguo</creatorcontrib><creatorcontrib>Qu, Shulei</creatorcontrib><creatorcontrib>Qiu, Yuanyuan</creatorcontrib><title>Few-Shot Medical Image Segmentation with Large Kernel Attention</title><description>Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image segmentation. To address this issue, few-shot segmentation methods based on meta-learning have been employed. Presently, the methods primarily focus on aligning the support set and query set to enhance performance, but this approach hinders further improvement of the model's effectiveness. In this paper, our objective is to propose a few-shot medical segmentation model that acquire comprehensive feature representation capabilities, which will boost segmentation accuracy by capturing both local and long-range features. To achieve this, we introduce a plug-and-play attention module that dynamically enhances both query and support features, thereby improving the representativeness of the extracted features. Our model comprises four key modules: a dual-path feature extractor, an attention module, an adaptive prototype prediction module, and a multi-scale prediction fusion module. Specifically, the dual-path feature extractor acquires multi-scale features by obtaining features of 32{\times}32 size and 64{\times}64 size. The attention module follows the feature extractor and captures local and long-range information. The adaptive prototype prediction module automatically adjusts the anomaly score threshold to predict prototypes, while the multi-scale fusion prediction module integrates prediction masks of various scales to produce the final segmentation result. We conducted experiments on publicly available MRI datasets, namely CHAOS and CMR, and compared our method with other advanced techniques. The results demonstrate that our method achieves state-of-the-art performance.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zO0NDSx4GSwd0st1w3OyC9R8E1NyUxOzFHwzE1MT1UITk3PTc0rSSzJzM9TKM8syVDwSSwCinunFuWl5ig4lpQAZYFyPAysaYk5xam8UJqbQd7NNcTZQxdsVXxBUWZuYlFlPMjKeLCVxoRVAAB1fTXq</recordid><startdate>20240726</startdate><enddate>20240726</enddate><creator>Wu, Xiaoxiao</creator><creator>Chen, Xiaowei</creator><creator>Gao, Zhenguo</creator><creator>Qu, Shulei</creator><creator>Qiu, Yuanyuan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240726</creationdate><title>Few-Shot Medical Image Segmentation with Large Kernel Attention</title><author>Wu, Xiaoxiao ; Chen, Xiaowei ; Gao, Zhenguo ; Qu, Shulei ; Qiu, Yuanyuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_191483</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Wu, Xiaoxiao</creatorcontrib><creatorcontrib>Chen, Xiaowei</creatorcontrib><creatorcontrib>Gao, Zhenguo</creatorcontrib><creatorcontrib>Qu, Shulei</creatorcontrib><creatorcontrib>Qiu, Yuanyuan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wu, Xiaoxiao</au><au>Chen, Xiaowei</au><au>Gao, Zhenguo</au><au>Qu, Shulei</au><au>Qiu, Yuanyuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Few-Shot Medical Image Segmentation with Large Kernel Attention</atitle><date>2024-07-26</date><risdate>2024</risdate><abstract>Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image segmentation. To address this issue, few-shot segmentation methods based on meta-learning have been employed. Presently, the methods primarily focus on aligning the support set and query set to enhance performance, but this approach hinders further improvement of the model's effectiveness. In this paper, our objective is to propose a few-shot medical segmentation model that acquire comprehensive feature representation capabilities, which will boost segmentation accuracy by capturing both local and long-range features. To achieve this, we introduce a plug-and-play attention module that dynamically enhances both query and support features, thereby improving the representativeness of the extracted features. Our model comprises four key modules: a dual-path feature extractor, an attention module, an adaptive prototype prediction module, and a multi-scale prediction fusion module. Specifically, the dual-path feature extractor acquires multi-scale features by obtaining features of 32{\times}32 size and 64{\times}64 size. The attention module follows the feature extractor and captures local and long-range information. The adaptive prototype prediction module automatically adjusts the anomaly score threshold to predict prototypes, while the multi-scale fusion prediction module integrates prediction masks of various scales to produce the final segmentation result. We conducted experiments on publicly available MRI datasets, namely CHAOS and CMR, and compared our method with other advanced techniques. The results demonstrate that our method achieves state-of-the-art performance.</abstract><doi>10.48550/arxiv.2407.19148</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2407.19148
ispartof
issn
language eng
recordid cdi_arxiv_primary_2407_19148
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Few-Shot Medical Image Segmentation with Large Kernel Attention
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T08%3A45%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Few-Shot%20Medical%20Image%20Segmentation%20with%20Large%20Kernel%20Attention&rft.au=Wu,%20Xiaoxiao&rft.date=2024-07-26&rft_id=info:doi/10.48550/arxiv.2407.19148&rft_dat=%3Carxiv_GOX%3E2407_19148%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true