Cargando…

CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images

Medical image segmentation plays a crucial role in clinical diagnosis, treatment planning, and disease monitoring. The automatic segmentation method based on deep learning has developed rapidly, with segmentation results comparable to clinical experts for large objects, but the segmentation accuracy...

Descripción completa

Detalles Bibliográficos
Autores principales: Cao, Ruifen, Ning, Long, Zhou, Chao, Wei, Pijing, Ding, Yun, Tan, Dayu, Zheng, Chunhou
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10650041/
https://www.ncbi.nlm.nih.gov/pubmed/37960438
http://dx.doi.org/10.3390/s23218739
_version_ 1785135688584265728
author Cao, Ruifen
Ning, Long
Zhou, Chao
Wei, Pijing
Ding, Yun
Tan, Dayu
Zheng, Chunhou
author_facet Cao, Ruifen
Ning, Long
Zhou, Chao
Wei, Pijing
Ding, Yun
Tan, Dayu
Zheng, Chunhou
author_sort Cao, Ruifen
collection PubMed
description Medical image segmentation plays a crucial role in clinical diagnosis, treatment planning, and disease monitoring. The automatic segmentation method based on deep learning has developed rapidly, with segmentation results comparable to clinical experts for large objects, but the segmentation accuracy for small objects is still unsatisfactory. Current segmentation methods based on deep learning find it difficult to extract multiple scale features of medical images, leading to an insufficient detection capability for smaller objects. In this paper, we propose a context feature fusion and attention mechanism based network for small target segmentation in medical images called CFANet. CFANet is based on U-Net structure, including the encoder and the decoder, and incorporates two key modules, context feature fusion (CFF) and effective channel spatial attention (ECSA), in order to improve segmentation performance. The CFF module utilizes contextual information from different scales to enhance the representation of small targets. By fusing multi-scale features, the network captures local and global contextual cues, which are critical for accurate segmentation. The ECSA module further enhances the network’s ability to capture long-range dependencies by incorporating attention mechanisms at the spatial and channel levels, which allows the network to focus on information-rich regions while suppressing irrelevant or noisy features. Extensive experiments are conducted on four challenging medical image datasets, namely ADAM, LUNA16, Thoracic OAR, and WORD. Experimental results show that CFANet outperforms state-of-the-art methods in terms of segmentation accuracy and robustness. The proposed method achieves excellent performance in segmenting small targets in medical images, demonstrating its potential in various clinical applications.
format Online
Article
Text
id pubmed-10650041
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106500412023-10-26 CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images Cao, Ruifen Ning, Long Zhou, Chao Wei, Pijing Ding, Yun Tan, Dayu Zheng, Chunhou Sensors (Basel) Article Medical image segmentation plays a crucial role in clinical diagnosis, treatment planning, and disease monitoring. The automatic segmentation method based on deep learning has developed rapidly, with segmentation results comparable to clinical experts for large objects, but the segmentation accuracy for small objects is still unsatisfactory. Current segmentation methods based on deep learning find it difficult to extract multiple scale features of medical images, leading to an insufficient detection capability for smaller objects. In this paper, we propose a context feature fusion and attention mechanism based network for small target segmentation in medical images called CFANet. CFANet is based on U-Net structure, including the encoder and the decoder, and incorporates two key modules, context feature fusion (CFF) and effective channel spatial attention (ECSA), in order to improve segmentation performance. The CFF module utilizes contextual information from different scales to enhance the representation of small targets. By fusing multi-scale features, the network captures local and global contextual cues, which are critical for accurate segmentation. The ECSA module further enhances the network’s ability to capture long-range dependencies by incorporating attention mechanisms at the spatial and channel levels, which allows the network to focus on information-rich regions while suppressing irrelevant or noisy features. Extensive experiments are conducted on four challenging medical image datasets, namely ADAM, LUNA16, Thoracic OAR, and WORD. Experimental results show that CFANet outperforms state-of-the-art methods in terms of segmentation accuracy and robustness. The proposed method achieves excellent performance in segmenting small targets in medical images, demonstrating its potential in various clinical applications. MDPI 2023-10-26 /pmc/articles/PMC10650041/ /pubmed/37960438 http://dx.doi.org/10.3390/s23218739 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cao, Ruifen
Ning, Long
Zhou, Chao
Wei, Pijing
Ding, Yun
Tan, Dayu
Zheng, Chunhou
CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images
title CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images
title_full CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images
title_fullStr CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images
title_full_unstemmed CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images
title_short CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images
title_sort cfanet: context feature fusion and attention mechanism based network for small target segmentation in medical images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10650041/
https://www.ncbi.nlm.nih.gov/pubmed/37960438
http://dx.doi.org/10.3390/s23218739
work_keys_str_mv AT caoruifen cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages
AT ninglong cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages
AT zhouchao cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages
AT weipijing cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages
AT dingyun cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages
AT tandayu cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages
AT zhengchunhou cfanetcontextfeaturefusionandattentionmechanismbasednetworkforsmalltargetsegmentationinmedicalimages