Cargando…
Medical Image Segmentation with Learning Semantic and Global Contextual Representation
Automatic medical image segmentation is an essential step toward accurate diseases diagnosis and designing a follow-up treatment. This assistive method facilitates the cancer detection process and provides a benchmark to highlight the affected area. The U-Net model has become the standard design cho...
Autor principal: | |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9319384/ https://www.ncbi.nlm.nih.gov/pubmed/35885454 http://dx.doi.org/10.3390/diagnostics12071548 |
_version_ | 1784755535991537664 |
---|---|
author | Alahmadi, Mohammad D. |
author_facet | Alahmadi, Mohammad D. |
author_sort | Alahmadi, Mohammad D. |
collection | PubMed |
description | Automatic medical image segmentation is an essential step toward accurate diseases diagnosis and designing a follow-up treatment. This assistive method facilitates the cancer detection process and provides a benchmark to highlight the affected area. The U-Net model has become the standard design choice. Although the symmetrical structure of the U-Net model enables this network to encode rich semantic representation, the intrinsic locality of the CNN layers limits this network’s capability in modeling long-range contextual dependency. On the other hand, sequence to sequence Transformer models with a multi-head attention mechanism can enable them to effectively model global contextual dependency. However, the lack of low-level information stemming from the Transformer architecture limits its performance for capturing local representation. In this paper, we propose a two parallel encoder model, where in the first path the CNN module captures the local semantic representation whereas the second path deploys a Transformer module to extract the long-range contextual representation. Next, by adaptively fusing these two feature maps, we encode both representations into a single representative tensor to be further processed by the decoder block. An experimental study demonstrates that our design can provide rich and generic representation features which are highly efficient for a fine-grained semantic segmentation task. |
format | Online Article Text |
id | pubmed-9319384 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93193842022-07-27 Medical Image Segmentation with Learning Semantic and Global Contextual Representation Alahmadi, Mohammad D. Diagnostics (Basel) Article Automatic medical image segmentation is an essential step toward accurate diseases diagnosis and designing a follow-up treatment. This assistive method facilitates the cancer detection process and provides a benchmark to highlight the affected area. The U-Net model has become the standard design choice. Although the symmetrical structure of the U-Net model enables this network to encode rich semantic representation, the intrinsic locality of the CNN layers limits this network’s capability in modeling long-range contextual dependency. On the other hand, sequence to sequence Transformer models with a multi-head attention mechanism can enable them to effectively model global contextual dependency. However, the lack of low-level information stemming from the Transformer architecture limits its performance for capturing local representation. In this paper, we propose a two parallel encoder model, where in the first path the CNN module captures the local semantic representation whereas the second path deploys a Transformer module to extract the long-range contextual representation. Next, by adaptively fusing these two feature maps, we encode both representations into a single representative tensor to be further processed by the decoder block. An experimental study demonstrates that our design can provide rich and generic representation features which are highly efficient for a fine-grained semantic segmentation task. MDPI 2022-06-25 /pmc/articles/PMC9319384/ /pubmed/35885454 http://dx.doi.org/10.3390/diagnostics12071548 Text en © 2022 by the author. 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 Alahmadi, Mohammad D. Medical Image Segmentation with Learning Semantic and Global Contextual Representation |
title | Medical Image Segmentation with Learning Semantic and Global Contextual Representation |
title_full | Medical Image Segmentation with Learning Semantic and Global Contextual Representation |
title_fullStr | Medical Image Segmentation with Learning Semantic and Global Contextual Representation |
title_full_unstemmed | Medical Image Segmentation with Learning Semantic and Global Contextual Representation |
title_short | Medical Image Segmentation with Learning Semantic and Global Contextual Representation |
title_sort | medical image segmentation with learning semantic and global contextual representation |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9319384/ https://www.ncbi.nlm.nih.gov/pubmed/35885454 http://dx.doi.org/10.3390/diagnostics12071548 |
work_keys_str_mv | AT alahmadimohammadd medicalimagesegmentationwithlearningsemanticandglobalcontextualrepresentation |