Rethinking the Encoder–decoder Structure in Medical Image Segmentation from Releasing Decoder Structure

Medical image segmentation has witnessed rapid advancements with the emergence of encoder–decoder based methods. In the encoder–decoder structure, the primary goal of the decoding phase is not only to restore feature map resolution, but also to mitigate the loss of feature information incurred durin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of bionics engineering Ročník 21; číslo 3; s. 1511 - 1521
Hlavní autoři: Ni, Jiajia, Mu, Wei, Pan, An, Chen, Zhengming
Médium: Journal Article
Jazyk:angličtina
Vydáno: Singapore Springer Nature Singapore 01.05.2024
Springer Nature B.V
Témata:
Artificial Intelligence
Biochemical Engineering
Bioinformatics
Biomaterials
Biomedical Engineering and Bioengineering
Biomedical Engineering/Biotechnology
Coders
Coding
Datasets
Decoding
Engineering
Feature maps
Image processing
Image segmentation
Medical imaging
Modules
Receptive field
Recovery
Research Article
Attention mechanisms
Encoder–decoder architecture
Releasing decoder architecture
Neural network
Medical image segmentation
ISSN:1672-6529, 2543-2141
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Medical image segmentation has witnessed rapid advancements with the emergence of encoder–decoder based methods. In the encoder–decoder structure, the primary goal of the decoding phase is not only to restore feature map resolution, but also to mitigate the loss of feature information incurred during the encoding phase. However, this approach gives rise to a challenge: multiple up-sampling operations in the decoder segment result in the loss of feature information. To address this challenge, we propose a novel network that removes the decoding structure to reduce feature information loss (CBL-Net). In particular, we introduce a Parallel Pooling Module (PPM) to counteract the feature information loss stemming from conventional and pooling operations during the encoding stage. Furthermore, we incorporate a Multiplexed Dilation Convolution (MDC) module to expand the network's receptive field. Also, although we have removed the decoding stage, we still need to recover the feature map resolution. Therefore, we introduced the Global Feature Recovery (GFR) module. It uses attention mechanism for the image feature map resolution recovery, which can effectively reduce the loss of feature information. We conduct extensive experimental evaluations on three publicly available medical image segmentation datasets: DRIVE, CHASEDB and MoNuSeg datasets. Experimental results show that our proposed network outperforms state-of-the-art methods in medical image segmentation. In addition, it achieves higher efficiency than the current network of coding and decoding structures by eliminating the decoding component.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1672-6529
2543-2141
DOI:10.1007/s42235-024-00513-7