HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation
Sensors · 2023
DOI: 10.3390/s23063067 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Sen Yang und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China. Hauptthemen laut MEDLINE: Electric Power Supplies, Skin Diseases. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation of China, Scientific and technological innovation 2030 major project.
Abstract (Originalsprache)
At present, convolutional neural networks (CNNs) have been widely applied to the task of skin disease image segmentation due to the fact of their powerful information discrimination abilities and have achieved good results. However, it is difficult for CNNs to capture the connection between long-range contexts when extracting deep semantic features of lesion images, and the resulting semantic gap leads to the problem of segmentation blur in skin lesion image segmentation. In order to solve the above problems, we designed a hybrid encoder network based on transformer and fully connected neural network (MLP) architecture, and we call this approach HMT-Net. In the HMT-Net network, we use the attention mechanism of the CTrans module to learn the global relevance of the feature map to improve the network’s ability to understand the overall foreground information of the lesion. On the other hand, we use the TokMLP module to effectively enhance the network’s ability to learn the boundary features of lesion images. In the TokMLP module, the tokenized MLP axial displacement operation strengthens the connection between pixels to facilitate the extraction of local feature information by our network. In order to verify the superiority of our network in segmentation tasks, we conducted extensive experiments on the proposed HMT-Net network and several newly proposed Transformer and MLP networks on three public datasets (ISIC2018, ISBI2017, and ISBI2016) and obtained the following results. Our method achieves 82.39%, 75.53%, and 83.98% on the Dice index and 89.35%, 84.93%, and 91.33% on the IOU. Compared with the latest skin disease segmentation network, FAC-Net, our method improves the Dice index by 1.99%, 1.68%, and 1.6%, respectively. In addition, the IOU indicators have increased by 0.45%, 2.36%, and 1.13%, respectively. The experimental results show that our designed HMT-Net achieves state-of-the-art performance superior to other segmentation methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
ORCID-Profile: Liejun Wang
Förderung
- National Science Foundation of China
- Scientific and technological innovation 2030 major project
Zitieren
APA
Yang, S., & Wang, L. (2023). HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation. Sensors. https://doi.org/10.3390/s23063067
Vancouver
Yang S, Wang L. HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation. Sensors. 2023. doi:10.3390/s23063067
BibTeX
@article{Yang2023,
author = {Yang, Sen and Wang, Liejun},
title = {HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23063067}
}
EUVIMED