ULFAC-Net: Ultra-Lightweight Fully Asymmetric Convolutional Network for Skin Lesion Segmentation

Segmentation of skin lesions is a critical step in the process of skin lesion diagnosis. Such segmentation is challenging due to the irregular shape, fuzzy contours and severe noise interference in the skin lesion region. Existing deep learning-based skin lesion segmentation methods are usually comp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of biomedical and health informatics Jg. 27; H. 6; S. 2886 - 2897
Hauptverfasser: Ma, Yuliang, Wu, Liping, Gao, Yunyuan, Gao, Farong, Zhang, Jianhai, Luo, Zhizeng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.06.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Asymmetric codec
asymmetric convolution
Asymmetry
Coders
Convolution
Convolutional codes
Datasets
Deep learning
Encoders-Decoders
Feature extraction
Floating point arithmetic
Lesions
Lightweight
lightweight segmentation
Modules
Parameters
Picture archiving and communication systems
Segmentation
Skin
Skin diseases
skin lesion segmentation
Skin lesions
Training
ISSN:2168-2194, 2168-2208, 2168-2208
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Segmentation of skin lesions is a critical step in the process of skin lesion diagnosis. Such segmentation is challenging due to the irregular shape, fuzzy contours and severe noise interference in the skin lesion region. Existing deep learning-based skin lesion segmentation methods are usually computationally expensive, hindering their deployment in dermoscopic devices with poor computational power. To address these challenges, we propose an ultralightweight fully asymmetric convolutional network for skin lesion segmentation, called ULFAC-Net. we use a parallel asymmetric convolutional (PAC) module to extract features instead of the traditional square convolution, and innovatively propose a PAC module with dual attention (Att-PAC) to enhance the feature representation. Based on the PAC and Att-PAC modules, we further propose a lightweight textual information submodule. To balance the number of parameters and performance of the model, we also hand-design an asymmetric encoder-decoder architecture. In this paper, we validate the effectiveness and robustness of the proposed ULFAC-Net on four publicly available skin lesion segmentation datasets (ISIC2018, ISBI2017, ISIC2016 and PH2 datasets). The experimental results show that ULFAC-Net achieves competitive segmentation performance with only 0.842 million(0.842M) parameters and 3.71 gigabytes of floating point operations (GFLOPs) compared to other state-of-the-art methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2168-2194
2168-2208
2168-2208
DOI:10.1109/JBHI.2023.3259802