Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularization
Computer Methods and Programs in Biomedicine · 2023
DOI: 10.1016/j.cmpb.2023.107601 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2023. Verfasst von Chuanbo Qin und 7 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China. Hauptthemen laut MEDLINE: Skin Diseases, Melanoma. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
BACKGROUND AND OBJECTIVE: Melanoma is a highly malignant skin tumor. Accurate segmentation of skin lesions from dermoscopy images is pivotal for computer-aided diagnosis of melanoma. However, blurred lesion boundaries, variable lesion shapes, and other interference factors pose a challenge in this regard. METHODS: This work proposes a novel framework called CFF-Net (Cross Feature Fusion Network) for supervised skin lesion segmentation. The encoder of the network includes dual branches, where the CNNs branch aims to extract rich local features while MLPs branch is used to establish both the global-spatial-dependencies and global-channel-dependencies for precise delineation of skin lesions. Besides, a feature-interaction module between two branches is designed for strengthening the feature representation by allowing dynamic exchange of spatial and channel information, so as to retain more spatial details and inhibit irrelevant noise. Moreover, an auxiliary prediction task is introduced to learn the global geometric information, highlighting the boundary of the skin lesion. RESULTS: Comprehensive experiments using four publicly available skin lesion datasets (i.e., ISIC 2018, ISIC 2017, ISIC 2016, and PH2) indicated that CFF-Net outperformed the state-of-the-art models. In particular, CFF-Net greatly increased the average Jaccard Index score from 79.71% to 81.86% in ISIC 2018, from 78.03% to 80.21% in ISIC 2017, from 82.58% to 85.38% in ISIC 2016, and from 84.18% to 89.71% in PH2 compared with U-Net. Ablation studies demonstrated the effectiveness of each proposed component. Cross-validation experiments in ISIC 2018 and PH2 datasets verified the generalizability of CFF-Net under different skin lesion data distributions. Finally, comparison experiments using three public datasets demonstrated the superior performance of our model. CONCLUSION: The proposed CFF-Net performed well in four public skin lesion datasets, especially for challenging cases with blurred edges of skin lesions and low contrast between skin lesions and background. CFF-Net can be employed for other segmentation tasks with better prediction and more accurate delineation of boundaries.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China.
- Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China. Electronic address: zengjunying@126.com.
- Departimento di Information, Università degli Studi di Milano, 20133 Milano, Italy.
Zitieren
APA
Qin, C., Zheng, B., Zeng, J., Chen, Z., Zhai, Y., Genovese, A., Piuri, V., & Scotti, F. (2023). Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularization. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2023.107601
Vancouver
Qin C, Zheng B, Zeng J, Chen Z, Zhai Y, Genovese A, et al. Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularization. Computer Methods and Programs in Biomedicine. 2023. doi:10.1016/j.cmpb.2023.107601
BibTeX
@article{Qin2023,
author = {Qin, Chuanbo and Zheng, Bin and Zeng, Junying and Chen, Zhuyuan and Zhai, Yikui and Genovese, Angelo and Piuri, Vincenzo and Scotti, Fabio},
title = {Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularization},
journal = {Computer Methods and Programs in Biomedicine},
year = {2023},
doi = {10.1016/j.cmpb.2023.107601}
}
EUVIMED