A Unified Multi-Task Learning Model with Joint Reverse Optimization for Simultaneous Skin Lesion Segmentation and Diagnosis
Bioengineering · 20.11.2024 · 11 (11) · 1173
DOI: 10.3390/bioengineering11111173 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 20.11.2024. Verfasst von Mohammed A Al-Masni und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence and Data Science, College of AI Convergence, Sejong University, Seoul 05006, Republic of Korea. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korean government (MSIT), National Research Foundation of Korea (NRF), University of Southampton Malaysia (UoSM).
Abstract (Originalsprache)
Classifying and segmenting skin cancer represent pivotal objectives for automated diagnostic systems that utilize dermoscopy images. However, these tasks present significant challenges due to the diverse shape variations of skin lesions and the inherently fuzzy nature of dermoscopy images, including low contrast and the presence of artifacts. Given the robust correlation between the classification of skin lesions and their segmentation, we propose that employing a combined learning method holds the promise of considerably enhancing the performance of both tasks. In this paper, we present a unified multi-task learning strategy that concurrently classifies abnormalities of skin lesions and allows for the joint segmentation of lesion boundaries. This approach integrates an optimization technique known as joint reverse learning, which fosters mutual enhancement through extracting shared features and limiting task dominance across the two tasks. The effectiveness of the proposed method was assessed using two publicly available datasets, ISIC 2016 and PH2, which included melanoma and benign skin cancers. In contrast to the single-task learning strategy, which solely focuses on either classification or segmentation, the experimental findings demonstrated that the proposed network improves the diagnostic capability of skin tumor screening and analysis. The proposed method achieves a significant segmentation performance on skin lesion boundaries, with Dice Similarity Coefficients (DSC) of 89.48% and 88.81% on the ISIC 2016 and PH2 datasets, respectively. Additionally, our multi-task learning approach enhances classification, increasing the F1 score from 78.26% (baseline ResNet50) to 82.07% on ISIC 2016 and from 82.38% to 85.50% on PH2. This work showcases its potential applicability across varied clinical scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Artificial Intelligence and Data Science, College of AI Convergence, Sejong University, Seoul 05006, Republic of Korea.
- School of Computer Science, University of Southampton Malaysia, Iskandar Puteri 79100, Johor, Malaysia.
ORCID-Profile: Mohammed A Al-Masni, Dildar Hussain, Yeong Hyeon Gu
Förderung
- Korean government (MSIT)
- National Research Foundation of Korea (NRF)
- University of Southampton Malaysia (UoSM)
- Institute of Information & communications Technology Planning & Evaluation (IITP)
Zitieren
APA
Al-Masni, M. A., Al-Shamiri, A. K., Hussain, D., & Gu, Y. H. (2024). A Unified Multi-Task Learning Model with Joint Reverse Optimization for Simultaneous Skin Lesion Segmentation and Diagnosis. Bioengineering, 11(11), 1173. https://doi.org/10.3390/bioengineering11111173
Vancouver
Al-Masni MA, Al-Shamiri AK, Hussain D, Gu YH. A Unified Multi-Task Learning Model with Joint Reverse Optimization for Simultaneous Skin Lesion Segmentation and Diagnosis. Bioengineering. 2024;11(11):1173. doi:10.3390/bioengineering11111173
BibTeX
@article{AlMasni2024,
author = {Al-Masni, Mohammed A and Al-Shamiri, Abobakr Khalil and Hussain, Dildar and Gu, Yeong Hyeon},
title = {A Unified Multi-Task Learning Model with Joint Reverse Optimization for Simultaneous Skin Lesion Segmentation and Diagnosis},
journal = {Bioengineering},
year = {2024},
volume = {11},
number = {11},
pages = {1173},
doi = {10.3390/bioengineering11111173}
}
EUVIMED