A Deep Multi-task Learning Approach to Skin Lesion Classification

2018/12/09 by Haofu Liao, Jiebo Luo, Liao, Haofu +1 · 3 citations
Computer Science · Engineering · Medicine · #AI in cancer detection #Artificial intelligence #Computer science #Context (archaeology) #Cutaneous Melanoma Detection and Management #Deep learning #Dermatological and COVID-19 studies #Engineering #Exploit #Identification (biology) #Lesion #Machine learning #Medicine #Pathology #Pattern recognition (psychology) #Skin lesion #Task (project management) #cs.CV

paper · pdf · doi:10.48550/arxiv.1812.03527

published in arXiv (Cornell University) (Cornell University) · AAAI 2017 Joint Workshop on Health Intelligence W3PHIAI 2017 (W3PHI & HIAI), San Francisco, CA, 2017

openalex publication_date 2018/12/09 · arxiv created 2022/03/23 · arxiv updated 2022/03/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

Skin lesion identification is a key step toward dermatological diagnosis. When describing a skin lesion, it is very important to note its body site distribution as many skin diseases commonly affect particular parts of the body. To exploit the correlation between skin lesions and their body site distributions, in this study, we investigate the possibility of improving skin lesion classification using the additional context information provided by body location. Specifically, we build a deep multi-task learning (MTL) framework to jointly optimize skin lesion classification and body location classification (the latter is used as an inductive bias). Our MTL framework uses the state-of-the-art ImageNet pretrained model with specialized loss functions for the two related tasks. Our experiments show that the proposed MTL based method performs more robustly than its standalone (single-task) counterpart.

Citations

• ImageNet classification with deep convolutional neural networks

Cited by

• Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification

Related

• A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification
• Optimizing Skin Lesion Classification via Multimodal Data and Auxiliary Task Integration
• Improved skin lesion recognition by a Self-Supervised Curricular Deep Learning approach
• Skin Lesion Classification Using Deep Multi-scale Convolutional Neural Networks
• A Dense CNN approach for skin lesion classification