Abstract
Introduction: This study introduces SkinLiTE, a lightweight supervised contrastive learning model tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the challenge of complexities and imbalances inherent in skin lesion datasets.
Methods: The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions.
Results: SkinLiTE demonstrated superior performance across various metrics, including accuracy, AUC, and F1 scores, particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities.
Conclusion: This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.
Keywords: Skin lesions, Dermoscopic images, Supervised contrastive learning, Skin disease classification, Skin condition, AI.
Call for Papers in Thematic Issues
Deep Learning Approaches for Image Enhancement in Medical Diagnostics
The medical and healthcare sectors are very different from one another. Consumers in these sectors need more affordable, superior offerings. Health or medical specialists are typically the ones who analyse medical data. In particular, medical imaging evaluation heavily relies on machine learning and deep learning. They not only yield outstanding ...read more
Emerging Biomedical Imaging Informatic for Smart Healthcare
Biomedical imaging informatics is a field that deals with the acquisition, processing, and interpretation of images in biomedicine using computational approaches. Biomedical imaging has progressed from early, simple X-rays for fracture diagnosis and foreign body identification to various techniques used to research biological structure and function and answer fundamental biomedical ...read more
Emerging Trends & Techniques in Medical Imaging using Machine Learning and Deep Learning Techniques
This special issue will aim to discuss different approaches, initiatives and applications in Medical Imaging fields (including Machine Intelligence, Mining Engineering, Modeling and Simulation, Computer, Communication, Networking and Information Engineering, Systems Engineering, Innovative Computing Systems, Adaptive Technologies for Sustainable Growth, and Theoretical and Applied Sciences). This collection should inspire various ...read more
Multimodal Imaging Using Spectroscopic Techniques for Improved Surgical Guidance
The majority of patients with solid malignancies have surgical excision as their primary and most successful method of medical care. On the other hand, patients experience recurrence and subsequent recurrence. Their objective was to provide a simpler and more concise explanation of the obstacles faced by physicians and the ways ...read more
10