SkiNet: A Deep Learning Solution for Skin Lesion Diagnosis with Uncertainty Estimation and Explainability
This work aims to provide a faster and more trustworthy skin lesion diagnosis solution for medical practitioners, particularly in regions with a shortage of dermatologists, by making AI predictions more transparent.
This paper proposes SkiNet, a deep learning architecture designed to assist in the early screening and diagnosis of skin lesions. It addresses the need for faster diagnostic solutions and interpretability in medical AI by providing uncertainty estimation and explainability for its predictions, though no specific performance numbers are provided in the abstract.
Skin cancer is considered to be the most common human malignancy. Around 5 million new cases of skin cancer are recorded in the United States annually. Early identification and evaluation of skin lesions is of great clinical significance, but the disproportionate dermatologist-patient ratio poses significant problem in most developing nations. Therefore a deep learning based architecture, known as SkiNet, is proposed with an objective to provide faster screening solution and assistance to newly trained physicians in the clinical diagnosis process. The main motive behind Skinet's design and development is to provide a white box solution, addressing a critical problem of trust and interpretability which is crucial for the wider adoption of Computer-aided diagnosis systems by the medical practitioners. SkiNet is a two-stage pipeline wherein the lesion segmentation is followed by the lesion classification. In our SkiNet methodology, Monte Carlo dropout and test time augmentation techniques have been employed to estimate epistemic and aleatoric uncertainty, while saliency-based methods are explored to provide post-hoc explanations of the deep learning models. The publicly available dataset, ISIC-2018, is used to perform experimentation and ablation studies. The results establish the robustness of the model on the traditional benchmarks while addressing the black-box nature of such models to alleviate the skepticism of medical practitioners by incorporating transparency and confidence to the model's prediction.