Out-of-Distribution Detection for Skin Lesion Images with Deep Isolation Forest
This addresses the problem of identifying unseen skin diseases for medical diagnosis, but it is incremental as it builds on existing isolation forest and deep learning techniques.
The paper tackles out-of-distribution detection in skin lesion images by proposing DeepIF, a non-parametric Isolation Forest method combined with deep convolutional networks, achieving state-of-the-art performance compared to three baseline models.
In this paper, we study the problem of out-of-distribution detection in skin disease images. Publicly available medical datasets normally have a limited number of lesion classes (e.g. HAM10000 has 8 lesion classes). However, there exists a few thousands of clinically identified diseases. Hence, it is important if lesions not in the training data can be differentiated. Toward this goal, we propose DeepIF, a non-parametric Isolation Forest based approach combined with deep convolutional networks. We conduct comprehensive experiments to compare our DeepIF with three baseline models. Results demonstrate state-of-the-art performance of our proposed approach on the task of detecting abnormal skin lesions.