Efficient Out-of-Distribution Detection of Melanoma with Wavelet-based Normalizing Flows

TL;DR

This paper introduces a wavelet-based normalizing flow approach for out-of-distribution detection of melanoma, improving accuracy and efficiency, which could assist early diagnosis and treatment of skin cancer.

Contribution

It presents a novel wavelet-enhanced normalizing flow model that leverages domain knowledge to improve melanoma OOD detection in imbalanced datasets.

Findings

9% increase in ROC AUC with wavelet-based NFs

Reduced model parameters for edge device deployment

Potential to aid early melanoma diagnosis

Abstract

Melanoma is a serious form of skin cancer with high mortality rate at later stages. Fortunately, when detected early, the prognosis of melanoma is promising and malignant melanoma incidence rates are relatively low. As a result, datasets are heavily imbalanced which complicates training current state-of-the-art supervised classification AI models. We propose to use generative models to learn the benign data distribution and detect Out-of-Distribution (OOD) malignant images through density estimation. Normalizing Flows (NFs) are ideal candidates for OOD detection due to their ability to compute exact likelihoods. Nevertheless, their inductive biases towards apparent graphical features rather than semantic context hamper accurate OOD detection. In this work, we aim at using these biases with domain-level knowledge of melanoma, to improve likelihood-based OOD detection of malignant images. Our encouraging results demonstrate potential for OOD detection of melanoma using NFs. We achieve a 9% increase in Area Under Curve of the Receiver Operating Characteristics by using wavelet-based NFs. This model requires significantly less parameters for inference making it more applicable on edge devices. The proposed methodology can aid medical experts with diagnosis of skin-cancer patients and continuously increase survival rates. Furthermore, this research paves the way for other areas in oncology with similar data imbalance issues.