Out of distribution detection for skin and malaria images

TL;DR

This paper introduces a novel OoD detection method for medical images that improves reliability without needing labeled OoD data during training, using metric learning and K-reciprocal nearest neighbors.

Contribution

It presents a new approach combining metric learning, data augmentation, and nearest neighbor techniques for OoD detection in skin and malaria images, achieving state-of-the-art results.

Findings

Achieved 5% and 4% improvements in TNR@TPR95% for skin cancer and malaria OoD detection.

Effectively distinguishes OoD samples using generated ID-like examples and K-reciprocal nearest neighbors.

Outperforms previous methods on multiple challenging medical image datasets.

Abstract

Deep neural networks have shown promising results in disease detection and classification using medical image data. However, they still suffer from the challenges of handling real-world scenarios especially reliably detecting out-of-distribution (OoD) samples. We propose an approach to robustly classify OoD samples in skin and malaria images without the need to access labeled OoD samples during training. Specifically, we use metric learning along with logistic regression to force the deep networks to learn much rich class representative features. To guide the learning process against the OoD examples, we generate ID similar-looking examples by either removing class-specific salient regions in the image or permuting image parts and distancing them away from in-distribution samples. During inference time, the K-reciprocal nearest neighbor is employed to detect out-of-distribution samples. For skin cancer OoD detection, we employ two standard benchmark skin cancer ISIC datasets as ID, and six different datasets with varying difficulty levels were taken as out of distribution. For malaria OoD detection, we use the BBBC041 malaria dataset as ID and five different challenging datasets as out of distribution. We achieved state-of-the-art results, improving 5% and 4% in TNR@TPR95% over the previous state-of-the-art for skin cancer and malaria OoD detection respectively.