Distractor-Aware Neuron Intrinsic Learning for Generic 2D Medical Image Classifications

TL;DR

This paper introduces a neuron intrinsic learning method that enhances CNN robustness in medical image classification by explicitly modeling distractors in feature space, leading to improved accuracy.

Contribution

It proposes a novel distractor-aware loss in CNN training that explicitly considers distractors in feature space, improving classification robustness.

Findings

Outperforms state-of-the-art methods on medical image benchmarks.

Effectively models distractors to improve CNN robustness.

Enhances classification accuracy in medical imaging tasks.

Abstract

Medical image analysis benefits Computer Aided Diagnosis (CADx). A fundamental analyzing approach is the classification of medical images, which serves for skin lesion diagnosis, diabetic retinopathy grading, and cancer classification on histological images. When learning these discriminative classifiers, we observe that the convolutional neural networks (CNNs) are vulnerable to distractor interference. This is due to the similar sample appearances from different categories (i.e., small inter-class distance). Existing attempts select distractors from input images by empirically estimating their potential effects to the classifier. The essences of how these distractors affect CNN classification are not known. In this paper, we explore distractors from the CNN feature space via proposing a neuron intrinsic learning method. We formulate a novel distractor-aware loss that encourages large distance between the original image and its distractor in the feature space. The novel loss is combined with the original classification loss to update network parameters by back-propagation. Neuron intrinsic learning first explores distractors crucial to the deep classifier and then uses them to robustify CNN inherently. Extensive experiments on medical image benchmark datasets indicate that the proposed method performs favorably against the state-of-the-art approaches.