Distractor-Aware Neuron Intrinsic Learning for Generic 2D Medical Image Classifications
This work addresses a specific issue in medical image analysis for CADx, offering an incremental improvement by enhancing classifier robustness to distractors.
The paper tackles the problem of convolutional neural networks being vulnerable to distractor interference in medical image classification due to small inter-class distances, and proposes a neuron intrinsic learning method with a distractor-aware loss that achieves favorable performance against state-of-the-art approaches on benchmark datasets.
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.