Anomaly Detection on X-Rays Using Self-Supervised Aggregation Learning

Abstract

Deep anomaly detection models using a supervised mode of learning usually work under a closed set assumption and suffer from overfitting to previously seen rare anomalies at training, which hinders their applicability in a real scenario. In addition, obtaining annotations for X-rays is very time consuming and requires extensive training of radiologists. Hence, training anomaly detection in a fully unsupervised or self-supervised fashion would be advantageous, allowing a significant reduction of time spent on the report by radiologists. In this paper, we present SALAD, an end-to-end deep self-supervised methodology for anomaly detection on X-Ray images. The proposed method is based on an optimization strategy in which a deep neural network is encouraged to represent prototypical local patterns of the normal data in the embedding space. During training, we record the prototypical patterns of normal training samples via a memory bank. Our anomaly score is then derived by measuring similarity to a weighted combination of normal prototypical patterns within a memory bank without using any anomalous patterns. We present extensive experiments on the challenging NIH Chest X-rays and MURA dataset, which indicate that our algorithm improves stateof-the-art methods by a wide margin.

Otoscopy video screening with deep anomaly detection

“…Notable methods along this line include SVD-RND [22], CutPaste [23], CSI [24], SSD [25] and MSC [26]. UAD has also been applied to medical imaging [27] across many domains, including Xray [28], [29], CT [30], [31], MRI [32], [33], [34] and endoscopy [35] datasets.…”

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

“…Also, CNN methods capture mostly local context information and do not explore the global aspects. Zhang et al in [191,153,152,155,157,24], [22,130,151], [79,51,78,49], [42,43,11], [90,77,88], [168,8,75,76] propose a squeeze and excitation network to capture the global characteristics thus leading to improved super resolution output. However, squeeze and excitation relies on CNN features to capture global context which is not optimal.…”

CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

“…Traditional augmentations such as image rotations or deformations have limited benefit as they do not fully represent the underlying data distribution of the training set and are sensitive to parameter choices. Recent data augmentation methods of [25], [131], [11], [113], [108], [106], [114], [129], [103], [69], [139], [39], [32], [33], [13], [73], [62], [63] use generative adversarial network (GAN), [ [23]], and show moderate success for medical image classification. However, they have limited relevance for segmentation since they do not model geometric relation between different organs and most augmentation approaches do not differentiate between normal and diseased samples.…”