Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion

by   Nicholas Konz, et al.

Automated tumor detection in Digital Breast Tomosynthesis (DBT) is a difficult task due to natural tumor rarity, breast tissue variability, and high resolution. Given the scarcity of abnormal images and the abundance of normal images for this problem, an anomaly detection/localization approach could be well-suited. However, most anomaly localization research in machine learning focuses on non-medical datasets, and we find that these methods fall short when adapted to medical imaging datasets. The problem is alleviated when we solve the task from the image completion perspective, in which the presence of anomalies can be indicated by a discrepancy between the original appearance and its auto-completion conditioned on the surroundings. However, there are often many valid normal completions given the same surroundings, especially in the DBT dataset, making this evaluation criterion less precise. To address such an issue, we consider pluralistic image completion by exploring the distribution of possible completions instead of generating fixed predictions. This is achieved through our novel application of spatial dropout on the completion network during inference time only, which requires no additional training cost and is effective at generating diverse completions. We further propose minimum completion distance (MCD), a new metric for detecting anomalies, thanks to these stochastic completions. We provide theoretical as well as empirical support for the superiority over existing methods of using the proposed method for anomaly localization. On the DBT dataset, our model outperforms other state-of-the-art methods by at least 10% AUROC for pixel-level detection.


page 1

page 4

page 5

page 8

page 10

page 11


Anomaly Detection with Deep Perceptual Autoencoders

Anomaly detection is the problem of recognizing abnormal inputs based on...

Image Synthesis as a Pretext for Unsupervised Histopathological Diagnosis

Anomaly detection in visual data refers to the problem of differentiatin...

Semi-supervised Anomaly Detection Using GANs for Visual Inspection in Noisy Training Data

The detection and the quantification of anomalies in image data are crit...

Energy-Based Anomaly Detection and Localization

This brief sketches initial progress towards a unified energy-based solu...

ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network

In this paper we consider the problem of unsupervised anomaly segmentati...

Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation

The goal of unsupervised anomaly segmentation (UAS) is to detect the pix...

A deep residual learning implementation of Metamorphosis

In medical imaging, most of the image registration methods implicitly as...

Please sign up or login with your details

Forgot password? Click here to reset