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

TL;DR

This paper introduces ASC-Net, an unsupervised adversarial network that segments medical anomalies without requiring annotated masks, leveraging user-defined reference distributions to improve anomaly detection across multiple datasets.

Contribution

The paper presents a novel adversarial-based selective cutting network that bridges deep clustering and anomaly detection for unsupervised medical image segmentation.

Findings

Achieves significant performance improvements over existing unsupervised methods.

Effective in segmenting anomalies in diverse medical imaging datasets.

Demonstrates potential for unsupervised medical diagnosis applications.

Abstract

In this paper we consider the problem of unsupervised anomaly segmentation in medical images, which has attracted increasing attention in recent years due to the expensive pixel-level annotations from experts and the existence of a large amount of unannotated normal and abnormal image scans. We introduce a segmentation network that utilizes adversarial learning to partition an image into two cuts, with one of them falling into a reference distribution provided by the user. This Adversarial-based Selective Cutting network (ASC-Net) bridges the two domains of cluster-based deep segmentation and adversarial-based anomaly/novelty detection algorithms. Our ASC-Net learns from normal and abnormal medical scans to segment anomalies in medical scans without any masks for supervision. We evaluate this unsupervised anomly segmentation model on three public datasets, i.e., BraTS 2019 for brain tumor segmentation, LiTS for liver lesion segmentation, and MS-SEG 2015 for brain lesion segmentation, and also on a private dataset for brain tumor segmentation. Compared to existing methods, our model demonstrates tremendous performance gains in unsupervised anomaly segmentation tasks. Although there is still room to further improve performance compared to supervised learning algorithms, the promising experimental results and interesting observations shed light on building an unsupervised learning algorithm for medical anomaly identification using user-defined knowledge.