# Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation

Source: [Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation](<https://www.sota2.com/research/paper/68fa69921e209131cea22bf0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:02:46.333Z

Authors: Chenxin Li, Yunlong Zhang, Jiongcheng Li, Yue Huang, Xinghao Ding

Published: 2021-03-16T14:15:30.000Z

## Abstract

The goal of unsupervised anomaly segmentation (UAS) is to detect the pixel-level anomalies unseen during training. It is a promising field in the medical imaging community, e.g, we can use the model trained with only healthy data to segment the lesions of rare diseases. Existing methods are mainly based on Information Bottleneck, whose underlying principle is modeling the distribution of normal anatomy via learning to compress and recover the healthy data with a low-dimensional manifold, and then detecting lesions as the outlier from this learned distribution. However, this dimensionality reduction inevitably damages the localization information, which is especially essential for pixel-level anomaly detection. In this paper, to alleviate this issue, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution. More precisely, we view the couple of segmentation and synthesis as a special Autoencoder, and propose a novel cycle translation framework with a journey of 'image-\>semantic-\>image'. Experimental results on the BraTS and ISLES databases show that the proposed approach achieves significantly superior performance compared to several prior methods and segments the anomalies more accurately.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.09094>)

[PDF](<https://arxiv.org/pdf/2103.09094.pdf>)
