IterMask2: Iterative Unsupervised Anomaly Segmentation via Spatial and Frequency Masking for Brain Lesions in MRI

Ziyun Liang*, Xiaoqing Guo, J. Alison Noble, Konstantinos Kamnitsas

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Unsupervised anomaly segmentation approaches to pathology segmentation train a model on images of healthy subjects, that they define as the ‘normal’ data distribution. At inference, they aim to segment any pathologies in new images as ‘anomalies’, as they exhibit patterns that deviate from those in ‘normal’ training data. Prevailing methods follow the ‘corrupt-and-reconstruct’ paradigm. They intentionally corrupt an input image, reconstruct it to follow the learned ‘normal’ distribution, and subsequently segment anomalies based on reconstruction error. Corrupting an input image, however, inevitably leads to suboptimal reconstruction even of normal regions, causing false positives. To alleviate this, we propose a novel iterative spatial mask-refining strategy IterMask2. We iteratively mask areas of the image, reconstruct them, and update the mask based on reconstruction error. This iterative process progressively adds information about areas that are confidently normal as per the model. The increasing content guides reconstruction of nearby masked areas, improving reconstruction of normal tissue under these areas, reducing false positives. We also use high-frequency image content as an auxiliary input to provide additional structural information for masked areas. This further improves reconstruction error of normal in comparison to anomalous areas, facilitating segmentation of the latter. We conduct experiments on several brain lesion datasets and demonstrate effectiveness of our method. Code is available at: https://github.com/ZiyunLiang/IterMask2

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2024
Subtitle of host publication27th International Conference, Marrakesh, Morocco, October 6–10, 2024, Proceedings, Part VIII
EditorsMarius George Linguraru, Qi Dou, Aasa Feragen, Stamatia Giannarou, Ben Glocker, Karim Lekadir, Julia A. Schnabel
PublisherSpringer Nature
Pages339-348
Number of pages10
ISBN (Electronic) 9783031721113
ISBN (Print)9783031721106
DOIs
Publication statusPublished - 6 Oct 2024
Event27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024 - Marrakesh, Morocco
Duration: 6 Oct 202410 Oct 2024
https://link.springer.com/book/10.1007/978-3-031-72083-3 (Conference Proceedings (Part IV))
https://link.springer.com/book/10.1007/978-3-031-72111-3 (Conference Proceedings (Part VIII))

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume15008
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameMICCAI: International Conference on Medical Image Computing and Computer-Assisted Intervention
PublisherSpringer

Conference

Conference27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024
Country/TerritoryMorocco
CityMarrakesh
Period6/10/2410/10/24
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • General Computer Science

User-Defined Keywords

  • Anomaly Segmentation
  • Brain Lesions
  • Unsupervised

Fingerprint

Dive into the research topics of 'IterMask2: Iterative Unsupervised Anomaly Segmentation via Spatial and Frequency Masking for Brain Lesions in MRI'. Together they form a unique fingerprint.

Cite this