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 language | English |
---|---|
Title of host publication | Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 |
Subtitle of host publication | 27th International Conference, Marrakesh, Morocco, October 6–10, 2024, Proceedings, Part VIII |
Editors | Marius George Linguraru, Qi Dou, Aasa Feragen, Stamatia Giannarou, Ben Glocker, Karim Lekadir, Julia A. Schnabel |
Publisher | Springer Nature |
Pages | 339-348 |
Number of pages | 10 |
ISBN (Electronic) | 9783031721113 |
ISBN (Print) | 9783031721106 |
DOIs | |
Publication status | Published - 6 Oct 2024 |
Event | 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024 - Marrakesh, Morocco Duration: 6 Oct 2024 → 10 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
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer |
Volume | 15008 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Name | MICCAI: International Conference on Medical Image Computing and Computer-Assisted Intervention |
---|---|
Publisher | Springer |
Conference
Conference | 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024 |
---|---|
Country/Territory | Morocco |
City | Marrakesh |
Period | 6/10/24 → 10/10/24 |
Internet address |
|
Scopus Subject Areas
- Theoretical Computer Science
- General Computer Science
User-Defined Keywords
- Anomaly Segmentation
- Brain Lesions
- Unsupervised