IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Ziyun, Guo, Xiaoqing, Xu, Wentian, Ibrahim, Yasin, Voets, Natalie, Pretorius, Pieter M, Noble, J. Alison, Kamnitsas, Konstantinos
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911210341924864
author Liang, Ziyun
Guo, Xiaoqing
Xu, Wentian
Ibrahim, Yasin
Voets, Natalie
Pretorius, Pieter M
Noble, J. Alison
Kamnitsas, Konstantinos
author_facet Liang, Ziyun
Guo, Xiaoqing
Xu, Wentian
Ibrahim, Yasin
Voets, Natalie
Pretorius, Pieter M
Noble, J. Alison
Kamnitsas, Konstantinos
contents Unsupervised anomaly detection and segmentation methods train a model to learn the training distribution as `normal'. In the testing phase, they identify patterns that deviate from this normal distribution as `anomalies'. To learn the `normal' distribution, prevailing methods corrupt the images and train a model to reconstruct them. During testing, the model attempts to reconstruct corrupted inputs based on the learned `normal' distribution. Deviations from this distribution lead to high reconstruction errors, which indicate potential anomalies. However, corrupting an input image inevitably causes information loss even in normal regions, leading to suboptimal reconstruction and an increased risk of false positives. To alleviate this, we propose $\rm{IterMask3D}$, an iterative spatial mask-refining strategy designed for 3D brain MRI. We iteratively spatially mask areas of the image as corruption and reconstruct them, then shrink the mask based on reconstruction error. This process iteratively unmasks `normal' areas to the model, whose information further guides reconstruction of `normal' patterns under the mask to be reconstructed accurately, reducing false positives. In addition, to achieve better reconstruction performance, we also propose using high-frequency image content as additional structural information to guide the reconstruction of the masked area. Extensive experiments on the detection of both synthetic and real-world imaging artifacts, as well as segmentation of various pathological lesions across multiple MRI sequences, consistently demonstrate the effectiveness of our proposed method. Code is available at https://github.com/ZiyunLiang/IterMask3D.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04911
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR
Liang, Ziyun
Guo, Xiaoqing
Xu, Wentian
Ibrahim, Yasin
Voets, Natalie
Pretorius, Pieter M
Noble, J. Alison
Kamnitsas, Konstantinos
Computer Vision and Pattern Recognition
Machine Learning
Unsupervised anomaly detection and segmentation methods train a model to learn the training distribution as `normal'. In the testing phase, they identify patterns that deviate from this normal distribution as `anomalies'. To learn the `normal' distribution, prevailing methods corrupt the images and train a model to reconstruct them. During testing, the model attempts to reconstruct corrupted inputs based on the learned `normal' distribution. Deviations from this distribution lead to high reconstruction errors, which indicate potential anomalies. However, corrupting an input image inevitably causes information loss even in normal regions, leading to suboptimal reconstruction and an increased risk of false positives. To alleviate this, we propose $\rm{IterMask3D}$, an iterative spatial mask-refining strategy designed for 3D brain MRI. We iteratively spatially mask areas of the image as corruption and reconstruct them, then shrink the mask based on reconstruction error. This process iteratively unmasks `normal' areas to the model, whose information further guides reconstruction of `normal' patterns under the mask to be reconstructed accurately, reducing false positives. In addition, to achieve better reconstruction performance, we also propose using high-frequency image content as additional structural information to guide the reconstruction of the masked area. Extensive experiments on the detection of both synthetic and real-world imaging artifacts, as well as segmentation of various pathological lesions across multiple MRI sequences, consistently demonstrate the effectiveness of our proposed method. Code is available at https://github.com/ZiyunLiang/IterMask3D.
title IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2504.04911