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

• URL: http://arxiv.org/abs/2406.02422v2
• Date: Wed, 5 Jun 2024 13:17:23 GMT
• Title: IterMask2: Iterative Unsupervised Anomaly Segmentation via Spatial and Frequency Masking for Brain Lesions in MRI
• Authors: Ziyun Liang, Xiaoqing Guo, J. Alison Noble, Konstantinos Kamnitsas,
• Abstract summary: Unsupervised anomaly segmentation approaches to pathology segmentation train a model on images of healthy subjects. They aim to segment any pathologies in new images as 'anomalies', as they exhibit patterns that deviate from those in 'normal' training data. We propose a novel iterative spatial mask-refining strategy IterMask2 to alleviate this problem.
• Score: 13.403122193463348
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR [10.763588041592703]
  Unsupervised anomaly detection and segmentation methods train a model to learn the training distribution as 'normal' prevailing methods corrupt the images and train a model to reconstruct them. We propose IterMask3D, an iterative spatial mask-refining strategy designed for 3D brain MRI.
  arXiv  Detail & Related papers  (2025-04-07T10:41:23Z)
• Spatial-aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image [63.59114880750643]
  We introduce a novel Spatial-aware Attention Generative Adrialversa Network (SAGAN) for one-class semi-supervised generation of health images. SAGAN generates high-quality health images corresponding to unlabeled data, guided by the reconstruction of normal images and restoration of pseudo-anomaly images. Extensive experiments on three medical datasets demonstrate that the proposed SAGAN outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-21T15:41:34Z)
• Learning to Rank Patches for Unbiased Image Redundancy Reduction [80.93989115541966]
  Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. We propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches.
  arXiv  Detail & Related papers  (2024-03-31T13:12:41Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation [78.13793505707952]
  Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. We propose a novel two-stage framework, which consists of Masked Quantization VAE (MQ-VAE) Stack model from modeling redundancy.
  arXiv  Detail & Related papers  (2023-05-23T02:15:53Z)
• Industrial and Medical Anomaly Detection Through Cycle-Consistent Adversarial Networks [0.6554326244334868]
  A new Anomaly Detection (AD) approach for industrial and medical images is proposed. The proposed method uses Cycle-Generative Adrial Networks (Cycle-GAN) for (ab)normal-to-normal translation. Results demonstrate accurate performance with a zero false negative constraint compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-02-10T10:25:12Z)
• Masked Transformer for image Anomaly Localization [14.455765147827345]
  We propose a new model for image anomaly detection based on Vision Transformer architecture with patch masking. We show that multi-resolution patches and their collective embeddings provide a large improvement in the model's performance. The proposed model has been tested on popular anomaly detection datasets such as MVTec and head CT.
  arXiv  Detail & Related papers  (2022-10-27T15:30:48Z)
• Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection [97.93062818228015]
  We propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video.
  arXiv  Detail & Related papers  (2021-11-17T13:30:31Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)
• Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation [31.396372591714695]
  Unsupervised anomaly segmentation (UAS) is a promising field in the medical imaging community. In this paper, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution. Experimental results on the BraTS and ISLES databases show that the proposed approach achieves significantly superior performance.
  arXiv  Detail & Related papers  (2021-03-16T14:15:30Z)
• Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Images [0.0]
  We propose a novel approach to the semantic segmentation of medical chest X-ray images with only image-level class labels as supervision. We show that this approach is applicable to chest X-rays for detecting an anomalous volume of air between the lung and the chest wall.
  arXiv  Detail & Related papers  (2020-07-01T20:48:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.