Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images

• URL: http://arxiv.org/abs/2403.08689v1
• Date: Wed, 13 Mar 2024 16:44:49 GMT
• Title: Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images
• Authors: Tiange Xiang, Yixiao Zhang, Yongyi Lu, Alan Yuille, Chaoyi Zhang, Weidong Cai, Zongwei Zhou
• Abstract summary: We propose a Simple Space-Aware Memory Matrix for In-painting and Detecting anomalies from radiography images (abbreviated as SimSID) During the training, SimSID can taxonomize the anatomical structures into recurrent visual patterns, and in the inference, it can identify anomalies from the test image. Our SimSID surpasses the state of the arts in unsupervised anomaly detection by +8.0%, +5.0%, and +9.9% AUC scores on ZhangLab, COVIDx, and CheXpert benchmark datasets.
• Score: 20.80801110403552
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Radiography imaging protocols focus on particular body regions, therefore producing images of great similarity and yielding recurrent anatomical structures across patients. Exploiting this structured information could potentially ease the detection of anomalies from radiography images. To this end, we propose a Simple Space-Aware Memory Matrix for In-painting and Detecting anomalies from radiography images (abbreviated as SimSID). We formulate anomaly detection as an image reconstruction task, consisting of a space-aware memory matrix and an in-painting block in the feature space. During the training, SimSID can taxonomize the ingrained anatomical structures into recurrent visual patterns, and in the inference, it can identify anomalies (unseen/modified visual patterns) from the test image. Our SimSID surpasses the state of the arts in unsupervised anomaly detection by +8.0%, +5.0%, and +9.9% AUC scores on ZhangLab, COVIDx, and CheXpert benchmark datasets, respectively. Code: https://github.com/MrGiovanni/SimSID

Related papers

• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Weakly Supervised Anomaly Detection for Chest X-Ray Image [6.506869371228188]
  We propose a weakly supervised anomaly detection framework for Chest X-Ray (CXR) examination. WSCXR firstly constructs sets of normal and anomaly image features respectively. It then refines the anomaly image features by eliminating normal region features through anomaly feature mining.
  arXiv  Detail & Related papers  (2023-11-16T07:53:34Z)
• K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment [71.27193056354741]
  The problem of how to assess cross-modality medical image synthesis has been largely unexplored. We propose a new metric K-CROSS to spur progress on this challenging problem. K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location.
  arXiv  Detail & Related papers  (2023-07-10T01:26:48Z)
• Unsupervised Anomaly Localization with Structural Feature-Autoencoders [6.667150890634173]
  Unsupervised Anomaly Detection has become a popular method to detect pathologies in medical images. We propose to tackle this problem using a feature-mapping function that transforms the input intensity images into a space with multiple channels. We then train an Autoencoder model in this space using structural similarity loss that does not only consider differences in intensity but also in contrast and structure.
  arXiv  Detail & Related papers  (2022-08-23T14:19:46Z)
• SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection [76.01333073259677]
  We propose the use of Space-aware Memory Queues for In-painting and Detecting anomalies from radiography images (abbreviated as SQUID) We show that SQUID can taxonomize the ingrained anatomical structures into recurrent patterns; and in the inference, it can identify anomalies (unseen/modified patterns) in the image.
  arXiv  Detail & Related papers  (2021-11-26T13:47:34Z)
• Generative Residual Attention Network for Disease Detection [51.60842580044539]
  We present a novel approach for disease generation in X-rays using a conditional generative adversarial learning. We generate a corresponding radiology image in a target domain while preserving the identity of the patient. We then use the generated X-ray image in the target domain to augment our training to improve the detection performance.
  arXiv  Detail & Related papers  (2021-10-25T14:15:57Z)
• Proxy-bridged Image Reconstruction Network for Anomaly Detection in Medical Images [59.700111685673846]
  Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. We propose a novel Proxy-bridged Image Reconstruction Network ( ProxyAno) for anomaly detection in medical images.
  arXiv  Detail & Related papers  (2021-10-05T00:40:43Z)
• SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images [23.582516309813425]
  We introduce Self-supervised Anatomical eMbedding (SAM) to learn the intrinsic structure from unlabeled images. SAM generates semantic embeddings for each image pixel that describes its anatomical location or body part. We demonstrate the effectiveness of SAM in multiple tasks with 2D and 3D image modalities.
  arXiv  Detail & Related papers  (2020-12-04T03:31:20Z)
• Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images [42.700275429734205]
  Anomaly detection in retinal image refers to the identification of abnormality caused by various retinal diseases/lesions. We propose to leverage the relation between the image texture and structure to design a deep neural network for anomaly detection.
  arXiv  Detail & Related papers  (2020-08-09T02:59:33Z)
• Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations [68.8204255655161]
  Anomaly detection for Magnetic Resonance Images (MRIs) can be solved with unsupervised methods. We have proposed a slice-wise semi-supervised method for tumour detection based on the computation of a dissimilarity function in the latent space of a Variational AutoEncoder. We show that by training the models on higher resolution images and by improving the quality of the reconstructions, we obtain results which are comparable with different baselines.
  arXiv  Detail & Related papers  (2020-07-24T14:02:09Z)

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.