Dissolving Is Amplifying: Towards Fine-Grained Anomaly Detection

• URL: http://arxiv.org/abs/2302.14696v3
• Date: Sat, 6 Jul 2024 23:33:31 GMT
• Title: Dissolving Is Amplifying: Towards Fine-Grained Anomaly Detection
• Authors: Jian Shi, Pengyi Zhang, Ni Zhang, Hakim Ghazzai, Peter Wonka,
• Abstract summary: DIA is a fine-grained anomaly detection framework for medical images. We employ diffusion with a generative diffusion model as a dedicated feature-aware denoiser. Second, we introduce an textitamplifying framework based on contrastive learning to learn a semantically meaningful representation of medical images.
• Score: 43.03629006199897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical imaging often contains critical fine-grained features, such as tumors or hemorrhages, crucial for diagnosis yet potentially too subtle for detection with conventional methods. In this paper, we introduce \textit{DIA}, dissolving is amplifying. DIA is a fine-grained anomaly detection framework for medical images. First, we introduce \textit{dissolving transformations}. We employ diffusion with a generative diffusion model as a dedicated feature-aware denoiser. Applying diffusion to medical images in a certain manner can remove or diminish fine-grained discriminative features. Second, we introduce an \textit{amplifying framework} based on contrastive learning to learn a semantically meaningful representation of medical images in a self-supervised manner, with a focus on fine-grained features. The amplifying framework contrasts additional pairs of images with and without dissolving transformations applied and thereby emphasizes the dissolved fine-grained features. DIA significantly improves the medical anomaly detection performance with around 18.40\% AUC boost against the baseline method and achieves an overall SOTA against other benchmark methods. Our code is available at \url{https://github.com/shijianjian/DIA.git}.

Related papers

• Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes [3.2720947374803777]
  We propose a novel anomaly detector for medical imagery based on diffusion models. We show how a similar process can be used to detect synthetic content by making a model reverse the diffusion on a suspected image. Our method significantly outperforms other state of the art unsupervised detectors with an increased AUC of 0.9 from 0.79 for injection and of 0.96 from 0.91 for removal.
  arXiv  Detail & Related papers  (2024-07-21T13:58:43Z)
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• Introducing Shape Prior Module in Diffusion Model for Medical Image Segmentation [7.7545714516743045]
  We propose an end-to-end framework called VerseDiff-UNet, which leverages the denoising diffusion probabilistic model (DDPM) Our approach integrates the diffusion model into a standard U-shaped architecture. We evaluate our method on a single dataset of spine images acquired through X-ray imaging.
  arXiv  Detail & Related papers  (2023-09-12T03:05:00Z)
• Chili Pepper Disease Diagnosis via Image Reconstruction Using GrabCut and Generative Adversarial Serial Autoencoder [0.0]
  Disease diagnosis belongs to the field of anomaly detection and aims to distinguish whether plants or fruits are normal or abnormal. Due to the limitation of the performance of image generation, SOTA's methods propose a score calculation method using a latent vector error. We propose a method of generating meaningful images using the GAN structure and classifying three results simultaneously by one discriminator.
  arXiv  Detail & Related papers  (2023-06-21T06:58:46Z)
• Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images [0.0]
  We propose MultiStain-CycleGAN, a multi-domain approach to stain normalization based on CycleGAN. Our modifications to CycleGAN allow us to normalize images of different origins without retraining or using different models.
  arXiv  Detail & Related papers  (2023-01-23T13:34:49Z)
• Stain-invariant self supervised learning for histopathology image analysis [74.98663573628743]
  We present a self-supervised algorithm for several classification tasks within hematoxylin and eosin stained images of breast cancer. Our method achieves the state-of-the-art performance on several publicly available breast cancer datasets.
  arXiv  Detail & Related papers  (2022-11-14T18:16:36Z)
• HealthyGAN: Learning from Unannotated Medical Images to Detect Anomalies Associated with Human Disease [13.827062843105365]
  A typical technique in the current medical imaging literature has focused on deriving diagnostic models from healthy subjects only. HealthyGAN learns to translate the images from the mixed dataset to only healthy images. Being one-directional, HealthyGAN relaxes the requirement of cycle consistency of existing unpaired image-to-image translation methods.
  arXiv  Detail & Related papers  (2022-09-05T08:10:52Z)
• FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss [58.58979566599889]
  We propose a novel self-supervised learning (FedMed) for brain image synthesis. An affine transform loss (ATL) was formulated to make use of severely distorted images without violating privacy legislation. The proposed method demonstrates advanced performance in both the quality of synthesized results under a severely misaligned and unpaired data setting.
  arXiv  Detail & Related papers  (2022-01-29T13:45:39Z)
• Cross-Modal Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop [63.81818077092879]
  We propose an end-to-end semi-supervised cross-modal contrastive learning framework for medical images. We first apply an image encoder to classify the chest X-rays and to generate the image features. The radiomic features are then passed through another dedicated encoder to act as the positive sample for the image features generated from the same chest X-ray.
  arXiv  Detail & Related papers  (2021-04-11T09:16:29Z)
• ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection [90.13718478362337]
  We introduce a novel ElixirNet that includes three components: 1) TruncatedRPN balances positive and negative data for false positive reduction; 2) Auto-lesion Block is automatically customized for medical images to incorporate relation-aware operations among region proposals; and 3) Relation transfer module incorporates the semantic relationship. Experiments on DeepLesion and Kits19 prove the effectiveness of ElixirNet, achieving improvement of both sensitivity and precision over FPN with fewer parameters.
  arXiv  Detail & Related papers  (2020-03-03T05:29:49Z)

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.