Semi-Supervised Anomaly Detection in Brain MRI Using a Domain-Agnostic Deep Reinforcement Learning Approach

• URL: http://arxiv.org/abs/2508.01137v1
• Date: Sat, 02 Aug 2025 01:39:13 GMT
• Title: Semi-Supervised Anomaly Detection in Brain MRI Using a Domain-Agnostic Deep Reinforcement Learning Approach
• Authors: Zeduo Zhang, Yalda Mohsenzadeh,
• Abstract summary: We develop a domain-agnostic, semi-supervised anomaly detection framework using deep reinforcement learning (DRL) to address challenges such as large-scale data, overfitting, and class imbalance.<n>This study used publicly available brain MRI datasets collected between 2005 and 2021.
• Score: 2.3633885460047765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To develop a domain-agnostic, semi-supervised anomaly detection framework that integrates deep reinforcement learning (DRL) to address challenges such as large-scale data, overfitting, and class imbalance, focusing on brain MRI volumes. This retrospective study used publicly available brain MRI datasets collected between 2005 and 2021. The IXI dataset provided 581 T1-weighted and 578 T2-weighted MRI volumes (from healthy subjects) for training, while the BraTS 2021 dataset provided 251 volumes for validation and 1000 for testing (unhealthy subjects with Glioblastomas). Preprocessing included normalization, skull-stripping, and co-registering to a uniform voxel size. Experiments were conducted on both T1- and T2-weighted modalities. Additional experiments and ablation analyses were also carried out on the industrial datasets. The proposed method integrates DRL with feature representations to handle label scarcity, large-scale data and overfitting. Statistical analysis was based on several detection and segmentation metrics including AUROC and Dice score. The proposed method achieved an AUROC of 88.7% (pixel-level) and 96.7% (image-level) on brain MRI datasets, outperforming State-of-The-Art (SOTA) methods. On industrial surface datasets, the model also showed competitive performance (AUROC = 99.8% pixel-level, 99.3% image-level) on MVTec AD dataset, indicating strong cross-domain generalization. Studies on anomaly sample size showed a monotonic increase in AUROC as more anomalies were seen, without evidence of overfitting or additional computational cost. The domain-agnostic semi-supervised approach using DRL shows significant promise for MRI anomaly detection, achieving strong performance on both medical and industrial datasets. Its robustness, generalizability and efficiency highlight its potential for real-world clinical applications.

Related papers

• GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models [1.0456203870202954]
  This work introduces a novel framework for brain tumor segmentation leveraging pre-trained GANs and Unet architectures.<n>By combining a global anomaly detection module with a refined mask generation network, the proposed model accurately identifies tumor-sensitive regions.<n>Multi-modal MRI data and synthetic image augmentation are employed to improve robustness and address the challenge of limited annotated datasets.
  arXiv  Detail & Related papers  (2025-06-26T13:28:09Z)
• BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification with Swin-HAFNet [1.1545092788508224]
  The dataset comprises 6,000 contrast-enhanced T1-weighted MRI scans annotated by radiologists and physicians.<n>Each sample includes high-resolution labels and is categorized across axial, sagittal, and coronal imaging planes.<n>Our method achieves the highest weighted mean Intersection-over-Union (IoU) of 82.3%, with improvements observed across all tumor categories.
  arXiv  Detail & Related papers  (2025-06-17T08:56:05Z)
• Deep Learning-Based Noninvasive Screening of Type 2 Diabetes with Chest X-ray Images and Electronic Health Records [2.2940141855172036]
  This study evaluates the integration of chest X-ray (CXR) images with other noninvasive data sources, including electronic health records (EHRs) and electrocardiography signals, for T2DM detection.<n>The end-to-end trained ResNet-LSTM model achieved an AUROC of 0.86, surpassing the CXR-only baseline by 2.3% with just 9863 training samples.
  arXiv  Detail & Related papers  (2024-12-14T20:18:16Z)
• SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms [60.35639972035727]
  The lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. Dice scores reached up to 0.838 $pm$ 0.066 and 0.716 $pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $pm$ 0.15.
  arXiv  Detail & Related papers  (2024-11-14T17:06:00Z)
• Unsupervised dMRI Artifact Detection via Angular Resolution Enhancement and Cycle Consistency Learning [45.3610312584439]
  Diffusion magnetic resonance imaging (dMRI) is a crucial technique in neuroimaging studies, allowing for the non-invasive probing of the underlying structures of brain tissues. Clinical dMRI data is susceptible to various artifacts during acquisition, which can lead to unreliable subsequent analyses. We propose a novel unsupervised deep learning framework called $textbfU$n $textbfd$MRI $textbfA$rtifact $textbfD$etection via $textbfA$ngular Resolution Enhancement and $textbfC$ycle
  arXiv  Detail & Related papers  (2024-09-24T08:56:10Z)
• ISLES'24 -- A Real-World Longitudinal Multimodal Stroke Dataset [9.501255615225428]
  Stroke remains a leading cause of global morbidity and mortality, imposing a heavy socioeconomic burden.<n> Developing machine learning algorithms that can create accurate models of brain function from stroke images requires large, diverse, and well annotated public datasets.<n>This multicenter dataset consists of 245 cases and is a solid basis for developing powerful machine-learning algorithms to facilitate clinical decision-making.
  arXiv  Detail & Related papers  (2024-08-20T18:59:52Z)
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models [69.9178140563928]
  Colonoscopy analysis is essential for assisting clinical diagnosis and treatment. The scarcity of annotated data limits the effectiveness and generalization of existing methods. We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-03T07:55:46Z)
• Revisiting Computer-Aided Tuberculosis Diagnosis [56.80999479735375]
  Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Computer-aided tuberculosis diagnosis (CTD) using deep learning has shown promise, but progress is hindered by limited training data. We establish a large-scale dataset, namely the Tuberculosis X-ray (TBX11K) dataset, which contains 11,200 chest X-ray (CXR) images with corresponding bounding box annotations for TB areas. This dataset enables the training of sophisticated detectors for high-quality CTD.
  arXiv  Detail & Related papers  (2023-07-06T08:27:48Z)
• Integrative Imaging Informatics for Cancer Research: Workflow Automation for Neuro-oncology (I3CR-WANO) [0.12175619840081271]
  We propose an artificial intelligence-based solution for the aggregation and processing of multisequence neuro-Oncology MRI data. Our end-to-end framework i) classifies MRI sequences using an ensemble classifier, ii) preprocesses the data in a reproducible manner, and iv) delineates tumor tissue subtypes. It is robust to missing sequences and adopts an expert-in-the-loop approach, where the segmentation results may be manually refined by radiologists.
  arXiv  Detail & Related papers  (2022-10-06T18:23:42Z)
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection [98.5549882883963]
  We present findings from the largest Federated ML study to-date, involving data from 71 healthcare institutions across 6 continents. We generate an automatic tumor boundary detector for the rare disease of glioblastoma. We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent.
  arXiv  Detail & Related papers  (2022-04-22T17:27:00Z)
• StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder [48.2010192865749]
  Unsupervised anomaly detection (UAD) can learn a data distribution from an unlabelled dataset of healthy subjects and then be applied to detect out of distribution samples. This research proposes a compact version of the "context-encoding" VAE (ceVAE) model, combined with pre and post-processing steps, creating a UAD pipeline (StRegA) The proposed pipeline achieved a Dice score of 0.642$pm$0.101 while detecting tumours in T2w images of the BraTS dataset and 0.859$pm$0.112 while detecting artificially induced anomalies.
  arXiv  Detail & Related papers  (2022-01-31T14:27:35Z)
• A Real-World Demonstration of Machine Learning Generalizability: Intracranial Hemorrhage Detection on Head CT [5.517017976008718]
  The purpose of this study was to demonstrate that ML model generalizability is achievable in medical imaging. An ML model was trained using 21,784 scans from the RSNA Intracranial Hemorrhage CT dataset. On external validation, the model demonstrated an AUC of 95.4%, sensitivity of 91.3%, and specificity of 94.1%.
  arXiv  Detail & Related papers  (2021-02-09T15:05:48Z)
• Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
  We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
  arXiv  Detail & Related papers  (2020-10-14T16:50:50Z)

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.