• Home
  • Search
  • Modeling Healthy Anatomy with Artificial Intelligence for Unsupervised Anomaly Detection in Brain MRI.
  • Open Access IconOpen Access
  • Cite Icon44
  • https://doi.org/10.1148/ryai.2021190169Copy DOI Icon

Modeling Healthy Anatomy with Artificial Intelligence for Unsupervised Anomaly Detection in Brain MRI.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

To develop an unsupervised deep learning model on MR images of normal brain anatomy to automatically detect deviations indicative of pathologic states on abnormal MR images. In this retrospective study, spatial autoencoders with skip-connections (which can learn to compress and reconstruct data) were leveraged to learn the normal variability of the brain from MR scans of healthy individuals. A total of 100 normal, in-house MR scans were used for training. Subsequently, as the model was unable to reconstruct anomalies well, this characteristic was exploited for detecting and delineating various diseases by computing the difference between the input data and their reconstruction. The unsupervised model was compared with a supervised U-Net- and threshold-based classifier trained on data from 50 patients with multiple sclerosis (in-house dataset) and 50 patients from The Cancer Imaging Archive. Both the unsupervised and supervised U-Net models were tested on five different datasets containing MR images of microangiopathy, glioblastoma, and multiple sclerosis. Precision-recall statistics and derivations thereof (mean area under the precision-recall curve, Dice score) were used to quantify lesion detection and segmentation performance. The unsupervised approach outperformed the naive thresholding approach in lesion detection (mean F1 scores ranging from 17% to 62% vs 6.4% to 15% across the five different datasets) and performed similarly to the supervised U-Net (20%-64%) across a variety of pathologic conditions. This outperformance was mostly driven by improved precision compared with the thresholding approach (mean precisions, 15%-59% vs 3.4%-10%). The model was also developed to create an anomaly heatmap display. The unsupervised deep learning model was able to automatically detect anomalies on brain MR images with high performance. Supplemental material is available for this article. Keywords: Brain/Brain Stem Computer Aided Diagnosis (CAD), Convolutional Neural Network (CNN), Experimental Investigations, Head/Neck, MR-Imaging, Quantification, Segmentation, Stacked Auto-Encoders, Technology Assessment, Tissue Characterization © RSNA, 2021.

Similar Papers
  • Research Article
  • Citations42

Unsupervised anomaly detection in brain MRI: Learning abstract distribution from massive healthy brains

  • Jan 25, 2023
  • Computers in Biology and Medicine
  • Guoting Luo +5
  • PDF
  • Research Article
  • Citations275

An Unsupervised Deep Learning Model for Early Network Traffic Anomaly Detection

  • Jan 01, 2020
  • IEEE Access
  • Ren-Hung Hwang +4
  • Research Article

Lateral connection convolutional neural networks for obstructive sleep apnea hypopnea classification

  • Jun 25, 2025
  • Computer Methods in Biomechanics and Biomedical Engineering
  • Junming Zhang +4
  • Research Article
  • Citations2

Leveraging productivity indicators for anomaly detection in swine breeding herds with unsupervised learning

  • Nov 17, 2025
  • Frontiers in Veterinary Science
  • Mafalda Pedro Mil-Homens +6
  • PDF
  • Research Article
  • Citations1

Discharge Summaries Based Sentiment Detection Using Multi-Head Attention and CNN-BiGRU

  • Jan 01, 2023
  • Computer Systems Science and Engineering
  • Samer Abdulateef Waheeb
  • PDF
  • Research Article
  • Citations16

An Unsupervised Deep Feature Learning Model Based on Parallel Convolutional Autoencoder for Intelligent Fault Diagnosis of Main Reducer

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Qing Ye +1
  • Book Chapter
  • Citations25

Basics of Supervised Deep Learning

  • Mar 15, 2019
  • M Arif Wani +3
  • Research Article
  • Citations11

Advancing aquifer vulnerability mapping through integrated deep learning approaches

  • Oct 29, 2024
  • Journal of Cleaner Production
  • Fatemeh Faal +3
  • Research Article

Real-Time Mental Health Monitoring and Intervention Using Unsupervised Deep Learning on EEG Data

  • Sep 08, 2025
  • Jordan Medical Journal
  • Geeta Sandeep Nadella +5
  • PDF
  • Research Article
  • Citations12

The Impact of a Number of Samples on Unsupervised Feature Extraction, Based on Deep Learning for Detection Defects in Printed Circuit Boards

  • Dec 23, 2021
  • Future Internet
  • Ihar Volkau +4
  • Research Article
  • Citations12

A framework towards data analytics on host–pathogen protein–protein interactions

  • Jan 20, 2020
  • Journal of Ambient Intelligence and Humanized Computing
  • Huaming Chen +3
  • Research Article
  • Citations20

An unsupervised deep learning model for dense velocity field reconstruction in particle image velocimetry (PIV) measurements

  • Jul 01, 2023
  • Physics of Fluids
  • Wei Zhang +3
  • Research Article
  • Citations3

EM-AUC: A Novel Algorithm for Evaluating Anomaly Based Network Intrusion Detection Systems

  • Dec 26, 2024
  • Sensors (Basel, Switzerland)
  • Kevin Z Bai +1
  • Research Article
  • Citations17

Data-Correlation-Aware Unsupervised Deep-Learning Model for Anomaly Detection in Cyber–Physical Systems

  • Nov 15, 2022
  • IEEE Internet of Things Journal
  • Liang Xi +2
  • PDF
  • Research Article
  • Citations78

Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery

  • Nov 20, 2021
  • Remote Sensing
  • Hejar Shahabi +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.