Back to Search
Start Over
An anomaly detection approach to identify chronic brain infarcts on MRI
- Source :
- Scientific Reports, Scientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
- Publication Year :
- 2021
- Publisher :
- Nature Publishing Group UK, 2021.
-
Abstract
- The performance of current machine learning methods to detect heterogeneous pathology is limited by the quantity and quality of pathology in medical images. A possible solution is anomaly detection; an approach that can detect all abnormalities by learning how ‘normal’ tissue looks like. In this work, we propose an anomaly detection method using a neural network architecture for the detection of chronic brain infarcts on brain MR images. The neural network was trained to learn the visual appearance of normal appearing brains of 697 patients. We evaluated its performance on the detection of chronic brain infarcts in 225 patients, which were previously labeled. Our proposed method detected 374 chronic brain infarcts (68% of the total amount of brain infarcts) which represented 97.5% of the total infarct volume. Additionally, 26 new brain infarcts were identified that were originally missed by the radiologist during radiological reading. Our proposed method also detected white matter hyperintensities, anomalous calcifications, and imaging artefacts. This work shows that anomaly detection is a powerful approach for the detection of multiple brain abnormalities, and can potentially be used to improve the radiological workflow efficiency by guiding radiologists to brain anomalies which otherwise remain unnoticed.
- Subjects :
- Male
medicine.medical_specialty
Cerebrovascular disorders
Science
Brain imaging
Article
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Image processing
Machine learning
Image Processing, Computer-Assisted
Medicine
Humans
Aged
Multidisciplinary
business.industry
Cerebral Infarction
Middle Aged
Magnetic Resonance Imaging
Hyperintensity
Infarct volume
Chronic Disease
Neural network architecture
Anomaly detection
Female
Radiology
Neural Networks, Computer
Mr images
business
Artifacts
030217 neurology & neurosurgery
Neurological disorders
Subjects
Details
- Language :
- English
- ISSN :
- 20452322
- Volume :
- 11
- Database :
- OpenAIRE
- Journal :
- Scientific Reports
- Accession number :
- edsair.doi.dedup.....4ccd22e0391b0aae3bcd72b0209a7ca1