Models to Identify Small Brain White Matter Hyperintensity Lesions

Topic: Brain proteins, microglia and lab models

According to the World Health Organization (WHO), peripheral and central neurological disorders affect approximately one billion people worldwide. Ischemic stroke and Alzheimer’s Disease and other dementias are the second and fifth leading causes of death, respectively. In this context, detecting and classifying brain lesions constitute a critical area of research in medical image processing, significantly impacting clinical practice. Traditional lesion detection, segmentation, and feature extraction methods are time-consuming and observer-dependent. In this sense, research in the machine and deep learning methods applied to medical image processing constitute one of the crucial tools for automatically learning hierarchical features to get better accuracy, quick diagnosis, treatment, and prognosis of diseases. This project aims to develop and implement deep learning models for detecting and classifying small brain White Matter hyperintensities (WMH) lesions in magnetic resonance images (MRI), specifically lesions concerning ischemic and demyelination diseases. The methods applied were the UNet and Segmenting Anything model (SAM) for segmentation, while YOLOV8 and Detectron2 (based on MaskRCNN) were also applied to detect and classify the lesions. Experimental results show a Dice coefficient (DSC) of 0.94, 0.50, 0.241, and 0.88 for segmentation of WMH lesions using the UNet, SAM, YOLOv8, and Detectron2, respectively. The Detectron2 model demonstrated an accuracy of 0.94 in detecting and 0.98 in classifying lesions, including small lesions where other models often fail. The methods developed give an outline for the detection, segmentation, and classification of small and irregular morphology brain lesions and could significantly aid clinical diagnostics, providing reliable support for physicians and improving patient outcomes.

Key findings

• In this context, detecting and classifying brain lesions constitute a critical area of research in medical image processing, significantly impacting clinical practice.
• Experimental results show a Dice coefficient (DSC) of 0.94, 0.50, 0.241, and 0.88 for segmentation of WMH lesions using the UNet, SAM, YOLOv8, and Detectron2, respectively.
• The Detectron2 model demonstrated an accuracy of 0.94 in detecting and 0.98 in classifying lesions, including small lesions where other models often fail.
• The methods developed give an outline for the detection, segmentation, and classification of small and irregular morphology brain lesions and could significantly aid clinical diagnostics, providing reliable support for physicians and improving patient outcomes.

Why it matters

This project developed deep learning models to detect and classify small white matter hyperintensity lesions on MRI, with the best model reaching high accuracy. It is a technical imaging study and does not test any treatment, cure or prevention for Alzheimer's disease.

Study details

• Evidence strengthLow

Read the original

• DOI: 10.3390/app15052830
• Original source →
• Free full text: Applied Sciences →

Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).

@article{castillo2025-1162a433,
  author  = {Castillo, Darwin and Rodríguez-Álvarez, María José and Samaniego, René and Lakshminarayanan, Vasudevan},
  title   = {{Models to Identify Small Brain White Matter Hyperintensity Lesions}},
  journal = {Applied Sciences},
  year    = {2025},
  doi     = {10.3390/app15052830},
  url     = {https://doi.org/10.3390/app15052830}
}

Related studies in Vascular contributions

• Progress of radiomics research on white matter hyperintensity lesions Frontiers in Neurology · 2025-08-26 · usefulness score 33/100
• The White Matter Hyperintensity Shape and Brain Clearance (WHIMAS) Study for Identification of Novel 7T Magnetic Resonance Imaging Markers of Cerebral Small Vessel Disease: Protocol for a Cross-Sectional Study JMIR Research Protocols · 2025-12-04 · usefulness score 40/100
• Protective Effects of Socioeconomic Status and Lifestyle on Amyloid‐ and White Matter Hyperintensity ‐Related Longitudinal Brain Atrophy and Cognitive Decline Annals of Neurology · 2025-08-09 · usefulness score 54/100
• Predicting White Matter Hyperintensity: Leveraging Portable MRI for Accessible Brain Health Screening American Journal of Neuroradiology · 2025-03-12 · usefulness score 53/100
• Insomnia, early and late rising are associated with small hippocampal volume and large white matter hyperintensity burden Alzheimer s Research & Therapy · 2025-04-05 · usefulness score 57/100
• DCE-MRI reveals spatial pattern in heterogeneous blood-brain barrier leakage within white matter in cerebral small vessel disease Journal of Cerebral Blood Flow & Metabolism · 2025-08-04 · usefulness score 47/100

Similar studies

• Association of Data-Driven White Matter Hyperintensity Spatial Signatures With Distinct Cerebral Small Vessel Disease Etiologies 2022 · Biomarkers
• Characterization of White Matter Hyperintensities in Large-Scale MRI-Studies 2019 · Disparities
• The clinical importance of white matter hyperintensities on brain magnetic resonance imaging: systematic review and meta-analysis 2010 · Vascular contributions
• Regional distribution of white matter hyperintensities in vascular dementia, Alzheimer's disease and healthy aging 2004 · Cognitive tests and assessment
• Testing the Association Between Neighborhood Disadvantage and White Matter Hyperintensities 2022 · Risk factors
• Identification of White Matter Hyperintensities in Routine Emergency Department Visits Using Portable Bedside Magnetic Resonance Imaging 2023 · Risk factors

More on Vascular contributions

• A review that covers this ground Do in vivo experimental models reflect human cerebral small vessel disease? A systematic review Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism · 2008-08-13 · usefulness score 64/100
• Newest in this subject Precision Nanocrystal Theranostics for Neurodegenerative Proteopathies: Strategies to Cross the Blood-Brain Barrier and Target Protein Aggregation Preprints.org · 2026-10-26 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Depth-Dependent Alterations in Cerebral Blood and Tissue Oxygenation Associated with Tau in Alzheimer’s Disease Models bioRxiv · 2026-10-16 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Vascular contributions →