Optimizing Stroke Classification with Pre-Trained Deep Learning Models
Background/Objectives: Insufficient blood supply to the brain, whether due to blocked arteries (ischemic stroke) or bleeding (hemorrhagic stroke), leads to brain cell death and cognitive impairment. Ischemic strokes, which are more common, occur when blood flow to the brain is obstructed. Magnetic r...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Journal of Vascular Diseases |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2813-2475/3/4/36 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850241840215752704 |
|---|---|
| author | Serra Aksoy Pinar Demircioglu Ismail Bogrekci |
| author_facet | Serra Aksoy Pinar Demircioglu Ismail Bogrekci |
| author_sort | Serra Aksoy |
| collection | DOAJ |
| description | Background/Objectives: Insufficient blood supply to the brain, whether due to blocked arteries (ischemic stroke) or bleeding (hemorrhagic stroke), leads to brain cell death and cognitive impairment. Ischemic strokes, which are more common, occur when blood flow to the brain is obstructed. Magnetic resonance imaging (MRI) scans are essential for distinguishing stroke types, but precise and timely identification of ischemic strokes is crucial for effective treatment. Manual diagnosis can be difficult due to high patient volumes and time constraints in hospitals. This study aims to investigate the use of deep learning techniques for predicting ischemic strokes with high accuracy, enabling earlier diagnosis and intervention. Methods: The study utilized advanced deep learning algorithms, specifically ConvNeXt Base, to analyze large datasets of medical imaging data, focusing on MRI scans. The model was trained and validated on a labeled dataset to identify critical indicators and patterns associated with stroke risk. The performance of the model was evaluated based on accuracy metrics to determine its predictive capabilities. Results: ConvNeXt Base achieved an overall accuracy of 84% on the validation set, demonstrating its effectiveness in identifying ischemic strokes. The model was able to detect key patterns linked to stroke risk, highlighting its potential for use in clinical settings to aid in early diagnosis and decision-making. Conclusions: ConvNeXt Base reveals promise in improving stroke prediction accuracy, enabling earlier diagnosis and personalized treatment, which could lead to faster, more effective medical interventions. |
| format | Article |
| id | doaj-art-e4bea3aaca33461eb26e6ba00fc7ce48 |
| institution | OA Journals |
| issn | 2813-2475 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Vascular Diseases |
| spelling | doaj-art-e4bea3aaca33461eb26e6ba00fc7ce482025-08-20T02:00:28ZengMDPI AGJournal of Vascular Diseases2813-24752024-12-013448049410.3390/jvd3040036Optimizing Stroke Classification with Pre-Trained Deep Learning ModelsSerra Aksoy0Pinar Demircioglu1Ismail Bogrekci2Institute of Computer Science, Ludwig Maximilian University of Munich (LMU), Oettingenstrasse 67, 80538 Munich, GermanyInstitute of Materials Science, Technical University of Munich (TUM), Boltzmannstr. 15, 85748 Garching b. Munich, GermanyDepartment of Mechanical Engineering, Aydin Adnan Menderes University (ADU), Aytepe, 09010 Aydin, TurkeyBackground/Objectives: Insufficient blood supply to the brain, whether due to blocked arteries (ischemic stroke) or bleeding (hemorrhagic stroke), leads to brain cell death and cognitive impairment. Ischemic strokes, which are more common, occur when blood flow to the brain is obstructed. Magnetic resonance imaging (MRI) scans are essential for distinguishing stroke types, but precise and timely identification of ischemic strokes is crucial for effective treatment. Manual diagnosis can be difficult due to high patient volumes and time constraints in hospitals. This study aims to investigate the use of deep learning techniques for predicting ischemic strokes with high accuracy, enabling earlier diagnosis and intervention. Methods: The study utilized advanced deep learning algorithms, specifically ConvNeXt Base, to analyze large datasets of medical imaging data, focusing on MRI scans. The model was trained and validated on a labeled dataset to identify critical indicators and patterns associated with stroke risk. The performance of the model was evaluated based on accuracy metrics to determine its predictive capabilities. Results: ConvNeXt Base achieved an overall accuracy of 84% on the validation set, demonstrating its effectiveness in identifying ischemic strokes. The model was able to detect key patterns linked to stroke risk, highlighting its potential for use in clinical settings to aid in early diagnosis and decision-making. Conclusions: ConvNeXt Base reveals promise in improving stroke prediction accuracy, enabling earlier diagnosis and personalized treatment, which could lead to faster, more effective medical interventions.https://www.mdpi.com/2813-2475/3/4/36strokeischemic strokeMRI scansdeep learningConvNeXt Base |
| spellingShingle | Serra Aksoy Pinar Demircioglu Ismail Bogrekci Optimizing Stroke Classification with Pre-Trained Deep Learning Models Journal of Vascular Diseases stroke ischemic stroke MRI scans deep learning ConvNeXt Base |
| title | Optimizing Stroke Classification with Pre-Trained Deep Learning Models |
| title_full | Optimizing Stroke Classification with Pre-Trained Deep Learning Models |
| title_fullStr | Optimizing Stroke Classification with Pre-Trained Deep Learning Models |
| title_full_unstemmed | Optimizing Stroke Classification with Pre-Trained Deep Learning Models |
| title_short | Optimizing Stroke Classification with Pre-Trained Deep Learning Models |
| title_sort | optimizing stroke classification with pre trained deep learning models |
| topic | stroke ischemic stroke MRI scans deep learning ConvNeXt Base |
| url | https://www.mdpi.com/2813-2475/3/4/36 |
| work_keys_str_mv | AT serraaksoy optimizingstrokeclassificationwithpretraineddeeplearningmodels AT pinardemircioglu optimizingstrokeclassificationwithpretraineddeeplearningmodels AT ismailbogrekci optimizingstrokeclassificationwithpretraineddeeplearningmodels |