0% Complete
English
صفحه اصلی
/
سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران
Leveraging Normal White Matter Hyperintensity Context for Enhanced Pathological Segmentation via Multi-Class Deep Learning
نویسندگان :
Mahdi Bashiri Bawil
1
Mousa Shamsi
2
Ali Fahmi Jafargholkhanloo
3
Abolhassan Shakeri Bavil
4
1- Tabriz University of Technology (Sahand)
2- Tabriz University of Technology (Sahand)
3- University of Mohaghegh Ardabili
4- Department of Radiology, Imam Reza Hospital Tabriz University of Medical Sciences Tabriz, Iran
کلمات کلیدی :
White matter hyperintensities (WMH)،deep learning،medical image segmentation،FLAIR MRI،multi-class classification،U-Net،pathological segmentation،neuroimaging
چکیده :
White matter hyperintensities (WMHs) on FLAIR MRI are critical indicators of cerebrovascular dysfunction associated with elevated risks of stroke, dementia, and death. Current automated segmentation methods suffer from false positive detection in periventricular regions, failing to distinguish normal or aging-related hyperintensities from pathologically significant lesions, which reduces clinical applicability and diagnostic accuracy. This study investigates whether training deep learning models to explicitly differentiate between normal and abnormal WMH improves pathological WMH segmentation performance compared to traditional binary approaches. Four state-of-the-art architectures (U-Net, Attention U-Net, DeepLabV3Plus, Trans-U-Net) were evaluated across two training scenarios using 1,974 FLAIR images from 100 MS patients with expert-annotated ground truths. Scenario 1 employed binary training (background vs abnormal WMH), while Scenario 2 utilized three-class training (background, normal WMH, abnormal WMH). Statistical analysis included paired t-tests and Cohen's d effect size calculations. U-Net achieved the most substantial improvement in Scenario 2 with 55.6% increase in Dice coefficient (0.693 vs 0.443) and 131% precision enhancement (p < 0.0001, Cohen's d = 0.971). Traditional CNN-based architectures demonstrated larger effect sizes than transformer-based models. The three-class training approach significantly enhances pathological WMH segmentation while maintaining clinical feasibility, providing a validated framework for improving automated neuroimaging tools' diagnostic utility.
لیست مقالات
لیست مقالات بایگانی شده
Plasma Electrolytic Oxidation-Derived HAp–Ta₂O₅ Coatings on Ti6Al4V for Biomedical Applications
Milad Hosseini - Jafar Khalil allafi - Mir saman Safavi
Depression detection based on EEG signal analysis utilizing Inter-hemispheric Asymmetry and Correlation Dimension assessment
Amirreza Ahmadi - Saeid Yarmohammdi - Ali Zeraatkar - Reza Rostami
کاربردها، تکنیکها، چالشها و ملاحظات اخلاقی و اجتماعی در سیستمهای پیشنهاددهنده
کیانا رحیمی - سمانه شیبانی
Mechanical properties of cancer cells as potential predictive biomarkers
Sayed Reza Ramezani - Afsaneh Mojra
بررسی تاثیر انعطاف پذیری مالی بر رابطه بین مدیریت ریسک و اجتناب مالیاتی
علیرضا عظیمی ثانی - رضا پورتقی
Corrective Insoles Enhance Center of Mass Stability During Stair Descent in Individuals with Leg Length Discrepancy
Kasra Alborzi - Alireza Hashemi Oskouei - Pouya Mansouri - Seyed Mehran Ayati Najafabadi
تاثیر هوش مصنوعی بر فرآیند تصمیمگیری دراستراتژیهای بازاریابی
مهدی بهشتی مقدم
مروری بر سیر تحول نظری برنامهریزی منطقهای مبتنی بر زنجیره ارزش با تاکید بر صنایع نساجی و پوشاک
محسن رفیعیان - شبنم جعفری
حسابداران مدیریت و حسابداری مدیریت استراتژیک نقش فرهنگ سازمانی و سیستمهای اطلاعاتی
حبیب عباس فرمند
Phase-Amplitude Coupling Reflects Functional Cortical Engagement During Dynamic and Static Motor Tasks
Seyed Saman Sajadi - Ahmad Reza Keihani - Fateme Karbasi - Mohammad Amin Fathollahi - Shahriar Nafissi - Erfan Azizi - Amir Homayoun Jafari
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.2