سامانه همایش‌ها TSTA | ثبت‌نام و ارسال مقاله کنفرانس‌ها و کنگره‌های ملی

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Accurate Brain Vessel Segmentation in T1-Weighted MRI based on UNETR: Improving Neurosurgical Planning

Authors :

Fatemeh Gholizadeh¹ Mahdiyeh Rahmani² Ahmad Pour-Rashidi³ Ebrahim Najafzadeh⁴ Parastoo Farnia⁵ Alireza Ahmadian⁶

1- دانشگاه علوم پزشکی تهران 2- دانشگاه علوم پزشکی تهران 3- Northwestern University 4- دانشگاه علوم پزشکی ایران 5- دانشگاه علوم پزشکی تهران 6- دانشگاه علوم پزشکی تهران

Keywords :

Brain Vessels Segmentation،T1CE MRI images،Deep Learning،Neurosurgical Pre-Planning

Abstract :

Preoperative planning for brain tumor surgeries is highly challenging and requires precise identification of vascular anatomy to minimize the risk of complications. While T1-weighted contrast-enhanced (T1CE) MRI is routinely used for preoperative assessment, automated vessel segmentation from these scans remains a significant challenge. The absence of reliable vessel maps can disrupt surgical workflows and may compromise patient safety, especially in settings where specialized angiographic imaging is not available. In this study, we propose a transformer-based UNETR model that leverages global contextual information to address the complexity of brain vessel segmentation. After standardized preprocessing, the model was trained and validated on 30 expert-annotated T1CE MRI scans. The approach achieved high performance, with a Dice score of 87%, IoU of 0.98, sensitivity of 0.99, and specificity of 0.99, showing strong capability in detecting both major vessels and smaller vascular branches. These findings highlight the potential of attention-based architectures to enhance routine clinical imaging by providing accurate vessel maps directly from standard MRI sequences already acquired for tumor evaluation. Such a framework could support safer and more efficient preoperative planning without requiring additional imaging resources.

Papers List

List of archived papers

An AI-Assisted Approach to Patient-specific 3D Modeling and Stress Analysis of the Temporomandibular Joint from CBCT Images

MOHAMMAD Akhlaghi - Masoud Shariat panahi - Sina Salehpour - Morad Karimpour - Hadi Ghatan Kashani

بررسی مفاهیم و کاربردهای جدید در حوزه یادگیری عمیق

سید حسن مرتضوی - علی عبدالعظیمی

Plasma Electrolytic Oxidation-Derived HAp–Ta₂O₅ Coatings on Ti6Al4V for Biomedical Applications

Milad Hosseini - Jafar Khalil allafi - Mir saman Safavi

A Combined Time-Frequency and Common Spatial-Spectral Pattern Approach for EEG-Based Motor Imagery Classification

Reza Nejati - Hamed Danandeh Hesar

Gait Retraining of Musculoskeletal Patients Using Deep Learning Techniques

Kourosh Alimadadi - Masoud Shariat Panahi - Morad Karimpour - Hadi Ghattan Kashani

مروری برمفاهیم دانش هیئت مدیره و فرآیندهای داخلی هیئت مدیره در حاکمیت شرکتی

زهرا سلیمانی زاده - زهره عارف منش

Innovative Biomimetic Skin Repair Strategies Utilizing Barium Titanate

Hossein Norouzi Bazmin Abadi - Zahra Mohammadi

Evaluating and Comparing Artificial Intelligence Tools in Solving Mathematical Problems

Marziyeh Felahat - Hossein Gholamalinejad

Microfluidic Flow-Focusing Systems for Alginate Microcapsule Preparation: Tuning Droplet Size and Frequency

Meisam Akbari laleh - Yasaman Pahlevanzadeh - Mina Shafiei - Javad Rahbar shahrouzi

Skin Thermomechanical Modeling: Assessing the Influence of Water and Ambient Air

Pezhman Namashiri - Akbar Allahverdizadeh - Fatemeh Khodadoost - Farid Vakili-Tahami