0% Complete
صفحه اصلی
/
سی و یکمین کنفرانس بین المللی مهندسی برق
Improved Attention U-Net combined with Conditional Random Field for Ischemic Lesion Segmentation from Magnetic Resonance Images
نویسندگان :
Ali Rezaei
1
Asieh Khosravanian
2
Habibollah Danyali
3
Kamran Kazemi
4
Ardalan Aarabi
5
1- دانشگاه صنعتی شیراز
2- دانشگاه صنعتی شیراز
3- دانشگاه صنعتی شیراز
4- دانشگاه صنعتی شیراز
5- University of Picardy Jules Verne
کلمات کلیدی :
Ischemic Stroke،Segmentation،Deep Learning،U-Net،Conditional Random Field
چکیده :
Stroke Lesion segmentation from magnetic resonance images is of great research interest due to its capability in providing appropriate clinical information for effective treatment of stroke. Deep learning methods have demonstrated promising results in medical image segmentation and U-Net is one of the most effective models. Nevertheless, these algorithms in the area of ischemic stroke lesion segmentation are in first stages of development and they lack performance compared to other problems for instance brain tumor segmentation. In this paper, we improved U-Net algorithm by applying blocks consist of depth-wise separable convolutions with skip connections instead of normal convolution layers and new attention blocks. Based on these improvements, the new architecture has better performance and accuracy with fewer parameter which would need simpler equipment for implementation. We utilized 3D fully connected Conditional Random Field (CRF) as post processing to improve the model prediction. Experimental results showed that the proposed end-to-end deep encoder-decoder model has a significant improvement compared to existing deep learning methods on the publicly available Anatomical Tracings of Lesion After Stroke (ATLAS) dataset.
لیست مقالات
لیست مقالات بایگانی شده
A Design Methodology for Submicron Low-Voltage Bandgap Voltage Reference
Mehdi Samavati - Samad Sheikhaei - Mohsen Jalali
Binomial Distribution based K-means for Graph Partitioning Approach in Partially Reconfigurable Computing system
Zahra Asgari - Maryam Sadat Mastoori
Optimization of 915nm laser diode asymmetric structure: experimental and theoretical studies in tandem
Seyed peyman Abbasi - Maryam Lajvardi - Arash Hodaei
Improving the Performance of ST-GCN on Multi-Site rs-fMRI Data Through Time Repetition Alignment
Mehrana Calagari - Hamidreza Hakimdavoodi
Development of Iterative Learning Control Method Based on Markov Parameters for High-Order Discrete-Time Singular Systems
Meysam Azhdari - Tahereh Binazadeh - Ali Gholami
بهینهسازی مبدلDC-DC منبع امپدانسی مبتنی بر ترانسفورماتور ایزوله گالوانیکی با کاهش تعداد سوئیچها
علی سلیمانی - رضا قاضی
Low-Leakage 6T SRAM Cell for In-Memory Computing with High Stability
Deniz Najafi - Behzad Ebrahimi
مرتب سازی اسپایک های عصبی با استخراج ویژگی مبتنی بر شبکه عمیق خود رمزگذار
شیدا معجونی - حسین حسینی نژاد محبتی - امین نیک انجام
A New Gradient Driver with only a Single DC Voltage Source For Using In MRI Systems
Amirabbas Naghipour Shahrbabaki - Reza Beiranvand
RCS Calculation of a Symmetrical Microstrip Array Using Discrete Bodies of Revolution Method
Hossein Mohammadzadeh - Abolghasem Zeidaabadi Nezhad - Zaker Hossein Firouzeh
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2