0% Complete
English
صفحه اصلی
/
سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران
GPU-Accelerated GRAPPA: A Fast Implementation Using PyTorch for MRI Reconstruction
نویسندگان :
Mehrdad Anvari-Fard
1
Mahdi Bazargani
2
Mohammad Javad Heidari
3
Hamid Soltanian-Zadeh
4
1- School of Electrical and Computer Engineering, College of Engineering, University of Tehran Tehran, Iran
2- School of Electrical and Computer Engineering, College of Engineering, University of Tehran Tehran, Iran
3- School of Electrical and Computer Engineering, College of Engineering, University of Tehran Tehran, Iran
4- School of Electrical and Computer Engineering, College of Engineering, University of Tehran Tehran, Iran
کلمات کلیدی :
GRAPPA،MRI Reconstruction،Deep Learning،FastMRI،GPU acceleration
چکیده :
GeneRalized Autocalibrating Partial Parallel Acquisition (GRAPPA) is a widely used algorithm in MRI parallel imaging that reconstructs accelerated MRI scans by estimating the unknown phase-encoding lines omitted during k-space data acquisition. Unlike SENSE (Sensitivity Encoding), which operates in the image domain, GRAPPA directly processes k-space data and offers high reconstruction quality without requiring prior knowledge of coil sensitivity maps, making it one of the most commonly used algorithms for MRI reconstruction in clinical practice. Recent MRI reconstruction trends increasingly combine classical methods with deep learning, either as end-to-end trainable networks or hybrid pipelines that use physics-based operators within learning frameworks. GRAPPA is often employed as a preprocessing step before feeding slice information into deep learning models for MRI reconstruction. Despite its effectiveness, GRAPPA is typically a time-consuming part of the training process. In this work, we leverage the GPU capabilities of the PyTorch library and employ several optimization techniques to accelerate the GRAPPA algorithm. Our implementation is compared against the PyGRAPPA repository, developed by Nicholas McKibben, using a subset of the NYU fastMRI dataset. The results demonstrate that our optimized implementation achieves more than 40-fold speedup, which is statistically significant (p < 0.01) while maintaining equivalent image quality with no significant differences in reconstruction metrics (p > 0.05).
لیست مقالات
لیست مقالات بایگانی شده
حکمرانی داده و هوش مصنوعی در اقتصاد دیجیتال: چالش ها، چارچوب ها و الزامات اخلاقی
علیرضا فولاد - ابوالفضل حسین زاده - علی عبدلی
سنجش میزان رضایت مشتریان بانک ملی شهرستان تنکابن با استفاده از مدل MCPDA
محمد اخشابی
تاثیر بعد استراتژی مالی وبعد پاسخگویی برکیفیت خدمات درک شده و خشنودی مشتریان )مورد مطالعه : فروشگاه افق کوروش(
حسین بوذری
مقایسه تطبیقی پیشینه حاکمیت شرکتی در ایران و سایر کشورها
جمال خراسانی
تأثیر تجزیه و تحلیل ارقام صورتهای مالی بر تصمیمگیری مدیریتی در افزایش و کاهش قیمت سهام
علی نمازیان - سمیه کهنوجی
Preparation of a plant-based multifunctional nanocomposite hydrogel with conductivity and self-healing property for health monitoring
Nahid Salimiyan - Roya Sedghi - Sepehr Salighehdar
یادگیری تبدیل تصویر به کمک شبکههای مولد تخاصمی
امیر خاکپور
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
Influence of artificial intelligence in the mining industry and its role in the economic development
Parinesa Moshefi
Designing a Machine Learning Model with LSTM and CNNs to Make the Quality Control Process of Liquefied Gas Tankers Intelligent
Raha Pakzad
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.2