دانشگاه مازندران

 آمار

تعداد نشریات31
تعداد شماره‌ها484
تعداد مقالات4,713
تعداد مشاهده مقاله7,347,796
تعداد دریافت فایل اصل مقاله5,492,740
Hashemi Kamangar, Mehrdad, Jalalzadeh, Amir Hossein. (1404). Deep Point Correspondence Estimation and SyN-Based Refinement for Multimodal Brain Image Registration. پژوهشنامه مدیریت اجرایی, (), -. doi: 10.22080/cste.2025.29117.1040
Mehrdad Hashemi Kamangar; Amir Hossein Jalalzadeh. "Deep Point Correspondence Estimation and SyN-Based Refinement for Multimodal Brain Image Registration". پژوهشنامه مدیریت اجرایی, , , 1404, -. doi: 10.22080/cste.2025.29117.1040
Hashemi Kamangar, Mehrdad, Jalalzadeh, Amir Hossein. (1404). 'Deep Point Correspondence Estimation and SyN-Based Refinement for Multimodal Brain Image Registration', پژوهشنامه مدیریت اجرایی, (), pp. -. doi: 10.22080/cste.2025.29117.1040
Hashemi Kamangar, Mehrdad, Jalalzadeh, Amir Hossein. Deep Point Correspondence Estimation and SyN-Based Refinement for Multimodal Brain Image Registration. پژوهشنامه مدیریت اجرایی, 1404; (): -. doi: 10.22080/cste.2025.29117.1040

Deep Point Correspondence Estimation and SyN-Based Refinement for Multimodal Brain Image Registration

Contributions of Science and Technology for Engineering
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 30 اردیبهشت 1404
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22080/cste.2025.29117.1040
نویسندگان
Mehrdad Hashemi Kamangar1؛ Amir Hossein Jalalzadeh* 2
1Department of Electrical and Electronic Engineering, Engineering Faculty, Shomal University, Amol, Iran
2Department of Biomedical Engineering, Engineering Faculty, Shahed University, Tehran, Iran
تاریخ دریافت: 08 اردیبهشت 1404،  تاریخ بازنگری: 30 اردیبهشت 1404،  تاریخ پذیرش: 30 اردیبهشت 1404 
چکیده
Accurate registration of preoperative Magnetic Resonance Imaging (MRI) with intraoperative ultrasound (US) is essential for effective neuronavigation, particularly in brain tumor surgeries where brain shift compromises anatomical fidelity. This study proposes a hybrid framework integrating a deep learning-based Multi-Layer Perceptron (MLP) with an optimization pipeline to enhance MR-to-US registration. The MLP is trained on paired anatomical landmarks extracted from the BITE and RESECT datasets to predict US coordinates from corresponding MRI points. An ensemble of five MLPs, weighted by inverse validation errors, is employed to estimate dense point correspondences, which are used to initialize an affine transformation. This transformation is refined using Symmetric Normalization (SyN) within the ANTs registration toolkit to model non-linear deformations. Quantitative evaluation demonstrates a mean squared error (MSE) of 0.1954 and a mean Euclidean distance of 4.97 mm—significantly outperforming a baseline rigid registration approach with 60% improvement in spatial alignment. The proposed pipeline executes in under 4 minutes per case on standard hardware, indicating potential for clinical integration. The results suggest combining learning-based correspondence prediction and classical registration yields accurate and computationally efficient multimodal Registration.
کلیدواژه‌ها
Image Registration؛ MRI؛ iUS؛ MLP؛ Deep Learning
آمار
تعداد مشاهده مقاله: 21


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب