Cited by 3D-2D Medical Image Registration Technology and Its Application Development: a Survey

GPU-Based Parallel Processing Techniques for Enhanced Brain Magnetic Resonance Imaging Analysis: A Review of Recent Advances DOI

Ayca Kirimtat, Ondřej Krejcar

Sensors, Год журнала: 2024, Номер 24(5), С. 1591 - 1591

Опубликована: Фев. 29, 2024

The approach of using more than one processor to compute in order overcome the complexity different medical imaging methods that make up an overall job is known as GPU (graphic processing unit)-based parallel processing. It extremely important for several techniques such image classification, object detection, segmentation, registration, and content-based retrieval, since GPU-based allows time-efficient computation by a software, allowing multiple computations be completed at once. On other hand, non-invasive technology may depict shape anatomy biological advancements human body magnetic resonance (MRI). Implementing approaches brain MRI analysis with might helpful achieving immediate timely capture. Therefore, this extended review (the extension IWBBIO2023 conference paper) offers thorough overview literature emphasis on expanding use MRIs mentioned above, given need quicker acquire early real-time feedback medicine. Between 2019 2023, we examined articles matrix include tasks, techniques, sequences, results. As result, discussed demonstrate achieved until now minimizing computing runtime well obstacles problems still solved future.

Язык: Английский

Процитировано

Dual Vision Transformer-DSUNET With Feature Fusion for Brain Tumor Segmentation DOI

Mohammed Zakariah, Muna Al‐Razgan, Taha Alfakih

и другие.

Heliyon, Год журнала: 2024, Номер 10(18), С. e37804 - e37804

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

An optimizing technique for using MATLAB HDL coder DOI

Somaya Kayed, Ghada Elsayed

Bulletin of the National Research Centre/Bulletin of the National Research Center, Год журнала: 2023, Номер 47(1)

Опубликована: Июнь 30, 2023

Abstract Background MathWorks has provided an invaluable tool for designing and implementing FPGAs. MATLAB HDL coder serves a dual purpose, providing quick proof of concept on the one hand g easy-to-use platform testing verification other. It main drawbacks over these advantages; it generates code that is not optimized both area frequency. Results In this paper, we provide technique optimizing frequency without losing advantages. The most affecting problem found loops. This paper classifies loop writing purposes into two types. first preferable introduces ease few lines instead repeating code. second type intended to solve. Type II appearing when algorithm should perform several clock cycles. Writing traditionally, force synthesizer implement all repetitive cycles as hardware be done in cycle. cycle wide time slow optimization problem. We compare before after implementation our proposed technique. Conclusions used Xilinx Spartan 6 XC6SLX4-2CPG196 FPGA. Our improves number slice LUTs (Look Up Tables) requirement from 366 72%. improved from: 26.574 185.355 MHz. Based that, now recommend using FPGA Design.

Язык: Английский

Процитировано

Dual Vision Transformer-DSUNET With Feature Fusion for Brain Tumor Segmentation DOI

Mohammed Zakariah, Muna Al‐Razgan, Taha Alfakih

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Март 15, 2024

Abstract Brain tumors are one of the leading causes cancer death; screening early is best strategy to diagnose and treat brain tumors. Magnetic Resonance Imaging (MRI) extensively utilized for tumor diagnosis; nevertheless, achieving improved accuracy performance, which a critical challenge in most previously reported automated medical diagnostics, difficult problem. The study introduces Dual Vision Transformer-DSUNET model, incorporates feature fusion techniques provide precise efficient differentiation between other regions by leveraging multi-modal MRI data. impetus this arises from necessity automating segmentation process imaging, component realms diagnosis therapy strategy. To tackle issue BRATS 2020 dataset employed, an This encompasses images, including T1-weighted, T2-weighted, T1Gd (contrast-enhanced), FLAIR modalities. proposed model dual vision idea comprehensively capture heterogeneous properties across several imaging Moreover, utilization implemented augment amalgamation data originating modalities, hence enhancing dependability segmentation. evaluation model's performance conducted employing Dice Coefficient as prevalent metric quantifying accuracy. results obtained experiment exhibit remarkable with values 91.47% enhanced tumors, 92.38% core 90.88% edema. cumulative score entirety classes 91.29%. In addition, has high level accuracy, roughly 99.93%, underscores its durability efficacy task segmenting Experimental findings demonstrate integrity suggested architecture, quickly detection many diseases.

Язык: Английский

Процитировано

3D-2D Medical Image Registration Technology and Its Application Development: a Survey DOI

Handan Xiao

Опубликована: Окт. 20, 2023

Due to the lack of spatial topology information in 2D medical images, doctors cannot accurately identify tissues patients during clinical diagnosis and treatment. 3D images can make up for images' topolospatial topological symmetry. Registration image space enhance original images. 3D-2D registration technology plays a key role radiotherapy, image-guided surgery preoperative lesions diagnosis. This study examined 48 articles on registration. The article explains how is used techniques were analyzed. Finally, paper summarizes future development trends challenges

Язык: Английский

Процитировано