Software design and FPGA implementation of optimized medical image fusion techniques DOI

E. A. Elshazly,

Walid El‐Shafai,

Heba M. El‐Hoseny

et al.

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: March 20, 2025

Language: Английский

Current advances and future perspectives of image fusion: A comprehensive review DOI
Shahid Karim, Geng Tong,

Jinyang Li

et al.

Information Fusion, Journal Year: 2022, Volume and Issue: 90, P. 185 - 217

Published: Sept. 29, 2022

Language: Английский

Citations

128
Recent trend in medical imaging modalities and their applications in disease diagnosis: a review DOI
Barsha Abhisheka, Saroj Kr. Biswas, Biswajit Purkayastha

et al.

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(14), P. 43035 - 43070

Published: Oct. 16, 2023

Language: Английский

Citations

50
High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling DOI Creative Commons
Chih‐Wei Chang, Junbo Peng, Mojtaba Safari

et al.

Physics in Medicine and Biology, Journal Year: 2024, Volume and Issue: 69(4), P. 045001 - 045001

Published: Jan. 19, 2024

Abstract Objective . High-resolution magnetic resonance imaging (MRI) can enhance lesion diagnosis, prognosis, and delineation. However, gradient power hardware limitations prohibit recording thin slices or sub-1 mm resolution. Furthermore, long scan time is not clinically acceptable. Conventional high-resolution images generated using statistical analytical methods include the limitation of capturing complex, high-dimensional image data with intricate patterns structures. This study aims to harness cutting-edge diffusion probabilistic deep learning techniques create a framework for generating MRI from low-resolution counterparts, improving uncertainty denoising models (DDPM). Approach DDPM includes two processes. The forward process employs Markov chain systematically introduce Gaussian noise images. In reverse process, U-Net model trained denoise produce conditioned on features their counterparts. proposed was demonstrated T2-weighted institutional prostate patients brain collected in Brain Tumor Segmentation Challenge 2020 (BraTS2020). Main results For dataset, bicubic interpolation (Bicubic), conditional generative-adversarial network (CGAN), our improved quality measure by 4.4%, 5.7%, 12.8%, respectively. Our method enhanced signal-to-noise ratios 11.7%, surpassing Bicubic (9.8%) CGAN (8.1%). BraTS2020 peak ratio resolution-degraded 9.1% 5.8%. multi-scale structural similarity indexes were 0.970 ± 0.019, 0.968 0.022, 0.967 0.023 method, CGAN, Bicubic, Significance explores learning-based MR Such be used improve clinical workflow obtaining without penalty time. Future investigation will likely focus prospectively testing efficacy this different indications.

Language: Английский

Citations

19
An overview of methods and techniques in multimodal data fusion with application to healthcare DOI
Siwar Chaabene, Amal Boudaya, Bassem Bouaziz

et al.

International Journal of Data Science and Analytics, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 10, 2025

Language: Английский

Citations

2
Diagnosis of brain diseases in fusion of neuroimaging modalities using deep learning: A review DOI
Afshin Shoeibi, Marjane Khodatars, Mahboobeh Jafari

et al.

Information Fusion, Journal Year: 2022, Volume and Issue: 93, P. 85 - 117

Published: Dec. 14, 2022

Language: Английский

Citations

67
Background selection schema on deep learning-based classification of dermatological disease DOI

Jiancun Zhou,

Zheng Wu, Zixi Jiang

et al.

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 149, P. 105966 - 105966

Published: Aug. 17, 2022

Language: Английский

Citations

40
Advancing MRI with magnetic nanoparticles: a comprehensive review of translational research and clinical trials DOI Creative Commons

Radu Lapusan,

Raluca Borlan, Monica Focşan

et al.

Nanoscale Advances, Journal Year: 2024, Volume and Issue: 6(9), P. 2234 - 2259

Published: Jan. 1, 2024

The nexus of advanced technology and medical therapeutics has ushered in a transformative epoch contemporary medicine. Within this arena, Magnetic Resonance Imaging (MRI) emerges as paramount tool, intertwining the advancements with art healing. MRI's pivotal role is evident its broad applicability, spanning from neurological diseases, soft-tissue tumour characterization, to many more applications. Though already foundational, aspirations remain further enhance capabilities. A significant avenue under exploration incorporation innovative nanotechnological contrast agents. Forefront among these are Superparamagnetic Iron Oxide Nanoparticles (SPIONs), recognized for their adaptability safety profile. SPION's intrinsic malleability allows them be tailored improved biocompatibility, while functionality broadened when equipped specific targeting molecules. Yet, path optimization not devoid challenges, renal clearance concerns potential side effects stemming iron overload. This review endeavors map intricate journey SPIONs MRI agents, offering chronological perspective evolution deployment. We provide an in-depth current outline most representative impactful pre-clinical clinical studies centered on integration MRI, tracing trajectory foundational research

Language: Английский

Citations

16
Advanced Medical Image Segmentation Enhancement: A Particle-Swarm-Optimization-Based Histogram Equalization Approach DOI Creative Commons
Shoffan Saifullah, Rafał Dreżewski

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(2), P. 923 - 923

Published: Jan. 22, 2024

Accurate medical image segmentation is paramount for precise diagnosis and treatment in modern healthcare. This research presents a comprehensive study of the efficacy particle swarm optimization (PSO) combined with histogram equalization (HE) preprocessing segmentation, focusing on lung CT scan chest X-ray datasets. Best-cost values reveal PSO algorithm’s performance, HE demonstrating significant stabilization enhanced convergence, particularly complex images. Evaluation metrics, including accuracy, precision, recall, F1-score/Dice, specificity, Jaccard, show substantial improvements preprocessing, emphasizing its impact accuracy. Comparative analyses against alternative methods, such as Otsu, Watershed, K-means, confirm competitiveness PSO-HE approach, especially The also underscores positive influence clarity precision. These findings highlight promise approach advancing accuracy reliability pave way further method integration to enhance this critical healthcare application.

Language: Английский

Citations

10
Using an LSTM network to monitor industrial reactors using electrical capacitance and impedance tomography – a hybrid approach DOI Creative Commons
Grzegorz Kłosowski, Tomasz Rymarczyk, Konrad Niderla

et al.

Eksploatacja i Niezawodnosc - Maintenance and Reliability, Journal Year: 2023, Volume and Issue: unknown

Published: Jan. 27, 2023

The article presents a new concept for monitoring industrial tank reactors. presented allows faster and more reliable of processes, which increases their reliability reduces operating costs. innovative method is based on electrical tomography. At the same time, it non-invasive enables imaging phase changes inside tanks filled with liquid. In particular, hybrid tomograph can detect gas bubbles crystals formed during processes. main novelty described solution simultaneous use two types tomography: impedance capacitance. Another LSTM network to solve tomographic inverse problem. It was made possible by taking measurement vector as data sequence. Research has shown that proposed algorithm work better than separate systems or capacitance

Language: Английский

Citations

21
Traditional and deep-learning-based denoising methods for medical images DOI
Walid El‐Shafai,

Samy Abd El‐Nabi,

Anas M. Ali

et al.

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(17), P. 52061 - 52088

Published: Nov. 8, 2023

Language: Английский

Citations

17