Study on anatomical and functional medical image registration methods

Gupta, Sandesh; Gupta, Phalguni; Verma, Vivek Singh

doi:10.1016/j.neucom.2020.08.085

Cited by 17 publications

(3 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Amsterdam Open MRI Collection [83] MRI, fMRI, DWI (MR) ADNI [86] MRI, CT, CBCT, US, TRUS, x-ray NIREP, LPBA, IBSR, CUMC, MGH [87] CT, MRI, x-ray, PET, SPECT, fMRI, OASIS ,ABIDE, ADHD200, MCIC, PPMI, HABS, Harvard GSP, the FreeSurfer Buckner40 [88] MRI, US OASIS, HCP-A, BIRN [89] MRI IXI Brain Development Dataset [90] MRI ENIGMA-Schizophrenia DTI [91] DTI BLSA, Cutting Pediatrics, ABIDE, IXI, ADHD200, NDAR, OASIS, fcon_1000, NKI_rockland [92] MRI BraTS , ALBERTs, CT-MRI dataset, LPBA40, IBSR18, CUMC12, MGH10, Continuous Registration Challenge [93] CT, MRI Heart NIH ChestXray14 [94] MRI, x-ray NLST, DIR-Lab [95] CineMRI, CT Grand Challenges in Biomedical Image Analysis, The Cancer Imaging Archive, "ChestX-ray 8" [96] CT, MRI, PET, x-ray…”

Section: Brainmentioning

confidence: 99%

NRAAF: A Framework for Comparative Analysis of fMRI Registration Algorithms and Their Impact on Resting-State Neuroimaging Accuracy

Svejda,

Elmitwally,

Asyhari

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The rapid evolution of neuroimaging techniques underscores the necessity for robust medical image registration algorithms, essential for the precise analysis of resting-state networks. This study introduces a comprehensive modular evaluation framework, designed to assess and compare the differences of four state-of-the-art algorithms in the field: FSL, ANTs, DARTEL, and AFNI. Our framework highlights the critical importance of algorithm selection in neuroimaging, addressing the unique challenges and strengths each algorithm presents in processing complex brain imaging data. Our rigorous evaluation delves into the algorithms' differences, with a focus on spatial localisation accuracy and the fidelity of resting-state network identification. The comparative analysis uncovers distinct advantages and limitations inherent to each algorithm, illuminating how specific characteristics can shape neuroimaging study outcomes. For instance, we reveal FSL's robustness in handling diverse datasets, ANTs' precision in spatial normalization, DARTEL's suitability for large-scale studies, and AFNI's adaptability in functional and structural image analysis. The findings highlight the nuanced considerations necessary in choosing the right registration algorithm for neuroimaging data, advocating for a bespoke approach based on the unique requirements of each study. This detailed analysis advances the field, guiding researchers towards more informed algorithm selection and application, thus aiming to improve the accuracy and reliability of neuroimaging outcomes. Presenting a clear, comprehensive overview of each algorithm within our novel framework, the study addresses the needs of the neuroimaging community and paves the way for future advancements in medical image registration.

show abstract

Section: Brainmentioning

confidence: 99%

NRAAF: A Framework for Comparative Analysis of fMRI Registration Algorithms and Their Impact on Resting-State Neuroimaging Accuracy

Svejda,

Elmitwally,

Asyhari

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This is particularly beneficial in cases where a single imaging modality may not provide sufficient information for a conclusive diagnosis. By merging diverse data sources, clinicians can obtain a more accurate representation of the pathology, leading to improved decision-making and treatment planning [2]. As technology advances, the refinement of image fusion algorithms continues to enhance the precision and efficiency of the diagnostic process.…”

Section: Introductionmentioning

confidence: 99%

Quantifying Visual Harmony-Evaluating Image Fusion Metrics

Gupta,

Gupta

2024

International Journal of Innovative Research in Computer Science and Technology (IJIRCST)

View full text Add to dashboard Cite

The discipline of medical imaging has advanced significantly in recent years. In the field of multi-focus image fusion, where combining two images with different focus areas is essential to producing a coherent and informative result that can be used for research and study, following guidelines is crucial. To ensure that the fused image serves its intended purpose, precise integration of discrete focus zones is necessary. Performance indicators are essential to determining how well this fusion process is going. Performance indicators serve as important instruments for evaluation, offering a methodical way to rate the quality of the combined image. They serve as parameters to measure the efficacy of the fusion process, enabling a thorough examination of whether the resultant image aligns with predefined criteria and encapsulates all pertinent information. These metrics play a pivotal role in validating the success of the fusion process, ensuring that no crucial details are lost in the transition. In essence, this endeavor not only seeks to shed light on the intricacies of multi-focus image fusion but also endeavor to establish a framework for evaluating the success of the fusion process through a thorough examination of performance metrics. The comprehensive exploration of subjective and objective metrics serves as a guide to ascertain the suitability of each parameter, thereby advancing the understanding of how and when these metrics contribute to achieving optimal results in the field of image fusion.

show abstract

“…Therefore, the precision and robustness of the obtained transformation model are higher than the feature-based image registration ( Frakes et al, 2008 ). The commonly used gray-level-based image registration methods are sequential similarity detection algorithm (SSDA), cross-correlation, mutual information, and phase correlation ( Gupta et al, 2021 ). Based on the traditional algorithms, Yan et al (2010) extracted a fast and effective algorithm, SSDA.…”

Section: Introductionmentioning

confidence: 99%

Medical Image Registration Algorithm Based on Bounded Generalized Gaussian Mixture Model

Wang

Xiang²,

Chen³

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

In this paper, a method for medical image registration based on the bounded generalized Gaussian mixture model is proposed. The bounded generalized Gaussian mixture model is used to approach the joint intensity of source medical images. The mixture model is formulated based on a maximum likelihood framework, and is solved by an expectation-maximization algorithm. The registration performance of the proposed approach on different medical images is verified through extensive computer simulations. Empirical findings confirm that the proposed approach is significantly better than other conventional ones.

show abstract

Study on anatomical and functional medical image registration methods

Cited by 17 publications

References 118 publications

NRAAF: A Framework for Comparative Analysis of fMRI Registration Algorithms and Their Impact on Resting-State Neuroimaging Accuracy

NRAAF: A Framework for Comparative Analysis of fMRI Registration Algorithms and Their Impact on Resting-State Neuroimaging Accuracy

Quantifying Visual Harmony-Evaluating Image Fusion Metrics

Medical Image Registration Algorithm Based on Bounded Generalized Gaussian Mixture Model

Contact Info

Product

Resources

About