Automatic 2D registration of renal perfusion image sequences by mutual information and adaptive prediction

Positano, Vincenzo; Bernardeschi, Ilaria; Zampa, Virna; Marinelli, Martina; Landini, Luigi; Santarelli, Maria Filomena

doi:10.1007/s10334-012-0337-4

Cited by 17 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluated perfusion reflected the renal function measured with serum creatinine in a cohort of 73 patients. The peak signal intensity, MTT, initial up-slope, and time-to-peak were also used to analyze the perfusion by Positano et al 83 Other research groups have exploited DCE-MRI for early detection of renal rejection following kidney transplantation. 10,[84][85][86][88][89][90][91][92] A DCE-MRI based CAD system for early diagnosis of acute renal transplant rejection proposed by Farag et al 85 and El-Baz et al 86,88 classified the kidney status of each patient using four indexes: peak signal intensity, time-to-peak, wash-in slope, and washout slope, calculated from the MRI signal for the kidney cortex.…”

Section: A Clinical Applications Of Nonparametric Approachesmentioning

confidence: 99%

“…The usefulness of the DCE-MRI in analyzing and predicting the survival of the breast cancer patients has been demonstrated also by Tuncbilek et al 59 Renal diseases, including cancer, artery stenosis, and transplant rejection, can also be diagnosed with nonparametric DCE-MRI techniques. 10,[81][82][83][84][85][86][87][88][89][90][91][92] A semiautomated framework by Ho et al 81 evaluated renal lesions, which were identified manually by observers, with a percentage of the enhancement ratio between the pre-and postcontrast signals in each set of images. A 15% threshold was used to distinguish between cysts and solid renal lesions.…”

Section: A Clinical Applications Of Nonparametric Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Models and methods for analyzing DCE‐MRI: A review

Khalifa¹,

Soliman²,

El-Baz³

et al. 2014

Medical Physics

261

230

View full text Add to dashboard Cite

show abstract

Section: A Clinical Applications Of Nonparametric Approachesmentioning

confidence: 99%

Section: A Clinical Applications Of Nonparametric Approachesmentioning

confidence: 99%

Models and methods for analyzing DCE‐MRI: A review

Khalifa¹,

Soliman²,

El-Baz³

et al. 2014

Medical Physics

261

230

View full text Add to dashboard Cite

show abstract

“…Others proposed registration algorithms based on MI. However, they all used a preregistration module before MI‐based registration.…”

Section: Discussionmentioning

confidence: 99%

Modified dixon‐based renal dynamic contrast‐enhanced MRI facilitates automated registration and perfusion analysis

Boer

Leiner

Vink

et al. 2017

Magnetic Resonance in Med

View full text Add to dashboard Cite

PurposeRenal dynamic contrast‐enhanced (DCE) MRI provides information on renal perfusion and filtration. However, clinical implementation is hampered by challenges in postprocessing as a result of misalignment of the kidneys due to respiration. We propose to perform automated image registration using the fat‐only images derived from a modified Dixon reconstruction of a dual‐echo acquisition because these provide consistent contrast over the dynamic series.MethodsDCE data of 10 hypertensive patients was used. Dual‐echo images were acquired at 1.5 T with temporal resolution of 3.9 s during contrast agent injection. Dixon fat, water, and in‐phase and opposed‐phase (OP) images were reconstructed. Postprocessing was automated. Registration was performed both to fat images and OP images for comparison. Perfusion and filtration values were extracted from a two‐compartment model fit.ResultsAutomatic registration to fat images performed better than automatic registration to OP images with visible contrast enhancement. Median vertical misalignment of the kidneys was 14 mm prior to registration, compared to 3 mm and 5 mm with registration to fat images and OP images, respectively (P = 0.03). Mean perfusion values and MR‐based glomerular filtration rates (GFR) were 233 ± 64 mL/100 mL/min and 60 ± 36 mL/minute, respectively, based on fat‐registered images. MR‐based GFR correlated with creatinine‐based GFR (P = 0.04) for fat‐registered images. For unregistered and OP‐registered images, this correlation was not significant.ConclusionAbsence of contrast changes on Dixon fat images improves registration in renal DCE MRI and enables automated postprocessing, resulting in a more accurate estimation of GFR. Magn Reson Med 80:66–76, 2018. © 2017 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

“…The evaluated perfusion reflected the renal function measured with serum creatinine in a cohort of 73 patients. The peak signal intensity, the MTT, the initial up-slope, and the time to peak were also used to analyze the perfusion by Positano et al [120]. Other research groups have exploited DCE-MRI for early detection of the renal rejection following the kidney transplantation [3,[121][122][123][124][125][126][127][128][129].…”

Section: Clinical Applications Of Nonparametric Approachesmentioning

confidence: 99%

Analysis of contrast-enhanced medical images.

Khalifa¹

View full text Add to dashboard Cite

DEDICATIONThis dissertation is dedicated to my mother. Words cannot express how much I wish that she was still with me to see the completion of this endeavor.iii ACKNOWLEDGMENTSIn the name of Allah the most merciful, the most compassionate. All deepest thanks are due to Almighty Allah for the uncountable gifts given to me.I would like to thank my dissertation advisor, Dr. Ayman El-Baz, for his continuous encouragement, guidance, and support over the course of my Ph.D. study. I thank him for giving me the opportunity to work in his research group and providing me the opportunity to work on promising applications and meet interesting people. Without his expertise, guidance, and commitment, my research would not have been possible. I truly appreciate his optimism whenever things looked impossible.I also express my deepest gratitude to Dr. Karla Conn Welch, my dissertation coadvisor, and Dr. Tamer Inanc, Dr. Cindy Harnett, Dr. Olfa Nasraoui, and Dr. Jake Wildstrom for being on my dissertation committee with enthusiasm and taking interest in my research in the midst of many other responsibilities and commitments.I also have to thank Dr. Georgy Gimel'farb for his useful discussions and valuable comments and feedback. He has never hesitated to share his experience in Markov-Gibbs random field and the field of image processing. I also would like to thank Dr. Mohamed Abou El-Ghar of the radiology department, Urology and Nephrology Center, University of Early detection of human organ diseases is of great importance for the accurate diagnosis and institution of appropriate therapies. This can potentially prevent progression to end-stage disease by detecting precursors that evaluate organ functionality. In addition, it also assists the clinicians for therapy evaluation, tracking diseases progression, and surgery operations. Advances in functional and contrast-enhanced (CE) medical images enabled accurate noninvasive evaluation of organ functionality due to their ability to provide superior anatomical and functional information about the tissue-of-interest. The main objective of this dissertation is to develop a computer-aided diagnostic (CAD) system for analyzing complex data from CE magnetic resonance imaging (MRI). The developed CAD system has been tested in three case studies: (i) early detection of acute renal transplant rejection,(ii) evaluation of myocardial perfusion in patients with ischemic heart disease after heart attack; and (iii), early detection of prostate cancer.However, developing a noninvasive CAD system for the analysis of CE medical images is subject to multiple challenges, including, but are not limited to, image noise and inhomogeneity, nonlinear signal intensity changes of the images over the time course of data acquisition, appearances and shape changes (deformations) of the organ-of-interest during data acquisition, determination of the best features (indexes) that describe the perfuvi sion of a contrast agent (CA) into the tissue. To address these challenges, this dissertation focuses on building n...

show abstract

Automatic 2D registration of renal perfusion image sequences by mutual information and adaptive prediction

Abstract: The developed method is able to automatically compensate for kidney motion in perfusion studies, which prevents the need for time-consuming manual image registration.

Cited by 17 publications

References 26 publications

Models and methods for analyzing DCE‐MRI: A review

Models and methods for analyzing DCE‐MRI: A review

Modified dixon‐based renal dynamic contrast‐enhanced MRI facilitates automated registration and perfusion analysis

Analysis of contrast-enhanced medical images.

Contact Info

Product

Resources

About