Ali Gholipour

Ali Gholipour

Auto-generated profile, based on publicly available information

Ali Gholipour

Harvard Medical School

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 March 2017 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AGAli Gholipour
Ali Gholipour
CRCaitlin K. Rollins
Caitlin K. Rollins
CVClemente Velasco-Annis
Clemente Velasco-Annis
AOAbdelhakim Ouaalam
Abdelhakim Ouaalam
AAAlireza Akhondi-Asl
Alireza Akhondi-Asl
SWSimon K. Warfield
Simon K. Warfield
Longitudinal characterization of early brain growthin-uterohas been limited by a number of challenges in fetal imaging, the rapid change in size, shape and volume of the developing brain, and the consequent lack of suitable algorithms for fetal brain image analysis. There is a need for an improved digital brain atlas of the spatiotemporal maturation of the fetal brain extending over the key developmental periods. We have developed an algorithm for construction of an unbiased four-dimensional atlas of the developing fetal brain by integrating symmetric diffeomorphic deformable registration in space with kernel regression in age. We applied this new algorithm to construct a spatiotemporal atlas from MRI of 81 normal fetuses scanned between 19 and 39 weeks of gestation and labeled the structures of the developing brain. We evaluated the use of this atlas and additional individual fetal brain MRI atlases for completely automatic multi-atlas segmentation of fetal brain MRI. The atlas is available online as a reference for anatomy and for registration and segmentation, to aid in connectivity analysis, and for groupwise and longitudinal analysis of early brain growth.

7 June 2010 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
AGAli Gholipour
Ali Gholipour
JEJ A Estroff
J A Estroff
SWSimon K. Warfield
Simon K. Warfield
Fast magnetic resonance imaging slice acquisition techniques such as single shot fast spin echo are routinely used in the presence of uncontrollable motion. These techniques are widely used for fetal magnetic resonance imaging (MRI) and MRI of moving subjects and organs. Although high-quality slices are frequently acquired by these techniques, inter-slice motion leads to severe motion artifacts that are apparent in out-of-plane views. Slice sequential acquisitions do not enable 3-D volume representation. In this study, we have developed a novel technique based on a slice acquisition model, which enables the reconstruction of a volumetric image from multiple-scan slice acquisitions. The super-resolution volume reconstruction is formulated as an inverse problem of finding the underlying structure generating the acquired slices. We have developed a robust M-estimation solution which minimizes a robust error norm function between the model-generated slices and the acquired slices. The accuracy and robustness of this novel technique has been quantitatively assessed through simulations with digital brain phantom images as well as high-resolution newborn images. We also report here successful application of our new technique for the reconstruction of volumetric fetal brain MRI from clinically acquired data.

10 February 2022 in Circulation
Verified
Journal Article
Closed access
PDF file
ASAnjali Sadhwani
Anjali Sadhwani
DWDavid Wypij
David Wypij
VRValerie Rofeberg
Valerie Rofeberg
AGAli Gholipour
Ali Gholipour
MMMaggie Mittleman
Maggie Mittleman
CRCaitlin K. Rollins
Caitlin K. Rollins
Background: Neurodevelopmental impairment is common in children with congenital heart disease (CHD), but postnatal variables explain only 30% of the variance in outcomes. To explore whether the antecedents for neurodevelopmental disabilities might begin in utero, we analyzed whether fetal brain volume predicted subsequent neurodevelopmental outcome in children with CHD. Methods: Fetuses with isolated CHD and sociodemographically comparable healthy control fetuses underwent fetal brain magnetic resonance imaging and 2-year neurodevelopmental evaluation with the Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III) and the Adaptive Behavior Assessment System, Third Edition (ABAS-3). Hierarchical regression evaluated potential predictors of Bayley-III and ABAS-3 outcomes in the CHD group, including fetal total brain volume adjusted for gestational age and sex, sociodemographic characteristics, birth measures, and medical history. Results: The CHD group (n=52) had lower Bayley-III cognitive, language, and motor scores than the control group (n=26), but fetal brain volumes were similar. Within the CHD group, larger fetal total brain volume correlated with higher Bayley-III cognitive, language, and motor scores and ABAS-3 adaptive functioning scores ( r =0.32–0.47; all P <0.05), but this was not noted in the control group. Fetal brain volume predicted 10% to 21% of the variance in neurodevelopmental outcome measures in univariate analyses. Multivariable models that also included social class and postnatal factors explained 18% to 45% of the variance in outcome, depending on developmental domain. Moreover, in final multivariable models, fetal brain volume was the most consistent predictor of neurodevelopmental outcome across domains. Conclusions: Small fetal brain volume is a strong independent predictor of 2-year neurodevelopmental outcomes and may be an important imaging biomarker of future neurodevelopmental risk in CHD. Future studies are needed to support this hypothesis. Our findings support inclusion of fetal brain volume in risk stratification models and as a possible outcome in fetal neuroprotective intervention studies.

1 February 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
SSSeyed Sadegh Mohseni Salehi
Seyed Sadegh Mohseni Salehi
SKShadab Khan
Shadab Khan
DEDeniz Erdogmus
Deniz Erdogmus
AGAli Gholipour
Ali Gholipour
With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-totemplate 3D rigid registration, we propose deep learning-based methods that are trained to find the 3D position of arbitrarily oriented subjects or anatomy in a canonical space based on slices or volumes of medical images. For this, we propose regression convolutional neural networks (CNNs) that learn to predict the angle-axis representation of 3D rotations and translations using image features. We use and compare mean square error and geodesic loss to train regression CNNs for 3D pose estimation used in two different scenarios: slice-to-volume registration and volume-to-volume registration. As an exemplary application, we applied the proposed methods to register arbitrarily oriented reconstructed images of fetuses scanned in-utero at a wide gestational age range to a standard atlas space. Our results show that in such registration applications that are amendable to learning, the proposed deep learning methods with geodesic loss minimization achieved 3D pose estimation with a wide capture range in real-time (< 100ms). We also tested the generalization capability of the trained CNNs on an expanded age range and on images of newborn subjects with similar and different MR image contrasts. We trained our models on T2-weighted fetal brain MRI scans and used them to predict the 3D pose of newborn brains based on T1-weighted MRI scans. We showed that the trained models generalized well for the new domain when we performed image contrast transfer through a conditional generative adversarial network. This indicates that the domain of application of the trained deep regression CNNs can be further expanded to image modalities and contrasts other than those used in training. A combination of our proposed methods with accelerated optimization-based registration algorithms can dramatically enhance the performance of automatic imaging devices and image processing methods of the future.

1 November 2014 in Concepts in Magnetic Resonance Part A
Verified
Journal Article
Open access
PDF file
AGAli Gholipour
Ali Gholipour
JEJudith A. Estroff
Judith A. Estroff
CBCarol E. Barnewolt
Carol E. Barnewolt
RRRichard L. Robertson
Richard L. Robertson
PGP. Ellen Grant
P. Ellen Grant
RMRobert V. Mulkern
Robert V. Mulkern
Fetal magnetic resonance imaging (MRI) examinations have become well‐established procedures at many institutions and can serve as useful adjuncts to ultrasound (US) exams when diagnostic doubts remain after US. Because of fetal motion, however, fetal MRI exams are challenging and require the MR scanner to be used in a somewhat different mode than that employed for more routine clinical studies. Herein we review the techniques most commonly used, and those that are available, for fetal MRI with an emphasis on the physics of the techniques and how to deploy them to improve success rates for fetal MRI exams. By far the most common technique employed is single‐shot T2‐weighted imaging due to its excellent tissue contrast and relative immunity to fetal motion. Despite the significant challenges involved, however, many of the other techniques commonly employed in conventional neuro‐ and body MRI such as T1 and T2*‐weighted imaging, diffusion, and perfusion weighted imaging, as well as spectroscopic methods remain of interest for fetal MR applications. An effort to understand the strengths and limitations of these basic methods within the context of fetal MRI is made in order to optimize their use and facilitate implementation of technical improvements for the further development of fetal MR imaging, both in acquisition and post‐processing strategies. © 2015 Wiley Periodicals, Inc. Concepts Magn Reson Part A 43A: 237–266, 2015.

1 August 2017 in NeuroImage
Verified
Journal Article
Closed access
BMBahram Marami
Bahram Marami
SSSeyed Sadegh Mohseni Salehi
Seyed Sadegh Mohseni Salehi
OAOnur Afacan
Onur Afacan
BSBenoit Scherrer
Benoit Scherrer
CRCaitlin K. Rollins
Caitlin K. Rollins
AGAli Gholipour
Ali Gholipour