Article
Neurosciences
Berke Doga Basaran, Paul M. Matthews, Wenjia Bai
Summary: This article proposes a deep learning-based pipeline for new lesion detection and segmentation in multiple sclerosis (MS), which performs well in the MICCAI 2021 MS new lesion segmentation challenge. By employing various data augmentation methods, the pipeline achieves significant improvement in lesion detection and segmentation performance.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Mathematics
Rehan Ahmad Khan Sherwani, Sadia Iqbal, Shumaila Abbas, Muhammad Aslam, Ali Hussein AL-Marshadi
Summary: This research introduces the neutrosophic negative binomial distribution to address issues related to interval-valued data under the negative binomial distribution, including derivations of various properties of the proposed distribution and discussions on its applications in real data scenarios.
JOURNAL OF MATHEMATICS
(2021)
Article
Neurosciences
Liliana Valencia, Albert Clerigues, Sergi Valverde, Mostafa Salem, Arnau Oliver, Alex Rovira, Xavier Llado
Summary: The assessment of disease activity using serial brain MRI scans is an important strategy for monitoring treatment response in multiple sclerosis patients. This paper investigates the impact of using synthetic T1-w images on the performance of a state-of-the-art approach for lesion detection, showing the advantages of synthetic images.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Neurosciences
Giordano Gentile, Mark Jenkinson, Ludovica Griffanti, Ludovico Luchetti, Matteo Leoncini, Maira Inderyas, Marzia Mortilla, Rosa Cortese, Nicola De Stefano, Marco Battaglini
Summary: In this study, a novel tool called BIANCA-MS is presented for brain white matter lesion segmentation in multiple sclerosis (MS). BIANCA-MS is able to generalize across different MRI acquisition protocols and heterogeneity of manually labeled data. It outperformed other available tools in high- and low-resolution images and provided comparable performance across different scanning protocols, sets of modalities, and image resolutions. The findings suggest that BIANCA-MS is a robust and accurate approach for automated MS lesion segmentation.
HUMAN BRAIN MAPPING
(2023)
Article
Neurosciences
Dongnan Liu, Mariano Cabezas, Dongang Wang, Zihao Tang, Lei Bai, Geng Zhan, Yuling Luo, Kain Kyle, Linda Ly, James Yu, Chun-Chien Shieh, Aria Nguyen, Ettikan Kandasamy Karuppiah, Ryan Sullivan, Fernando Calamante, Michael Barnett, Wanli Ouyang, Weidong Cai, Chenyu Wang
Summary: This paper proposes a Federated Learning (FL) framework for multiple sclerosis (MS) lesion segmentation, applying two effective re-weighting mechanisms to address the challenges in FL's applications in neuroimage analysis tasks. The experimental results demonstrate the superiority of the proposed method over other FL methods, and the segmentation performance of FL incorporating the proposed aggregation mechanism can achieve comparable performance to that from centralized training with all the raw data.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Clinical Neurology
Sandra M. Hurtado Rua, Ulrike W. Kaunzner, Sneha Pandya, Elizabeth Sweeney, Ceren Tozlu, Amy Kuceyeski, Thanh D. Nguyen, Susan A. Gauthier
Summary: The study analyzed MS patients using MRI features and grouped them into two distinct patient clusters. Lesion MWF and volume distribution played a significant role in cluster formation, which was associated with patient EDSS evaluations.
EUROPEAN JOURNAL OF NEUROLOGY
(2022)
Article
Clinical Neurology
Markus Lauerer, Julian McGinnis, Matthias Bussas, Malek El Husseini, Viola Pongratz, Christina Engl, Alexander Wuschek, Achim Berthele, Isabelle Riederer, Jan S. Kirschke, Claus Zimmer, Bernhard Hemmer, Mark Muehlau
Summary: Spinal cord lesions are associated with unfavorable clinical outcomes in multiple sclerosis. The relation between the number and volume of spinal cord lesions and the future occurrence and type of disability accumulation remains largely unexplored.
JOURNAL OF NEUROLOGY NEUROSURGERY AND PSYCHIATRY
(2023)
Article
Clinical Neurology
Riccardo Galbusera, Erik Bahn, Matthias Weigel, Sabine Schaedelin, Jonas Franz, Po-Jui Lu, Muhamed Barakovic, Lester Melie-Garcia, Peter Dechent, Antoine Lutti, Pascal Sati, Daniel S. Reich, Govind Nair, Wolfgang Brueck, Ludwig Kappos, Christine Stadelmann, Cristina Granziera
Summary: Quantitative MRI (qMRI) is used to explore the microstructural properties of the central nervous system (CNS) by measuring the biophysical characteristics of tissue. This study aimed to identify qMRI measures that can distinguish different histological lesion types in postmortem multiple sclerosis (MS) brains, particularly remyelinated lesions. The study also investigated the relationship between these qMRI measures and quantitative histological markers of myelin, axons, and astrocytes. The results demonstrate the potential of qMRI in differentiating MS lesions and provide insights into the associations between qMRI measures and specific tissue components.
Article
Clinical Neurology
Ashok Adams, William Tilden, Jonathan Bestwick, David Holden, Lucia Bianchi, Ide Smets, Gavin Giovannoni, Sharmilee Gnanapavan
Summary: The study found that the relationship between CSF NfL and MRI activity and lesion location is unclear, but MRI activity can explain 53% of the variation in CSF NfL.
EUROPEAN JOURNAL OF NEUROLOGY
(2022)
Article
Biology
Francesco La Rosa, Thomas Yu, German Barquero, Jean-Philippe Thiran, Cristina Granziera, Meritxell Bach Cuadra
Summary: This study aims to improve automatic lesion and tissue segmentation in multiple sclerosis patients by generating MP2RAGE UNI images from acquired MPRAGE images using a generative adversarial network (GAN). Results showed that synthetic MP2RAGE UNI significantly enhanced lesion and tissue segmentation compared to MPRAGE, with no statistically significant differences between the synthetic and acquired MP2RAGE UNI.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Biology
Maryam Hashemi, Mahsa Akhbari, Christian Jutten
Summary: This paper proposes a framework for segmenting lesions of Multiple Sclerosis (MS) using modified U-Net and modified Attention U-Net. By applying preprocessing, modifying the loss function, and using the union of FLAIR and T2 predictions, the performance is significantly improved.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Clinical Neurology
Bence Bozsik, Eszter Toth, Ilona Polyak, Fanni Kerekes, Nikoletta Szabo, Krisztina Bencsik, Peter Klivenyi, Zsigmond Tamas Kincses
Summary: The lesion number and burden are important indicators for predicting the outcome and progression of multiple sclerosis. The localization of the lesions also plays a significant role in disease progression. However, the reproducibility of lesion count is not well-known. In this study, five raters evaluated lesion count in different localizations in 140 patients with multiple sclerosis. The results showed moderate reproducibility overall, with the optic nerve region and atrophy judgment showing the worst results. Higher reproducibility was found when the lesion count was in the mid-range.
FRONTIERS IN NEUROLOGY
(2022)
Article
Clinical Neurology
Karolina Kania, Wojciech Ambrosius, Wojciech Kozubski, Alicja Kalinowska
Summary: Balo's concentric sclerosis (BCS) is a rare demyelinating disorder with a debated connection to classic multiple sclerosis. Our report presents a case of a patient who developed a symptomatic Balo-like lesion following years of treatment for relapsing-remitting multiple sclerosis with dimethyl fumarate.
FRONTIERS IN NEUROLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Besma Mnassri, Amira Echtioui, Fathi Kallel, Ahmed Ben Hamida, Mariem Dammak, Chokri Mhiri, Kheireddine Ben Mahfoudh
Summary: Multiple sclerosis (MS) is a serious neurological disease that often leads to non-traumatic disability in young adults. Early diagnosis of MS through magnetic resonance imaging (MRI) is crucial, but low contrast MRI images can hide important information. Researchers have proposed a new automated contrast enhancement method to improve the low contrast of MRI images and enhance the detection of MS lesions. Experimental results demonstrate the effectiveness of the developed method compared to conventional contrast enhancement techniques.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Neuroimaging
Hang Zhang, Jinwei Zhang, Chao Li, Elizabeth M. Sweeney, Pascal Spincemaille, Thanh D. Nguyen, Susan A. Gauthier, Yi Wang
Summary: The ALL-Net algorithm, based on deep convolutional neural network and anatomic information, achieved significant improvements in both pixel-wise and lesion-wise metrics on the ISBI-2015 challenge dataset and the Cornell MS dataset. This method effectively addressed the challenges of accurately detecting and segmenting MS brain lesions.
NEUROIMAGE-CLINICAL
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ivar J. H. G. Wamelink, Joost P. A. Kuijer, Beatriz E. Padrela, Yi Zhang, Frederik Barkhof, Henk J. M. M. Mutsaerts, Jan Petr, Elsmarieke van de Giessen, Vera C. Keil
Summary: This study investigates the reproducibility of cerebral APT-CEST imaging in healthy tissue and gliomas at 3 T. The results indicate that cerebral APT-CEST shows good scan-rescan reproducibility in healthy tissue and tumors, and short-term measurement effects may be the dominant components for reproducibility.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Endocrinology & Metabolism
Khazar Ahmadi, Joana B. Pereira, David Berron, Jacob Vogel, Silvia Ingala, Olof T. Strandberg, Shorena Janelidze, Frederik Barkhof, Josef Pfeuffer, Linda Knutsson, Danielle van Westen, Sebastian Palmqvist, Henk J. M. M. Mutsaerts, Oskar Hansson
Summary: This study investigated the role of decreased cerebral blood flow in Alzheimer's disease and found that tau tangles and neurodegeneration are more closely connected with GM-CBF changes than A beta pathology.
JOURNAL OF CEREBRAL BLOOD FLOW AND METABOLISM
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Junjie Li, Peng Zhang, Liying Qu, Ting Sun, Yunyun Duan, Minghao Wu, Jinyuan Weng, Zhaohui Li, Xiaodong Gong, Xing Liu, Yongzhi Wang, Wenqing Jia, Xiaorui Su, Qiang Yue, Jianrui Li, Zhiqiang Zhang, Frederik Barkhof, Raymond Y. Huang, Ken Chang, Haris Sair, Chuyang Ye, Liwei Zhang, Zhizheng Zhuo, Yaou Liu
Summary: A deep learning approach was developed to predict H3 K27M mutation in diffuse midline glioma using T2-weighted images. The segmentation performance and predictive accuracy of H3 K27M mutation status in both midline brain gliomas and spinal cord gliomas were evaluated. The method showed good predictive performance across different institutions.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Clinical Neurology
H. Vrenken, M. Battaglini, M. L. de Vos, G. J. Nagtegaal, B. C. A. Teixeira, A. Seitzinger, D. Jack, M. P. Sormani, B. M. J. Uitdehaag, A. Versteeg, G. Comi, L. Kappos, N. De Stefano, F. Barkhof
Summary: A post hoc analysis found that subcutaneous interferon ss-1a (sc IFN ss-1a) treatment can reduce the number of new lesions and the likelihood of these lesions evolving into black holes in patients with a first clinical demyelinating event (FCDE), compared to placebo.
JOURNAL OF NEUROLOGY
(2023)
Review
Clinical Neurology
Massimo Filippi, Paolo Preziosa, Douglas L. Arnold, Frederik Barkhof, Daniel M. Harrison, Pietro Maggi, Caterina Mainero, Xavier Montalban, Elia Sechi, Brian G. Weinshenker, Maria A. Rocca
Summary: The use of MRI in the diagnosis of MS has evolved considerably, with the introduction of the 2017 McDonald criteria and new MRI markers. Artificial intelligence tools may complement human assessment in improving diagnosis and patient classification.
JOURNAL OF NEUROLOGY
(2023)
Article
Clinical Neurology
C. Mallinckrodt, Y. Tian, P. S. Aisen, F. Barkhof, S. Cohen, G. Dent, O. Hansson, K. Harrison, T. Iwatsubo, C. J. Mummery, K. K. Muralidharan, I. Nestorov, L. Nisenbaum, R. Rajagovindan, C. von Hehn, C. H. van Dyck, B. Vellas, S. Wu, Y. Zhu, A. Sandrock, T. Chen, S. Budd Haeberlein
Summary: Post-hoc analyses of the EMERGE and ENGAGE studies showed that the outcomes in the high-dose group of ENGAGE were affected by an imbalance in a small number of rapidly progressing patients and lower exposure to the target dose. However, these factors were only present in early enrolled patients and did not affect later enrolled patients. Baseline characteristics and amyloid-related imaging abnormalities did not contribute to the difference in results between the high-dose arms.
JPAD-JOURNAL OF PREVENTION OF ALZHEIMERS DISEASE
(2023)
Article
Clinical Neurology
Eline Coerver, Sophie Janssens, Aroosa Ahmed, Mark Wessels, Zoe van Kempen, Bas Jasperse, Frederik Barkhof, Marcus Koch, Jop Mostert, Bernard Uitdehaag, Joep Killestein, Eva Strijbis
Summary: Inflammatory disease activity in multiple sclerosis (MS) decreases with advancing age, and this study investigated the relation between age and MRI measures of inflammatory disease activity in a real-world cohort of people with relapse onset MS.
EUROPEAN JOURNAL OF NEUROLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Denise Visser, Sander C. J. Verfaillie, Iris Bosch, Iman Brouwer, Hayel Tuncel, Emma M. Coomans, Roos M. Rikken, Sophie E. Mastenbroek, Sandeep S. V. Golla, Frederik Barkhof, Elsmarieke van de Giessen, Bart N. M. van Berckel, Wiesje M. van der Flier, Rik Ossenkoppele
Summary: The purpose of this study was to investigate the association between Tau pathology, atrophy, and cerebral blood flow (CBF) in Alzheimer's disease (AD). The results showed that increased Tau load was associated with cortical thinning, but not with decreased relative CBF. Baseline Tau PET load was a stronger predictor of cortical thinning than changes in Tau PET signal over time.
EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING
(2023)
Article
Neurosciences
Mathijs B. J. Dijsselhof, Michelle Barboure, Michael Stritt, Wibeke Nordhoy, Alle Meije Wink, Dani Beck, Lars T. Westlye, James H. Cole, Frederik Barkhof, Henk J. M. M. Mutsaerts, Jan Petr
Summary: This study investigated the optimal combination of structural and physiological MRI features and algorithms for brain age prediction. The addition of ASL features to structural brain age, combined with the ElasticNetCV algorithm, improved brain age prediction the most and performed best in a cross-sectional and repeatability comparison.
HUMAN BRAIN MAPPING
(2023)
Article
Clinical Neurology
Alberto Calvi, Zoe Mendelsohn, Weaam Hamed, Declan Chard, Carmen Tur, Jon Stutters, David MacManus, Baris Kanber, Claudia A. M. Gandini Wheeler-Kingshott, Frederik Barkhof, Ferran Prados
Summary: This study retrospectively analyzed a fingolimod trial in patients with primary progressive MS (PPMS) and found that newly appearing lesions are common and can develop into chronic active lesions. Treatment can reduce the number of these lesions.
EUROPEAN JOURNAL OF NEUROLOGY
(2023)
Article
Peripheral Vascular Disease
Julia H. I. Wiersinga, Hanneke F. M. Rhodius-Meester, Frank J. Wolters, Marijke C. Trappenburg, Afina W. Lemstra, Frederik Barkhof, Mike J. L. Peters, Wiesje M. van der Flier, Majon Mueller
Summary: Orthostatic hypotension (OH) is associated with cognitive decline and dementia, possibly through cerebral small vessel disease (CSVD). This study found that longer duration and larger magnitude of blood pressure drop were associated with increased risk of CSVD, but these associations were largely explained by high supine blood pressure.
JOURNAL OF HYPERTENSION
(2023)
Article
Clinical Neurology
Ying Jin, Dan Cheng, Yunyun Duan, Zhizheng Zhuo, Jinyuan Weng, Chengzhou Zhang, Mingwang Zhu, Xing Liu, Jiang Du, Tiantian Hua, Hongfang Li, Sven Haller, Frederik Barkhof, Yaou Liu
Summary: The purpose of this study was to investigate the predictive value of the soap bubble sign on molecular subtypes of posterior fossa ependymomas (PF-EPNs). The soap bubble sign was observed in PFB cases but not in PFA cases. The findings suggest that the soap bubble sign is a highly specific imaging marker for the PFB molecular subtype of PF-EPNs.
Review
Clinical Neurology
Janine Hendriks, Henk-Jan Mutsaerts, Richard Joules, Oscar Pena-Nogales, Paulo R. Rodrigues, Robin Wolz, George L. Burchell, Frederik Barkhof, Anouk Schrantee
Summary: This systematic review provides an overview of the available (semi-)automatic QC algorithms and software packages for raw, structural T1-weighted (T1w) MRI datasets, and analyzes the differences among these algorithms in terms of their features, performance, and benchmarks.
Article
Clinical Neurology
Rozemarijn M. Mattiesing, Eline Kramer, Eva M. M. Strijbis, Iman Brouwer, Ronald A. van Schijndel, Giordano Gentile, Marco Battaglini, Nicola De Stefano, Bernard M. J. Uitdehaag, Frederik Barkhof, Hugo Vrenken, Menno M. Schoonheim
Summary: The degree of inflammation and neurodegeneration after treatment initiation in multiple sclerosis (MS) can predict disease progression. This study found that global atrophy and/or pseudo-atrophy as well as positive lesion activity in MRI results during the first and second years of treatment were related to an increased probability and faster conversion to clinically definite MS. Negative lesion activity in the first year and slower central atrophy in the second year were predictive of disability progression.
MULTIPLE SCLEROSIS JOURNAL
(2023)
Article
Clinical Neurology
Nitin Sahi, Lukas Haider, Karen Chung, Ferran Prados Carrasco, Baris Kanber, Rebecca Samson, Alan J. Thompson, Claudia A. M. Gandini Wheeler-Kingshott, S. Anand Trip, Wallace Brownlee, Olga Ciccarelli, Frederik Barkhof, Carmen Tur, Henry Houlden, Declan Chard
Summary: This retrospective study explores the genetic influences on long-term disease course and severity in multiple sclerosis. The findings show that specific genes are associated with different pathological mechanisms of the disease, such as white matter inflammation, disability worsening, and the risk of developing secondary progressive multiple sclerosis. These findings are significant for a better understanding of the genetic factors and prognosis of multiple sclerosis.
BRAIN COMMUNICATIONS
(2023)