1
|
Phillips JS, Adluru N, Chung MK, Radhakrishnan H, Olm CA, Cook PA, Gee JC, Cousins KAQ, Arezoumandan S, Wolk DA, McMillan CT, Grossman M, Irwin DJ. Greater white matter degeneration and lower structural connectivity in non-amnestic vs. amnestic Alzheimer's disease. Front Neurosci 2024; 18:1353306. [PMID: 38567286 PMCID: PMC10986184 DOI: 10.3389/fnins.2024.1353306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2023] [Accepted: 02/26/2024] [Indexed: 04/04/2024] Open
Abstract
Introduction Multimodal evidence indicates Alzheimer's disease (AD) is characterized by early white matter (WM) changes that precede overt cognitive impairment. WM changes have overwhelmingly been investigated in typical, amnestic mild cognitive impairment and AD; fewer studies have addressed WM change in atypical, non-amnestic syndromes. We hypothesized each non-amnestic AD syndrome would exhibit WM differences from amnestic and other non-amnestic syndromes. Materials and methods Participants included 45 cognitively normal (CN) individuals; 41 amnestic AD patients; and 67 patients with non-amnestic AD syndromes including logopenic-variant primary progressive aphasia (lvPPA, n = 32), posterior cortical atrophy (PCA, n = 17), behavioral variant AD (bvAD, n = 10), and corticobasal syndrome (CBS, n = 8). All had T1-weighted MRI and 30-direction diffusion-weighted imaging (DWI). We performed whole-brain deterministic tractography between 148 cortical and subcortical regions; connection strength was quantified by tractwise mean generalized fractional anisotropy. Regression models assessed effects of group and phenotype as well as associations with grey matter volume. Topological analyses assessed differences in persistent homology (numbers of graph components and cycles). Additionally, we tested associations of topological metrics with global cognition, disease duration, and DWI microstructural metrics. Results Both amnestic and non-amnestic patients exhibited lower WM connection strength than CN participants in corpus callosum, cingulum, and inferior and superior longitudinal fasciculi. Overall, non-amnestic patients had more WM disease than amnestic patients. LvPPA patients had left-lateralized WM degeneration; PCA patients had reductions in connections to bilateral posterior parietal, occipital, and temporal areas. Topological analysis showed the non-amnestic but not the amnestic group had more connected components than controls, indicating persistently lower connectivity. Longer disease duration and cognitive impairment were associated with more connected components and fewer cycles in individuals' brain graphs. Discussion We have previously reported syndromic differences in GM degeneration and tau accumulation between AD syndromes; here we find corresponding differences in WM tracts connecting syndrome-specific epicenters. Determining the reasons for selective WM degeneration in non-amnestic AD is a research priority that will require integration of knowledge from neuroimaging, biomarker, autopsy, and functional genetic studies. Furthermore, longitudinal studies to determine the chronology of WM vs. GM degeneration will be key to assessing evidence for WM-mediated tau spread.
Collapse
Affiliation(s)
- Jeffrey S. Phillips
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Nagesh Adluru
- Waisman Center, University of Wisconsin-Madison, Madison, WI, United States
- Department of Radiology, University of Wisconsin-Madison, Madison, WI, United States
| | - Moo K. Chung
- Department of Biostatistics and Medical Informatics, School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI, United States
| | - Hamsanandini Radhakrishnan
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Christopher A. Olm
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Philip A. Cook
- Penn Image Computing and Science Laboratory, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - James C. Gee
- Penn Image Computing and Science Laboratory, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Katheryn A. Q. Cousins
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Sanaz Arezoumandan
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - David A. Wolk
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Penn Memory Center, University of Pennsylvania Health System, Philadelphia, PA, United States
| | - Corey T. McMillan
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Murray Grossman
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - David J. Irwin
- Penn Frontotemporal Degeneration Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
- Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| |
Collapse
|
2
|
Planche V, Mansencal B, Manjon JV, Meissner WG, Tourdias T, Coupé P. Staging of progressive supranuclear palsy-Richardson syndrome using MRI brain charts for the human lifespan. Brain Commun 2024; 6:fcae055. [PMID: 38444913 PMCID: PMC10914441 DOI: 10.1093/braincomms/fcae055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 12/22/2023] [Accepted: 02/19/2024] [Indexed: 03/07/2024] Open
Abstract
Brain charts for the human lifespan have been recently proposed to build dynamic models of brain anatomy in normal aging and various neurological conditions. They offer new possibilities to quantify neuroanatomical changes from preclinical stages to death, where longitudinal MRI data are not available. In this study, we used brain charts to model the progression of brain atrophy in progressive supranuclear palsy-Richardson syndrome. We combined multiple datasets (n = 8170 quality controlled MRI of healthy subjects from 22 cohorts covering the entire lifespan, and n = 62 MRI of progressive supranuclear palsy-Richardson syndrome patients from the Four Repeat Tauopathy Neuroimaging Initiative (4RTNI)) to extrapolate lifetime volumetric models of healthy and progressive supranuclear palsy-Richardson syndrome brain structures. We then mapped in time and space the sequential divergence between healthy and progressive supranuclear palsy-Richardson syndrome charts. We found six major consecutive stages of atrophy progression: (i) ventral diencephalon (including subthalamic nuclei, substantia nigra, and red nuclei), (ii) pallidum, (iii) brainstem, striatum and amygdala, (iv) thalamus, (v) frontal lobe, and (vi) occipital lobe. The three structures with the most severe atrophy over time were the thalamus, followed by the pallidum and the brainstem. These results match the neuropathological staging of tauopathy progression in progressive supranuclear palsy-Richardson syndrome, where the pathology is supposed to start in the pallido-nigro-luysian system and spreads rostrally via the striatum and the amygdala to the cerebral cortex, and caudally to the brainstem. This study supports the use of brain charts for the human lifespan to study the progression of neurodegenerative diseases, especially in the absence of specific biomarkers as in PSP.
Collapse
Affiliation(s)
- Vincent Planche
- Institut des Maladies Neurodégénératives, Univ. Bordeaux, CNRS, UMR 5293, F-33000 Bordeaux, France
- Centre Mémoire Ressources Recherches, Service de Neurologie des Maladies Neurodégénératives, Pôle de Neurosciences Cliniques, CHU de Bordeaux, F-33000 Bordeaux, France
| | - Boris Mansencal
- CNRS, Univ. Bordeaux, Bordeaux INP, Laboratoire Bordelais de Recherche en Informatique (LABRI), UMR5800, F-33400 Talence, France
| | - Jose V Manjon
- Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València, Camino de Vera s/n, 46022, Valencia, Spain
| | - Wassilios G Meissner
- Institut des Maladies Neurodégénératives, Univ. Bordeaux, CNRS, UMR 5293, F-33000 Bordeaux, France
- Service de Neurologie des Maladies Neurodégénératives, Réseau NS-Park/FCRIN, CHU Bordeaux, F-33000, Bordeaux, France
- Department of Medicine, Christchurch, and New Zealand Brain Research Institute, Christchurch, 8011, New Zealand
| | - Thomas Tourdias
- Inserm U1215—Neurocentre Magendie, Bordeaux F-33000, France
- Service de Neuroimagerie diagnostique et thérapeutique, CHU de Bordeaux, F-33000 Bordeaux, France
| | - Pierrick Coupé
- CNRS, Univ. Bordeaux, Bordeaux INP, Laboratoire Bordelais de Recherche en Informatique (LABRI), UMR5800, F-33400 Talence, France
| |
Collapse
|
3
|
Young AL, Oxtoby NP, Garbarino S, Fox NC, Barkhof F, Schott JM, Alexander DC. Data-driven modelling of neurodegenerative disease progression: thinking outside the black box. Nat Rev Neurosci 2024; 25:111-130. [PMID: 38191721 DOI: 10.1038/s41583-023-00779-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/30/2023] [Indexed: 01/10/2024]
Abstract
Data-driven disease progression models are an emerging set of computational tools that reconstruct disease timelines for long-term chronic diseases, providing unique insights into disease processes and their underlying mechanisms. Such methods combine a priori human knowledge and assumptions with large-scale data processing and parameter estimation to infer long-term disease trajectories from short-term data. In contrast to 'black box' machine learning tools, data-driven disease progression models typically require fewer data and are inherently interpretable, thereby aiding disease understanding in addition to enabling classification, prediction and stratification. In this Review, we place the current landscape of data-driven disease progression models in a general framework and discuss their enhanced utility for constructing a disease timeline compared with wider machine learning tools that construct static disease profiles. We review the insights they have enabled across multiple neurodegenerative diseases, notably Alzheimer disease, for applications such as determining temporal trajectories of disease biomarkers, testing hypotheses about disease mechanisms and uncovering disease subtypes. We outline key areas for technological development and translation to a broader range of neuroscience and non-neuroscience applications. Finally, we discuss potential pathways and barriers to integrating disease progression models into clinical practice and trial settings.
Collapse
Affiliation(s)
- Alexandra L Young
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.
- Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
| | - Neil P Oxtoby
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.
| | - Sara Garbarino
- Life Science Computational Laboratory, IRCCS Ospedale Policlinico San Martino, Genova, Italy
| | - Nick C Fox
- Dementia Research Centre, UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Frederik Barkhof
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
- Department of Radiology & Nuclear Medicine, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | - Jonathan M Schott
- Dementia Research Centre, UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Daniel C Alexander
- UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK
| |
Collapse
|
4
|
Uchida W, Kamagata K, Andica C, Takabayashi K, Saito Y, Owaki M, Fujita S, Hagiwara A, Wada A, Akashi T, Sano K, Hori M, Aoki S. Fiber-specific micro- and macroscopic white matter alterations in progressive supranuclear palsy and corticobasal syndrome. NPJ Parkinsons Dis 2023; 9:122. [PMID: 37591877 PMCID: PMC10435458 DOI: 10.1038/s41531-023-00565-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Accepted: 08/02/2023] [Indexed: 08/19/2023] Open
Abstract
Progressive supranuclear palsy (PSP) and corticobasal syndrome (CBS) are characterized by progressive white matter (WM) alterations associated with the prion-like spreading of four-repeat tau, which has been pathologically confirmed. It has been challenging to monitor the WM degeneration patterns underlying the clinical deficits in vivo. Here, a fiber-specific fiber density and fiber cross-section, and their combined measure estimated using fixel-based analysis (FBA), were cross-sectionally and longitudinally assessed in PSP (n = 20), CBS (n = 17), and healthy controls (n = 20). FBA indicated disease-specific progression patterns of fiber density loss and subsequent bundle atrophy consistent with the tau propagation patterns previously suggested in a histopathological study. This consistency suggests the new insight that FBA can monitor the progressive tau-related WM changes in vivo. Furthermore, fixel-wise metrics indicated strong correlations with motor and cognitive dysfunction and the classifiability of highly overlapping diseases. Our findings might also provide a tool to monitor clinical decline and classify both diseases.
Collapse
Affiliation(s)
- Wataru Uchida
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Koji Kamagata
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan.
| | - Christina Andica
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
- Faculty of Health Data Science, Juntendo University, Urayasu, Chiba, 279-0013, Japan
| | - Kaito Takabayashi
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Yuya Saito
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Mana Owaki
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
- Department of Radiological Sciences, Graduate School of Human Health Sciences, Tokyo Metropolitan University, Arakawa-ku, Tokyo, 116-8551, Japan
| | - Shohei Fujita
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Akifumi Hagiwara
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Akihiko Wada
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Toshiaki Akashi
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Katsuhiro Sano
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
| | - Masaaki Hori
- Department of Radiology, Toho University Omori Medical Center, Ota-ku, Tokyo, 143-8541, Japan
| | - Shigeki Aoki
- Department of Radiology, Juntendo University Graduate School of Medicine, Bunkyo-ku, Tokyo, 113-8421, Japan
- Faculty of Health Data Science, Juntendo University, Urayasu, Chiba, 279-0013, Japan
| |
Collapse
|
5
|
Whitwell JL. Clinical and neuroimaging features of the progressive supranuclear palsy- corticobasal degeneration continuum. Curr Opin Neurol 2023; 36:283-290. [PMID: 37462045 PMCID: PMC10586719 DOI: 10.1097/wco.0000000000001175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/20/2023]
Abstract
PURPOSE OF REVIEW The aim of this study was to discuss how recent work has increased our understanding of progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). The investigation of large and autopsy-confirmed cohorts, imaging modalities to assess different aspects of pathophysiology, clinical phenotypes and the application of advanced machine learning techniques, have led to recent advances in the field that will be discussed. RECENT FINDINGS Literature over the past 18 months will be discussed under the following themes: studies assessing how different neuroimaging modalities can improve the diagnosis of PSP and CBD from other neurodegenerative and parkinsonian disorders, including the investigation of pathological targets such as tau, iron, neuromelanin and dopamine and cholinergic systems; work improving our understanding of clinical, neuroanatomical and pathological heterogeneity in PSP and CBD; and work using advanced neuroimaging tools to investigate patterns of disease spread, as well as biological mechanisms potentially driving spread through the brain in PSP and CBD. SUMMARY The findings help improve the imaging-based diagnosis of PSP and CBD, allow more targeted prognostic estimates for patients accounting for phenotype or disease, and will aid in the development of appropriate and better-targeted disease biomarkers for clinical treatment trials.
Collapse
|
6
|
Scotton WJ, Shand C, Todd E, Bocchetta M, Cash DM, VandeVrede L, Heuer H, Young AL, Oxtoby N, Alexander DC, Rowe JB, Morris HR, Boxer AL, Rohrer JD, Wijeratne PA. Uncovering spatiotemporal patterns of atrophy in progressive supranuclear palsy using unsupervised machine learning. Brain Commun 2023; 5:fcad048. [PMID: 36938523 PMCID: PMC10016410 DOI: 10.1093/braincomms/fcad048] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2022] [Revised: 11/22/2022] [Accepted: 02/27/2023] [Indexed: 03/06/2023] Open
Abstract
To better understand the pathological and phenotypic heterogeneity of progressive supranuclear palsy and the links between the two, we applied a novel unsupervised machine learning algorithm (Subtype and Stage Inference) to the largest MRI data set to date of people with clinically diagnosed progressive supranuclear palsy (including progressive supranuclear palsy-Richardson and variant progressive supranuclear palsy syndromes). Our cohort is comprised of 426 progressive supranuclear palsy cases, of which 367 had at least one follow-up scan, and 290 controls. Of the progressive supranuclear palsy cases, 357 were clinically diagnosed with progressive supranuclear palsy-Richardson, 52 with a progressive supranuclear palsy-cortical variant (progressive supranuclear palsy-frontal, progressive supranuclear palsy-speech/language, or progressive supranuclear palsy-corticobasal), and 17 with a progressive supranuclear palsy-subcortical variant (progressive supranuclear palsy-parkinsonism or progressive supranuclear palsy-progressive gait freezing). Subtype and Stage Inference was applied to volumetric MRI features extracted from baseline structural (T1-weighted) MRI scans and then used to subtype and stage follow-up scans. The subtypes and stages at follow-up were used to validate the longitudinal consistency of subtype and stage assignments. We further compared the clinical phenotypes of each subtype to gain insight into the relationship between progressive supranuclear palsy pathology, atrophy patterns, and clinical presentation. The data supported two subtypes, each with a distinct progression of atrophy: a 'subcortical' subtype, in which early atrophy was most prominent in the brainstem, ventral diencephalon, superior cerebellar peduncles, and the dentate nucleus, and a 'cortical' subtype, in which there was early atrophy in the frontal lobes and the insula alongside brainstem atrophy. There was a strong association between clinical diagnosis and the Subtype and Stage Inference subtype with 82% of progressive supranuclear palsy-subcortical cases and 81% of progressive supranuclear palsy-Richardson cases assigned to the subcortical subtype and 82% of progressive supranuclear palsy-cortical cases assigned to the cortical subtype. The increasing stage was associated with worsening clinical scores, whilst the 'subcortical' subtype was associated with worse clinical severity scores compared to the 'cortical subtype' (progressive supranuclear palsy rating scale and Unified Parkinson's Disease Rating Scale). Validation experiments showed that subtype assignment was longitudinally stable (95% of scans were assigned to the same subtype at follow-up) and individual staging was longitudinally consistent with 90% remaining at the same stage or progressing to a later stage at follow-up. In summary, we applied Subtype and Stage Inference to structural MRI data and empirically identified two distinct subtypes of spatiotemporal atrophy in progressive supranuclear palsy. These image-based subtypes were differentially enriched for progressive supranuclear palsy clinical syndromes and showed different clinical characteristics. Being able to accurately subtype and stage progressive supranuclear palsy patients at baseline has important implications for screening patients on entry to clinical trials, as well as tracking disease progression.
Collapse
Affiliation(s)
- William J Scotton
- Dementia Research Centre, Department of Neurodegenerative Disease, UCL Queen Square Institute of Neurology, University College London, London WC1N 3AR, UK
| | - Cameron Shand
- Centre for Medical Image Computing, Department of Computer Science, University College London, London WC1V 6LJ, UK
| | - Emily Todd
- Dementia Research Centre, Department of Neurodegenerative Disease, UCL Queen Square Institute of Neurology, University College London, London WC1N 3AR, UK
| | - Martina Bocchetta
- Dementia Research Centre, Department of Neurodegenerative Disease, UCL Queen Square Institute of Neurology, University College London, London WC1N 3AR, UK
| | - David M Cash
- Dementia Research Centre, Department of Neurodegenerative Disease, UCL Queen Square Institute of Neurology, University College London, London WC1N 3AR, UK
| | - Lawren VandeVrede
- Department of Neurology, Memory and Aging Center, University of California, San Francisco, CA 94158, USA
| | - Hilary Heuer
- Department of Neurology, Memory and Aging Center, University of California, San Francisco, CA 94158, USA
| | - Alexandra L Young
- Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London SE5 8AF, UK
| | - Neil Oxtoby
- Centre for Medical Image Computing, Department of Computer Science, University College London, London WC1V 6LJ, UK
| | - Daniel C Alexander
- Centre for Medical Image Computing, Department of Computer Science, University College London, London WC1V 6LJ, UK
| | - James B Rowe
- Cambridge University Department of Clinical Neurosciences and Cambridge University Hospitals NHS Trust, Medical Research Council Cognition and Brain Sciences Unit, Cambridge CB2 0QQ, UK
| | - Huw R Morris
- Department of Clinical and Movement Neurosciences, University College London Queen Square Institute of Neurology, London WC1N 3BG, UK
- Movement Disorders Centre, University College London Queen Square Institute of Neurology, London WC1N 3BG, UK
| | - Adam L Boxer
- Department of Neurology, Memory and Aging Center, University of California, San Francisco, CA 94158, USA
| | - Jonathan D Rohrer
- Dementia Research Centre, Department of Neurodegenerative Disease, UCL Queen Square Institute of Neurology, University College London, London WC1N 3AR, UK
| | - Peter A Wijeratne
- Centre for Medical Image Computing, Department of Computer Science, University College London, London WC1V 6LJ, UK
| |
Collapse
|
7
|
Kiakou D, Adamopoulos A, Scherf N. Graph-Based Disease Prediction in Neuroimaging: Investigating the Impact of Feature Selection. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2023; 1424:223-230. [PMID: 37486497 DOI: 10.1007/978-3-031-31982-2_24] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/25/2023]
Abstract
In biomedical machine learning, data often appear in the form of graphs. Biological systems such as protein interactions and ecological or brain networks are instances of applications that benefit from graph representations. Geometric deep learning is an arising field of techniques that has extended deep neural networks to non-Euclidean domains such as graphs. In particular, graph convolutional neural networks have achieved advanced performance in semi-supervised learning in those domains. Over the last years, these methods have gained traction in neuroscience as they could be the key to a deeper understanding in clinical diagnosis at the systems or network level (for an individual brain but also for across a cohort of subjects). As a proof-of-principle, we study and validate a previous implementation of graph-based semi-supervised classification using a ridge classifier and graph convolutional neural networks. The models are trained on population graphs that integrate imaging and phenotypic information. Our analysis employs neuroimaging data of structural and functional connectivity for prediction of neurodevelopmental and neurodegenerative disorders. Here, we particularly study the effect of different strategies to reduce the dimensionality of the neuroimaging features on the graph nodes on the classification performance.
Collapse
Affiliation(s)
- Dimitra Kiakou
- Hellenic Open University, Patra, Greece.
- Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany.
| | - Adam Adamopoulos
- Hellenic Open University, Patra, Greece
- Democritus University of Thrace, Department of Medicine, Medical Physics Lab, Alexandroupolis, Greece
| | - Nico Scherf
- Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany
- Center for Scalable Data Analytics and Artificial Intelligence ScaDS.AI, Dresden/Leipzig, Leipzig, Germany
| |
Collapse
|