Filters








80 Hits in 3.5 sec

Multimodal image fusion via deep generative models [article]

Giovanna Maria Dimitri, Simeon Spasov, Andrea Duggento, Luca Passamonti, Pietro Lio', Nicola Toschi
2021 bioRxiv   pre-print
utilization) in order to a) fuse multiple 3D neuroimaging modalities on a voxel-wise level, b) efficiently convert them into informative latent embeddings through heavy dimensionality reduction, c) maintain  ...  In this paper we design and validate a deep learning architecture based on generative models rooted in a modular approach and separable convolutional blocks (which result in a 20-fold decrease in parameter  ...  to map to distinct phenotypic groups, we clustered the population in the latent embeddings space.  ... 
doi:10.1101/2021.03.08.434427 fatcat:jf5o2ux6izh6zckkosglspb7dq

Subtyping brain diseases from imaging data [article]

Junhao Wen, Erdem Varol, Zhijian Yang, Gyujoon Hwang, Dominique Dwyer, Anahita Fathi Kazerooni, Paris Alexandros Lalousis, Christos Davatzikos
2022 arXiv   pre-print
Therefore, in such cases, seeking a single disease signature might be ineffectual in delivering individualized precision diagnostics.  ...  Clinical neuroscience and cancer imaging have been two areas in which ML has offered particular promise.  ...  Acknowledgments This work was supported, in part, by NIH grants R01NS042645, U01AG068057, R01MH112070 and RF1AG054409.  ... 
arXiv:2202.10945v1 fatcat:3sqq4lrilnguzgbm4iwtzm7wc4

Deep representation learning of electronic health records to unlock patient stratification at scale

Isotta Landi, Benjamin S. Glicksberg, Hao-Chih Lee, Sarah Cherng, Giulia Landi, Matteo Danieletto, Joel T. Dudley, Cesare Furlanello, Riccardo Miotto
2020 npj Digital Medicine  
Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale  ...  We introduce a representation learning model based on word embeddings, convolutional neural networks, and autoencoders (i.e., ConvAE) to transform patient trajectories into low-dimensional latent vectors  ...  Fig. 1 1 Patient stratification framework and ConvAE architecture. a Framework enabling patient stratification analysis from deep unsupervised EHR representations; b Details of the ConvAE representation  ... 
doi:10.1038/s41746-020-0301-z pmid:32699826 pmcid:PMC7367859 fatcat:ddt7xa36jvbzzdkpirhdslxnty

Integration of Machine Learning Methods to Dissect Genetically Imputed Transcriptomic Profiles in Alzheimer's Disease

Carlo Maj, Tiago Azevedo, Valentina Giansanti, Oleg Borisov, Giovanna Maria Dimitri, Simeon Spasov, Pietro Lió, Ivan Merelli, Alzheimer's Disease Neuroimaging Initiative
2019 Frontiers in Genetics  
In line with the expected low heritability that can be apportioned to eQTL variants, we were able to achieve only relatively low prediction capability with deep learning classification models.  ...  Interestingly, the achieved gene prioritizations can be efficiently integrated as a feature selection step for improving the accuracy of deep learning classifier networks.  ...  ADNI data collection and sharing was funded by the Alzheimer's Disease Neuroimaging Initiative (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH  ... 
doi:10.3389/fgene.2019.00726 pmid:31552082 pmcid:PMC6735530 fatcat:kbj6dpolyfcsnhtg7yiazplowu

Modern Views of Machine Learning for Precision Psychiatry [article]

Zhe Sage Chen, Prathamesh Kulkarni, Isaac R. Galatzer-Levy, Benedetta Bigio, Carla Nasca, Yu Zhang
2022 arXiv   pre-print
In this review, we provide a comprehensive review of the ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice.  ...  In light of the NIMH's Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and  ...  The deep autoencoder, also known as stacked autoencoder, aims to learn latent representations of input data through an encoder and uses these representations to reconstruct output data through a decoder  ... 
arXiv:2204.01607v2 fatcat:coo557v2jzh6debycy3mhccfze

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
Latent Representation Learning 277 Towards radiotherapy enhancement and real time tumor radiation dosimetry through 3D imaging of gold nanoparticles using XFCT 279 Automatic Lacunae Localization in Placental  ...  and Recurrent Hourglass Networks 551 Some Investigations on Robustness of Deep Learning in Limited Angle Tomography 554 Normative Modeling of Neuroimaging Data using Scalable Multi-Task Gaussian Processes  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Deep Representation Learning of Electronic Health Records to Unlock Patient Stratification at Scale [article]

Isotta Landi , Hao-Chih Lee, Matteo Danieletto, Cesare Furlanello (1 and 7), and Riccardo Miotto Bruno Kessler Foundation, Trento, Italy Hasso Plattner Institute for Digital Health at Mount Sinai, NY, Institute for Next Generation Healthcare, NY, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, NY, Department of Mental Health and Pathological Addiction (+3 others)
2020 arXiv   pre-print
Here, we present a novel unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification  ...  We introduce a representation learning model based on word embeddings, convolutional neural networks and autoencoders (i.e., "ConvAE") to transform patient trajectories into low-dimensional latent vectors  ...  Figure 1 : 1 Framework enabling patient stratification analysis from deep unsupervised EHR representations (a); Details of the ConvAE representation learning architecture (b).  ... 
arXiv:2003.06516v1 fatcat:l2mg5ox6orbi3e7tnlhmbiuesu

Non-linearity matters: a deep learning solution to the generalization of hidden brain patterns across population cohorts [article]

Mariam Zabihi, Seyed Mostafa Kia, Thomas Wolfers, Richard Dinga, Alberto Llera, Danilo Bzdok, Christian Beckmann, Andre marquand
2021 bioRxiv   pre-print
The increasing number of neuroimaging scans in recent years has facilitated the use of complex nonlinear approaches to analyzing such data.  ...  Next, in a transfer learning setting, we tested the generalization of our latent space on UK Biobank data as an independent dataset.  ...  In particular, the applications of deep learning to neuroimaging data are rapidly increasing, mostly the use of supervised learning approaches to solve, for example, classification problems [2] [3] [4  ... 
doi:10.1101/2021.03.10.434856 fatcat:cv3ymi57czhgxgqk3faou3dfay

TAPAS: An Open-Source Software Package for Translational Neuromodeling and Computational Psychiatry

Stefan Frässle, Eduardo A. Aponte, Saskia Bollmann, Kay H. Brodersen, Cao T. Do, Olivia K. Harrison, Samuel J. Harrison, Jakob Heinzle, Sandra Iglesias, Lars Kasper, Ekaterina I. Lomakina, Christoph Mathys (+9 others)
2021 Frontiers in Psychiatry  
This has motivated the genesis of two closely intertwined fields: (i) Translational Neuromodeling (TN), which develops "computational assays" for inferring patient-specific disease processes from neuroimaging  ...  In this paper, we present the Translational Algorithms for Psychiatry-Advancing Science (TAPAS) software package, an open-source collection of building blocks for computational assays in psychiatry.  ...  Second, prediction of clinical trajectories and treatment outcome as well as stratification of spectrum disorders can be achieved by means of supervised and unsupervised generative embedding [GE; (197  ... 
doi:10.3389/fpsyt.2021.680811 pmid:34149484 pmcid:PMC8206497 fatcat:ichfqltpdbdfflh2ozfk4lduda

Early prediction of cognitive deficits in very preterm infants using functional connectome data in an artificial neural network framework

Lili He, Hailong Li, Scott K. Holland, Weihong Yuan, Mekibib Altaye, Nehal A. Parikh
2018 NeuroImage: Clinical  
improved individual risk stratification.  ...  The proposed ANN model was unsupervised learned using brain connectome data from 884 subjects in autism brain imaging data exchange database and SVM was cross-validated on 28 very preterm infants (born  ...  Acknowledgements Supported in part by funding from the National Institutes of Neurological Disorders and Stroke of NIH grants R01-NS094200 and R01-NS096037.  ... 
doi:10.1016/j.nicl.2018.01.032 pmid:29876249 pmcid:PMC5987842 fatcat:ov45kmhk7fe53dtz636de3lrpi

TAPAS: an open-source software package for Translational Neuromodeling and Computational Psychiatry [article]

Stefan Frässle, Eduardo A Aponte, Saskia A Bollmann, Kay H Brodersen, Cao Tri Do, Olivia K Harrison, Samuel J Harrison, Jakob Heinzle, Sandra Iglesias, Lars Kasper, Ekaterina I Lomakina, Christoph Mathys (+9 others)
2021 bioRxiv   pre-print
This has motivated the genesis of two closely intertwined fields: (i) Translational Neuromodeling (TN), which develops "computational assays" for inferring patient-specific disease processes from neuroimaging  ...  In this paper, we present the Translational Algorithms for Psychiatry-Advancing Science (TAPAS) software package, an open-source collection of building blocks for computational assays in psychiatry.  ...  Second, prediction of clinical trajectories and treatment outcome as well as stratification of spectrum disorders can be achieved by means of supervised and unsupervised generative embedding (GE; Shawe  ... 
doi:10.1101/2021.03.12.435091 fatcat:b6t53rzjdreqbgtid4kexcuw6q

Machine Learning for Precision Psychiatry: Opportunities and Challenges

Danilo Bzdok, Andreas Meyer-Lindenberg
2018 Biological Psychiatry: Cognitive Neuroscience and Neuroimaging  
Moreover, clinical biomarkers derived from genetics or neuroimaging will potentially be accredited through randomized clinical trials. ii) Data availability: The primary limitation for deploying state-of-the-art  ...  Example: latent Dirichlet allocation, autoencoders, nonnegative matrix factorization (NMF), isomap, tdistributed stochastic neighbor embedding (t-SNE) K-means clustering A popular clustering model that  ... 
doi:10.1016/j.bpsc.2017.11.007 pmid:29486863 fatcat:fbpyr23razeyfohqcookxva7hu

MRI-Based Classification of Neuropsychiatric Systemic Lupus Erythematosus Patients With Self-Supervised Contrastive Learning

Francesca Inglese, Minseon Kim, Gerda M. Steup-Beekman, Tom W. J. Huizinga, Mark A. van Buchem, Jeroen de Bresser, Dae-Shik Kim, Itamar Ronen
2022 Frontiers in Neuroscience  
Structural brain abnormalities are commonly found in SLE and NPSLE, but their role in diagnosis is limited, and their usefulness in distinguishing between NPSLE patients and patients in which the NP symptoms  ...  Self-supervised contrastive learning algorithms proved to be useful in classification tasks in rare diseases with limited number of datasets.  ...  A survey on deep learning for neuroimaging-based brain disorder analysis. Front.  ... 
doi:10.3389/fnins.2022.695888 pmid:35250439 pmcid:PMC8889016 fatcat:hdkknjx5wjh5niru5zzbwdexii

TransforMesh: A Transformer Network for Longitudinal modeling of Anatomical Meshes [article]

Ignacio Sarasua, Sebastian Pölsterl, Christian Wachinger
2021 arXiv   pre-print
Moreover, we also explore the capabilities of TransforMesh in detecting structural anomalies of the hippocampus in patients developing AD.  ...  While transformer and mesh networks have recently shown impressive performances in natural language processing and computer vision, their application to medical image analysis has been very limited.  ...  was supported by the Bavarian State Ministry of Science and the Arts and coordinated by the Bavarian Research Institute for Digital Transformation, and the Federal Ministry of Education and Research in  ... 
arXiv:2109.00532v2 fatcat:sevky4z6jbgyzhaewzge33spai

Machine Learning in Amyotrophic Lateral Sclerosis: Achievements, Pitfalls, and Future Directions

Vincent Grollemund, Pierre-François Pradat, Giorgia Querin, François Delbot, Gaétan Le Chat, Jean-François Pradat-Peyre, Peter Bede
2019 Frontiers in Neuroscience  
Prognostic models have been tested using core clinical variables, biological, and neuroimaging data. These models also offer patient stratification opportunities for future clinical trials.  ...  Methods: The objective of this paper is the comprehensive, systematic, and critical review of ML initiatives in ALS to date and their potential in research, clinical, and pharmacological applications.  ...  Unsupervised learning can be particularly helpful in addressing patient stratification problems.  ... 
doi:10.3389/fnins.2019.00135 pmid:30872992 pmcid:PMC6403867 fatcat:5o6rjl5yjrbhrfxdzj2lq72hzq
« Previous Showing results 1 — 15 out of 80 results