151
|
Abstract
Precision medicine is an emerging approach to clinical research and patient care that focuses on understanding and treating disease by integrating multi-modal or multi-omics data from an individual to make patient-tailored decisions. With the large and complex datasets generated using precision medicine diagnostic approaches, novel techniques to process and understand these complex data were needed. At the same time, computer science has progressed rapidly to develop techniques that enable the storage, processing, and analysis of these complex datasets, a feat that traditional statistics and early computing technologies could not accomplish. Machine learning, a branch of artificial intelligence, is a computer science methodology that aims to identify complex patterns in data that can be used to make predictions or classifications on new unseen data or for advanced exploratory data analysis. Machine learning analysis of precision medicine's multi-modal data allows for broad analysis of large datasets and ultimately a greater understanding of human health and disease. This review focuses on machine learning utilization for precision medicine's "big data", in the context of genetics, genomics, and beyond.
Collapse
Affiliation(s)
- Sarah J MacEachern
- Department of Pediatrics, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.,Alberta Children's Hospital Research Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada
| | - Nils D Forkert
- Alberta Children's Hospital Research Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.,Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada
| |
Collapse
|
152
|
Bellantuono L, Marzano L, La Rocca M, Duncan D, Lombardi A, Maggipinto T, Monaco A, Tangaro S, Amoroso N, Bellotti R. Predicting brain age with complex networks: From adolescence to adulthood. Neuroimage 2020; 225:117458. [PMID: 33099008 DOI: 10.1016/j.neuroimage.2020.117458] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2020] [Accepted: 10/13/2020] [Indexed: 01/21/2023] Open
Abstract
In recent years, several studies have demonstrated that machine learning and deep learning systems can be very useful to accurately predict brain age. In this work, we propose a novel approach based on complex networks using 1016 T1-weighted MRI brain scans (in the age range 7-64years). We introduce a structural connectivity model of the human brain: MRI scans are divided in rectangular boxes and Pearson's correlation is measured among them in order to obtain a complex network model. Brain connectivity is then characterized through few and easy-to-interpret centrality measures; finally, brain age is predicted by feeding a compact deep neural network. The proposed approach is accurate, robust and computationally efficient, despite the large and heterogeneous dataset used. Age prediction accuracy, in terms of correlation between predicted and actual age r=0.89and Mean Absolute Error MAE =2.19years, compares favorably with results from state-of-the-art approaches. On an independent test set including 262 subjects, whose scans were acquired with different scanners and protocols we found MAE =2.52. The only imaging analysis steps required in the proposed framework are brain extraction and linear registration, hence robust results are obtained with a low computational cost. In addition, the network model provides a novel insight on aging patterns within the brain and specific information about anatomical districts displaying relevant changes with aging.
Collapse
Affiliation(s)
- Loredana Bellantuono
- Dipartimento Interateneo di Fisica, Universitá degli Studi di Bari Aldo Moro, Bari, Italy
| | - Luca Marzano
- Dipartimento Interateneo di Fisica, Universitá degli Studi di Bari Aldo Moro, Bari, Italy
| | - Marianna La Rocca
- University of Southern California, Laboratory of NeuroImaging, USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, Los Angeles, CA, United States
| | - Dominique Duncan
- University of Southern California, Laboratory of NeuroImaging, USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, Los Angeles, CA, United States
| | - Angela Lombardi
- Istituto Nazionale di Fisica Nucleare, Sez. di Bari, Bari, Italy
| | - Tommaso Maggipinto
- Dipartimento Interateneo di Fisica, Universitá degli Studi di Bari Aldo Moro, Bari, Italy
| | - Alfonso Monaco
- Istituto Nazionale di Fisica Nucleare, Sez. di Bari, Bari, Italy.
| | - Sabina Tangaro
- Istituto Nazionale di Fisica Nucleare, Sez. di Bari, Bari, Italy; Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Universitá degli Studi di Bari Aldo Moro, Bari, Italy
| | - Nicola Amoroso
- Dipartimento di Farmacia - Scienze del Farmaco, Universitá degli Studi di Bari Aldo Moro, Bari, Italy; Istituto Nazionale di Fisica Nucleare, Sez. di Bari, Bari, Italy
| | - Roberto Bellotti
- Istituto Nazionale di Fisica Nucleare, Sez. di Bari, Bari, Italy; Dipartimento Interateneo di Fisica, Universitá degli Studi di Bari Aldo Moro, Bari, Italy
| |
Collapse
|
153
|
Zhao X, Zhao XM. Deep learning of brain magnetic resonance images: A brief review. Methods 2020; 192:131-140. [PMID: 32931932 DOI: 10.1016/j.ymeth.2020.09.007] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2020] [Revised: 08/22/2020] [Accepted: 09/09/2020] [Indexed: 01/24/2023] Open
Abstract
Magnetic resonance imaging (MRI) is one of the most popular techniques in brain science and is important for understanding brain function and neuropsychiatric disorders. However, the processing and analysis of MRI is not a trivial task with lots of challenges. Recently, deep learning has shown superior performance over traditional machine learning approaches in image analysis. In this survey, we give a brief review of the recent popular deep learning approaches and their applications in brain MRI analysis. Furthermore, popular brain MRI databases and deep learning tools are also introduced. The strength and weaknesses of different approaches are addressed, and challenges as well as future directions are also discussed.
Collapse
Affiliation(s)
- Xingzhong Zhao
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 200433, China; Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education, China
| | - Xing-Ming Zhao
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 200433, China; Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education, China; Research Institute of Intelligent Complex Systems, Fudan University, Shanghai 200433, China.
| |
Collapse
|
154
|
Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty. Neuroimage 2020; 223:117316. [PMID: 32890745 DOI: 10.1016/j.neuroimage.2020.117316] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Revised: 07/25/2020] [Accepted: 08/24/2020] [Indexed: 12/30/2022] Open
Abstract
MRI-based brain age prediction has been widely used to characterize normal brain development, and deviations from the typical developmental trajectory are indications of brain abnormalities. Age prediction of the fetal brain remains unexplored, although it can be of broad interest to prenatal examination given the limited diagnostic tools available for assessment of the fetal brain. In this work, we built an attention-based deep residual network based on routine clinical T2-weighted MR images of 659 fetal brains, which achieved an overall mean absolute error of 0.767 weeks and R2 of 0.920 in fetal brain age prediction. The predictive uncertainty and estimation confidence were simultaneously quantified from the network as markers for detecting fetal brain anomalies using an ensemble method. The novel markers overcame the limitations in conventional brain age estimation and demonstrated promising diagnostic power in differentiating several types of fetal abnormalities, including small head circumference, malformations and ventriculomegaly with the area under the curve of 0.90, 0.90 and 0.67, respectively. In addition, attention maps were derived from the network, which revealed regional features that contributed to fetal age estimation at each gestational stage. The proposed attention-based deep ensembles demonstrated superior performance in fetal brain age estimation and fetal anomaly detection, which has the potential to be translated to prenatal diagnosis in clinical practice.
Collapse
|
155
|
Brain imaging genomics: influences of genomic variability on the structure and function of the human brain. MED GENET-BERLIN 2020. [DOI: 10.1515/medgen-2020-2007] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Abstract
Brain imaging genomics is an emerging discipline in which genomic and brain imaging data are integrated in order to elucidate the molecular mechanisms that underly brain phenotypes and diseases, including neuropsychiatric disorders. As with all genetic analyses of complex traits and diseases, brain imaging genomics has evolved from small, individual candidate gene investigations towards large, collaborative genome-wide association studies. Recent investigations, mostly population-based, have studied well-powered cohorts comprising tens of thousands of individuals and identified multiple robust associations of single-nucleotide polymorphisms and copy number variants with structural and functional brain phenotypes. Such systematic genomic screens of millions of genetic variants have generated initial insights into the genetic architecture of brain phenotypes and demonstrated that their etiology is polygenic in nature, involving multiple common variants with small effect sizes and rare variants with larger effect sizes. Ongoing international collaborative initiatives are now working to obtain a more complete picture of the underlying biology. As in other complex phenotypes, novel approaches – such as gene–gene interaction, gene–environment interaction, and epigenetic analyses – are being implemented in order to investigate their contribution to the observed phenotypic variability. An important consideration for future research will be the translation of brain imaging genomics findings into clinical practice.
Collapse
|
156
|
Bashyam VM, Erus G, Doshi J, Habes M, Nasrallah IM, Truelove-Hill M, Srinivasan D, Mamourian L, Pomponio R, Fan Y, Launer LJ, Masters CL, Maruff P, Zhuo C, Völzke H, Johnson SC, Fripp J, Koutsouleris N, Satterthwaite TD, Wolf D, Gur RE, Gur RC, Morris J, Albert MS, Grabe HJ, Resnick S, Bryan RN, Wolk DA, Shou H, Davatzikos C. MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide. Brain 2020; 143:2312-2324. [PMID: 32591831 PMCID: PMC7364766 DOI: 10.1093/brain/awaa160] [Citation(s) in RCA: 126] [Impact Index Per Article: 31.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2019] [Revised: 03/17/2020] [Accepted: 03/31/2020] [Indexed: 01/21/2023] Open
Abstract
Deep learning has emerged as a powerful approach to constructing imaging signatures of normal brain ageing as well as of various neuropathological processes associated with brain diseases. In particular, MRI-derived brain age has been used as a comprehensive biomarker of brain health that can identify both advanced and resilient ageing individuals via deviations from typical brain ageing. Imaging signatures of various brain diseases, including schizophrenia and Alzheimer's disease, have also been identified using machine learning. Prior efforts to derive these indices have been hampered by the need for sophisticated and not easily reproducible processing steps, by insufficiently powered or diversified samples from which typical brain ageing trajectories were derived, and by limited reproducibility across populations and MRI scanners. Herein, we develop and test a sophisticated deep brain network (DeepBrainNet) using a large (n = 11 729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages and geographic locations around the world. Tests using both cross-validation and a separate replication cohort of 2739 individuals indicate that DeepBrainNet obtains robust brain-age estimates from these diverse datasets without the need for specialized image data preparation and processing. Furthermore, we show evidence that moderately fit brain ageing models may provide brain age estimates that are most discriminant of individuals with pathologies. This is not unexpected as tightly-fitting brain age models naturally produce brain-age estimates that offer little information beyond age, and loosely fitting models may contain a lot of noise. Our results offer some experimental evidence against commonly pursued tightly-fitting models. We show that the moderately fitting brain age models obtain significantly higher differentiation compared to tightly-fitting models in two of the four disease groups tested. Critically, we demonstrate that leveraging DeepBrainNet, along with transfer learning, allows us to construct more accurate classifiers of several brain diseases, compared to directly training classifiers on patient versus healthy control datasets or using common imaging databases such as ImageNet. We, therefore, derive a domain-specific deep network likely to reduce the need for application-specific adaptation and tuning of generic deep learning networks. We made the DeepBrainNet model freely available to the community for MRI-based evaluation of brain health in the general population and over the lifespan.
Collapse
Affiliation(s)
- Vishnu M Bashyam
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA,Correspondence to: Vishnu Bashyam3700 Hamilton Walk, 7th FloorCenter of Biomedical Image Computing and Analytics, University of PennsylvaniaPhiladelphia, PA 19104, USA E-mail: Website: https://www.med.upenn.edu/cbica/
| | - Guray Erus
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Jimit Doshi
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Mohamad Habes
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA,Department of Neurology, University of Pennsylvania, Philadelphia, USA
| | - Ilya M Nasrallah
- Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Monica Truelove-Hill
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Dhivya Srinivasan
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Liz Mamourian
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Raymond Pomponio
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Yong Fan
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA
| | - Lenore J Launer
- Laboratory of Epidemiology and Population Sciences, National Institute on Aging, Bethesda, USA
| | - Colin L Masters
- Florey Institute of Neuroscience and Mental Health, University of Melbourne, Melbourne, Australia
| | - Paul Maruff
- Florey Institute of Neuroscience and Mental Health, University of Melbourne, Melbourne, Australia
| | - Chuanjun Zhuo
- Tianjin Mental Health Center, Nankai University Affiliated Tianjin Anding Hospital, Tianjin, China,Department of Psychiatry, Tianjin Medical University, Tianjin, China
| | - Henry Völzke
- Institute for Community Medicine, University of Greifswald, Germany,German Centre for Cardiovascular Research, Partner Sit Greifswald, Germany
| | - Sterling C Johnson
- Wisconsin Alzheimer’s Institute, University of Wisconsin School of Medicine and Public Health, Madison, USA
| | - Jurgen Fripp
- CSIRO Health and Biosecurity, Australian e-Health Research Centre CSIRO, Melbourne, Australia
| | - Nikolaos Koutsouleris
- Department of Psychiatry and Psychotherapy, Ludwig Maximilian University of Munich, Munich, Germany
| | - Theodore D Satterthwaite
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA,Department of Psychiatry, University of Pennsylvania, Philadelphia, USA
| | - Daniel Wolf
- Department of Psychiatry, University of Pennsylvania, Philadelphia, USA
| | - Raquel E Gur
- Department of Radiology, University of Pennsylvania, Philadelphia, USA,Department of Psychiatry, University of Pennsylvania, Philadelphia, USA
| | - Ruben C Gur
- Department of Radiology, University of Pennsylvania, Philadelphia, USA,Department of Psychiatry, University of Pennsylvania, Philadelphia, USA
| | - John Morris
- Department of Neurology, Washington University in St. Louis, St Louis, USA
| | - Marilyn S Albert
- Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, USA
| | - Hans J Grabe
- Department of Psychiatry and Psychotherapy, Ernst-Moritz-Arndt University, Greifswald, Mecklenburg-Vorpommern, Germany
| | - Susan Resnick
- Laboratory of Behavioral Neuroscience, National Institute on Aging, Bethesda, USA
| | - R Nick Bryan
- Department of Diagnostic Medicine, University of Texas at Austin, Austin, USA
| | - David A Wolk
- Department of Neurology, University of Pennsylvania, Philadelphia, USA
| | - Haochang Shou
- Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadephia, USA
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics, Department of Radiology, University of Pennsylvania, Philadelphia, USA,Correspondence may also be addressed to: Christos DavatzikosE-mail:
| |
Collapse
|
157
|
Couvy-Duchesne B, Faouzi J, Martin B, Thibeau-Sutre E, Wild A, Ansart M, Durrleman S, Dormont D, Burgos N, Colliot O. Ensemble Learning of Convolutional Neural Network, Support Vector Machine, and Best Linear Unbiased Predictor for Brain Age Prediction: ARAMIS Contribution to the Predictive Analytics Competition 2019 Challenge. Front Psychiatry 2020; 11:593336. [PMID: 33384629 PMCID: PMC7770104 DOI: 10.3389/fpsyt.2020.593336] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/10/2020] [Accepted: 11/20/2020] [Indexed: 12/14/2022] Open
Abstract
We ranked third in the Predictive Analytics Competition (PAC) 2019 challenge by achieving a mean absolute error (MAE) of 3.33 years in predicting age from T1-weighted MRI brain images. Our approach combined seven algorithms that allow generating predictions when the number of features exceeds the number of observations, in particular, two versions of best linear unbiased predictor (BLUP), support vector machine (SVM), two shallow convolutional neural networks (CNNs), and the famous ResNet and Inception V1. Ensemble learning was derived from estimating weights via linear regression in a hold-out subset of the training sample. We further evaluated and identified factors that could influence prediction accuracy: choice of algorithm, ensemble learning, and features used as input/MRI image processing. Our prediction error was correlated with age, and absolute error was greater for older participants, suggesting to increase the training sample for this subgroup. Our results may be used to guide researchers to build age predictors on healthy individuals, which can be used in research and in the clinics as non-specific predictors of disease status.
Collapse
Affiliation(s)
- Baptiste Couvy-Duchesne
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France.,Institute for Molecular Bioscience, The University of Queensland, St Lucia, QLD, Australia
| | - Johann Faouzi
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Benoît Martin
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Elina Thibeau-Sutre
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Adam Wild
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Manon Ansart
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Stanley Durrleman
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Didier Dormont
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France.,AP-HP, Hôpital de la Pitié-Salpêtrière, Department of Neuroradiology, Paris, France
| | - Ninon Burgos
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| | - Olivier Colliot
- Paris Brain Institute, ICM, Paris, France.,Inserm, U 1127, Paris, France.,CNRS, UMR 7225, Paris, France.,Sorbonne Université, Paris, France.,Inria Paris, Aramis project-team, Paris, France
| |
Collapse
|
158
|
Da Costa PF, Dafflon J, Pinaya WHL. Brain-Age Prediction Using Shallow Machine Learning: Predictive Analytics Competition 2019. Front Psychiatry 2020; 11:604478. [PMID: 33343431 PMCID: PMC7738323 DOI: 10.3389/fpsyt.2020.604478] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/09/2020] [Accepted: 11/09/2020] [Indexed: 01/03/2023] Open
Abstract
As we age, our brain structure changes and our cognitive capabilities decline. Although brain aging is universal, rates of brain aging differ markedly, which can be associated with pathological mechanism of psychiatric and neurological diseases. Predictive models have been applied to neuroimaging data to learn patterns associated with this variability and develop a neuroimaging biomarker of the brain condition. Aiming to stimulate the development of more accurate brain-age predictors, the Predictive Analytics Competition (PAC) 2019 provided a challenge that included a dataset of 2,640 participants. Here, we present our approach which placed between the top 10 of the challenge. We developed an ensemble of shallow machine learning methods (e.g., Support Vector Regression and Decision Tree-based regressors) that combined voxel-based and surface-based morphometric data. We used normalized brain volume maps (i.e., gray matter, white matter, or both) and features of cortical regions and anatomical structures, like cortical thickness, volume, and mean curvature. In order to fine-tune the hyperparameters of the machine learning methods, we combined the use of genetic algorithms and grid search. Our ensemble had a mean absolute error of 3.7597 years on the competition, showing the potential that shallow methods still have in predicting brain-age.
Collapse
Affiliation(s)
- Pedro F Da Costa
- Centre for Neuroimaging Sciences, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, United Kingdom.,Centre for Brain and Cognitive Development, Birkbeck College, London, United Kingdom
| | - Jessica Dafflon
- Centre for Neuroimaging Sciences, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, United Kingdom
| | - Walter H L Pinaya
- Department of Biomedical Engineering, King's College London, London, United Kingdom
| |
Collapse
|
159
|
Lombardi A, Monaco A, Donvito G, Amoroso N, Bellotti R, Tangaro S. Brain Age Prediction With Morphological Features Using Deep Neural Networks: Results From Predictive Analytic Competition 2019. Front Psychiatry 2020; 11:619629. [PMID: 33551880 PMCID: PMC7854554 DOI: 10.3389/fpsyt.2020.619629] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/20/2020] [Accepted: 12/18/2020] [Indexed: 12/05/2022] Open
Abstract
Morphological changes in the brain over the lifespan have been successfully described by using structural magnetic resonance imaging (MRI) in conjunction with machine learning (ML) algorithms. International challenges and scientific initiatives to share open access imaging datasets also contributed significantly to the advance in brain structure characterization and brain age prediction methods. In this work, we present the results of the predictive model based on deep neural networks (DNN) proposed during the Predictive Analytic Competition 2019 for brain age prediction of 2638 healthy individuals. We used FreeSurfer software to extract some morphological descriptors from the raw MRI scans of the subjects collected from 17 sites. We compared the proposed DNN architecture with other ML algorithms commonly used in the literature (RF, SVR, Lasso). Our results highlight that the DNN models achieved the best performance with MAE = 4.6 on the hold-out test, outperforming the other ML strategies. We also propose a complete ML framework to perform a robust statistical evaluation of feature importance for the clinical interpretability of the results.
Collapse
Affiliation(s)
- Angela Lombardi
- Istituto Nazionale di Fisica Nucleare, Bari, Italy.,Dipartimento Interateneo di Fisica, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | | | | | - Nicola Amoroso
- Istituto Nazionale di Fisica Nucleare, Bari, Italy.,Dipartimento di Farmacia - Scienze del Farmaco, Universitá degli Studi di Bari Aldo Moro, Bari, Italy
| | - Roberto Bellotti
- Istituto Nazionale di Fisica Nucleare, Bari, Italy.,Dipartimento Interateneo di Fisica, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Sabina Tangaro
- Istituto Nazionale di Fisica Nucleare, Bari, Italy.,Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
| |
Collapse
|