scholarly journals Towards the Interpretability of Deep Learning Models for Human Neuroimaging

2021 ◽  
Author(s):  
Simon M. Hofmann ◽  
Frauke Beyer ◽  
Sebastian Lapuschkin ◽  
Loeffler Markus ◽  
Klaus-Robert Mueller ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Brain Aging ◽  
Accelerated Aging ◽  
Population Based ◽  
Learning Models ◽  
Brain Images ◽  
Subarachnoid Spaces ◽  
Magnetic Resonance Imaging Mri ◽  
Brain Age

Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with Layer-wise Relevance Propagation (LRP) to detect which brain features contribute to BA. Trained on magnetic resonance imaging (MRI) data of a population-based study (n=2637, 18-82 years), our models estimated age accurately based on single and multiple modalities, regionally restricted and whole-brain images (mean absolute errors 3.38-5.07 years). We find that BA estimates capture aging at both small and large-scale changes, revealing gross enlargements of ventricles and subarachnoid spaces, as well as lesions, iron accumulations and atrophies that appear throughout the brain. Divergence from expected aging reflected cardiovascular risk factors and accelerated aging was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-aging in healthy and at-risk individuals throughout adulthood.

scholarly journals From a deep learning model back to the brain - inferring morphological markers and their relation to aging

2019 ◽  
Author(s):  
Gidon Levakov ◽  
Gideon Rosenthal ◽  
Ilan Shelef ◽  
Tammy Riklin Raviv ◽  
Galia Avidan
Keyword(s):  
Deep Learning ◽  
Brain Aging ◽  
Absolute Error ◽  
Structural Mri ◽  
Brain Regions ◽  
Population Based ◽  
List Type ◽  
Brain Images ◽  
Brain Age ◽  
Age Prediction

AbstractWe present a Deep Learning framework for the prediction of chronological age from structural MRI scans. Previous findings associate an overestimation of brain age with neurodegenerative diseases and higher mortality rates. However, the importance of brain age prediction goes beyond serving as biomarkers for neurological disorders. Specifically, utilizing convolutional neural network (CNN) analysis to identify brain regions contributing to the prediction can shed light on the complex multivariate process of brain aging. Previous work examined methods to attribute pixel/voxel-wise contributions to the prediction in a single image, resulting in ‘explanation maps’ that were found noisy and unreliable. To address this problem, we developed an inference framework for combining these maps across subjects, thus creating a population-based rather than a subject-specific map. We applied this method to a CNN ensemble trained on predicting subjects’ age from raw T1 brain images of 10,176 subjects. Evaluating the model on an untouched test set resulted in mean absolute error of 3.07 years and a correlation between chronological and predicted age of r=0.98. Using the inference method, we revealed that cavities containing CSF, previously found as general atrophy markers, had the highest contribution for age prediction. Comparing maps derived from different models within the ensemble allowed to assess differences and similarities in brain regions utilized by the model. We showed that this method substantially increased the replicability of explanation maps, converged with results from voxel-based morphometry age studies and highlighted brain regions whose volumetric variability contributed the most to the prediction.HighlightsCNNs ensemble is shown to estimate “brain age” from sMRI with an MAE of ∼3.1 yearsA novel framework enables to highlight brain regions contributing to the predictionThis framework results in explanation maps showing consistency with the literatureAs sample size increases, these maps show higher inter-sample replicabilityCSF cavities reflecting general atrophy were found as a prominent aging biomarker

scholarly journals Deep learning based quantification of the accelerated brain aging rate in glioma patients after radiotherapy

2021 ◽  
Author(s):  
Selena I. Huisman ◽  
Arthur T.J. van der Boog ◽  
Fia Cialdella ◽  
Joost J.C. Verhoeff ◽  
Szabolcs David
Keyword(s):  
Deep Learning ◽  
Brain Aging ◽  
Accelerated Aging ◽  
Learning Model ◽  
Aging Rate ◽  
Saliency Maps ◽  
Mri Scans ◽  
Brain Age ◽  
Deep Learning Model

Background and purpose. Changes of healthy appearing brain tissue after radiotherapy have been previously observed, however, they remain difficult to quantify. Due to these changes, patients undergoing radiotherapy may have a higher risk of cognitive decline, leading to a reduced quality of life. The experienced tissue atrophy is similar to the effects of normal aging in healthy individuals. We propose a new way to quantify tissue changes after cranial RT as accelerated brain aging using the BrainAGE framework. Materials and methods. BrainAGE was applied to longitudinal MRI scans of 32 glioma patients, who have undergone radiotherapy. Utilizing a pre-trained deep learning model, brain age is estimated for all patients' pre-radiotherapy planning and follow-up MRI scans to get a quantification of the changes occurring in the brain over time. Saliency maps were extracted from the model to spatially identify which areas of the brain the deep learning model weighs highest for predicting age. The predicted ages from the deep learning model were used in a linear mixed effects model to quantity aging and aging rates for patients after radiotherapy. Results. The linear mixed effects model resulted in an accelerated aging rate of 2.78 years per year, a significant increase over a normal aging rate of 1 (p <0.05, confidence interval (CI) = 2.54-3.02). Furthermore, the saliency maps showed numerous anatomically well-defined areas, e.g.: Heschl's gyrus among others, determined by the model as important for brain age prediction. Conclusion. We found that patients undergoing radiotherapy are affected by significant radiation- induced accelerated aging, with several anatomically well-defined areas contributing to this aging. The estimated brain age could provide a method for quantifying quality of life post-radiotherapy.

scholarly journals A reusable benchmark of brain-age prediction from M/EEG resting-state signals

2021 ◽  
Author(s):  
Denis A Engemann ◽  
Apolline Mellot ◽  
Richard Hoechenberger ◽  
Hubert Banville ◽  
David Sabbagh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Brain Aging ◽  
Population Level ◽  
Learning Approaches ◽  
Eeg Signals ◽  
Brain Images ◽  
Clinical Endpoints ◽  
Starting Point ◽  
Brain Age

Population-level modeling can define quantitative measures of individual aging by applying machine learning to large volumes of brain images. These measures of brain age, obtained from the general population, helped characterize disease severity in neurological populations, improving estimates of diagnosis or prognosis. Magnetoencephalography (MEG) and Electroencephalography (EEG) have the potential to further generalize this approach towards prevention and public health by enabling assessments of brain health at large scales in socioeconomically diverse environments. However, more research is needed to define methods that can handle the complexity and diversity of M/EEG signals across diverse real-world contexts. To catalyse this effort, here we propose reusable benchmarks of competing machine learning approaches for brain age modeling. We benchmarked popular classical machine learning pipelines and deep learning architectures previously used for pathology decoding or brain age estimation in 4 international M/EEG cohorts from diverse countries and cultural contexts, including recordings from more than 2500 participants. Our benchmarks were built on top of the M/EEG adaptations of the BIDS standard, providing tools that can be applied with minimal modification on any M/EEG dataset provided in the BIDS format. Our results suggest that, regardless of whether classical machine learning or deep learning was used, the highest performance was reached by pipelines and architectures involving spatially aware representations of the M/EEG signals, leading to R^2 scores between 0.60-0.71. Hand-crafted features paired with random forest regression provided robust benchmarks even in situations in which other approaches failed. Taken together, this set of benchmarks, accompanied by open-source software and high-level Python scripts, can serve as a starting point and quantitative reference for future efforts at developing M/EEG-based measures of brain aging. The generality of the approach renders this benchmark reusable for other related objectives such as modeling specific cognitive variables or clinical endpoints.

scholarly journals Accelerated aging in the brain, epigenetic aging in blood, and polygenic risk for schizophrenia

2020 ◽  
Author(s):  
Jalmar Teeuw ◽  
Anil PS Ori ◽  
Rachel M Brouwer ◽  
Sonja MC de Zwarte ◽  
Hugo G Schnack ◽  
...  
Keyword(s):  
Brain Aging ◽  
Accelerated Aging ◽  
Disease Status ◽  
Risk Scores ◽  
Brain Images ◽  
Polygenic Risk ◽  
Acceleration Rate ◽  
Epigenetic Aging ◽  
Brain Age ◽  
The Brain

Schizophrenia patients show signs of accelerated aging in cognitive and physiological domains. Both schizophrenia and accelerated aging, as measured by MRI brain images and epigenetic clocks, are correlated with increased mortality. However, the association between these aging measures have not yet been studied in schizophrenia patients. In schizophrenia patients and healthy subjects, accelerated aging was assessed in brain tissue using a longitudinal MRI (N=715 scans; mean scan interval 3.4 year) and in blood using two epigenetic age clocks (N=172). Differences ('gaps') between estimated ages and chronological ages were calculated, as well as the acceleration rate of brain aging. The correlations between these aging measures as well as with polygenic risk scores for schizophrenia (PRS; N=394) were investigated. Brain aging and epigenetic aging were not significantly correlated. Polygenic risk for schizophrenia was significantly correlated with brain age gap, brain age acceleration rate, and negatively correlated with DNAmAge gap, but not with PhenoAge gap. However, after controlling for disease status and multiple comparisons correction, these effects were no longer significant. Our results imply that the (accelerated) aging observed in the brain and blood reflect distinct biological processes. Our findings will require replication in a larger cohort.

scholarly journals Statistical Estimation of Accelerated Biological Brain Aging After Mild Traumatic Brain Injury in Older Adults

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 890-890
Author(s):  
Andrei Irimia ◽  
Jun Kim ◽  
Shania Wang ◽  
Hyung Jun Lee ◽  
Van Ngo ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Mild Traumatic Brain Injury ◽  
Brain Aging ◽  
Rate Of Change ◽  
Time Period ◽  
Weighted Magnetic Resonance Imaging ◽  
Neurological Conditions ◽  
Magnetic Resonance Imaging Mri ◽  
Brain Age

Abstract Estimating biological brain age (BA) has the potential of identifying individuals at relatively high risk for accelerated neurodegeneration. This study compares the brain’s chronological age (CA) to its BA and reveals the BA rate of change after mild traumatic brain injury (mTBI) in an aging cohort. Using T1-weighted magnetic resonance imaging (MRI) volumes and cortical thickness, volume, surface area, and Gaussian curvature obtained using FreeSurfer software; we formulated a multivariate linear regression to determine the rate of BA increase associated with mTBI. 95 TBI patients (age in years (y): μ = 41 y, σ = 17 y; range = 18 to 83) were compared to 462 healthy controls (HCs) (age: μ = 69 y, σ = 18 y; range = 25 to 95) over a 6-month time period following mTBI. Across the initial ~6 months following injury, patients’ BAs increased by ~3.0 ± 1.2 years due to their mTBIs alone, i.e., above and beyond typical brain aging. The superior temporal and parahippocampal gyri, two structures involved in memory formation and retrieval, exhibited the fastest rates of TBI-related BA. In both hemispheres, the volume of the hippocampus decreased (left: μ=0.28%, σ=4.40%; right: μ=0.12%, σ=4.84%). These findings illustrate BA estimation techniques’ potential to identify TBI patients with accelerated neurodegeneration, whose rate is strongly associated with the risk for dementia and other aging-related neurological conditions.

scholarly journals EyeHealer: A large-scale anterior eye segment dataset with eye structure and lesion annotations

2021 ◽  
Author(s):  
Wenjia Cai ◽  
Jie Xu ◽  
Ke Wang ◽  
Xiaohong Liu ◽  
Wenqin Xu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Image Annotation ◽  
Clinical Care ◽  
Significant Proportion ◽  
Anterior Segment ◽  
Future Research ◽  
Learning Models ◽  
Anterior Eye Segment ◽  
Segmentation Models

Abstract Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide, including diseases associated with corneal pathologies, anterior chamber abnormalities (e.g. blood or inflammation) and lens diseases. The construction of an automatic tool for the segmentation of anterior segment eye lesions will greatly improve the efficiency of clinical care. With research on artificial intelligence progressing in recent years, deep learning models have shown their superiority in image classification and segmentation. The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise, however, such data are relatively scarce in the domain of medicine. Herein, the authors developed a new medical image annotation system, called EyeHealer. It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level. Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation. The results showed that semantic segmentation models outperformed medical segmentation models. This paper describes the establishment of the system for automated classification and segmentation tasks. The dataset will be made publicly available to encourage future research in this area.

scholarly journals A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

2019 ◽  
Author(s):  
Mojtaba Haghighatlari ◽  
Gaurav Vishwakarma ◽  
Mohammad Atif Faiz Afzal ◽  
Johannes Hachmann
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Organic Molecules ◽  
Learning Model ◽  
Training Data ◽  
Refractive Indices ◽  
Learning Models ◽  
Deep Learning Model ◽  
Machine Learning Models

<div><div><div><p>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</p></div></div></div>

scholarly journals The Diagnosis of Alzheimer’s Disease: An Ensemble Approach

2020 ◽  
Author(s):  
Jingyan Qiu ◽  
Linjian Li ◽  
Yida Liu ◽  
Yingjun Ou ◽  
Yubei Lin
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Large Scale ◽  
Early Stage ◽  
Training Transfer ◽  
Detection And Diagnosis ◽  
Magnetic Resonance Imaging Mri ◽  
Deep Learning Model ◽  
The Brain

Alzheimer’s disease (AD) is one of the most common forms of dementia. The early stage of the disease is defined as Mild Cognitive Impairment (MCI). Recent research results have shown the prospect of combining Magnetic Resonance Imaging (MRI) scanning of the brain and deep learning to diagnose AD. However, the CNN deep learning model requires a large scale of samples for training. Transfer learning is the key to enable a model with high accuracy by using limited data for training. In this paper, DenseNet and Inception V4, which were pre-trained on the ImageNet dataset to obtain initialization values of weights, are, respectively, used for the graphic classification task. The ensemble method is employed to enhance the effectiveness and efficiency of the classification models and the result of different models are eventually processed through probability-based fusion. Our experiments were completely conducted on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) public dataset. Only the ternary classification is made due to a higher demand for medical detection and diagnosis. The accuracies of AD/MCI/Normal Control (NC) of different models are estimated in this paper. The results of the experiments showed that the accuracies of the method achieved a maximum of 92.65%, which is a remarkable outcome compared with the accuracies of the state-of-the-art methods.

scholarly journals Validating the validation: reanalyzing a large-scale comparison of deep learning and machine learning models for bioactivity prediction

2020 ◽  
Vol 34 (7) ◽  
pp. 717-730 ◽  
Author(s):  
Matthew C. Robinson ◽  
Robert C. Glen ◽  
Alpha A. Lee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Numerical Experiments ◽  
Large Scale ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Learning Models ◽  
Bioactivity Prediction ◽  
Operating Characteristic Curve ◽  
Machine Learning Models

Abstract Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening. We further suggest that area under the precision–recall curve should be used in conjunction with the receiver operating characteristic curve. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.

Sign in / Sign up

Export Citation Format

Share Document