Identifying Morphological Indicators of Aging With Neural Networks on Large-Scale Whole-Body MRI

eXplainable Artificial Intelligence (XAI) in aging clock models

XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.

Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes

Brain age prediction from 3D MRI volumes using deep learning has recently become a popular research topic, as brain age has been shown to be an important biomarker. Training deep networks can be very computationally demanding for large datasets like the U.K. Biobank (currently 29,035 subjects). In our previous work, it was demonstrated that using a few 2D projections (mean and standard deviation along three axes) instead of each full 3D volume leads to much faster training at the cost of a reduction in prediction accuracy. Here, we investigated if another set of 2D projections, based on higher-order statistical central moments and eigenslices, leads to a higher accuracy. Our results show that higher-order moments do not lead to a higher accuracy, but that eigenslices provide a small improvement. We also show that an ensemble of such models provides further improvement.

Deep learning-based age estimation from clinical Computed Tomography image data of the thorax and abdomen in the adult population

Aging is an important risk factor for disease, leading to morphological change that can be assessed on Computed Tomography (CT) scans. We propose a deep learning model for automated age estimation based on CT- scans of the thorax and abdomen generated in a clinical routine setting. These predictions could serve as imaging biomarkers to estimate a "biological" age, that better reflects a patient's true physical condition. A pre-trained ResNet-18 model was modified to predict chronological age as well as to quantify its aleatoric uncertainty. The model was trained using 1653 non-pathological CT-scans of the thorax and abdomen of subjects aged between 20 and 85 years in a 5-fold cross-validation scheme. Generalization performance as well as robustness and reliability was assessed on a publicly available test dataset consisting of thorax-abdomen CT-scans of 421 subjects. Score-CAM saliency maps were generated for interpretation of model outputs. We achieved a mean absolute error of 5.76 ± 5.17 years with a mean uncertainty of 5.01 ± 1.44 years after 5-fold cross-validation. A mean absolute error of 6.50 ± 5.17 years with a mean uncertainty of 6.39 ± 1.46 years was obtained on the test dataset. CT-based age estimation accuracy was largely uniform across all age groups and between male and female subjects. The generated saliency maps highlighted especially the lumbar spine and abdominal aorta. This study demonstrates, that accurate and generalizable deep learning-based automated age estimation is feasible using clinical CT image data. The trained model proved to be robust and reliable. Methods of uncertainty estimation and saliency analysis improved the interpretability.

Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections

Using 3D CNNs on high-resolution medical volumes is very computationally demanding, especially for large datasets like UK Biobank, which aims to scan 100,000 subjects. Here, we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of 3D volumes leads to reasonable test accuracy (mean absolute error of about 3.5 years) when predicting age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 20-50 s using a single GPU, which is two orders of magnitude faster than a small 3D CNN. This speedup is explained by the fact that 3D brain volumes contain a lot of redundant information, which can be efficiently compressed using 2D projections. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs.

Recent Advances in Explainable Artificial Intelligence for Magnetic Resonance Imaging

Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as "black boxes". There is an unmet need to demystify DL models so domain experts can trust these high-performance DL models. This has resulted in a sub-domain of AI research called explainable artificial intelligence (XAI). In the last decade, many experts have dedicated their efforts to developing novel XAI methods that are competent at visualizing and explaining the logic behind data-driven DL models. However, XAI techniques are still in their infancy for medical MRI image analysis. This study aims to outline the XAI applications that are able to interpret DL models for MRI data analysis. We first introduce several common MRI data modalities. Then, a brief history of DL models is discussed. Next, we highlight XAI frameworks and elaborate on the principles of multiple popular XAI methods. Moreover, studies on XAI applications in MRI image analysis are reviewed across the tissues/organs of the human body. A quantitative analysis is conducted to reveal the insights of MRI researchers on these XAI techniques. Finally, evaluations of XAI methods are discussed. This survey presents recent advances in the XAI domain for explaining the DL models that have been utilized in MRI applications.

Age-Related Differences of Cortical Topology Across the Adult Lifespan: Evidence From a Multisite MRI Study With 1427 Individuals

BACKGROUND

Healthy aging is usually accompanied by alterations in brain network architecture, influencing information processing and cognitive performance. However, age-associated coordination patterns of morphological networks and cognitive variation are not well understood.

PURPOSE

To investigate the age-related differences of cortical topology in morphological brain networks from multiple perspectives.

STUDY TYPE

Prospective, observational multisite study.

POPULATION

A total of 1427 healthy participants (59.1% female, 51.75 ± 19.82 years old) from public datasets.

FIELD STRENGTH/SEQUENCE

1.5 T/3 T, T1-weighted magnetization prepared rapid gradient echo (MP-RAGE) sequence.

ASSESSMENT

The multimodal parcellation atlas was used to define regions of interest (ROIs). The Jensen-Shannon divergence-based individual morphological networks were constructed by estimating the interregional similarity of cortical thickness distribution. Graph-theory based global network properties were then calculated, followed by ROI analysis (including global/nodal topological analysis and hub analysis) with statistical tests.

STATISTICAL TESTS

Chi-square test, Jensen-Shannon divergence-based similarity measurement, general linear model with false discovery rate correction. Significance was set at P < 0.05.

RESULTS

The clustering coefficient (q = 0.016), global efficiency (q = 0.007), and small-worldness (q = 0.006) were significantly negatively quadratic correlated with age. The group-level hubs of seven age groups were found mainly distributed in default mode network, visual network, salient network, and somatosensory motor network (the sum of these hubs' distribution in each group exceeds 55%). Further ROI-wise analysis showed significant nodal trajectories of intramodular connectivities.

DATA CONCLUSION

These results demonstrated the age-associated reconfiguration of morphological networks. Specifically, network segregation/integration had an inverted U-shaped relationship with age, which indicated age-related differences in transmission efficiency.

EVIDENCE LEVEL

2 TECHNICAL EFFICACY: Stage 1.

Using deep learning to predict abdominal age from liver and pancreas magnetic resonance images

With age, the prevalence of diseases such as fatty liver disease, cirrhosis, and type two diabetes increases. Approaches to both predict abdominal age and identify risk factors for accelerated abdominal age may ultimately lead to advances that will delay the onset of these diseases. We build an abdominal age predictor by training convolutional neural networks to predict abdominal age (or "AbdAge") from 45,552 liver magnetic resonance images [MRIs] and 36,784 pancreas MRIs (R-Squared = 73.3 ± 0.6; mean absolute error = 2.94 ± 0.03 years). Attention maps show that the prediction is driven by both liver and pancreas anatomical features, and surrounding organs and tissue. Abdominal aging is a complex trait, partially heritable (h_g² = 26.3 ± 1.9%), and associated with 16 genetic loci (e.g. in PLEKHA1 and EFEMP1), biomarkers (e.g body impedance), clinical phenotypes (e.g, chest pain), diseases (e.g. hypertension), environmental (e.g smoking), and socioeconomic (e.g education, income) factors.

Improving brain age estimates with deep learning leads to identification of novel genetic factors associated with brain aging

To study genetic factors associated with brain aging, we first need to quantify brain aging. Statistical models have been created for estimating the apparent age of the brain, or predicted brain age (PBA), using imaging data. Recent studies have refined these models to obtain a more accurate PBA, but research has yet to demonstrate the scientific value of doing so. Here, we show that a more accurate PBA leads to better characterization of genetic factors associated with brain aging. We trained a convolutional neural network (CNN) model on 16,998 UK Biobank subjects to derive PBA, then conducted a genome-wide association study on the PBA, in which we identified single nucleotide polymorphisms from four independent loci significantly associated with brain aging, three of which were novel. By comparing association results based on the CNN-derived PBA to those based on a linear regression-derived PBA, we concluded that a more accurate PBA enables the discovery of novel genetic associations. Our results may be valuable for identifying other lifestyle factors associated with brain aging.

Large-scale biometry with interpretable neural network regression on UK Biobank body MRI

In a large-scale medical examination, the UK Biobank study has successfully imaged more than 32,000 volunteer participants with magnetic resonance imaging (MRI). Each scan is linked to extensive metadata, providing a comprehensive medical survey of imaged anatomy and related health states. Despite its potential for research, this vast amount of data presents a challenge to established methods of evaluation, which often rely on manual input. To date, the range of reference values for cardiovascular and metabolic risk factors is therefore incomplete. In this work, neural networks were trained for image-based regression to infer various biological metrics from the neck-to-knee body MRI automatically. The approach requires no manual intervention or direct access to reference segmentations for training. The examined fields span 64 variables derived from anthropometric measurements, dual-energy X-ray absorptiometry (DXA), atlas-based segmentations, and dedicated liver scans. With the ResNet50, the standardized framework achieves a close fit to the target values (median R\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^2 > 0.97$$\end{document}2>0.97) in cross-validation. Interpretation of aggregated saliency maps suggests that the network correctly targets specific body regions and limbs, and learned to emulate different modalities. On several body composition metrics, the quality of the predictions is within the range of variability observed between established gold standard techniques.

Differentiating novel coronavirus pneumonia from general pneumonia based on machine learning

BACKGROUND

Chest CT screening as supplementary means is crucial in diagnosing novel coronavirus pneumonia (COVID-19) with high sensitivity and popularity. Machine learning was adept in discovering intricate structures from CT images and achieved expert-level performance in medical image analysis.

METHODS

An integrated machine learning framework on chest CT images for differentiating COVID-19 from general pneumonia (GP) was developed and validated. Seventy-three confirmed COVID-19 cases were consecutively enrolled together with 27 confirmed general pneumonia patients from Ruian People's Hospital, from January 2020 to March 2020. To accurately classify COVID-19, region of interest (ROI) delineation was implemented based on ground-glass opacities (GGOs) before feature extraction. Then, 34 statistical texture features of COVID-19 and GP ROI images were extracted, including 13 gray-level co-occurrence matrix (GLCM) features, 15 gray-level-gradient co-occurrence matrix (GLGCM) features and 6 histogram features. High-dimensional features impact the classification performance. Thus, ReliefF algorithm was leveraged to select features. The relevance of each feature was the average weights calculated by ReliefF in n times. Features with relevance larger than the empirically set threshold T were selected. After feature selection, the optimal feature set along with 4 other selected feature combinations for comparison were applied to the ensemble of bagged tree (EBT) and four other machine learning classifiers including support vector machine (SVM), logistic regression (LR), decision tree (DT), and K-nearest neighbor with Minkowski distance equal weight (KNN) using tenfold cross-validation.

RESULTS AND CONCLUSIONS

The classification accuracy (ACC), sensitivity (SEN), specificity (SPE) of our proposed method yield 94.16%, 88.62% and 100.00%, respectively. The area under the receiver operating characteristic curve (AUC) was 0.99. The experimental results indicate that the EBT algorithm with statistical textural features based on GGOs for differentiating COVID-19 from general pneumonia achieved high transferability, efficiency, specificity, sensitivity, and impressive accuracy, which is beneficial for inexperienced doctors to more accurately diagnose COVID-19 and essential for controlling the spread of the disease.