Predicting Body Mass Index From Structural MRI Brain Images Using a Deep Convolutional Neural Network

Using Advanced Convolutional Neural Network Approaches to Reveal Patient Age, Gender, and Weight Based on Tongue Images

The human tongue has been long believed to be a window to provide important insights into a patient's health in medicine. The present study introduced a novel approach to predict patient age, gender, and weight inferences based on tongue images using pretrained deep convolutional neural networks (CNNs). Our results demonstrated that the deep CNN models (e.g., ResNeXt) trained on dorsal tongue images produced excellent results for age prediction with a Pearson correlation coefficient of 0.71 and a mean absolute error (MAE) of 8.5 years. We also obtained an excellent classification of gender, with a mean accuracy of 80% and an AUC (area under the receiver operating characteristic curve) of 88%. ResNeXt model also obtained a moderate level of accuracy for weight prediction, with a Pearson correlation coefficient of 0.39 and a MAE of 9.06 kg. These findings support our hypothesis that the human tongue contains crucial information about a patient. This study demonstrated the feasibility of using the pretrained deep CNNs along with a large tongue image dataset to develop computational models to predict patient medical conditions for noninvasive, convenient, and inexpensive patient health monitoring and diagnosis.

The effect of head motion on brain age prediction using deep convolutional neural networks

Deep learning can be used effectively to predict participants' age from brain magnetic resonance imaging (MRI) data, and a growing body of evidence suggests that the difference between predicted and chronological age-referred to as brain-predicted age difference (brain-PAD)-is related to various neurological and neuropsychiatric disease states. A crucial aspect of the applicability of brain-PAD as a biomarker of individual brain health is whether and how brain-predicted age is affected by MR image artifacts commonly encountered in clinical settings. To investigate this issue, we trained and validated two different 3D convolutional neural network architectures (CNNs) from scratch and tested the models on a separate dataset consisting of motion-free and motion-corrupted T1-weighted MRI scans from the same participants, the quality of which were rated by neuroradiologists from a clinical diagnostic point of view. Our results revealed a systematic increase in brain-PAD with worsening image quality for both models. This effect was also observed for images that were deemed usable from a clinical perspective, with brains appearing older in medium than in good quality images. These findings were also supported by significant associations found between the brain-PAD and standard image quality metrics indicating larger brain-PAD for lower-quality images. Our results demonstrate a spurious effect of advanced brain aging as a result of head motion and underline the importance of controlling for image quality when using brain-predicted age based on structural neuroimaging data as a proxy measure for brain health.

Artificial intelligence-enhanced electrocardiography derived body mass index as a predictor of future cardiometabolic disease

The electrocardiogram (ECG) can capture obesity-related cardiac changes. Artificial intelligence-enhanced ECG (AI-ECG) can identify subclinical disease. We trained an AI-ECG model to predict body mass index (BMI) from the ECG alone. Developed from 512,950 12-lead ECGs from the Beth Israel Deaconess Medical Center (BIDMC), a secondary care cohort, and validated on UK Biobank (UKB) (n = 42,386), the model achieved a Pearson correlation coefficient (r) of 0.65 and 0.62, and an R2 of 0.43 and 0.39 in the BIDMC cohort and UK Biobank, respectively for AI-ECG BMI vs. measured BMI. We found delta-BMI, the difference between measured BMI and AI-ECG-predicted BMI (AI-ECG-BMI), to be a biomarker of cardiometabolic health. The top tertile of delta-BMI showed increased risk of future cardiometabolic disease (BIDMC: HR 1.15, p < 0.001; UKB: HR 1.58, p < 0.001) and diabetes mellitus (BIDMC: HR 1.25, p < 0.001; UKB: HR 2.28, p < 0.001) after adjusting for covariates including measured BMI. Significant enhancements in model fit, reclassification and improvements in discriminatory power were observed with the inclusion of delta-BMI in both cohorts. Phenotypic profiling highlighted associations between delta-BMI and cardiometabolic diseases, anthropometric measures of truncal obesity, and pericardial fat mass. Metabolic and proteomic profiling associates delta-BMI positively with valine, lipids in small HDL, syntaxin-3, and carnosine dipeptidase 1, and inversely with glutamine, glycine, colipase, and adiponectin. A genome-wide association study revealed associations with regulators of cardiovascular/metabolic traits, including SCN10A, SCN5A, EXOG and RXRG. In summary, our AI-ECG-BMI model accurately predicts BMI and introduces delta-BMI as a non-invasive biomarker for cardiometabolic risk stratification.

Associations between maternal pre-pregnancy BMI and infant striatal mean diffusivity

BACKGROUND

It is well-established that parental obesity is a strong risk factor for offspring obesity. Further, a converging body of evidence now suggests that maternal weight profiles may affect the developing offspring's brain in a manner that confers future obesity risk. Here, we investigated how pre-pregnancy maternal weight status influences the reward-related striatal areas of the offspring's brain during in utero development.

METHODS

We used diffusion tensor imaging to quantify the microstructure of the striatal brain regions of interest in neonates (N = 116 [66 males, 50 females], mean gestational weeks at birth [39.88], SD = 1.14; at scan [43.56], SD = 1.05). Linear regression was used to test the associations between maternal pre-pregnancy body mass index (BMI) and infant striatal mean diffusivity.

RESULTS

High maternal pre-pregnancy BMI was associated with higher mean MD values in the infant's left caudate nucleus. Results remained unchanged after the adjustment for covariates.

CONCLUSIONS

In utero exposure to maternal adiposity might have a growth-impairing impact on the mean diffusivity of the infant's left caudate nucleus. Considering the involvement of the caudate nucleus in regulating eating behavior and food-related reward processing later in life, this finding calls for further investigations to define the prognostic relevance of early-life caudate nucleus development and weight trajectories of the offspring.

Deep learning-based BMI inference from structural brain MRI reflects brain alterations following lifestyle intervention

Obesity is associated with negative effects on the brain. We exploit Artificial Intelligence (AI) tools to explore whether differences in clinical measurements following lifestyle interventions in overweight population could be reflected in brain morphology. In the DIRECT-PLUS clinical trial, participants with criterion for metabolic syndrome underwent an 18-month lifestyle intervention. Structural brain MRIs were acquired before and after the intervention. We utilized an ensemble learning framework to predict Body-Mass Index (BMI) scores, which correspond to adiposity-related clinical measurements from brain MRIs. We revealed that patient-specific reduction in BMI predictions was associated with actual weight loss and was significantly higher in active diet groups compared to a control group. Moreover, explainable AI (XAI) maps highlighted brain regions contributing to BMI predictions that were distinct from regions associated with age prediction. Our DIRECT-PLUS analysis results imply that predicted BMI and its reduction are unique neural biomarkers for obesity-related brain modifications and weight loss.

Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics

Head motion artifacts in magnetic resonance imaging (MRI) are an important confounding factor concerning brain research as well as clinical practice. For this reason, several machine learning-based methods have been developed for the automatic quality control of structural MRI scans. Deep learning offers a promising solution to this problem, however, given its data-hungry nature and the scarcity of expert-annotated datasets, its advantage over traditional machine learning methods in identifying motion-corrupted brain scans is yet to be determined. In the present study, we investigated the relative advantage of the two methods in structural MRI quality control. To this end, we collected publicly available T1-weighted images and scanned subjects in our own lab under conventional and active head motion conditions. The quality of the images was rated by a team of radiologists from the point of view of clinical diagnostic use. We present a relatively simple, lightweight 3D convolutional neural network trained in an end-to-end manner that achieved a test set (N = 411) balanced accuracy of 94.41% in classifying brain scans into clinically usable or unusable categories. A support vector machine trained on image quality metrics achieved a balanced accuracy of 88.44% on the same test set. Statistical comparison of the two models yielded no significant difference in terms of confusion matrices, error rates, or receiver operating characteristic curves. Our results suggest that these machine learning methods are similarly effective in identifying severe motion artifacts in brain MRI scans, and underline the efficacy of end-to-end deep learning-based systems in brain MRI quality control, allowing the rapid evaluation of diagnostic utility without the need for elaborate image pre-processing.

The habenular volume and PDE7A allelic polymorphism in major depressive disorder: preliminary findings

OBJECTIVES

The habenula is a brain structure implicated in depression, yet with unknown molecular mechanisms. Several phosphodiesterases (PDEs) have been associated with a risk of depression. Although the role of PDE7A in the brain is unknown, it has enriched expression in the medial habenula, suggesting that it may play a role in depression.

METHODS

We analysed: (1) habenula volume assessed by 3-T magnetic resonance imaging (MRI) in 84 patients with major depressive disorder (MDD) and 41 healthy controls; (2) frequencies of 10 single nucleotide polymorphisms (SNPs) in PDE7A gene in 235 patients and 41 controls; and (3) both indices in 80 patients and 27 controls. The analyses considered gender, age, body mass index and season of the MRI examination.

RESULTS

The analysis did not reveal habenula volumetric changes in MDD patients regardless of PDE7A SNPs. However, in the combined group, the carriers of one or more mutations among 10 SNPs in the PDE7A gene had a lower volume of the left habenula (driven mainly by rs972362 and rs138599850 mutations) and consequently had the reduced habenular laterality index in comparison with individuals without PDE7A mutations.

CONCLUSIONS

Our findings suggest the implication of the PDE7A gene into mechanisms determining the habenula structure.

Artificial Neural Network Models for Accurate Predictions of Fat-Free and Fat Masses, Using Easy-to-Measure Anthropometric Parameters

Abdominal fat and fat-free masses report a close association with cardiometabolic risks, therefore this specific body compartment presents more interest than whole-body masses. This research aimed to develop accurate algorithms that predict body masses and specifically trunk fat and fat-free masses from easy to measure parameters in any setting. The study included 104 apparently healthy subjects, but with a higher-than-normal percent of adiposity or waist circumference. Multiple linear regression (MLR) and artificial neural network (ANN) models were built for predicting abdominal fat and fat-free masses in patients with relatively low cardiometabolic risks. The data were divided into training, validation and test sets, and this process was repeated 20 times per each model to reduce the bias of data division on model accuracy. The best performance models used a maximum number of five anthropometric inputs, with higher R² values for ANN models than for MLR models (R² = 0.96-0.98 vs. R² = 0.80-0.94, p = 0.006). The root mean square error (RMSE) for all predicted parameters was significantly lower for ANN models than for MLR models, suggesting a higher accuracy for ANN models. From all body masses predicted, trunk fat mass and fat-free mass registered the best performance with ANN, allowing a possible error of 1.84 kg for predicting the correct trunk fat mass and 1.48 kg for predicting the correct trunk fat-free mass. The developed algorithms represent cost-effective prediction tools for the most relevant adipose and lean tissues involved in the physiopathology of cardiometabolic risks.

Distributional Transformation Improves Decoding Accuracy When Predicting Chronological Age From Structural MRI

When predicting a certain subject-level variable (e.g., age in years) from measured biological data (e.g., structural MRI scans), the decoding algorithm does not always preserve the distribution of the variable to predict. In such a situation, distributional transformation (DT), i.e., mapping the predicted values to the variable's distribution in the training data, might improve decoding accuracy. Here, we tested the potential of DT within the 2019 Predictive Analytics Competition (PAC) which aimed at predicting chronological age of adult human subjects from structural MRI data. In a low-dimensional setting, i.e., with less features than observations, we applied multiple linear regression, support vector regression and deep neural networks for out-of-sample prediction of subject age. We found that (i) when the number of features is low, no method outperforms linear regression; and (ii) except when using deep regression, distributional transformation increases decoding performance, reducing the mean absolute error (MAE) by about half a year. We conclude that DT can be advantageous when predicting variables that are non-controlled, but have an underlying distribution in healthy or diseased populations.