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

Vakli, Pál; Deák-Meszlényi, Regina J.; Auer, Tibor; Vidnyánszky, Zoltán

doi:10.3389/fninf.2020.00010

Cited by 18 publications

(10 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although it is important to note that the lack of bilateral findings may simply due to the high amount of noise present in newborn MRI 51 . However, in a deep learning study where the researchers used the anatomical scans of almost 18,000 adult participants to create a convolutional neural network to predict the BMI with high accuracy, it was found that left caudate had a strong influence on predicting the BMI 52 . This could imply that true hemispheric asymmetry is indeed present in the studied mechanisms.…”

Section: Discussionmentioning

confidence: 99%

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

Rosberg,

Merisaari,

Lewis

et al. 2023

Preprint

View full text Add to dashboard Cite

Background/ObjectivesIt is well-established that parental obesity is a strong risk factor for associates with offspring obesity. Further, a converging body of evidence now suggests that maternal weight profiles may affect the developing offspring 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 brain duringin uterodevelopment.MethodsWe used diffusion tensor imaging to quantify the microstructure of the striatal brain regions of interest in neonates (N = 116 mean gestational weeks at birth 39.88, SD = 1.14; and at scan 43.56, SD = 1.05). Linear regression was used to test the associations between maternal pre-pregnancy body mass index and infant striatal mean diffusivity.ResultsA strong positive association was found between the maternal pre-pregnancy body mass index and newborn left caudate nucleus mean diffusivity. Results remained unchanged after the adjustment for covariates.ConclusionsIn uteroexposure to maternal adiposity might have a growth impairing impact on the mean diffusivity of infant left caudate nucleus. Considering the involvement of caudate nucleus in regulating eating behaviour and food-related reward processing later in life, this finding calls for further investigations to define the prognostic relevance of early life caudate development and weight trajectories of the offspring.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Rosberg,

Merisaari,

Lewis

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…BMI is a simple, widely used measure for assessing obesity, while taking height into consideration. Previous studies showed that BMI could be estimated from structural MRI using convolutional DNNs (Vakli et al, 2020 ; Yadav & Razavian, 2019 ). In this work, we adapted a similar strategy to explore whether differences in clinical measurements following lifestyle intervention in an overweight population could be reflected in the brain.…”

Section: Introductionmentioning

confidence: 99%

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

Finkelstein,

Levakov,

Kaplan

et al. 2024

Human Brain Mapping

View full text Add to dashboard Cite

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.

show abstract

“…We tested the general hypothesis that advanced machine learning techniques can be used to automatically exact crucial information from the color photographs of the tongue to accurately predict a patient's age, gender, and weight. This hypothesis is based on extensive research that has revealed the information about a patient's age, gender, and weight to be readily extracted from images of the patient's face, body, and MRI scans (e.g., [28][29][30][31][32][33][34], thus suggesting that similar results can be obtained from tongue images.…”

Section: Introductionmentioning

confidence: 99%

Using advanced convolutional neural network approaches to reveal patient age, gender, and weight based on tongue images

Wei

et al. 2023

Preprint

View full text Add to dashboard Cite

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 pre-trained deep CNNs. Our results demonstrated that the deep CNN models trained on dorsal tongue images produced excellent results for age prediction with a Pearson correlation coefficient of 0.71 and a mean absolute error of 8.5 years. We also obtained an excellent classification of gender, with a mean accuracy of 80% and an AUC of 88%. The model also obtained a moderate level of accuracy for weight prediction, with a Pearson correlation coefficient of 0.39 and a mean absolute error of 9.06 kilograms. These findings support our hypothesis that the human tongue contains crucial information about a patient. This study demonstrated the feasibility of using the pre-trained deep CNNs along with a large tongue image dataset to develop computational models to predict patient medical conditions for non-invasive, convenient, and inexpensive patient health monitoring and diagnosis.

show abstract

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

Cited by 18 publications

References 73 publications

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

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

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

Using advanced convolutional neural network approaches to reveal patient age, gender, and weight based on tongue images

Contact Info

Product

Resources

About