Identifying subtypes of obesity using brain functional connectivity
Poster No:
1433
Submission Type:
Abstract Submission
Authors:
Yang Liu1,2, Wenchao Zhang1,2, Guanya Li1,2, Yang Hu1,2, Jinxu Zhang1,2, Yufei Dong1,2, Shilong Yu1,2, Yi Zhang1,2
Institutions:
1Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi 710126, China, 2International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China
First Author:
Yang Liu
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Co-Author(s):
Wenchao Zhang
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Guanya Li
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Yang Hu
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Jinxu Zhang
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Yufei Dong
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Shilong Yu
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Yi Zhang
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Center for Brain Imaging, School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education|International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment & Xi'an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information, School of Life Science and Technology, Xidian University
Xi'an, Shaanxi 710126, China|Xi'an, Shaanxi 710126, China
Introduction:
Obesity has tripled over the past 40 years and has become a major public health issue. It is generally recognized that obesity is the result of overeating and lack of exercise, therefore the current treatment for obesity is mainly through dietary restriction and exercise enhancement. However, the causes of obesity are heterogeneous, and clinical behavioral characteristics vary across patients with obesity, e.g., partial patients do not have overeating behaviors (E. Oliveros, et al. 2014). Neuroimaging studies have found that binge eating behaviors in patients with obesity are related to abnormalities in brain function and structure (Carnell S, et al. 2017). Nevertheless, group-level analysis was applied to previous studies, ignoring individual differences in patients with obesity and potential subtypes of obesity. To further investigate differences in brain functions in patients with obesity, the current study employed an autoencoder to identify obesity subtypes through resting-state functional magnetic resonance imaging (rs-fMRI) and to lay the foundation for the subsequent neuromodulation treatment of obesity.
Methods:
262 patients with obesity (OB) and 110 participants with normal weight (NW) were recruited and resting-state functional magnetic resonance images of participants were collected in the current study. Firstly, functional MRI volumes were divided into 246 regions of interest (ROI) based on the Brainnetome Atlas, and whole-brain functional connectivity matrices were constructed with the dimension of 246 × 246 and each correlation matrix was thresholded at a sparse level of 30% (He, et al. 2008). Then, a supervised variational autoencoder (VAE) was used to extract obesity-related latent features from the functional connectivity matrix. The VAE model involves two substructures, and one is a standard VAE with an encoder based on row and column convolution (J. Kawahara, et al. 2017) aiming to extract latent features from the input as well as a transposed convolution-based decoder to construct original input data from the latent features. The other one is a classifier that takes the latent features as input and outputs the predicted labels of OB or NW (Figure. 1A). The classifier branch introduces a classification loss into VAE's reconstruction loss, which makes the latent features carry obesity-related information. The dataset was divided into training, validation, and test datasets with ratios of 60, 20, and 20%, respectively. In the training stage, functional connectivity matrices of OB and NW were input into the model and the model was trained to reduce the classification loss and reconstruction loss at the same time. After model training, latent features extracted for OB were clustered with K-means (Figure. 1B). The optimal number of clusters was determined by the largest consensus coefficient. Finally, independent samples t-tests were applied to compare the eating behavior assessed by the Dutch Eating Behavior Questionnaire (DEBQ) and functional connectivities between the subgroups identified by clustering.
Results:
The classifier branch achieved an accuracy of 80%, indicating the latent features were related to obesity. OB were clustered into two subgroups, and subgroup 1 showed significantly lower scores in emotional eating (P = 0.002), and disinhibition eating (P = 0.004) in DEBQ (Figure. 2A). In addition, subgroup 1 showed stronger functional connectivities among the temporal lobe, parietal lobe, and occipital lobe, and subgroup 2 showed stronger functional connectivities related to the thalamus (Figure. 2B).
Conclusions:
Patients with obesity were clustered into two subgroups based on the representation learning model and rs-fMRI functional connectivity, one subgroup with healthier eating behavior and the other with eating disorder. In addition, there were significant differences in brain functional connectivities, indicating different neuromodulation targets were required for the two subgroups of patients.
Modeling and Analysis Methods:
Classification and Predictive Modeling 2
fMRI Connectivity and Network Modeling 1
Novel Imaging Acquisition Methods:
BOLD fMRI
Keywords:
FUNCTIONAL MRI
Machine Learning
Other - Autoencoder, subtypes of obesity, classification
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
E. Oliveros. The concept of normal weight obesity, Prog. Cardiovasc. Dis. (2014)
He. Structural insights into aberrant topological patterns of large-scale cortical networks in Alzheimer's disease. Journal of Neuroscience, 28(18), 4756–4766.
J. Kawahara. “BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment,”NeuroImage, vol. 146, pp. 1038–1049, Feb. 2017
Guanya Li. Brain functional and structural magnetic resonance imaging of obesity and weight loss interventions. Mol Psychiatry. 2023
T. van Strien.
References
E. Oliveros, V.K. Somers, O. Sochor, K. Goel, F. Lopez-Jimenez, The concept of normal weight obesity, Prog. Cardiovasc. Dis. (2014).
Carnell S, Benson L, Chang KV, Wang Z, Huo Y, Geliebter A, et al. Neural correlates of familial obesity risk and overweight in adolescence. Neuroimage 2017; 159:236–47.
Li G, Hu Y, Zhang W, Wang J, Ji W, Manza P, Volkow ND, Zhang Y, Wang GJ. Brain functional and structural magnetic resonance imaging of obesity and weight loss interventions. Mol Psychiatry. 2023 Apr;28(4):1466-1479.
He, Y., Chen, Z., & Evans, A. (2008). Structural insights into aberrant topological patterns of large-scale cortical networks in Alzheimer’s disease. Journal of Neuroscience, 28(18), 4756–4766.
J. Kawahara et al., “BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment,” NeuroImage, vol. 146, pp. 1038–1049, Feb. 2017, doi: 10.1016/j.neuroimage.2016.09.046.
T. van Strien, J.E.R. Frijters, G.P.A. Bergers, P.B. Defares, The Dutch Eating Behavior Questionnaire (DEBQ) for assessment of restrained, emotional, and external eating behavior, Int. J. Eat. Disord. (1986).