Biology subjects

Badea, C. T.

Publications and source records attributed to Badea, C. T..

4 recordsLinked to original sources

bioRxiv2026

Calibration-Aware and Interpretable Graph Learning for Multi-Cohort Diffusion Connectome Brain-Age Modeling

Brain-age models derived from diffusion MRI-based structural connectomes may provide imaging biomarkers of accelerated brain aging, but their biological interpretation and transportability across heterogeneous populations remain uncertain. We developed a calibration-aware and hierarchically interpretable graph-learning framework and evaluated it across four independent aging and Alzheimer's disease-related cohorts: ADNI, Duke/UNC ADRC, HABS-HD, and AD-DECODE. The analysis included 1,093 connectome sessions from 789 participants. Cohort-specific graph neural networks were trained using participant-grouped cross-validation across five imaging and multimodal feature configurations. Prediction performance varied more strongly across cohorts than across feature sets, with imaging-only out-of-fold mean absolute error ranging from 4.72 years in ADNI to 9.75 years in AD-DECODE. The imaging-only graph neural network was competitive with ridge, elastic-net, and gradient-boosted regression models trained on matched vectorized connectome features, but was not uniformly superior. Age-bias-corrected brain-age gap was most consistently associated with reduced diffusion-derived microstructural integrity and structural-network organization across cohorts. In longitudinal analyses, corrected brain-age gap showed moderate-to-good within-person preservation in ADNI and HABS-HD, with intraclass correlation coefficients of 0.67 and 0.81, respectively; higher baseline values also predicted subsequent microstructural and network deterioration in ADNI. Multiscale SHAP analysis identified distributed contributions from global graph topology, regional imaging features, edge-derived regional summaries, and individual structural connections involving thalamic, striatal, frontal, parietal, cerebellar, hippocampal, and entorhinal circuitry. External transfer was highly sensitive to cohort shift: across 12 off-diagonal train-test evaluations, median mean absolute error decreased from 17.39 to 8.22 years after target-cohort linear recalibration, whereas median Pearson correlation remained 0.17. Because recalibration used target-cohort chronological age, it was interpreted as a diagnostic sensitivity analysis rather than deployable external validation. Together, these findings support calibration-aware diffusion-connectome brain age as an interpretable imaging biomarker of structural brain aging and prospective microstructural and network vulnerability, while emphasizing the need for cohort-specific calibration before external application.

neuroscience↗

bioRxiv2023

Feature attention graph neural network for estimating brain age and identifying important neural connections in mouse models of genetic risk for Alzheimer's disease

Alzheimers disease (AD) remains one of the most extensively researched neurodegenerative disorders due to its widespread prevalence and complex risk factors. Age is a crucial risk factor for AD, which can be estimated by the disparity between physiological age and estimated brain age. To model AD risk more effectively, integrating biological, genetic, and cognitive markers is essential. Here, we utilized mouse models expressing the major APOE human alleles and human nitric oxide synthase 2 to replicate genetic risk for AD and a humanized innate immune response. We estimated brain age employing a multivariate dataset that includes brain connectomes, APOE genotype, subject traits such as age and sex, and behavioral data. Our methodology used Feature Attention Graph Neural Networks (FAGNN) for integrating different data types. Behavioral data were processed with a 2D Convolutional Neural Network (CNN), subject traits with a 1D CNN, brain connectomes through a Graph Neural Network using quadrant attention module. The model yielded a mean absolute error for age prediction of 31.85 days, with a root mean squared error of 41.84 days, outperforming other, reduced models. In addition, FAGNN identified key brain connections involved in the aging process. The highest weights were assigned to the connections between cingulum and corpus callosum, striatum, hippocampus, thalamus, hypothalamus, cerebellum, and piriform cortex. Our study demonstrates the feasibility of predicting brain age in models of aging and genetic risk for AD. To verify the validity of our findings, we compared Fractional Anisotropy (FA) along the tracts of regions with the highest connectivity, the Return-to-Origin Probability (RTOP), Return-to-Plane Probability (RTPP), and Return-to-Axis Probability (RTAP), which showed significant differences between young, middle-aged, and old age groups. Younger mice exhibited higher FA, RTOP, RTAP, and RTPP compared to older groups in the selected connections, suggesting that degradation of white matter tracts plays a critical role in aging and for FAGNNs selections. Our analysis suggests a potential neuroprotective role of APOE2, relative to APOE3 and APOE4, where APOE2 appears to mitigate age-related changes. Our findings highlighted a complex interplay of genetics and brain aging in the context of AD risk modeling.

bioengineering↗

bioRxiv2019

Photon-counting cine-cardiac CT in the mouse

The maturation of photon-counting detector (PCD) technology promises to enhance routine CT imaging applications with high-fidelity spectral information. In this paper, we demonstrate the power of this synergy and our complementary reconstruction techniques, performing 4D, cardiac PCD-CT data acquisition and reconstruction in a mouse model of atherosclerosis, including calcified plaque. Specifically, in vivo cardiac micro-CT scans were performed in four ApoE knockout mice, following their development of calcified plaques. The scans were performed with a prototype PCD (DECTRIS, Ltd.) with 4 energy thresholds. Projection sampling was performed with 10 ms temporal resolution, allowing the reconstruction of 10 cardiac phases at each of 4 energies (40, 3D volumes per mouse scan). Reconstruction was performed iteratively using the split Bregman method with constraints on spectral rank and spatio-temporal gradient sparsity. The reconstructed images represent the first in vivo, 4D PCD-CT data in a mouse model of atherosclerosis. Robust regularization during iterative reconstruction yields high-fidelity results: an 8-fold reduction in noise standard deviation for the highest energy threshold (relative to algebraic reconstruction), while absolute spectral bias measurements remain below 13 Hounsfield units across all energy thresholds and scans. Qualitatively, image domain material decomposition results show clear separation of iodinated contrast and soft tissue from calcified plaque in the in vivo data. Quantitatively, spatial, spectral, and temporal fidelity are verified through a water phantom scan and a realistic MOBY phantom simulation experiment: spatial resolution is robustly preserved by iterative reconstruction (10% MTF: 2.8-3.0 lp/mm), left-ventricle, cardiac functional metrics can be measured from iodine map segmentations with [~]1% error, and small calcifications (615 m) can be detected during slow moving phases of the cardiac cycle. Given these preliminary results, we believe that PCD technology will enhance dynamic CT imaging applications with high-fidelity spectral and material information.

bioengineering↗

bioRxiv2018

Bridging the translational gap: Implementation of multimodal small animal imaging strategies for tumor burden assessment in a co-clinical trial

In designing co-clinical cancer studies, preclinical imaging brings unique challenges that emphasize the gap between man and mouse. Our group is developing quantitative imaging methods for the preclinical arm of a co-clinical trial studying immunotherapy and radiotherapy in a soft tissue sarcoma model. In line with treatment for patients enrolled in the clinical trial SU2C-SARC032, primary mouse sarcomas are imaged with multi-contrast micro-MRI (T1 weighted, T2 weighted, and T1 with contrast) before and after immune checkpoint inhibition and pre-operative radiation therapy. Similar to the patients, after surgery the mice will be screened for lung metastases with micro-CT using respiratory gating. A systems evaluation was undertaken to establish a quantitative baseline for both the MR and micro-CT systems against which others systems might be compared. We have constructed imaging protocols which provide clinically-relevant resolution and contrast in a genetically engineered mouse model of sarcoma. We have employed tools in 3D Slicer for semi-automated segmentation of both MR and micro-CT images to measure tumor volumes efficiently and reliably in a large number of animals. Assessment of tumor burden in the resulting images was precise, repeatable, and reproducible. Furthermore, we have implemented a publicly accessible platform for sharing imaging data collected during the study, as well as protocols, supporting information, and data analyses. In doing so, we aim to improve the clinical relevance of small animal imaging and begin establishing standards for preclinical imaging of tumors from the perspective of a co-clinical trial.

bioengineering↗