Summary:
Johns Hopkins researchers utilizing artificial intelligence on chest CT and brain MRI scans discovered that lower thoracic vertebral bone mineral density is tied to faster cognitive decline and accelerated microstructural white matter injury. The findings point to shared systemic metabolic drivers that simultaneously erode bone integrity and accelerate brain aging.
Key Facts:
- Accelerated Cognitive Deterioration: Lower baseline volumetric bone mineral density (vBMD) measured in the spine was significantly associated with a faster rate of global cognitive decline over time.
- Regional White Matter Vulnerability: Reduced spinal bone density correlated with microstructural decay in specific executive-function networks, specifically increased white matter hyperintensities in the corpus callosum and steeper fractional anisotropy loss in the anterior limb of the internal capsule.
- Shared Metabolic Drivers, Not Direct Causation: Investigators emphasize that bone loss does not cause dementia; rather, both conditions appear to stem from parallel metabolic aging mechanisms such as insulin resistance, dyslipidemia, and menopausal shifts.
Source: Radiological Society of North America (RSNA) / Johns Hopkins Medicine
Uncovering the Hidden Link Between Bone and Brain
Bone mineral density serves as a standard benchmark for skeletal durability, signaling when calcium loss makes bones brittle and vulnerable to fractures. While osteoporosis and cognitive impairment frequently co-occur in aging adults, science has largely investigated the skeleton and the central nervous system in isolation.
Now, a study published in Radiology by researchers at Johns Hopkins University shows that skeletal deterioration in the spine is closely linked to accelerated brain degeneration and cognitive decline.
Using a deep learning model to evaluate clinical imaging data, investigators discovered that individuals with lower bone density in their thoracic vertebrae experienced faster cognitive decline and exhibited progressive microstructural injury across key white matter pathways in the brain.
“This study is the first longitudinal secondary analysis linking baseline vertebral bone mineral density to changes in white matter structure, white matter hyperintensity progression and cognition,” said senior author Shadpour Demehri, M.D., professor of radiology at Johns Hopkins University. “This comprehensive study using both imaging and clinical assessments sends a clear signal that bone density at baseline is associated with both functional and imaging measures of age-related brain degeneration.”
AI Unlocks Opportunistic Biomarkers from Routine Scans
The research team, led by postdoctoral fellow Sara Momtazmanesh, M.D., analyzed data from the Multi-Ethnic Study of Atherosclerosis (MESA). They utilized a deep learning algorithm engineered in Dr. Demehri’s laboratory to extract thoracic vertebral volumetric bone mineral density (vBMD) directly from non-contrast chest CT scans across 2,086 individuals.
From this group, the investigators evaluated a final cohort of 715 participants who had both established vBMD metrics and completed multimodal brain MRI exams and longitudinal cognitive testing.
To trace brain pathology, the team evaluated two key imaging biomarkers of vascular and microstructural deterioration:
- White Matter Hyperintensities (WMHs): Visible bright patches on MRI scans indicative of small vessel disease and localized ischemic injury. Longitudinal data was available for 408 participants.
- Reduced Fractional Anisotropy (FA): A diffusion tensor imaging marker indicating a loss of white matter tract integrity and structural organization. Longitudinal tracking covered 405 participants.
The analyses revealed that participants with lower baseline spinal bone density experienced a faster drop in global cognition. Furthermore, structural damage was localized to specific functional hubs. Participants with low vBMD showed increased white matter hyperintensities in the corpus callosum—a critical white matter bridge supporting working memory, executive function, and attention—as well as a steeper decline in fractional anisotropy within the anterior limb of the internal capsule.
A Parallel Metabolic Breakdown
The authors noted that the findings should not be interpreted as evidence that osteoporosis directly causes dementia. Instead, the co-occurrence indicates a broader, shared metabolic failure that silently damages both organ systems concurrently.
“This study is not about cause and effect, but rather the observation of a metabolic syndrome that may cause both bone and brain degeneration,” Dr. Demehri clarified. “The co-occurrence observed in the study may reflect shared metabolic drivers of aging, including insulin resistance, dyslipidemia, and menopausal change, rather than a direct bone-to-brain effect.”
Opportunistic Screening for At-Risk Patients
Because millions of patients undergo routine chest CT scans each year for lung cancer screening, heart calcium scoring, or pulmonary nodule follow-ups, AI algorithms could opportunistically measure spinal bone density from existing scans without additional radiation or cost. Flagging early bone loss could serve as an early warning sign for patients at elevated risk of accelerated neurocognitive decline, paving the way for joint preventive interventions.
“Diagnostic images contain an immense amount of data that AI can now synthesize at scale across multiple organ systems,” Dr. Demehri said. “This creates a robust, newly feasible opportunity to interconnect co-existing age-related pathologies that have traditionally been studied in isolation and to identify shared biological pathways and potential common causal mechanisms.”
Editorial Notes:
- This article was edited by a Neuroscience News editor.
- Journal paper reviewed in full.
- Additional context added by our staff.
About this Genetics and Neuroregeneration Research:
- Media Contact: Linda Brooks
- Source: RSNA
- Image Credit: Image credited to Neuroscience News
- Original Research is Open Access: Radiology (September 22, 2026). “Deep Learning-derived Bone Mineral Density and Longitudinal White Matter Microstructure and Cognitive Decline: Multi-Ethnic Study of Atherosclerosis.” Authors: Sara Momtazmanesh, Quincy A. Hathaway, Michael P. Bancks, David A. Bluemke, R. Graham Barr, Wendy S. Post, Mohamad Habes, Ilya Nasrallah, Susan R. Heckbert, R. Nick Bryan, Jose A. Luchsinger, Mei Wan, Matthew Budoff, João A. C. Lima, Timothy M. Hughes, Christos Davatzikos, and Shadpour Demehri.
- DOI: 10.1148/radiol.260656
Abstract
Deep Learning-derived Bone Mineral Density and Longitudinal White Matter Microstructure and Cognitive Decline: Multi-Ethnic Study of Atherosclerosis
Background
White matter (WM) microstructural degeneration and WM hyperintensities (WMH) are imaging markers of brain aging. Low bone mineral density (BMD) and brain aging co-occur, but longitudinal evidence linking skeletal health to WM injury and cognitive decline remains limited.
Purpose
To determine whether deep learning–derived thoracic vertebral BMD (vBMD) from noncontrast chest CT is associated with longitudinal changes in WM integrity, WMH burden, and cognitive decline.
Materials and Methods
This secondary analysis of a prospective study conducted from September 2016 to March 2024 included participants without clinically recognized cardiovascular disease from the Multi-Ethnic Study of Atherosclerosis. Participants underwent noncontrast chest CT, multimodal brain MRI (diffusion tensor imaging and fluid-attenuated inversion recovery), and cognitive testing. Thoracic vBMD was quantified at baseline using a validated deep learning algorithm. Linear mixed-effects models related baseline vBMD to longitudinal changes in WMH volume, WM fractional anisotropy, and cognition, adjusting for demographics, apolipoprotein E-ε4, cardiometabolic risk factors, lifestyle, and medications.
Results
This study included 715 participants (median age [IQR], 69 years [65–75 years]; 397 men and 318 women). Lower baseline vBMD was associated with faster decline in total WM fractional anisotropy (n = 405; β = −0.036 SD/year/0.1 g/cm3 vBMD decrease [95% CI: −0.065, −0.006]; nominal P = .02), although this did not survive false discovery rate correction (adjusted P = .07). Regionally, lower vBMD was associated with faster fractional anisotropy decline in the anterior limb of the internal capsule (β = −0.048 SD/year; adjusted P = .006) and faster WMH accumulation in the corpus callosum (n = 408; β = 12.8%/year; adjusted P = .04). Lower vBMD was also associated with faster decline in the global cognitive composite (n = 639; β = −0.025 SD/year; P = .002) and the Cognitive Abilities Screening Instrument (n = 675; β = −0.320/year; P < .001). Diabetes amplified associations with WMH progression (β = 4.99%; P = .03).
Conclusion
Lower vBMD from noncontrast chest CT was associated with modestly accelerated regional WM injury and faster cognitive decline, particularly among participants with diabetes, suggesting utility for detecting accelerated brain aging.
ClinicalTrials.gov: NCT00005487
