Parasagittal dural space hypertrophy and amyloid-β deposition in Alzheimer's disease

A Review of Machine Learning Approaches for Brain Positron Emission Tomography Data Analysis

Positron emission tomography (PET) imaging has moved forward the development of medical diagnostics and research across various domains, including cardiology, neurology, infection detection, and oncology. The integration of machine learning (ML) algorithms into PET data analysis has further enhanced their capabilities of including disease diagnosis and classification, image segmentation, and quantitative analysis. ML algorithms empower researchers and clinicians to extract valuable insights from complex big PET datasets, which enabling automated pattern recognition, predictive health outcome modeling, and more efficient data analysis. This review explains the basic knowledge of PET imaging, statistical methods for PET image analysis, and challenges of PET data analysis. We also discussed the improvement of analysis capabilities by combining PET data with machine learning algorithms and the application of this combination in various aspects of PET image research. This review also highlights current trends and future directions in PET imaging, emphasizing the driving and critical role of machine learning and big PET image data analytics in improving diagnostic accuracy and personalized medical approaches. Integration between PET imaging will shape the future of medical diagnosis and research.

Deep learning segmentation of peri-sinus structures from structural magnetic resonance imaging: validation and normative ranges across the adult lifespan

BACKGROUND

Peri-sinus structures such as arachnoid granulations (AG) and the parasagittal dural (PSD) space have gained much recent attention as sites of cerebral spinal fluid (CSF) egress and neuroimmune surveillance. Neurofluid circulation dysfunction may manifest as morphological changes in these structures, however, automated quantification of these structures is not possible and rather characterization often requires exogenous contrast agents and manual delineation.

METHODS

We propose a deep learning architecture to automatically delineate the peri-sinus space (e.g., PSD and intravenous AG structures) using two cascaded 3D fully convolutional neural networks applied to submillimeter 3D T2-weighted non-contrasted MRI images, which can be routinely acquired on all major MRI scanner vendors. The method was evaluated through comparison with gold-standard manual tracing from a neuroradiologist (n = 80; age range = 11-83 years) and subsequently applied in healthy participants (n = 1,872; age range = 5-100 years), using data from the Human Connectome Project, to provide exemplar metrics across the lifespan. Dice-Sørensen and a generalized linear model was used to assess PSD and AG changes across the human lifespan using quadratic restricted splines, incorporating age and sex as covariates.

RESULTS

Findings demonstrate that the PSD and AG volumes can be segmented using T2-weighted MRI with a Dice-Sørensen coefficient and accuracy of 80.7 and 74.6, respectively. Across the lifespan, we observed that total PSD volume increases with age with a linear interaction of gender and age equal to 0.9 cm3 per year (p < 0.001). Similar trends were observed in the frontal and parietal, but not occipital, PSD. An increase in AG volume was observed in the third to sixth decades of life, with a linear effect of age equal to 0.64 mm3 per year (p < 0.001) for total AG volume and 0.54 mm3 (p < 0.001) for maximum AG volume.

CONCLUSIONS

A tool that can be applied to quantify PSD and AG volumes from commonly acquired T2-weighted MRI scans is reported and exemplar volumetric ranges of these structures are provided, which should provide an exemplar for studies of neurofluid circulation dysfunction. Software and training data are made freely available online ( https://github.com/hettk/spesis ).

Cerebral microhemorrhages in children with congenital heart disease: Prevalence, risk factors, and impact on neurodevelopmental outcomes

Background

Infants with complex congenital heart disease (CHD) require life-saving corrective/palliative heart surgery in the first weeks of life. These infants are at risk for brain injury and poor neurodevelopmental outcomes. Cerebral microhemorrhages (CMH) are frequently seen after neonatal bypass heart surgery, but it remains unknown if CMH are a benign finding or constitute injury. Herein, we investigate the risk factors for developing CMH and their clinical significance.

Methods

192 infants with CHD undergoing corrective cardiac surgery with cardiopulmonary bypass (CPB) at a single institution were prospectively evaluated with pre-(n = 183) and/or postoperative (n = 162) brain magnetic resonance imaging (MRI). CMH severity was scored based on total number of microhemorrhages. Antenatal, perioperative, and postoperative candidate risk factors for CMH and neurodevelopmental (ND) outcomes were analyzed. Eighteen-month neurodevelopmental outcomes were assessed using the Bayley-III Scales of Infants and Toddler Development in a subset of patients (n = 82). Linear regression was used to analyze associations between risk factors or ND outcomes and presence/number of CMH.

Results

The most common CHD subtypes were hypoplastic left heart syndrome (HLHS) (37%) and transposition of the great arteries (TGA) (33%). Forty-two infants (23%) had CMH present on MRI before surgery and 137 infants (85%) post-surgery. No parameters evaluated were significant risk factors for preoperative CMH. In multivariate analysis, cardiopulmonary bypass (CPB) duration (p < 0.0001), use of extracorporeal membrane oxygenation (ECMO) support (p < 0.0005), postoperative seizure(s) (p < 0.03), and lower birth weight (p < 0.03) were associated with new or worsened CMH postoperatively. Higher CMH number was associated with lower scores on motor (p < 0.03) testing at 18 months.

Conclusion

CMH is a common imaging finding in infants with CHD with increased prevalence and severity after CPB and adverse impact on neurodevelopmental outcomes starting at a young age. Longer duration of CPB and need for postoperative ECMO were the most significant risk factors for developing CMH. However, presence of CMH on preoperative scans indicates non-surgical risk factors that are yet to be identified. Neuroprotective strategies to mitigate risk factors for CMH may improve neurodevelopmental outcomes in this vulnerable population.