Search

Machine learning has been increasingly applied to neuroimaging data to predict age, deriving a personalized biomarker with potential clinical applications. The scientific and clinical value of these models depends on their applicability to independently acquired scans from diverse sources. Accordingly, we evaluated the generalizability of two brain age models that were trained across the lifespan by applying them to three distinct early‐life samples with participants aged 8–22 years. These models were chosen based on the size and diversity of their training data, but they also differed greatly in their processing methods and predictive algorithms. Specifically, one brain age model was built by applying gradient tree boosting (GTB) to extracted features of cortical thickness, surface area, and brain volume. The other model applied a 2D convolutional neural network (DBN) to minimally preprocessed slices of T1‐weighted scans. Additional model variants were created to understand how generalizability changed when each model was trained with data that became more similar to the test samples in terms of age and acquisition protocols. Our results illustrated numerous trade‐offs. The GTB predictions were relatively more accurate overall and yielded more reliable predictions when applied to lower quality scans. In contrast, the DBN displayed the most utility in detecting associations between brain age gaps and cognitive functioning. Broadly speaking, the largest limitations affecting generalizability were acquisition protocol differences and biased brain age estimates. If such confounds could eventually be removed without post‐hoc corrections, brain age predictions may have greater utility as personalized biomarkers of healthy aging. [ABSTRACT FROM AUTHOR]

Background: In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability. Purpose: To develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction. Study Type: Retrospective. Population: Eight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites. Field Strength/Sequence: Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T. Assessment: StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data. Statistical Tests: Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model. Results: Our results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization. Data Conclusion: While further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization. [ABSTRACT FROM AUTHOR]

Heterogeneity of brain diseases is a challenge for precision diagnosis/prognosis. We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a semi-supervised deep-clustering method, which examines neuroanatomical heterogeneity contrasted against normal brain structure, to identify disease subtypes through neuroimaging signatures. When applied to regional volumes derived from T1-weighted MRI (two studies; 2,832 participants; 8,146 scans) including cognitively normal individuals and those with cognitive impairment and dementia, Smile-GAN identified four patterns or axes of neurodegeneration. Applying this framework to longitudinal data revealed two distinct progression pathways. Measures of expression of these patterns predicted the pathway and rate of future neurodegeneration. Pattern expression offered complementary performance to amyloid/tau in predicting clinical progression. These deep-learning derived biomarkers offer potential for precision diagnostics and targeted clinical trial recruitment. Alzheimer's disease is heterogeneous in its neuroimaging and clinical phenotypes. Here the authors present a semi-supervised deep learning method, Smile-GAN, to show four neurodegenerative patterns and two progression pathways providing prognostic and clinical information. [ABSTRACT FROM AUTHOR]

Background: As β‐amyloid (Aβ) targeted clinical trials have had questionable benefit in treating patients with early symptomatic Alzheimer's disease, treatment would presumably be most effective if administered during the disease's preclinical phase. PET scans, while highly sensitive to AD pathology, are less practical for screening a large, cognitively normal population for evidence of preclinical AD. Recruitment methods that produce an Aβ enriched sample before PET data collection would decrease participant burden and potentially lower costs. Here, we develop a simple predictive model using subject demographics, structural MRI, and APOE4 status. Using the model's estimates of one's probability of Aβ positivity, we significantly increase the proportion of Aβ+ subjects in a cognitively normal sample. Method: Data from 875 participants from the Baltimore Longitudinal Study of Aging, Penn Memory Center and the Alzheimer's Disease Neuroimaging Initiative database were separated into a discovery set including AD, MCI, and cognitively normal participants (n = 673) and a cognitively normal replication set (n = 202). Aβ prediction performance of a logistic regression model was compared across multiple predictor sets. Regression‐based probability values were used to threshold the data, i.e., participants whose values fell below a cutoff were excluded from the thresholded sample. The proportion of Aβ+ individuals between the restricted and complete samples was compared across multiple cutoffs. Result: Applying a probability cutoff of 0.4 yielded samples with significantly higher proportions of Aβ+ subjects in 3 of the 5 tested models (Table 1). The Lesions model achieved the highest sample enrichment; 40.54% of the thresholded sample were Aβ+, significantly higher than the base rate of 28.22%, χ2 (1) = 8.32, p =.004 (Figure 1). However, there were no significant differences between the enriched sample produced by the Lesions model and those produced by the other significant models, indicating sample enrichment is possible even with different predictors. Conclusion: Aβ+ probability metrics produced by predictive models provide a novel method of sample enrichment and can be used as an individualized measure of Aβ classification certainty. Fewer PET scans will be necessary to obtain a sufficient Aβ+ sample, reducing burden on participants and researchers and potentially lowering costs. [ABSTRACT FROM AUTHOR]

Availability of large and diverse medical datasets is often challenged by privacy and data sharing restrictions. For successful application of machine learning techniques for disease diagnosis, prognosis, and precision medicine, large amounts of data are necessary for model building and optimization. To help overcome such limitations in the context of brain MRI, we present GenMIND: a collection of generative models of normative regional volumetric features derived from structural brain imaging. GenMIND models are trained on real brain imaging regional volumetric measures from the iSTAGING consortium, which encompasses over 40,000 MRI scans across 13 studies, incorporating covariates such as age, sex, and race. Leveraging GenMIND, we produce and offer 18,000 synthetic samples spanning the adult lifespan (ages 22-90 years), alongside the model's capability to generate unlimited data. Experimental results indicate that samples generated from GenMIND agree with the distributions obtained from real data. Most importantly, the generated normative data significantly enhance the accuracy of downstream machine learning models on tasks such as disease classification. Data and models are available at: https://huggingface.co/spaces/rongguangw/GenMIND., Competing Interests: Competing interests The authors declare no competing interests.