Resilience to AD pathology in Top Cognitive Performers.

Successful cognitive aging is often thought to result from resistance to the accumulation of pathology, resilience to the effects of pathological accumulation, or some combination of the two. While evidence for resilience has been found in typical aging populations, the oldest-old provide us with a unique window into the role of pathological accumulation in impacting cognition. Here, we aimed to assess group differences in measures of amyloid and tau across older age groups using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI age: 60-89) and The 90+ Study (age: 90-101). Additionally, using the ADNI dataset, we performed exploratory analyses of regional cingulate AV-45 SUVRs to assess if amyloid load in particular areas was associated with Top Cognitive Performance (TCP). Consistent with the literature, results showed no group differences in amyloid SUVRs both regionally and in the whole cortex. For tau with AV-1451, we also observed no differences in Braak composite SUVRs. Interestingly, these relationships persisted in the oldest-old. This indicates that Top Cognitive Performance throughout aging does not reflect resistance to amyloid and tau burden, but that other mechanisms may be associated with protection against amyloid and tau related neurodegeneration.

Alzheimer's disease detection using data fusion with a deep supervised encoder.

Alzheimer's disease (AD) is affecting a growing number of individuals. As a result, there is a pressing need for accurate and early diagnosis methods. This study aims to achieve this goal by developing an optimal data analysis strategy to enhance computational diagnosis. Although various modalities of AD diagnostic data are collected, past research on computational methods of AD diagnosis has mainly focused on using single-modal inputs. We hypothesize that integrating, or "fusing," various data modalities as inputs to prediction models could enhance diagnostic accuracy by offering a more comprehensive view of an individual's health profile. However, a potential challenge arises as this fusion of multiple modalities may result in significantly higher dimensional data. We hypothesize that employing suitable dimensionality reduction methods across heterogeneous modalities would not only help diagnosis models extract latent information but also enhance accuracy. Therefore, it is imperative to identify optimal strategies for both data fusion and dimensionality reduction. In this paper, we have conducted a comprehensive comparison of over 80 statistical machine learning methods, considering various classifiers, dimensionality reduction techniques, and data fusion strategies to assess our hypotheses. Specifically, we have explored three primary strategies: (1) Simple data fusion, which involves straightforward concatenation (fusion) of datasets before inputting them into a classifier; (2) Early data fusion, in which datasets are concatenated first, and then a dimensionality reduction technique is applied before feeding the resulting data into a classifier; and (3) Intermediate data fusion, in which dimensionality reduction methods are applied individually to each dataset before concatenating them to construct a classifier. For dimensionality reduction, we have explored several commonly-used techniques such as principal component analysis (PCA), autoencoder (AE), and LASSO. Additionally, we have implemented a new dimensionality-reduction method called the supervised encoder (SE), which involves slight modifications to standard deep neural networks. Our results show that SE substantially improves prediction accuracy compared to PCA, AE, and LASSO, especially in combination with intermediate fusion for multiclass diagnosis prediction.

Digital cognitive assessments as low-burden markers for predicting future cognitive decline and tau accumulation across the Alzheimer's spectrum.

Digital cognitive assessments, particularly those that can be done at home, present as low burden biomarkers for participants and patients alike, but their effectiveness in diagnosis of Alzheimer's or predicting its trajectory is still unclear. Here, we assessed what utility or added value these digital cognitive assessments provide for identifying those at high risk for cognitive decline. We analyzed >500 ADNI participants who underwent a brief digital cognitive assessment and Aß/tau PET scans, examining their ability to distinguish cognitive status and predict cognitive decline. Performance on the digital cognitive assessment were superior to both cortical Aß and entorhinal tau in detecting mild cognitive impairment and future cognitive decline, with mnemonic discrimination deficits emerging as the most critical measure for predicting decline and future tau accumulation. Digital assessments are effective in identifying at-risk individuals, supporting their utility as low-burden tools for early Alzheimer's detection and monitoring.

Cognitive modeling of the Mnemonic Similarity Task as a digital biomarker for Alzheimer's Disease.

AD related pathologies, such as beta-amyloid (Aß) and phosphorylated tau (pTau), are evident decades before any noticeable decline in memory occurs. Identifying individuals during this asymptomatic phase is crucial for timely intervention. The Mnemonic Similarity Task (MST), a modified recognition memory task, is especially relevant for early AD screening, as it assesses hippocampal integrity, a region affected (both directly and indirectly) early in the progression of the disease. Further, strong inferences on the underlying cognitive mechanisms that support performance on this task can be made using Bayesian cognitive modeling. We assessed whether analyzing MST performance using a cognitive model could detect subtle changes in cognitive function and AD biomarker status prior to overt cognitive decline. We analyzed MST data from >200 individuals (young, cognitively healthy older adults, and individuals with MCI), a subset of which also had existing CSF Aß and pTau data. Traditional performance scores and cognitive modeling using multinomial processing trees was applied to each participants MST data using Bayesian approaches. We assessed how well each could predict age group, memory ability, MCI status, Aß/pTau status using ROC analyses. Both approaches predicted age group membership equally, but cognitive modeling approaches exceeded traditional metrics in all other comparisons. This work establishes that cognitive modeling of the MST can detect individuals with AD prior to cognitive decline, making it a potentially useful tool for both screening and monitoring older adults during the asymptomatic phase of AD.

Age-Related Brain Atrophy and the Positive Effects of Behavioral Enrichment in Middle-Aged Beagles.

Aging dogs serve as a valuable preclinical model for Alzheimer's disease (AD) due to their natural age-related development of ß-amyloid (Aß) plaques, human-like metabolism, and large brains that are ideal for studying structural brain aging trajectories from serial neuroimaging. Here we examined the effects of chronic treatment with the calcineurin inhibitor (CNI) tacrolimus or the nuclear factor of activated T cells (NFAT)-inhibiting compound Q134R on age-related canine brain atrophy from a longitudinal study in middle-aged beagles (36 females, 7 males) undergoing behavioral enrichment. Annual MRI was analyzed using modern, automated techniques for region-of-interest-based and voxel-based volumetric assessments. We found that the frontal lobe showed accelerated atrophy with age, while the caudate nucleus remained relatively stable. Remarkably, the hippocampus increased in volume in all dogs. None of these changes were influenced by tacrolimus or Q134R treatment. Our results suggest that behavioral enrichment can prevent atrophy and increase the volume of the hippocampus but does not prevent aging-associated prefrontal cortex atrophy.

Cortical and Subcortical Mechanisms of Orthographic Word-form Learning.

We examined the initial stages of orthographic learning in real time as literate adults learned spellings for spoken pseudowords during fMRI scanning. Participants were required to learn and store orthographic word forms because the pseudoword spellings were not uniquely predictable from sound to letter mappings. With eight learning trials per word form, we observed changes in the brain's response as learning was taking place. Accuracy was evaluated during learning, immediately after scanning, and 1 week later. We found evidence of two distinct learning systems-hippocampal and neocortical-operating during orthographic learning, consistent with the predictions of dual systems theories of learning/memory such as the complementary learning systems framework [McClelland, J. L., McNaughton, B. L., & O'Reilly, R. C. Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory. Psychological Review, 102, 419-457, 1995]. The bilateral hippocampus and the visual word form area (VWFA) showed significant BOLD response changes over learning, with the former exhibiting a rising pattern and the latter exhibiting a falling pattern. Moreover, greater BOLD signal increase in the hippocampus was associated with better postscan recall. In addition, we identified two distinct bilateral brain networks that mirrored the rising and falling patterns of the hippocampus and VWFA. Functional connectivity analysis revealed that regions within each network were internally synchronized. These novel findings highlight, for the first time, the relevance of multiple learning systems in orthographic learning and provide a paradigm that can be used to address critical gaps in our understanding of the neural bases of orthographic learning in general and orthographic word-form learning specifically.

Improving clinical efficiency in screening for cognitive impairment due to Alzheimer's.

INTRODUCTION: To reduce demands on expert time and improve clinical efficiency, we developed a framework to evaluate whether inexpensive, accessible data could accurately classify Alzheimer's disease (AD) clinical diagnosis and predict the likelihood of progression. METHODS: We stratified relevant data into three tiers: obtainable at primary care (low-cost), mostly available at specialty visits (medium-cost), and research-only (high-cost). We trained several machine learning models, including a hierarchical model, an ensemble model, and a clustering model, to distinguish between diagnoses of cognitively unimpaired, mild cognitive impairment, and dementia due to AD. RESULTS: All models showed viable classification, but the hierarchical and ensemble models outperformed the conventional model. Classifier "error" was predictive of progression rates, and cluster membership identified subgroups with high and low risk of progression within 1.5 to 3 years. DISCUSSION: Accessible, inexpensive clinical data can be used to guide AD diagnosis and are predictive of current and future disease states. HIGHLIGHTS: Classification performance using cost-effective features was accurate and robustHierarchical classification outperformed conventional multinomial classificationClassification labels indicated significant changes in conversion risk at follow-upA clustering-classification method identified subgroups at high risk of decline.

Acute cycling exercise and hippocampal subfield function and microstructure in healthy older adults.

Aging is associated with deterioration in dentate gyrus (DG) and CA3, both crucial hippocampal subfields for age susceptible memory processes such as mnemonic discrimination (MD). Meanwhile, a single aerobic exercise session alters DG/CA3 function and neural activity in both rats and younger adults and can elicit short-term microstructural alterations in the hippocampus of older adults. However, our understanding of the effects of acute exercise on hippocampal subfield integrity via function and microstructure in older adults is limited. Thus, a within subject-design was employed to determine if 20-min of moderate to vigorous aerobic exercise alters bilateral hippocampal subfield function and microstructure using high-resolution functional magnetic resonance imaging (fMRI) during an MD task (n = 35) and high angular resolution multi-shell diffusion imaging (n = 31), in healthy older adults, compared to seated rest. Following the exercise condition, participants exhibited poorer MD performance, particularly when their perception of effort was higher. Exercise was also related to lower MD-related activity within the DG/CA3 but not CA1 subfield. Finally, after controlling for whole brain gray matter diffusion, exercise was associated with lower neurite density index (NDI) within the DG/CA3. However, exercise-related differences in DG/CA3 activity and NDI were not associated with differences in MD performance. Our results suggest moderate to vigorous aerobic exercise may temporarily inhibit MD performance, and suppress DG/CA3 MD-related activity and NDI, potentially through neuroinflammatory/glial processes. However, additional studies are needed to confirm whether these short-term changes in behavior and hippocampal subfield neurophysiology are beneficial and how they might relate to long-term exercise habits.

Meta-analysis and open-source database for in vivo brain Magnetic Resonance spectroscopy in health and disease.

Proton (1H) Magnetic Resonance Spectroscopy (MRS) is a non-invasive tool capable of quantifying brain metabolite concentrations in vivo. Prioritization of standardization and accessibility in the field has led to the development of universal pulse sequences, methodological consensus recommendations, and the development of open-source analysis software packages. One on-going challenge is methodological validation with ground-truth data. As ground-truths are rarely available for in vivo measurements, data simulations have become an important tool. The diverse literature of metabolite measurements has made it challenging to define ranges to be used within simulations. Especially for the development of deep learning and machine learning algorithms, simulations must be able to produce accurate spectra capturing all the nuances of in vivo data. Therefore, we sought to determine the physiological ranges and relaxation rates of brain metabolites which can be used both in data simulations and as reference estimates. Using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, we've identified relevant MRS research articles and created an open-source database containing methods, results, and other article information as a resource. Using this database, expectation values and ranges for metabolite concentrations and T2 relaxation times are established based upon a meta-analyses of healthy and diseased brains.

Assessments of dentate gyrus function: discoveries and debates.

There has been considerable speculation regarding the function of the dentate gyrus (DG) - a subregion of the mammalian hippocampus - in learning and memory. In this Perspective article, we compare leading theories of DG function. We note that these theories all critically rely on the generation of distinct patterns of activity in the region to signal differences between experiences and to reduce interference between memories. However, these theories are divided by the roles they attribute to the DG during learning and recall and by the contributions they ascribe to specific inputs or cell types within the DG. These differences influence the information that the DG is thought to impart to downstream structures. We work towards a holistic view of the role of DG in learning and memory by first developing three critical questions to foster a dialogue between the leading theories. We then evaluate the extent to which previous studies address our questions, highlight remaining areas of conflict, and suggest future experiments to bridge these theories.

Meta-analysis and Open-source Database for In Vivo Brain Magnetic Resonance Spectroscopy in Health and Disease.

Proton ( 1 H) Magnetic Resonance Spectroscopy (MRS) is a non-invasive tool capable of quantifying brain metabolite concentrations in vivo . Prioritization of standardization and accessibility in the field has led to the development of universal pulse sequences, methodological consensus recommendations, and the development of open-source analysis software packages. One on-going challenge is methodological validation with ground-truth data. As ground-truths are rarely available for in vivo measurements, data simulations have become an important tool. The diverse literature of metabolite measurements has made it challenging to define ranges to be used within simulations. Especially for the development of deep learning and machine learning algorithms, simulations must be able to produce accurate spectra capturing all the nuances of in vivo data. Therefore, we sought to determine the physiological ranges and relaxation rates of brain metabolites which can be used both in data simulations and as reference estimates. Using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, we've identified relevant MRS research articles and created an open-source database containing methods, results, and other article information as a resource. Using this database, expectation values and ranges for metabolite concentrations and T 2 relaxation times are established based upon a meta-analyses of healthy and diseased brains.

Application of a 1H Brain MRS Benchmark Dataset to Deep Learning for Out-of-Voxel Artifacts.

Neural networks are potentially valuable for many of the challenges associated with MRS data. The purpose of this manuscript is to describe the AGNOSTIC dataset, which contains 259,200 synthetic 1H MRS examples for training and testing neural networks. AGNOSTIC was created using 270 basis sets that were simulated across 18 field strengths and 15 echo times. The synthetic examples were produced to resemble in vivo brain data with combinations of metabolite, macromolecule, residual water signals, and noise. To demonstrate the utility, we apply AGNOSTIC to train two Convolutional Neural Networks (CNNs) to address out-of-voxel (OOV) echoes. A Detection Network was trained to identify the point-wise presence of OOV echoes, providing proof of concept for real-time detection. A Prediction Network was trained to reconstruct OOV echoes, allowing subtraction during post-processing. Complex OOV signals were mixed into 85% of synthetic examples to train two separate CNNs for the detection and prediction of OOV signals. AGNOSTIC is available through Dryad and all Python 3 code is available through GitHub. The Detection network was shown to perform well, identifying 95% of OOV echoes. Traditional modeling of these detected OOV signals was evaluated and may prove to be an effective method during linear-combination modeling. The Prediction Network greatly reduces OOV echoes within FIDs and achieved a median log10 normed-MSE of -1.79, an improvement of almost two orders of magnitude.

Electroacupuncture for the management of symptom clusters in cancer patients and survivors (EAST).

BACKGROUND: Neuropsychiatric symptoms, comprising cognitive impairment, fatigue, insomnia, depression, and anxiety, are prevalent and may co-occur during and after chemotherapy treatment for cancer. Electroacupuncture (EA), which involves mild electrical stimulation with acupuncture, holds great potential in addressing the management of individual symptoms. However, there is a lack of studies evaluating if EA can manage concurrent neuropsychiatric symptoms in cancer (i.e., symptom cluster). Hence, we designed a trial to evaluate the efficacy, safety, and feasibility of administering EA as an intervention to mitigate neuropsychiatric symptom clusters amongst cancer patients and survivors. METHODS: The EAST study is a randomized, sham-controlled, patient- and assessor-blinded clinical trial. Sixty-four cancer patients and survivors with complaints of one or more neuropsychiatric symptom(s) in the seven days prior to enrollment are recruited from the University of California Irvine (UCI) and Children's Hospital of Orange County (CHOC). Individuals with needle phobia, metastases, bleeding disorders, electronic implants, epilepsy, exposure to acupuncture in the three months prior to enrollment, and who are breastfeeding, pregnant, or planning to get pregnant during the duration of the study will be excluded. Screening for metal fragments and claustrophobia are performed prior to the optional neuroimaging procedures. Recruited patients will be randomized (1:1) in random blocks of four or six to receive either ten weekly verum EA (treatment arm, vEA) or weekly sham EA (control arm, sEA) treatment visits with a follow-up appointment four to twelve weeks after their last treatment visit. The treatment arm will receive EA at 13 acupuncture points (acupoints) chosen for their therapeutic effects, while the control arm receives minimal EA at 7 non-disease-related acupoints. Questionnaires and cognitive assessments are administered, and blood drawn to assess changes in symptom clusters and biomarkers, respectively. CONCLUSION: The EAST study can provide insight into the efficacy of EA, an integrative medicine modality, in the management of cancer symptom clusters in routine clinical practice. TRIAL REGISTRATION: This trial is registered with clinicaltrials.gov NCT05283577.

Modulation of amygdala activity for emotional faces due to botulinum toxin type A injections that prevent frowning.

According to the facial feedback hypothesis, when we see an angry or happy face, we contract or flex the relevant muscles to recreate the expression to assist in identifying and experiencing the emotion reflected. We investigated the facial feedback hypothesis by using botulinum toxin type A (onabotulinumtoxinA; onabotA) injections to induce temporary paralysis in the glabellar muscles (responsible for frowning) and measured functional brain activity during the processing of emotional faces. Ten females viewed pictures of happy and angry faces during two functional magnetic resonance imaging (fMRI) scan sessions: one prior (Pre) to onabotA and one following (Active) onabotA injections. We found Pre vs. Active onabotA modulation of activity in the amygdala for both happy and angry faces, as well as modulation of activity in the fusiform gyrus for happy faces. Consistent with our predictions, preventing frowning through inhibition of glabellar muscle contraction altered amygdala processing for emotional faces. The modulation of amygdala and fusiform gyrus activity following onabotA may reflect compensatory processes in a neuroanatomical circuit involved in emotional processing that is engaged when facial feedback is impaired. These data contribute to a growing literature suggesting that inhibition of glabellar muscle contraction alters neural activity for emotional processing.Clinical Trials.gov registration number: NCT03373162.

Optimizing the mnemonic similarity task for efficient, widespread use.

Introduction: The Mnemonic Similarity Task (MST) has become a popular test of memory and, in particular, of hippocampal function. It has been heavily used in research settings and is currently included as an alternate outcome measure on a number of clinical trials. However, as it typically requires ~15 min to administer and benefits substantially from an experienced test administrator to ensure the instructions are well-understood, its use in trials and in other settings is somewhat restricted. Several different variants of the MST are in common use that alter the task format (study-test vs. continuous) and the response prompt given to participants (old/similar/new vs. old/new). Methods: In eight online experiments, we sought to address three main goals: (1) To determine whether a robust version of the task could be created that could be conducted in half the traditional time; (2) To determine whether the test format or response prompt choice significantly impacted the MST's results; and (3) To determine how robust the MST is to repeat testing. In Experiments 1-7, participants received both the traditional and alternate forms of the MST to determine how well the alternate version captured the traditional task's performance. In Experiment 8, participants were given the MST four times over approximately 4 weeks. Results: In Experiments 1-7, we found that test format had no effect on the reliability of the MST, but that shifting to the two-choice response format significantly reduced its ability to reflect the traditional MST's score. We also found that the full running time could be cut it half or less without appreciable reduction in reliability. We confirmed the efficacy of this reduced task in older adults as well. Here, and in Experiment 8, we found that while there often are no effects of repeat-testing, small effects are possible, but appear limited to the initial testing session. Discussion: The optimized version of the task developed here (oMST) is freely available for web-based experiment delivery and provides an accurate estimate of the same memory ability as the classic MST in less than half the time.

Effects of acute aerobic exercise on mnemonic discrimination performance in older adults.

OBJECTIVES: Ample evidence suggests exercise is beneficial for hippocampal function. Furthermore, a single session of aerobic exercise provides immediate benefits to mnemonic discrimination performance, a highly hippocampal-specific memory process, in healthy younger adults. However, it is unknown if a single session of aerobic exercise alters mnemonic discrimination in older adults, who generally exhibit greater hippocampal deterioration and deficits in mnemonic discrimination performance. METHODS: We conducted a within subject acute exercise study in 30 cognitively healthy and physically active older adults who underwent baseline testing and then completed two experimental visits in which they performed a mnemonic discrimination task before and after either 30 min of cycling exercise or 30 min of seated rest. Linear mixed-effects analyses were conducted in which condition order and age were controlled, time (pre vs. post) and condition (exercise vs. rest) were modeled as fixed effects, and subject as a random effect. RESULTS: No significant time by condition interaction effect was found for object recognition (p = .254, η2=.01), while a significant reduction in interference was found for mnemonic discrimination performance following the exercise condition (p = .012, η2=.07). A post-intervention only analysis indicated that there was no difference between condition for object recognition (p = .186, η2=.06), but that participants had better mnemonic discrimination performance (p < .001, η2=.22) following the exercise. CONCLUSIONS: Our results suggest a single session of moderate-intensity aerobic exercise may reduce interference and elicit better mnemonic discrimination performance in healthy older adults, suggesting benefits for hippocampal-specific memory function.

Bayesian Modeling of the Mnemonic Similarity Task Using Multinomial Processing Trees.

The Mnemonic Similarity Task (MST: Stark et al., 2019) is a modified recognition memory task designed to place strong demand on pattern separation. The sensitivity and reliability of the MST make it an extremely valuable tool in clinical settings. We develop new cognitive models, based on the multinomial processing tree framework, for two versions of the MST. The models are implemented as generative probabilistic models and applied to behavioral data using Bayesian graphical modeling methods. We demonstrate how the combination of cognitive modeling and Bayesian methods allows for flexible and powerful inferences about performance on the MST. These demonstrations include latent-mixture extensions for identifying individual differences in decision strategies, and hierarchical extensions that measure fine-grained differences in the ability to detect lures. One key finding is that the availability of a "similar" response in the MST reduces individual differences in decision strategies and allows for more direct measurement of recognition memory.

Adaptive Design Optimization for a Mnemonic Similarity Task.

The Mnemonic Similarity Task (MST: Stark et al., 2019) is a modified recognition memory task designed to place strong demand on pattern separation. The sensitivity and reliability of the MST make it an extremely valuable tool in clinical settings, where it has been used to identify hippocampal dysfunction associated with healthy aging, dementia, schizophrenia, depression, and other disorders. As with any test used in a clinical setting, it is especially important for the MST to be administered as efficiently as possible. We apply adaptive design optimization methods (Lesmes et al., 2015; Myung et al., 2013) to optimize the presentation of test stimuli in accordance with previous responses. This optimization is based on a signal-detection model of an individual's memory capabilities and decision-making processes. We demonstrate that the adaptive design optimization approach generally reduces the number of test stimuli needed to provide these measures.

Sleep facilitates spatial memory but not navigation using the Minecraft Memory and Navigation task.

Sleep facilitates hippocampal-dependent memories, supporting the acquisition and maintenance of internal representation of spatial relations within an environment. In humans, however, findings have been mixed regarding sleep's contribution to spatial memory and navigation, which may be due to task designs or outcome measurements. We developed the Minecraft Memory and Navigation (MMN) task for the purpose of disentangling how spatial memory accuracy and navigation change over time, and to study sleep's independent contributions to each. In the MMN task, participants learned the locations of objects through free exploration of an open field computerized environment. At test, they were teleported to random positions around the environment and required to navigate to the remembered location of each object. In study 1, we developed and validated four unique MMN environments with the goal of equating baseline learning and immediate test performance. A total of 86 participants were administered the training phases and immediate test. Participants' baseline performance was equivalent across all four environments, supporting the use of the MMN task. In study 2, 29 participants were trained, tested immediately, and again 12 h later after a period of sleep or wake. We found that the metric accuracy of object locations, i.e., spatial memory, was maintained over a night of sleep, while after wake, metric accuracy declined. In contrast, spatial navigation improved over both sleep and wake delays. Our findings support the role of sleep in retaining the precise spatial relationships within a cognitive map; however, they do not support a specific role of sleep in navigation.

Using Advanced Diffusion-Weighted Imaging to Predict Cell Counts in Gray Matter: Potential and Pitfalls.

Recent advances in diffusion imaging have given it the potential to non-invasively detect explicit neurobiological properties, beyond what was previously possible with conventional structural imaging. However, there is very little known about what cytoarchitectural properties these metrics, especially those derived from newer multi-shell models like Neurite Orientation Dispersion and Density Imaging (NODDI) correspond to. While these diffusion metrics do not promise any inherent cell type specificity, different brain cells have varying morphologies, which could influence the diffusion signal in distinct ways. This relationship is currently not well-characterized. Understanding the possible cytoarchitectural signatures of diffusion measures could allow them to estimate important neurobiological properties like cell counts, potentially resulting in a powerful clinical diagnostic tool. Here, using advanced diffusion imaging (NODDI) in the mouse brain, we demonstrate that different regions have unique relationships between cell counts and diffusion metrics. We take advantage of this exclusivity to introduce a framework to predict cell counts of different types of cells from the diffusion metrics alone, in a region-specific manner. We also outline the challenges of reliably developing such a model and discuss the precautions the field must take when trying to tie together medical imaging modalities and histology.