Assessing the Seasonality of Lab Tests Among Patients with Alzheimer's Disease and Related Dementias in OneFlorida Data Trust.

About 1 in 9 older adults over 65 has Alzheimer's disease (AD), many of whom also have multiple other chronic conditions such as hypertension and diabetes, necessitating careful monitoring through laboratory tests. Understanding the patterns of laboratory tests in this population aids our understanding and management of these chronic conditions along with AD. In this study, we used an unimodal cosinor model to assess the seasonality of lab tests using electronic health record (EHR) data from 34,303 AD patients from the OneFlorida+ Clinical Research Consortium. We observed significant seasonal fluctuations-higher in winter in lab tests such as glucose, neutrophils per 100 white blood cells (WBC), and WBC. Notably, certain leukocyte types like eosinophils, lymphocytes, and monocytes are elevated during summer, likely reflecting seasonal respiratory diseases and allergens. Seasonality is more pronounced in older patients and varies by gender. Our findings suggest that recognizing these patterns and adjusting reference intervals for seasonality would allow healthcare providers to enhance diagnostic precision, tailor care, and potentially improve patient outcomes.

Protocol for EHR laboratory data preprocessing and seasonal adjustment using R and RStudio.

Seasonality in laboratory healthcare data is associated with possible under- and overdiagnoses of patients in the clinic. Here, we present a protocol to analyze electronic health record data for seasonality patterns and adjust existing reference intervals for these changes using R software. We describe steps for preprocessing population-wide patient laboratory data into a single dataset. We then detail steps for defining strata, normalizing to median, and fitting data to selected functions. For complete details on the use and execution of this protocol, please refer to Muse et al. (2023).1.

Seasonally adjusted laboratory reference intervals to improve the performance of machine learning models for classification of cardiovascular diseases.

BACKGROUND: Variation in laboratory healthcare data due to seasonal changes is a widely accepted phenomenon. Seasonal variation is generally not systematically accounted for in healthcare settings. This study applies a newly developed adjustment method for seasonal variation to analyze the effect seasonality has on machine learning model classification of diagnoses. METHODS: Machine learning methods were trained and tested on ~ 22 million unique records from ~ 575,000 unique patients admitted to Danish hospitals. Four machine learning models (adaBoost, decision tree, neural net, and random forest) classifying 35 diseases of the circulatory system (ICD-10 diagnosis codes, chapter IX) were run before and after seasonal adjustment of 23 laboratory reference intervals (RIs). The effect of the adjustment was benchmarked via its contribution to machine learning models trained using hyperparameter optimization and assessed quantitatively using performance metrics (AUROC and AUPRC). RESULTS: Seasonally adjusted RIs significantly improved cardiovascular disease classification in 24 of the 35 tested cases when using neural net models. Features with the highest average feature importance (via SHAP explainability) across all disease models were sex, C- reactive protein, and estimated glomerular filtration. Classification of diseases of the vessels, such as thrombotic diseases and other atherosclerotic diseases consistently improved after seasonal adjustment. CONCLUSIONS: As data volumes increase and data-driven methods are becoming more advanced, it is essential to improve data quality at the pre-processing level. This study presents a method that makes it feasible to introduce seasonally adjusted RIs into the clinical research space in any disease domain. Seasonally adjusted RIs generally improve diagnoses classification and thus, ought to be considered and adjusted for in clinical decision support methods.

Stratification of Kidney Transplant Recipients Into Five Subgroups Based on Temporal Disease Trajectories.

Background: Kidney transplantation is the treatment of choice for patients with end-stage renal disease. Considerable clinical research has focused on improving graft survival and an increasing number of kidney recipients die with a functioning graft. There is a need to improve patient survival and to better understand the individualized risk of comorbidities and complications. Here, we developed a method to stratify recipients into similar subgroups based on previous comorbidities and subsequently identify complications and for a subpopulation, laboratory test values associated with survival. Methods: First, we identified significant disease patterns based on all hospital diagnoses from the Danish National Patient Registry for 5752 kidney transplant recipients from 1977 to 2018. Using hierarchical clustering, these longitudinal patterns of diseases segregate into 3 main clusters of glomerulonephritis, hypertension, and diabetes. As some recipients are diagnosed with diseases from >1 cluster, recipients are further stratified into 5 more fine-grained trajectory subgroups for which survival, stratified complication patterns as well as laboratory test values are analyzed. Results: The study replicated known associations indicating that diabetes and low levels of albumin are associated with worse survival when investigating all recipients. However, stratification of recipients by trajectory subgroup showed additional associations. For recipients with glomerulonephritis, higher levels of basophils are significantly associated with poor survival, and these patients are more often diagnosed with bacterial infections. Additional associations were also found. Conclusions: This study demonstrates that disease trajectories can confirm known comorbidities and furthermore stratify kidney transplant recipients into clinical subgroups in which we can characterize stratified risk factors. We hope to motivate future studies to stratify recipients into more fine-grained, homogenous subgroups to better discover associations relevant for the individual patient and thereby enable more personalized disease-management and improve long-term outcomes and survival.

Correlation of Radiomics with Treatment Response in Liver Metastases.

RATIONALE AND OBJECTIVES: To assess differences in radiomics derived from semi-automatic segmentation of liver metastases for stable disease (SD), partial response (PR), and progressive disease (PD) based on RECIST1.1 and to assess if radiomics alone at baseline can predict response. MATERIALS AND METHODS: Our IRB-approved study included 203 women (mean age 54 ± 11 years) with metastatic liver disease from breast cancer. All patients underwent contrast abdomen-pelvis CT in the portal venous phase at two points: baseline (pre-treatment) and follow-up (between 3 and 12 months following treatment). Patients were subcategorized into three subgroups based on RECIST 1.1 criteria (Response Evaluation Criteria in Solid Tumors version 1.1): 66 with SD, 69 with PR, and 68 with PD on follow-up CT. The deidentified baseline and follow-up CT images were exported to the radiomics prototype. The prototype enabled semi-automatic segmentation of the target liver lesions for the extraction of first and high order radiomics. Statistical analyses with logistic regression and random forest classifiers were performed to differentiate SD from PD and PR. RESULTS: There was no significant difference between the radiomics on the baseline and follow-up CT images of patients with SD (area under the curve (AUC): 0.3). Random forest classifier differentiated patients with PR with an AUC of 0.845. The most relevant feature was the large dependence emphasis's high and low pass wavelet filter (derived gray level dependence matrix features). Random forest classifier differentiated PD with an AUC of 0.731, with the most relevant feature being the surface-to-volume ratio. There was no difference in radiomics among the three groups at baseline; therefore, a response could not be predicted. CONCLUSION: Radiomics of liver metastases with semi-automatic segmentation demonstrate differences between SD from PR and PD. SUMMARY STATEMENT: Semiautomatic segmentation and radiomics of metastatic liver disease demonstrate differences in SD from the PR and progressive metastatic on the baseline and follow-up CT. Despite substantial variations in the scanners, acquisition, and reconstruction parameters, radiomics had an AUC of 0.84-0.89 for differentiating stable hepatic metastases from decreasing and increasing metastatic disease.

Population-wide analysis of hospital laboratory tests to assess seasonal variation and temporal reference interval modification.

We identified mortality-, age-, and sex-associated differences in relation to reference intervals (RIs) for laboratory tests in population-wide data from nearly 2 million hospital patients in Denmark and comprising more than 300 million measurements. A low-parameter mathematical wave-based modification method was developed to adjust for dietary and environment influences during the year. The resulting mathematical fit allowed for improved association rates between re-classified abnormal laboratory tests, patient diagnoses, and mortality. The study highlights the need for seasonally modified RIs and presents an approach that has the potential to reduce over- and underdiagnosis, affecting both physician-patient interactions and electronic health record research as a whole.

Evaluation of an Artificial Intelligence Model for Detection of Pneumothorax and Tension Pneumothorax in Chest Radiographs.

Importance: Early detection of pneumothorax, most often via chest radiography, can help determine need for emergent clinical intervention. The ability to accurately detect and rapidly triage pneumothorax with an artificial intelligence (AI) model could assist with earlier identification and improve care. Objective: To compare the accuracy of an AI model vs consensus thoracic radiologist interpretations in detecting any pneumothorax (incorporating both nontension and tension pneumothorax) and tension pneumothorax. Design, Setting, and Participants: This diagnostic study was a retrospective standalone performance assessment using a data set of 1000 chest radiographs captured between June 1, 2015, and May 31, 2021. The radiographs were obtained from patients aged at least 18 years at 4 hospitals in the Mass General Brigham hospital network in the United States. Included radiographs were selected using 2 strategies from all chest radiography performed at the hospitals, including inpatient and outpatient. The first strategy identified consecutive radiographs with pneumothorax through a manual review of radiology reports, and the second strategy identified consecutive radiographs with tension pneumothorax using natural language processing. For both strategies, negative radiographs were selected by taking the next negative radiograph acquired from the same radiography machine as each positive radiograph. The final data set was an amalgamation of these processes. Each radiograph was interpreted independently by up to 3 radiologists to establish consensus ground-truth interpretations. Each radiograph was then interpreted by the AI model for the presence of pneumothorax and tension pneumothorax. This study was conducted between July and October 2021, with the primary analysis performed between October and November 2021. Main Outcomes and Measures: The primary end points were the areas under the receiver operating characteristic curves (AUCs) for the detection of pneumothorax and tension pneumothorax. The secondary end points were the sensitivities and specificities for the detection of pneumothorax and tension pneumothorax. Results: The final analysis included radiographs from 985 patients (mean [SD] age, 60.8 [19.0] years; 436 [44.3%] female patients), including 307 patients with nontension pneumothorax, 128 patients with tension pneumothorax, and 550 patients without pneumothorax. The AI model detected any pneumothorax with an AUC of 0.979 (95% CI, 0.970-0.987), sensitivity of 94.3% (95% CI, 92.0%-96.3%), and specificity of 92.0% (95% CI, 89.6%-94.2%) and tension pneumothorax with an AUC of 0.987 (95% CI, 0.980-0.992), sensitivity of 94.5% (95% CI, 90.6%-97.7%), and specificity of 95.3% (95% CI, 93.9%-96.6%). Conclusions and Relevance: These findings suggest that the assessed AI model accurately detected pneumothorax and tension pneumothorax in this chest radiograph data set. The model's use in the clinical workflow could lead to earlier identification and improved care for patients with pneumothorax.

Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency.

Importance: The efficient and accurate interpretation of radiologic images is paramount. Objective: To evaluate whether a deep learning-based artificial intelligence (AI) engine used concurrently can improve reader performance and efficiency in interpreting chest radiograph abnormalities. Design, Setting, and Participants: This multicenter cohort study was conducted from April to November 2021 and involved radiologists, including attending radiologists, thoracic radiology fellows, and residents, who independently participated in 2 observer performance test sessions. The sessions included a reading session with AI and a session without AI, in a randomized crossover manner with a 4-week washout period in between. The AI produced a heat map and the image-level probability of the presence of the referrable lesion. The data used were collected at 2 quaternary academic hospitals in Boston, Massachusetts: Beth Israel Deaconess Medical Center (The Medical Information Mart for Intensive Care Chest X-Ray [MIMIC-CXR]) and Massachusetts General Hospital (MGH). Main Outcomes and Measures: The ground truths for the labels were created via consensual reading by 2 thoracic radiologists. Each reader documented their findings in a customized report template, in which the 4 target chest radiograph findings and the reader confidence of the presence of each finding was recorded. The time taken for reporting each chest radiograph was also recorded. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were calculated for each target finding. Results: A total of 6 radiologists (2 attending radiologists, 2 thoracic radiology fellows, and 2 residents) participated in the study. The study involved a total of 497 frontal chest radiographs-247 from the MIMIC-CXR data set (demographic data for patients were not available) and 250 chest radiographs from MGH (mean [SD] age, 63 [16] years; 133 men [53.2%])-from adult patients with and without 4 target findings (pneumonia, nodule, pneumothorax, and pleural effusion). The target findings were found in 351 of 497 chest radiographs. The AI was associated with higher sensitivity for all findings compared with the readers (nodule, 0.816 [95% CI, 0.732-0.882] vs 0.567 [95% CI, 0.524-0.611]; pneumonia, 0.887 [95% CI, 0.834-0.928] vs 0.673 [95% CI, 0.632-0.714]; pleural effusion, 0.872 [95% CI, 0.808-0.921] vs 0.889 [95% CI, 0.862-0.917]; pneumothorax, 0.988 [95% CI, 0.932-1.000] vs 0.792 [95% CI, 0.756-0.827]). AI-aided interpretation was associated with significantly improved reader sensitivities for all target findings, without negative impacts on the specificity. Overall, the AUROCs of readers improved for all 4 target findings, with significant improvements in detection of pneumothorax and nodule. The reporting time with AI was 10% lower than without AI (40.8 vs 36.9 seconds; difference, 3.9 seconds; 95% CI, 2.9-5.2 seconds; P < .001). Conclusions and Relevance: These findings suggest that AI-aided interpretation was associated with improved reader performance and efficiency for identifying major thoracic findings on a chest radiograph.

Thoracic Imaging Manifestations of Treated Lymphomas: Response Evaluation, Posttherapeutic Sequelae, and Complications.

Lymphoma is the most common hematologic malignancy comprising a diverse group of neoplasms arising from multiple blood cell lineages. Any structure of the thorax may be involved at any stage of disease. Imaging has a central role in the initial staging, response assessment, and surveillance of lymphoma, and updated standardized assessment criteria are available to assist with imaging interpretation and reporting. Radiologists should be aware of the modern approaches to lymphoma treatment, the role of imaging in posttherapeutic surveillance, and manifestations of therapy-related complications.

Quantitative Evaluation of Dendritic Nanoparticles in Mice: Biodistribution Dynamics and Downstream Tumor Efficacy Outcomes.

A physiologically based pharmacokinetic model was developed to describe the tissue distribution kinetics of a dendritic nanoparticle and its conjugated active pharmaceutical ingredient (API) in plasma, liver, spleen, and tumors. Tumor growth data from MV-4-11 tumor-bearing mice were incorporated to investigate the exposure/efficacy relationship. The nanoparticle demonstrated improved antitumor activity compared to the conventional API formulation, owing to the extended released API concentrations at the site of action. Model simulations further enabled the identification of critical parameters that influence API exposure in tumors and downstream efficacy outcomes upon nanoparticle administration. The model was utilized to explore a range of dosing schedules and their effect on tumor growth kinetics, demonstrating the improved antitumor activity of nanoparticles with less frequent dosing compared to the same dose of naked APIs in conventional formulations.

An Artificial Intelligence-Based Chest X-ray Model on Human Nodule Detection Accuracy From a Multicenter Study.

Importance: Most early lung cancers present as pulmonary nodules on imaging, but these can be easily missed on chest radiographs. Objective: To assess if a novel artificial intelligence (AI) algorithm can help detect pulmonary nodules on radiographs at different levels of detection difficulty. Design, Setting, and Participants: This diagnostic study included 100 posteroanterior chest radiograph images taken between 2000 and 2010 of adult patients from an ambulatory health care center in Germany and a lung image database in the US. Included images were selected to represent nodules with different levels of detection difficulties (from easy to difficult), and comprised both normal and nonnormal control. Exposures: All images were processed with a novel AI algorithm, the AI Rad Companion Chest X-ray. Two thoracic radiologists established the ground truth and 9 test radiologists from Germany and the US independently reviewed all images in 2 sessions (unaided and AI-aided mode) with at least a 1-month washout period. Main Outcomes and Measures: Each test radiologist recorded the presence of 5 findings (pulmonary nodules, atelectasis, consolidation, pneumothorax, and pleural effusion) and their level of confidence for detecting the individual finding on a scale of 1 to 10 (1 representing lowest confidence; 10, highest confidence). The analyzed metrics for nodules included sensitivity, specificity, accuracy, and receiver operating characteristics curve area under the curve (AUC). Results: Images from 100 patients were included, with a mean (SD) age of 55 (20) years and including 64 men and 36 women. Mean detection accuracy across the 9 radiologists improved by 6.4% (95% CI, 2.3% to 10.6%) with AI-aided interpretation compared with unaided interpretation. Partial AUCs within the effective interval range of 0 to 0.2 false positive rate improved by 5.6% (95% CI, -1.4% to 12.0%) with AI-aided interpretation. Junior radiologists saw greater improvement in sensitivity for nodule detection with AI-aided interpretation as compared with their senior counterparts (12%; 95% CI, 4% to 19% vs 9%; 95% CI, 1% to 17%) while senior radiologists experienced similar improvement in specificity (4%; 95% CI, -2% to 9%) as compared with junior radiologists (4%; 95% CI, -3% to 5%). Conclusions and Relevance: In this diagnostic study, an AI algorithm was associated with improved detection of pulmonary nodules on chest radiographs compared with unaided interpretation for different levels of detection difficulty and for readers with different experience.

High fat diet worsens Alzheimer's disease-related behavioral abnormalities and neuropathology in APP/PS1 mice, but not by synergistically decreasing cerebral blood flow.

Obesity is linked to increased risk for and severity of Alzheimer's disease (AD). Cerebral blood flow (CBF) reductions are an early feature of AD and are also linked to obesity. We recently showed that non-flowing capillaries, caused by adhered neutrophils, contribute to CBF reduction in mouse models of AD. Because obesity could exacerbate the vascular inflammation likely underlying this neutrophil adhesion, we tested links between obesity and AD by feeding APP/PS1 mice a high fat diet (Hfd) and evaluating behavioral, physiological, and pathological changes. We found trends toward poorer memory performance in APP/PS1 mice fed a Hfd, impaired social interactions with either APP/PS1 genotype or a Hfd, and synergistic impairment of sensory-motor function in APP/PS1 mice fed a Hfd. The Hfd led to increases in amyloid-beta monomers and plaques in APP/PS1 mice, as well as increased brain inflammation. These results agree with previous reports showing obesity exacerbates AD-related pathology and symptoms in mice. We used a crowd-sourced, citizen science approach to analyze imaging data to determine the impact of the APP/PS1 genotype and a Hfd on capillary stalling and CBF. Surprisingly, we did not see an increase in the number of non-flowing capillaries or a worsening of the CBF deficit in APP/PS1 mice fed a Hfd as compared to controls, suggesting that capillary stalling is not a mechanistic link between a Hfd and increased severity of AD in mice. Reducing capillary stalling by blocking neutrophil adhesion improved CBF and short-term memory function in APP/PS1 mice, even when fed a Hfd.

Image Quality and Lesion Detection on Deep Learning Reconstruction and Iterative Reconstruction of Submillisievert Chest and Abdominal CT.

OBJECTIVE. The objective of this study was to compare image quality and clinically significant lesion detection on deep learning reconstruction (DLR) and iterative reconstruction (IR) images of submillisievert chest and abdominopelvic CT. MATERIALS AND METHODS. Our prospective multiinstitutional study included 59 adult patients (33 women, 26 men; mean age ± SD, 65 ± 12 years old; mean body mass index [weight in kilograms divided by the square of height in meters] = 27 ± 5) who underwent routine chest (n = 22; 16 women, six men) and abdominopelvic (n = 37; 17 women, 20 men) CT on a 640-MDCT scanner (Aquilion ONE, Canon Medical Systems). All patients gave written informed consent for the acquisition of low-dose (LD) CT (LDCT) after a clinically indicated standard-dose (SD) CT (SDCT). The SDCT series (120 kVp, 164-644 mA) were reconstructed with interactive reconstruction (IR) (adaptive iterative dose reduction [AIDR] 3D, Canon Medical Systems), and the LDCT (100 kVp, 120 kVp; 30-50 mA) were reconstructed with filtered back-projection (FBP), IR (AIDR 3D and forward-projected model-based iterative reconstruction solution [FIRST], Canon Medical Systems), and deep learning reconstruction (DLR) (Advanced Intelligent Clear-IQ Engine [AiCE], Canon Medical Systems). Four subspecialty-trained radiologists first read all LD image sets and then compared them side-by-side with SD AIDR 3D images in an independent, randomized, and blinded fashion. Subspecialty radiologists assessed image quality of LDCT images on a 3-point scale (1 = unacceptable, 2 = suboptimal, 3 = optimal). Descriptive statistics were obtained, and the Wilcoxon sign rank test was performed. RESULTS. Mean volume CT dose index and dose-length product for LDCT (2.1 ± 0.8 mGy, 49 ± 13mGy·cm) were lower than those for SDCT (13 ± 4.4 mGy, 567 ± 249 mGy·cm) (p < 0.0001). All 31 clinically significant abdominal lesions were seen on SD AIDR 3D and LD DLR images. Twenty-five, 18, and seven lesions were detected on LD AIDR 3D, LD FIRST, and LD FBP images, respectively. All 39 pulmonary nodules detected on SD AIDR 3D images were also noted on LD DLR images. LD DLR images were deemed acceptable for interpretation in 97% (35/37) of abdominal and 95-100% (21-22/22) of chest LDCT studies (p = 0.2-0.99). The LD FIRST, LD AIDR 3D, and LD FBP images had inferior image quality compared with SD AIDR 3D images (p < 0.0001). CONCLUSION. At submillisievert chest and abdominopelvic CT doses, DLR enables image quality and lesion detection superior to commercial IR and FBP images.

Non-Diagnostic CT-Guided Percutaneous Needle Biopsy of the Lung: Predictive Factors and Final Diagnoses.

OBJECTIVE: To investigate the predictive factors for a non-diagnostic result and the final diagnosis of pulmonary lesions with an initial non-diagnostic result on CT-guided percutaneous transthoracic needle biopsy. MATERIALS AND METHODS: All percutaneous transthoracic needle biopsies performed over a 4-year period were retrospectively reviewed. The initial pathological results were classified into three categories-malignant, benign, and non-diagnostic. A non-diagnostic result was defined when no malignant cells were seen and a specific benign diagnosis could not be made. The demographic data of patients, lesions' characteristics, technique, complications, initial pathological results, and final diagnosis were reviewed. Statistical analysis was performed using binary logistic regression. RESULTS: Of 894 biopsies in 861 patients (male:female, 398:463; mean age 67, range 18-92 years), 690 (77.2%) were positive for malignancy, 55 (6.2%) were specific benign, and 149 (16.7%) were non-diagnostic. Of the 149 non-diagnostic biopsies, excluding 27 cases in which the final diagnosis could not be confirmed, 36% revealed malignant lesions and 64% revealed benign lesions. Predictive factors for a non-diagnostic biopsy included the size ≤ 15 mm, needle tract traversing emphysematous lung parenchyma, introducer needle outside the lesion, procedure time > 60 minutes, and presence of alveolar hemorrhage. Non-diagnostic biopsies with a history of malignancy or atypical cells on pathology were more likely to be malignant (p = 0.043 and p = 0.001). CONCLUSION: The predictive factors for a non-diagnostic biopsy were lesion size ≤ 15 mm, needle tract traversing emphysema, introducer needle outside the lesion, procedure time > 60 minutes, and presence of alveolar hemorrhage. Thirty-six percent of the non-diagnostic biopsies yielded a malignant diagnosis. In cases with a history of malignancy or the presence of atypical cells in the biopsy sample, a repeat biopsy or surgical intervention should be considered.

On the potential of in vitro organ-chip models to define temporal pharmacokinetic-pharmacodynamic relationships.

Functional human-on-a-chip systems hold great promise to enable quantitative translation to in vivo outcomes. Here, we explored this concept using a pumpless heart only and heart:liver system to evaluate the temporal pharmacokinetic/pharmacodynamic (PKPD) relationship for terfenadine. There was a time dependent drug-induced increase in field potential duration in the cardiac compartment in response to terfenadine and that response was modulated using a metabolically competent liver module that converted terfenadine to fexofenadine. Using this data, a mathematical model was developed to predict the effect of terfenadine in preclinical species. Developing confidence that microphysiological models could have a transformative effect on drug discovery, we also tested a previously discovered proprietary AstraZeneca small molecule and correctly determined the cardiotoxic response to its metabolite in the heart:liver system. Overall our findings serve as a guiding principle to future investigations of temporal concentration response relationships in these innovative in vitro models, especially, if validated across multiple time frames, with additional pharmacological mechanisms and molecules representing a broad chemical diversity.

Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models.

The health and function of tissue rely on its vasculature network to provide reliable blood perfusion. Volumetric imaging approaches, such as multiphoton microscopy, are able to generate detailed 3D images of blood vessels that could contribute to our understanding of the role of vascular structure in normal physiology and in disease mechanisms. The segmentation of vessels, a core image analysis problem, is a bottleneck that has prevented the systematic comparison of 3D vascular architecture across experimental populations. We explored the use of convolutional neural networks to segment 3D vessels within volumetric in vivo images acquired by multiphoton microscopy. We evaluated different network architectures and machine learning techniques in the context of this segmentation problem. We show that our optimized convolutional neural network architecture with a customized loss function, which we call DeepVess, yielded a segmentation accuracy that was better than state-of-the-art methods, while also being orders of magnitude faster than the manual annotation. To explore the effects of aging and Alzheimer's disease on capillaries, we applied DeepVess to 3D images of cortical blood vessels in young and old mouse models of Alzheimer's disease and wild type littermates. We found little difference in the distribution of capillary diameter or tortuosity between these groups, but did note a decrease in the number of longer capillary segments (>75µm) in aged animals as compared to young, in both wild type and Alzheimer's disease mouse models.

Neutrophil adhesion in brain capillaries reduces cortical blood flow and impairs memory function in Alzheimer's disease mouse models.

Cerebral blood flow (CBF) reductions in Alzheimer's disease patients and related mouse models have been recognized for decades, but the underlying mechanisms and resulting consequences for Alzheimer's disease pathogenesis remain poorly understood. In APP/PS1 and 5xFAD mice we found that an increased number of cortical capillaries had stalled blood flow as compared to in wild-type animals, largely due to neutrophils that had adhered in capillary segments and blocked blood flow. Administration of antibodies against the neutrophil marker Ly6G reduced the number of stalled capillaries, leading to both an immediate increase in CBF and rapidly improved performance in spatial and working memory tasks. This study identified a previously uncharacterized cellular mechanism that explains the majority of the CBF reduction seen in two mouse models of Alzheimer's disease and demonstrated that improving CBF rapidly enhanced short-term memory function. Restoring cerebral perfusion by preventing neutrophil adhesion may provide a strategy for improving cognition in Alzheimer's disease patients.

Deep learning in chest radiography: Detection of findings and presence of change.

BACKGROUND: Deep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs. METHODS AND FINDINGS: We processed 874 de-identified frontal CXR from 724 adult patients (> 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis. RESULTS: About 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2-0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837-0.929 and 0.693-0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities. CONCLUSIONS: DL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings.