Protocol and rationale of the Australian multicentre registry for serial cardiac computed tomography angiography (ARISTOCRAT): a prospective observational study of the natural history of pericoronary adipose tissue attenuation and radiomics.

Background: Vascular inflammation plays a crucial role in the development of atherosclerosis and atherosclerotic plaque rupture resulting in acute coronary syndrome (ACS). Pericoronary adipose tissue (PCAT) attenuation quantified from routine coronary computed tomography angiography (CCTA) has emerged as a promising non-invasive imaging biomarker of coronary inflammation. However, a detailed understanding of the natural history of PCAT attenuation is required before it can be used as a surrogate endpoint in trials of novel therapies targeting coronary inflammation. This article aims to explore the natural history of PCAT attenuation and its association with changes in plaque characteristics. Methods: The Australian natuRal hISTOry of periCoronary adipose tissue attenuation, RAdiomics and plaque by computed Tomographic angiography (ARISTOCRAT) registry is a multi-centre observational registry enrolling patients undergoing clinically indicated serial CCTA in 9 centres across Australia. CCTA scan parameters will be matched across serial scans. Quantitative analysis of plaque and PCAT will be performed using semiautomated software. Discussion: The primary endpoint is to explore temporal changes in patient-level and lesion-level PCAT attenuation by CCTA and their associations with changes in plaque characteristics. Secondary endpoints include evaluating: (I) impact of statin therapy on PCAT attenuation and plaque characteristics; and (II) changes in PCAT attenuation and plaque characteristics in specific subgroups according to sex and risk factors. ARISTOCRAT will further our understanding of the natural history of PCAT attenuation and its association with changes in plaque characteristics. Trial Registration: This study has been prospectively registered with the Australia and New Zealand Clinical Trials Registry (ACTRN12621001018808).

Sensory encoding and memory in the mushroom body: signals, noise, and variability.

To survive in changing environments, animals need to learn to associate specific sensory stimuli with positive or negative valence. How do they form stimulus-specific memories to distinguish between positively/negatively associated stimuli and other irrelevant stimuli? Solving this task is one of the functions of the mushroom body, the associative memory center in insect brains. Here we summarize recent work on sensory encoding and memory in the Drosophila mushroom body, highlighting general principles such as pattern separation, sparse coding, noise and variability, coincidence detection, and spatially localized neuromodulation, and placing the mushroom body in comparative perspective with mammalian memory systems.

Ultrasensitive quantification of PD-L1+ extracellular vesicles in melanoma patient plasma using a parallelized high throughput droplet digital assay.

The expression of programmed death-ligand 1 (PD-L1) on extracellular vesicles (EVs) is an emerging biomarker for cancer, and has gained particular interest for its role mediating immunotherapy. However, precise quantification of PD-L1+ EVs in clinical samples remains challenging due to their sparse concentration and the enormity of the number of background EVs in human plasma, limiting applicability of conventional approaches. In this study, we develop a high-throughput droplet-based extracellular vesicle analysis (DEVA) assay for ultrasensitive quantification of EVs in plasma that are dual positive for both PD-L1 and tetraspanin (CD81) known to be expressed on EVs. We achieve a performance that significantly surpasses conventional approaches, demonstrating 360× enhancement in the limit of detection (LOD) and a 750× improvement in the limit of quantitation (LOQ) compared to conventional plate enzyme-linked immunoassay (ELISA). Underlying this performance is DEVA's high throughput analysis of individual EVs one at a time and the high specificity to targeted EVs versus background. We achieve a 0.006% false positive rate per droplet by leveraging avidity effects that arise from EVs having multiple copies of their target ligands on their surface. We use parallelized optofluidics to rapidly process 10 million droplets per minute, ∼100× greater than conventional approaches. A validation study on a cohort of 14 patients with melanoma confirms DEVA's ability to match conventional ELISA measurements with reduced plasma sample volume and without the need for prior EV purification. This proof-of-concept study demonstrates DEVA's potential for clinical utility to enhance prognosis as well as guide treatment for cancer.

Distributed Maritime Operations and the Medical Challenge: How a Medical Common Operating Picture Can Help Bridge the Gap.

This work explores the challenges of delivering medical care in the geographically dispersed and resource-constrained environment of Distributed Maritime Operations (DMO) and Expeditionary Advanced Base Operations (EABO). Traditional medical planning approaches may struggle to adapt to the vast operational space, extended evacuation times, and limited medical force present in these scenarios. The concept of a Medical Common Operating Picture (COP) emerges as a potential solution. By providing a shared view of the medical situation across the theater, encompassing logistics, personnel, and patient data, a medical COP has the potential to facilitate medical command and control (MED C2) in DMO/EABO. The implementation of a medical COP has the potential to optimize resource allocation, enhance situational awareness, streamline medical evacuation, and reduce healthcare provider moral injury in large-scale combat operations. A medical COP will allow medical planners to make informed decisions on triage, resupply, and evacuation, ensuring the best use of limited medical resources. This is done by leveraging a comprehensive understanding of the medical landscape, enabling informed clinical and operational decision-making by humanitarian and combat personnel respectively. A fully realized medical COP system will enable a dynamic theater evacuation policy, balancing the conflicting needs of patient care at higher echelons with the operational expediency of returning servicemembers to their operational units, thereby maximizing evacuation effectiveness. It will further enable medical personnel to perform dynamic casualty triage based on operational realities, mitigating potential ethical dilemmas. Implementing such a medical COP system will require overcoming communication limitations to facilitate data exchange and potentially integrating clinical decision support tools for real-time data analysis and recommendations. It will also require the rapid adoption of modernized operational medicine documentation solutions by medical assets within the operational forces. Ultimately, this work suggests that a medical COP has the potential to bridge the gap between traditional medical planning and the unique demands of DMO/EABO, ultimately optimizing casualty care, maximizing resource efficiency, and preserving the fighting force.

Variation of computed tomography-derived extracellular volume fraction and the impact of protocol parameters: A systematic review and meta-analysis.

BACKGROUND: Cardiac computed tomography quantification of extracellular volume fraction (CT-ECV) is an emerging biomarker of myocardial fibrosis which has demonstrated high reproducibility, diagnostic and prognostic utility. However, there has been wide variation in the CT-ECV protocol in the literature and useful disease cut-offs are yet to be established. The objectives of this meta-analysis were to describe mean CT-ECV estimates and to estimate the effect of CT-ECV protocol parameters on between-study variation. METHODS: We conducted a meta-analysis of studies assessing CT-ECV in healthy and diseased participants. We used meta-analytic methods to pool estimates of CT-ECV and performed meta-regression to identify the contribution of protocol parameters to CT-ECV heterogeneity. RESULTS: Thirteen studies had a total of 248 healthy participants who underwent CT-ECV assessment. Studies of healthy participants had high variation in CT-ECV protocol parameters. The pooled estimate of CT-ECV in healthy participants was 27.6% (95%CI 25.7%-29.4%) with significant heterogeneity (I2 â€‹= â€‹93%) compared to 50.2% (95%CI 46.2%-54.2%) in amyloidosis, 31.2% (28.5%-33.8%) in severe aortic stenosis and 36.9% (31.6%-42.3%) in non-ischaemic dilated cardiomyopathies. Meta-regression revealed that CT protocol parameters account for approximately 25% of the heterogeneity in CT-ECV estimates. CONCLUSION: CT-ECV estimates for healthy individuals vary widely in the literature and there is significant overlap with estimates in cardiac disease. One quarter of this heterogeneity is explained by differences in CT-ECV protocol parameters. Standardization of CT-ECV protocols is necessary for widespread implementation of CT-ECV assessment for diagnosis and prognosis.

Noninvasive Atherosclerotic Phenotyping: The Next Frontier into Understanding the Pathobiology of Coronary Artery Disease.

PURPOSE OF REVIEW: Despite recent advances, coronary artery disease remains one of the leading causes of mortality worldwide. Noninvasive imaging allows atherosclerotic phenotyping by measurement of plaque burden, morphology, activity and inflammation, which has the potential to refine patient risk stratification and guide personalized therapy. This review describes the current and emerging roles of advanced noninvasive cardiovascular imaging methods for the assessment of coronary artery disease. RECENT FINDINGS: Cardiac computed tomography enables comprehensive, noninvasive imaging of the coronary vasculature, and is used to assess luminal stenoses, coronary calcifications, and distinct adverse plaque characteristics, helping to identify patients prone to future events. Novel software tools, implementing artificial intelligence solutions, can automatically quantify and characterize atherosclerotic plaque from standard computed tomography datasets. These quantitative imaging biomarkers have been shown to improve patient risk stratification beyond clinical risk scores and current clinical interpretation of cardiac computed tomography. In addition, noninvasive molecular imaging in higher risk patients can be used to assess plaque activity and plaque thrombosis. Noninvasive imaging allows unique insight into the burden, morphology and activity of atherosclerotic coronary plaques. Such phenotyping of atherosclerosis can potentially improve individual patient risk prediction, and in the near future has the potential for clinical implementation.

Genome-wide loss of heterozygosity predicts aggressive, treatment-refractory behavior in pituitary neuroendocrine tumors.

Pituitary neuroendocrine tumors (PitNETs) exhibiting aggressive, treatment-refractory behavior are the rare subset that progress after surgery, conventional medical therapies, and an initial course of radiation and are characterized by unrelenting growth and/or metastatic dissemination. Two groups of patients with PitNETs were sequenced: a prospective group of patients (n = 66) who consented to sequencing prior to surgery and a retrospective group (n = 26) comprised of aggressive/higher risk PitNETs. A higher mutational burden and fraction of loss of heterozygosity (LOH) was found in the aggressive, treatment-refractory PitNETs compared to the benign tumors (p = 1.3 × 10-10 and p = 8.5 × 10-9, respectively). Within the corticotroph lineage, a characteristic pattern of recurrent chromosomal LOH in 12 specific chromosomes was associated with treatment-refractoriness (occurring in 11 of 14 treatment-refractory versus 1 of 14 benign corticotroph PitNETs, p = 1.7 × 10-4). Across the cohort, a higher fraction of LOH was identified in tumors with TP53 mutations (p = 3.3 × 10-8). A machine learning approach identified loss of heterozygosity as the most predictive variable for aggressive, treatment-refractory behavior, outperforming the most common gene-level alteration, TP53, with an accuracy of 0.88 (95% CI: 0.70-0.96). Aggressive, treatment-refractory PitNETs are characterized by significant aneuploidy due to widespread chromosomal LOH, most prominently in the corticotroph tumors. This LOH predicts treatment-refractoriness with high accuracy and represents a novel biomarker for this poorly defined PitNET category.

Can non-invasive brain stimulation modulate peak alpha frequency in the human brain? A systematic review and meta-analysis.

Peak alpha frequency (PAF), the dominant oscillatory frequency within the alpha range (8-12 Hz), is associated with cognitive function and several neurological conditions, including chronic pain. Manipulating PAF could offer valuable insight into the relationship between PAF and various functions and conditions, potentially providing new treatment avenues. This systematic review aimed to comprehensively synthesise effects of non-invasive brain stimulation (NIBS) on PAF speed. Relevant studies assessing PAF pre- and post-NIBS in healthy adults were identified through systematic searches of electronic databases (Embase, PubMed, PsychINFO, Scopus, The Cochrane Library) and trial registers. The Cochrane risk-of-bias tool was employed for assessing study quality. Quantitative analysis was conducted through pairwise meta-analysis when possible; otherwise, qualitative synthesis was performed. The review protocol was registered with PROSPERO (CRD42020190512) and the Open Science Framework (https://osf.io/2yaxz/). Eleven NIBS studies were included, all with a low risk-of-bias, comprising seven transcranial alternating current stimulation (tACS), three repetitive transcranial magnetic stimulation (rTMS), and one transcranial direct current stimulation (tDCS) study. Meta-analysis of active tACS conditions (eight conditions from five studies) revealed no significant effects on PAF (mean difference [MD] = -0.12, 95% CI = -0.32 to 0.08, p = 0.24). Qualitative synthesis provided no evidence that tDCS altered PAF and moderate evidence for transient increases in PAF with 10 Hz rTMS. However, it is crucial to note that small sample sizes were used, there was substantial variation in stimulation protocols, and most studies did not specifically target PAF alteration. Further studies are needed to determine NIBS's potential for modulating PAF.

Application of Quantitative Assessment of Coronary Atherosclerosis by Coronary Computed Tomographic Angiography.

Coronary computed tomography angiography (CCTA) has emerged as a pivotal tool for diagnosing and risk-stratifying patients with suspected coronary artery disease (CAD). Recent advancements in image analysis and artificial intelligence (AI) techniques have enabled the comprehensive quantitative analysis of coronary atherosclerosis. Fully quantitative assessments of coronary stenosis and lumen attenuation have improved the accuracy of assessing stenosis severity and predicting hemodynamically significant lesions. In addition to stenosis evaluation, quantitative plaque analysis plays a crucial role in predicting and monitoring CAD progression. Studies have demonstrated that the quantitative assessment of plaque subtypes based on CT attenuation provides a nuanced understanding of plaque characteristics and their association with cardiovascular events. Quantitative analysis of serial CCTA scans offers a unique perspective on the impact of medical therapies on plaque modification. However, challenges such as time-intensive analyses and variability in software platforms still need to be addressed for broader clinical implementation. The paradigm of CCTA has shifted towards comprehensive quantitative plaque analysis facilitated by technological advancements. As these methods continue to evolve, their integration into routine clinical practice has the potential to enhance risk assessment and guide individualized patient management. This article reviews the evolving landscape of quantitative plaque analysis in CCTA and explores its applications and limitations.

Real-World Use of Hypofractionated Radiotherapy for Primary CNS Tumors in the Elderly, and Implications on Medicare Spending.

BACKGROUND: For elderly patients with high-grade gliomas, 3-week hypofractionated radiotherapy (HFRT) is noninferior to standard long-course radiotherapy (LCRT). We analyzed real-world utilization of HFRT with and without systemic therapy in Medicare beneficiaries treated with RT for primary central nervous system (CNS) tumors using Centers for Medicare & Medicaid Services data. METHODS: Radiation modality, year, age (65-74, 75-84, or ≥85 years), and site of care (freestanding vs hospital-affiliated) were evaluated. Utilization of HFRT (11-20 fractions) versus LCRT (21-30 or 31-40 fractions) and systemic therapy was evaluated by multivariable logistic regression. Medicare spending over the 90-day episode after RT planning initiation was analyzed using multivariable linear regression. RESULTS: From 2015 to 2019, a total of 10,702 RT courses (ie, episodes) were included (28% HFRT; 65% of patients aged 65-74 years). A considerable minority died within 90 days of RT planning initiation (n=1,251; 12%), and 765 (61%) of those received HFRT. HFRT utilization increased (24% in 2015 to 31% in 2019; odds ratio [OR], 1.2 per year; 95% CI, 1.1-1.2) and was associated with older age (≥85 vs 65-74 years; OR, 6.8; 95% CI, 5.5-8.4), death within 90 days of RT planning initiation (OR, 5.0; 95% CI, 4.4-5.8), hospital-affiliated sites (OR, 1.4; 95% CI, 1.3-1.6), conventional external-beam RT (vs intensity-modulated RT; OR, 2.7; 95% CI, 2.3-3.1), and no systemic therapy (OR, 1.2; 95% CI, 1.1-1.3; P<.001 for all). Increasing use of HFRT was concentrated in hospital-affiliated sites (P=.002 for interaction). Most patients (69%) received systemic therapy with no differences by site of care (P=.12). Systemic therapy utilization increased (67% in 2015 to 71% in 2019; OR, 1.1 per year; 95% CI, 1.0-1.1) and was less likely for older patients, patients who died within 90 days of RT planning initiation, those who received conventional external-beam RT, and those who received HFRT. HFRT significantly reduced spending compared with LCRT (adjusted ß for LCRT = +$8,649; 95% CI, $8,544-$8,755), whereas spending modestly increased with systemic therapy (adjusted ß for systemic therapy = +$270; 95% CI, $176-$365). CONCLUSIONS: Although most Medicare beneficiaries received LCRT for primary brain tumors, HFRT utilization increased in hospital-affiliated centers. Despite high-level evidence for elderly patients, discrepancy in HFRT implementation by site of care persists. Further investigation is needed to understand why patients with short survival may still receive LCRT, because this has major quality-of-life and Medicare spending implications.

Targeted Next-Generation Sequencing Assay for Direct Detection and Serotyping of Salmonella from Enrichment.

In this study, an automated, targeted next-generation sequencing (tNGS) assay to detect and serotype Salmonella from sample enrichments was evaluated. The assay generates millions of reads to detect multiple Salmonella-specific genes and serotype-specific alleles, detecting all Salmonella spp. tested to date, and serotyping 62 common Salmonella serotypes. Accuracy was tested on 291 pure reference cultures (251 Salmonella, 40 non-Salmonella), 21 artificially contaminated poultry carcass rinse samples, and 363 naturally contaminated poultry environmental samples. Among the 291 pure reference cultures, the automated tNGS assay resulted in 100% detection accuracy, 100% serotyping accuracy for the claimed serotypes, and 0% false positives. The limit of detection was estimated at 5 × 104 CFU/mL by testing enumerated cultures of strains representative of six serotypes. In cocontamination studies with mixtures of two serotypes (Enteritidis, Typhimurium, Kentucky, Infantis, and Newport) at a 1:1 ratio, tNGS detected both serotypes with 100% accuracy. The assay demonstrated 100% accuracy in artificially contaminated poultry carcass rinse sample enrichments. Targeted NGS was highly effective in detecting Salmonella in samples collected from poultry production facilities. Results demonstrated that tNGS could detect Salmonella and provide accurate serotyping information consistent with conventional serology. These findings highlight the reliable and efficient performance of a fully automated tNGS Salmonella assay in detecting and identifying Salmonella strains in complex matrices, reducing the time to results from 4 to 5 days required by the traditional isolation and serotyping to 10-12 h for tNGS after primary enrichment.

Macromolecular condensation organizes nucleolar sub-phases to set up a pH gradient.

Nucleoli are multicomponent condensates defined by coexisting sub-phases. We identified distinct intrinsically disordered regions (IDRs), including acidic (D/E) tracts and K-blocks interspersed by E-rich regions, as defining features of nucleolar proteins. We show that the localization preferences of nucleolar proteins are determined by their IDRs and the types of RNA or DNA binding domains they encompass. In vitro reconstitutions and studies in cells showed how condensation, which combines binding and complex coacervation of nucleolar components, contributes to nucleolar organization. D/E tracts of nucleolar proteins contribute to lowering the pH of co-condensates formed with nucleolar RNAs in vitro. In cells, this sets up a pH gradient between nucleoli and the nucleoplasm. By contrast, juxta-nucleolar bodies, which have different macromolecular compositions, featuring protein IDRs with very different charge profiles, have pH values that are equivalent to or higher than the nucleoplasm. Our findings show that distinct compositional specificities generate distinct physicochemical properties for condensates.

Different patient versus provider perspectives on living with Cushing's disease.

CONTEXT: Patients with Cushing's disease (CD) face challenges living with and receiving appropriate care for this rare, chronic condition. Even with successful treatment, many patients experience ongoing symptoms and impaired quality of life (QoL). Different perspectives and expectations between patients and healthcare providers (HCPs) may also impair well-being. OBJECTIVE: To examine differences in perspectives on living with CD between patients and HCPs, and to compare care goals and unmet needs. DESIGN: Memorial Sloan Kettering Pituitary Center established an annual pituitary symposium for pituitary patients and HCPs. Through anonymous pre-program surveys distributed at the 2020 and 2022 symposia, patients and HCPs answered questions related to their own sense, or perception of their patients' sense, of hope, choice, and loneliness in the context of living with CD. PARTICIPANTS: From 655 participants over two educational events, 46 patients with CD and 116 HCPs were included. Median age of both groups was 51 years. 78.3% of the patients were female vs. 53.0% of the HCPs. RESULTS: More patients than HCPs reported they had no choices in their treatment (21.7% vs. 0.9%, P < 0.001). More patients reported feeling alone living with CD than HCPs' perception of such (60.9% vs. 45.5%, P = 0.08). The most common personal care goal concern for patients was 'QoL/mental health,' vs. 'medical therapies/tumor control' for HCPs. The most common CD unmet need reported by patients was 'education/awareness' vs. 'medical therapies/tumor control' for HCPs. CONCLUSIONS: CD patients experience long term symptoms and impaired QoL which may in part be due to a perception of lack of effective treatment options and little hope for improvement. Communicating experiences and care goals may improve long term outcomes for CD patients.

Surgical Casualty Care in Contested Distributed Maritime Operations: Lessons Learned From the Falklands War.

The Falklands Campaign was fought a significant distance from the home base of the British Fleet. The planning and delivery of medical care during this campaign can provide significant lessons for strategic medical planning in other far spread geographic locations, including the Indo-Pacific region. Consideration of doctrine, including Role 1-4 facilities and the golden hour, may need to be reconsidered in light of changing scenarios. New concepts such as the "90-in-90" and "3-in-3" are also discussed as a framework for future planning in the U.S. Indo-Pacific Command area of responsibility.

Reduced-Intensity Compared to Nonmyeloablative Conditioning in Patients with Non-Hodgkin Lymphoma Undergoing Allogeneic Hematopoietic Stem Cell Transplantation.

Reduced-intensity conditioning (RIC) and nonmyeloablative (NMA) conditioning are preferred for patients with non-Hodgkin lymphoma (NHL) undergoing allogeneic hematopoietic stem cell transplantation (allo-HCT). Although prior studies have suggested that higher-intensity regimens in RIC-NMA conditioning are associated with inferior outcomes in patients with NHL, the optimal conditioning regimen remains unknown. We performed a retrospective single-center analysis to determine outcomes of adult patients with B cell and T cell NHL who underwent allo-HCT and received either RIC or NMA conditioning between March 2008 and December 2019. RIC regimens included fludarabine-cyclophosphamide-thiotepa-4 Gy-total body irradiation (Flu-Cy-TT-4Gy-TBI), fludarabine-melphalan (Flu-Mel), fludarabine-cyclophosphamide-4 Gy-total body irradiation (Flu-Cy-4Gy-TBI), and fludarabine-busulfan-4 (Flu-Bu-4). The NMA regimen comprised fludarabine-cyclophosphamide-2 Gy-total body irradiation (Flu-Cy-2Gy-TBI). The primary outcome was overall survival (OS); secondary outcomes included progression-free survival (PFS), nonrelapse mortality (NRM), and the incidence of acute and chronic graft-versus-host-disease (GVHD). Of 279 transplants recipients (median age, 58 years), 110 received RIC (55% Flu-Mel, 38% Flu-Cy-TT-4Gy-TBI, 6% Flu-Bu-4, 1% Flu-Cy-4Gy-TBI) and 169 received NMA conditioning with Flu-Cy-2Gy-TBI. With a median of 64 months of follow-up post-allo-HCT, there was no significant difference in OS between the NMA and RIC groups (median, not reached [NR] versus 103 months; P = .1), and this was maintained on multivariable analysis. Similarly, after adjustment for all independently significant covariates (age, Karnofsky Performance Status [KPS], Hematopoietic Cell Transplantation Comorbidity Index [HCT-CI], and disease histology), the regression analysis showed no significant difference in PFS with RIC compared to NMA conditioning (hazard ratio [HR] 1.38; 95% confidence interval [CI], .92 to 2.09; P = .24). On univariable analysis, there was no significant difference in NRM between the RIC and NMA arms (100-day estimate, 10.0% versus 1.8%; P = .5). After adjustment for age, ethnicity, KPS, HCT-CI, GVHD prophylaxis, and donor source, RIC conditioning was associated with a significantly higher incidence of NRM compared to NMA conditioning (HR, 2.61; 95% CI, 1.04 to 6.52; P = .039). On multivariable analysis, compared with the NMA arm, the RIC arm had higher rates of grade II-IV (HR, 2.25; 95% CI, 1.31 to 3.86; P = .002) and grade III-IV acute GVHD (HR, 5.62; 95% CI, 2.03 to 15.6; P < .001). The findings of this study suggest that NMA conditioning with Flu-Cy-TBI-2Gy may be considered over more intensive RIC regimens for patients with NHL undergoing allo-HCT.

Ultra-wide field and new wide field composite retinal image registration with AI-enabled pipeline and 3D distortion correction algorithm.

PURPOSE: This study aimed to compare a new Artificial Intelligence (AI) method to conventional mathematical warping in accurately overlaying peripheral retinal vessels from two different imaging devices: confocal scanning laser ophthalmoscope (cSLO) wide-field images and SLO ultra-wide field images. METHODS: Images were captured using the Heidelberg Spectralis 55-degree field-of-view and Optos ultra-wide field. The conventional mathematical warping was performed using Random Sample Consensus-Sample and Consensus sets (RANSAC-SC). This was compared to an AI alignment algorithm based on a one-way forward registration procedure consisting of full Convolutional Neural Networks (CNNs) with Outlier Rejection (OR CNN), as well as an iterative 3D camera pose optimization process (OR CNN + Distortion Correction [DC]). Images were provided in a checkerboard pattern, and peripheral vessels were graded in four quadrants based on alignment to the adjacent box. RESULTS: A total of 660 boxes were analysed from 55 eyes. Dice scores were compared between the three methods (RANSAC-SC/OR CNN/OR CNN + DC): 0.3341/0.4665/4784 for fold 1-2 and 0.3315/0.4494/4596 for fold 2-1 in composite images. The images composed using the OR CNN + DC have a median rating of 4 (out of 5) versus 2 using RANSAC-SC. The odds of getting a higher grading level are 4.8 times higher using our OR CNN + DC than RANSAC-SC (p < 0.0001). CONCLUSION: Peripheral retinal vessel alignment performed better using our AI algorithm than RANSAC-SC. This may help improve co-localizing retinal anatomy and pathology with our algorithm.