Influence of learned landmark correspondences on lung CT registration.

BACKGROUND: Disease or injury may cause a change in the biomechanical properties of the lungs, which can alter lung function. Image registration can be used to measure lung ventilation and quantify volume change, which can be a useful diagnostic aid. However, lung registration is a challenging problem because of the variation in deformation along the lungs, sliding motion of the lungs along the ribs, and change in density. PURPOSE: Landmark correspondences have been used to make deformable image registration robust to large displacements. METHODS: To tackle the challenging task of intra-patient lung computed tomography (CT) registration, we extend the landmark correspondence prediction model deep convolutional neural network-Match by introducing a soft mask loss term to encourage landmark correspondences in specific regions and avoid the use of a mask during inference. To produce realistic deformations to train the landmark correspondence model, we use data-driven synthetic transformations. We study the influence of these learned landmark correspondences on lung CT registration by integrating them into intensity-based registration as a distance-based penalty. RESULTS: Our results on the public thoracic CT dataset COPDgene show that using learned landmark correspondences as a soft constraint can reduce median registration error from approximately 5.46 to 4.08 mm compared to standard intensity-based registration, in the absence of lung masks. CONCLUSIONS: We show that using landmark correspondences results in minor improvements in local alignment, while significantly improving global alignment.

The relationship between object-based spatial ability and virtual navigation performance.

Spatial navigation is a multi-faceted behaviour drawing on many different aspects of cognition. Visuospatial abilities, such as mental rotation and visuospatial working memory, in particular, may be key factors. A range of tests have been developed to assess visuospatial processing and memory, but how such tests relate to navigation ability remains unclear. This understanding is important to advance tests of navigation for disease monitoring in various disorders (e.g., Alzheimer's disease) where spatial impairment is an early symptom. Here, we report the use of an established mobile gaming app, Sea Hero Quest (SHQ), as a measure of navigation ability in a sample of young, predominantly female university students (N = 78; 20; female = 74.3%; mean age = 20.33 years). We used three separate tests of navigation embedded in SHQ: wayfinding, path integration and spatial memory in a radial arm maze. In the same participants, we also collected measures of mental rotation (Mental Rotation Test), visuospatial processing (Design Organization Test) and visuospatial working memory (Digital Corsi). We found few strong correlations across our measures. Being good at wayfinding in a virtual navigation test does not mean an individual will also be good at path integration, have a superior memory in a radial arm maze, or rate themself as having a strong sense of direction. However, we observed that participants who were good in the wayfinding task of SHQ tended to perform well on the three visuospatial tasks examined here, and to also use a landmark strategy in the radial maze task. These findings help clarify the associations between different abilities involved in spatial navigation.

Bayesian modelling disentangles language versus executive control disruption in stroke.

Stroke is the leading cause of long-term disability worldwide. Incurred brain damage can disrupt cognition, often with persisting deficits in language and executive capacities. Yet, despite their clinical relevance, the commonalities and differences between language versus executive control impairments remain under-specified. To fill this gap, we tailored a Bayesian hierarchical modelling solution in a largest-of-its-kind cohort (1080 patients with stroke) to deconvolve language and executive control with respect to the stroke topology. Cognitive function was assessed with a rich neuropsychological test battery including global cognitive function (tested with the Mini-Mental State Exam), language (assessed with a picture naming task), executive speech function (tested with verbal fluency tasks), executive control functions (Trail Making Test and Digit Symbol Coding Task), visuospatial functioning (Rey Complex Figure), as well as verbal learning and memory function (Soul Verbal Learning). Bayesian modelling predicted interindividual differences in eight cognitive outcome scores three months after stroke based on specific tissue lesion topologies. A multivariate factor analysis extracted four distinct cognitive factors that distinguish left- and right-hemispheric contributions to ischaemic tissue lesions. These factors were labelled according to the neuropsychological tests that had the strongest factor loadings: One factor delineated language and general cognitive performance and was mainly associated with damage to left-hemispheric brain regions in the frontal and temporal cortex. A factor for executive control summarized mental flexibility, task switching and visual-constructional abilities. This factor was strongly related to right-hemispheric brain damage of posterior regions in the occipital cortex. The interplay of language and executive control was reflected in two distinct factors that were labelled as executive speech functions and verbal memory. Impairments on both factors were mainly linked to left-hemispheric lesions. These findings shed light onto the causal implications of hemispheric specialization for cognition; and make steps towards subgroup-specific treatment protocols after stroke.

Acute Cholecystitis Due to Lactococcus lactis and Single-Center Experience with Infections Due to Lactococcus spp.

Background: Lactococcus species are used to ferment milk to yogurt, cheese, and other products. The gram-positive coccus causes diseases in amphibia and fish and is a rare human pathogen. Patients and Methods: A 51-year-old male underwent laparoscopic cholecystectomy for acute and chronic calculous cholecystitis. Lactococcus lactis was isolated from pus from his gallbladder empyema. Results: Our institutional database was searched for other cases of Lactococcus spp. infections and four patients (2 males, 2 females; aged 51, 64, 78, and 80 years) were identified during a four-year period. The three other patients had positive blood cultures associated with pneumonia, toxic megacolon, and severe gastroenteritis. All isolates were monocultures with Lactococcus lactis (2), Lactococcus garvieae (1) and Lactococcus raffinolactis (1). Two patients died related to their sepsis. We report the second case of cholecystitis involving Lactococcus. Conclusions: Lactococcus is a very rare pathogen mainly causing blood stream infections but needs to be considered to cause serious surgical infections in humans.

Cdk8/CDK19 promotes mitochondrial fission through Drp1 phosphorylation and can phenotypically suppress pink1 deficiency in Drosophila.

Cdk8 in Drosophila is the orthologue of vertebrate CDK8 and CDK19. These proteins have been shown to modulate transcriptional control by RNA polymerase II. We found that neuronal loss of Cdk8 severely reduces fly lifespan and causes bang sensitivity. Remarkably, these defects can be rescued by expression of human CDK19, found in the cytoplasm of neurons, suggesting a non-nuclear function of CDK19/Cdk8. Here we show that Cdk8 plays a critical role in the cytoplasm, with its loss causing elongated mitochondria in both muscles and neurons. We find that endogenous GFP-tagged Cdk8 can be found in both the cytoplasm and nucleus. We show that Cdk8 promotes the phosphorylation of Drp1 at S616, a protein required for mitochondrial fission. Interestingly, Pink1, a mitochondrial kinase implicated in Parkinson's disease, also phosphorylates Drp1 at the same residue. Indeed, overexpression of Cdk8 significantly suppresses the phenotypes observed in flies with low levels of Pink1, including elevated levels of ROS, mitochondrial dysmorphology, and behavioral defects. In summary, we propose that Pink1 and Cdk8 perform similar functions to promote Drp1-mediated fission.

Variant-specific effects of GBA1 mutations on dopaminergic neuron proteostasis.

Glucocerebrosidase 1 (GBA1) mutations are the most important genetic risk factors for Parkinson's disease (PD). Clinically, mild (e.g., p.N370S) and severe (e.g., p.L444P and p.D409H) GBA1 mutations have different PD phenotypes, with differences in age at disease onset, progression, and the severity of motor and non-motor symptoms. We hypothesize that GBA1 mutations cause the accumulation of α-synuclein by affecting the cross-talk between cellular protein degradation mechanisms, leading to neurodegeneration. Accordingly, we tested whether mild and severe GBA1 mutations differentially affect the degradation of α-synuclein via the ubiquitin-proteasome system (UPS), chaperone-mediated autophagy (CMA), and macroautophagy and differentially cause accumulation and/or release of α-synuclein. Our results demonstrate that endoplasmic reticulum (ER) stress and total ubiquitination rates were significantly increased in cells with severe GBA1 mutations. CMA was found to be defective in induced pluripotent stem cell (iPSC)-derived dopaminergic neurons with mild GBA1 mutations, but not in those with severe GBA1 mutations. When examining macroautophagy, we observed reduced formation of autophagosomes in cells with the N370S and D409H GBA1 mutations and impairments in autophagosome-lysosome fusion in cells with the L444P GBA1 mutation. Accordingly, severe GBA1 mutations were found to trigger the accumulation and release of oligomeric α-synuclein in iPSC-derived dopaminergic neurons, primarily as a result of increased ER stress and defective macroautophagy, while mild GBA1 mutations affected CMA, which is mainly responsible for the degradation of the monomeric form of α-synuclein. Overall, our findings provide new insight into the molecular basis of the clinical variability in PD associated with different GBA1 mutations.

Strategic white matter hyperintensity locations associated with post-stroke cognitive impairment: a multicenter study in 1568 stroke patients.

BACKGROUND: Post-stroke cognitive impairment (PSCI) occurs in up to 50% of stroke survivors. Presence of pre-existing vascular brain injury, in particular the extent of white matter hyperintensities (WMH), is associated with worse cognitive outcome after stroke, but the role of WMH location in this association is unclear. AIM: We determined if WMH in strategic white matter tracts explain cognitive performance after stroke. METHODS: Individual patient data from 9 ischemic stroke cohorts with MRI were harmonized through the Meta VCI Map consortium. The association between WMH volumes in strategic tracts and domain-specific cognitive functioning (attention and executive functioning, information processing speed, language and verbal memory) was assessed using linear mixed models and lasso regression. We used a hypothesis-driven design, primarily addressing four white matter tracts known to be strategic in memory clinic patients: the left and right anterior thalamic radiation, forceps major and left inferior fronto-occipital fasciculus. RESULTS: The total study sample consisted of 1568 patients (39.9% female, mean age: 67.3 years). Total WMH volume was strongly related to cognitive performance on all four cognitive domains. WMH volume in the left anterior thalamic radiation was significantly associated with cognitive performance on attention and executive functioning and information processing speed, and WMH volume in the forceps major with information processing speed. The multivariable lasso regression showed that these associations were independent of age, sex, education, and total infarct volume and had larger coefficients than total WMH volume. CONCLUSIONS: These results show tract-specific relations between WMH volume and cognitive performance after ischemic stroke, independent of total WMH volume. This implies that the concept of strategic lesions in PSCI extends beyond acute infarcts and also involves pre-existing WMH. DATA AVAILABILITY: The Meta VCI Map consortium is dedicated to data sharing, following our guidelines.

Analysis of bitter compounds in traditional preparations of Gentiana purpurea L.

Roots of Gentiana purpurea are known to have an intense bitter taste due to its high content of secoiridoids. In folk medicine roots have commonly been prepared as water decoctions, soaked in ethanol, or boiled with milk, wine, or beer. The aim of this study was to explore how various historical preparation methods influence yields of major bitter compounds in G. purpurea. HPLC-DAD analysis revealed that maceration with 40% and 70% ethanol, boiling with acetic acid (3% and 6%), vinegar and raw milk gave the highest extraction yields of gentiopicrin. Erythrocentaurin was detected when the roots were added to cold water before boiling, possibly because of enzymatic degradation. In contrast, erythrocentaurin was not detected in preparations where roots were added to boiling water, or when they were extracted with acetic acid or alcohol. The results stress the significance of traditional preparation methods to optimize yield of bioactive compounds.

Whole organism snRNA-seq reveals systemic peripheral changes in Alzheimer's Disease fly models.

Peripheral tissues become disrupted in Alzheimer's Disease (AD). However, a comprehensive understanding of how the expression of AD-associated toxic proteins, Aß42 and Tau, in neurons impacts the periphery is lacking. Using Drosophila, a prime model organism for studying aging and neurodegeneration, we generated the Alzheimer's Disease Fly Cell Atlas (AD-FCA): whole-organism single-nucleus transcriptomes of 219 cell types from adult flies neuronally expressing human Aß42 or Tau. In-depth analyses and functional data reveal impacts on peripheral sensory neurons by Aß42 and on various non-neuronal peripheral tissues by Tau, including the gut, fat body, and reproductive system. This novel AD atlas provides valuable insights into potential biomarkers and the intricate interplay between the nervous system and peripheral tissues in response to AD-associated proteins.

Amyloid pathology and vascular risk are associated with distinct patterns of cerebral white matter hyperintensities: A multicenter study in 3132 memory clinic patients.

INTRODUCTION: White matter hyperintensities (WMH) are associated with key dementia etiologies, in particular arteriolosclerosis and amyloid pathology. We aimed to identify WMH locations associated with vascular risk or cerebral amyloid-ß1-42 (Aß42)-positive status. METHODS: Individual patient data (n = 3,132; mean age 71.5 ± 9 years; 49.3% female) from 11 memory clinic cohorts were harmonized. WMH volumes in 28 regions were related to a vascular risk compound score (VRCS) and Aß42 status (based on cerebrospinal fluid or amyloid positron emission tomography), correcting for age, sex, study site, and total WMH volume. RESULTS: VRCS was associated with WMH in anterior/superior corona radiata (B = 0.034/0.038, p < 0.001), external capsule (B = 0.052, p < 0.001), and middle cerebellar peduncle (B = 0.067, p < 0.001), and Aß42-positive status with WMH in posterior thalamic radiation (B = 0.097, p < 0.001) and splenium (B = 0.103, p < 0.001). DISCUSSION: Vascular risk factors and Aß42 pathology have distinct signature WMH patterns. This regional vulnerability may incite future studies into how arteriolosclerosis and Aß42 pathology affect the brain's white matter. HIGHLIGHTS: Key dementia etiologies may be associated with specific patterns of white matter hyperintensities (WMH). We related WMH locations to vascular risk and cerebral Aß42 status in 11 memory clinic cohorts. Aß42 positive status was associated with posterior WMH in splenium and posterior thalamic radiation. Vascular risk was associated with anterior and infratentorial WMH. Amyloid pathology and vascular risk have distinct signature WMH patterns.

De novo variants in FRYL are associated with developmental delay, intellectual disability, and dysmorphic features.

FRY-like transcription coactivator (FRYL) belongs to a Furry protein family that is evolutionarily conserved from yeast to humans. The functions of FRYL in mammals are largely unknown, and variants in FRYL have not previously been associated with a Mendelian disease. Here, we report fourteen individuals with heterozygous variants in FRYL who present with developmental delay, intellectual disability, dysmorphic features, and other congenital anomalies in multiple systems. The variants are confirmed de novo in all individuals except one. Human genetic data suggest that FRYL is intolerant to loss of function (LoF). We find that the fly FRYL ortholog, furry (fry), is expressed in multiple tissues, including the central nervous system where it is present in neurons but not in glia. Homozygous fry LoF mutation is lethal at various developmental stages, and loss of fry in mutant clones causes defects in wings and compound eyes. We next modeled four out of the five missense variants found in affected individuals using fry knockin alleles. One variant behaves as a severe LoF variant, whereas two others behave as partial LoF variants. One variant does not cause any observable defect in flies, and the corresponding human variant is not confirmed to be de novo, suggesting that this is a variant of uncertain significance. In summary, our findings support that fry is required for proper development in flies and that the LoF variants in FRYL cause a dominant disorder with developmental and neurological symptoms due to haploinsufficiency.

Deep learning analysis of epicardial adipose tissue to predict cardiovascular risk in heavy smokers.

BACKGROUND: Heavy smokers are at increased risk for cardiovascular disease and may benefit from individualized risk quantification using routine lung cancer screening chest computed tomography. We investigated the prognostic value of deep learning-based automated epicardial adipose tissue quantification and compared it to established cardiovascular risk factors and coronary artery calcium. METHODS: We investigated the prognostic value of automated epicardial adipose tissue quantification in heavy smokers enrolled in the National Lung Screening Trial and followed for 12.3 (11.9-12.8) years. The epicardial adipose tissue was segmented and quantified on non-ECG-synchronized, non-contrast low-dose chest computed tomography scans using a validated deep-learning algorithm. Multivariable survival regression analyses were then utilized to determine the associations of epicardial adipose tissue volume and density with all-cause and cardiovascular mortality (myocardial infarction and stroke). RESULTS: Here we show in 24,090 adult heavy smokers (59% men; 61 ± 5 years) that epicardial adipose tissue volume and density are independently associated with all-cause (adjusted hazard ratios: 1.10 and 1.38; P < 0.001) and cardiovascular mortality (adjusted hazard ratios: 1.14 and 1.78; P < 0.001) beyond demographics, clinical risk factors, body habitus, level of education, and coronary artery calcium score. CONCLUSIONS: Our findings suggest that automated assessment of epicardial adipose tissue from low-dose lung cancer screening images offers prognostic value in heavy smokers, with potential implications for cardiovascular risk stratification in this high-risk population.

Heavy smokers are at increased risk of poor health outcomes, particularly outcomes related to cardiovascular disease. We explore how fat surrounding the heart, known as epicardial adipose tissue, may be an indicator of the health of heavy smokers. We use an artificial intelligence system to measure the heart fat on chest scans of heavy smokers taken during a lung cancer screening trial and following their health for 12 years. We find that higher amounts and denser epicardial adipose tissue are linked to an increased risk of death from any cause, specifically from heart-related issues, even when considering other health factors. This suggests that measuring epicardial adipose tissue during lung cancer screenings could be a valuable tool for identifying heavy smokers at greater risk of heart problems and death, possibly helping to guide their medical management and improve their cardiovascular health.

Foundation model for cancer imaging biomarkers.

Foundation models in deep learning are characterized by a single large-scale model trained on vast amounts of data serving as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labelled datasets are often scarce. Here, we developed a foundation model for cancer imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of cancer imaging-based biomarkers. We found that it facilitated better and more efficient learning of imaging biomarkers and yielded task-specific models that significantly outperformed conventional supervised and other state-of-the-art pretrained implementations on downstream tasks, especially when training dataset sizes were very limited. Furthermore, the foundation model was more stable to input variations and showed strong associations with underlying biology. Our results demonstrate the tremendous potential of foundation models in discovering new imaging biomarkers that may extend to other clinical use cases and can accelerate the widespread translation of imaging biomarkers into clinical settings.

Experience with Laparoscopic and Robotic Colon Surgery Together with Other Major Minimally Invasive Procedures for Unrelated Pathologies.

Background: Indications for combined colon surgery together with other procedures include oncologic multivisceral resections and abdominal trauma. It is unclear if combining minimally invasive (MI) colon surgery with unrelated other procedures increases the risk for complications. Patients and Methods: The surgical database from two institutions during a 10-year period was queried for combined colon surgeries together with other interventions. All open cases, combined cases performed for one pathology and MI colectomies together with a minor procedure, were excluded. Results: Median age of the 6 men and 7 women was 64.4 (range 42.7-75.4) years. Colon surgeries included right (5), sigmoid (4) transverse (1) colectomies, rectum resection (1), rectopexy (1), and colostomy reversal (1) with indications of colorectal cancer (5), diverticulitis (3), benign ileocecal mass (1), colonic volvulus (3) and rectal prolapse (1). Second procedures included two splenectomies (sarcoidosis, ITP), paraesophageal hernia repairs (4), right diaphragmatic repairs [eventration (2) and Morgagni type hernia]; cholecystectomies (2), appendectomy (acute appendicitis), duodenal wedge resection (carcinoid), reversal of a gastric bypass (Roux limb stricture) one each. Cases were done laparoscopically (7) and robotic assisted (6). In most cases only 4 trocars were used. Median OR time was 4.3 (range 2.5 to 6.6) hours. No anastomotic breakdown was observed. Conclusions: Combining MI colectomy and other major abdominal surgeries can be safely done and in this series did not increase morbidity or mortality but avoids a second operation. Patient selection seems important and port placement may need to be altered to achieve good exposure for both procedures.

Deep Learning to Estimate Cardiovascular Risk From Chest Radiographs : A Risk Prediction Study.

BACKGROUND: Guidelines for primary prevention of atherosclerotic cardiovascular disease (ASCVD) recommend a risk calculator (ASCVD risk score) to estimate 10-year risk for major adverse cardiovascular events (MACE). Because the necessary inputs are often missing, complementary approaches for opportunistic risk assessment are desirable. OBJECTIVE: To develop and test a deep-learning model (CXR CVD-Risk) that estimates 10-year risk for MACE from a routine chest radiograph (CXR) and compare its performance with that of the traditional ASCVD risk score for implications for statin eligibility. DESIGN: Risk prediction study. SETTING: Outpatients potentially eligible for primary cardiovascular prevention. PARTICIPANTS: The CXR CVD-Risk model was developed using data from a cancer screening trial. It was externally validated in 8869 outpatients with unknown ASCVD risk because of missing inputs to calculate the ASCVD risk score and in 2132 outpatients with known risk whose ASCVD risk score could be calculated. MEASUREMENTS: 10-year MACE predicted by CXR CVD-Risk versus the ASCVD risk score. RESULTS: Among 8869 outpatients with unknown ASCVD risk, those with a risk of 7.5% or higher as predicted by CXR CVD-Risk had higher 10-year risk for MACE after adjustment for risk factors (adjusted hazard ratio [HR], 1.73 [95% CI, 1.47 to 2.03]). In the additional 2132 outpatients with known ASCVD risk, CXR CVD-Risk predicted MACE beyond the traditional ASCVD risk score (adjusted HR, 1.88 [CI, 1.24 to 2.85]). LIMITATION: Retrospective study design using electronic medical records. CONCLUSION: On the basis of a single CXR, CXR CVD-Risk predicts 10-year MACE beyond the clinical standard and may help identify individuals at high risk whose ASCVD risk score cannot be calculated because of missing data. PRIMARY FUNDING SOURCE: None.

Homozygous missense variants in YKT6 result in loss of function and are associated with developmental delay, with or without severe infantile liver disease and risk for hepatocellular carcinoma.

PURPOSE: YKT6 plays important roles in multiple intracellular vesicle trafficking events but has not been associated with Mendelian diseases. METHODS: We report three unrelated individuals with rare homozygous missense variants in YKT6 who exhibited neurological disease with or without a progressive infantile liver disease. We modeled the variants in Drosophila. We generated wild-type and variant genomic rescue constructs (GRs) of the fly ortholog dYkt6 and compared their ability in rescuing the loss-of-function phenotypes in mutant flies. We also generated a dYkt6KozakGAL4 allele to assess the expression pattern of dYkt6. RESULTS: Two individuals are homozygous for YKT6 [NM_006555.3:c.554A>G p.(Tyr185Cys)] and exhibited normal prenatal course followed by failure to thrive, developmental delay and progressive liver disease. Haplotype analysis identified a shared homozygous region flanking the variant, suggesting a common ancestry. The third individual is homozygous for YKT6 [NM_006555.3:c.191A>G p.(Tyr64Cys)] and exhibited neurodevelopmental disorders and optic atrophy. Fly dYkt6 is essential and is expressed in the fat body (analogous to liver) and central nervous system. Wild-type GR can rescue the lethality and autophagic flux defects whereas the variants are less efficient in rescuing the phenotypes. CONCLUSION: The YKT6 variants are partial loss-of-function alleles and the p.(Tyr185Cys) is more severe than p.(Tyr64Cys).

Noninvasive Molecular Subtyping of Pediatric Low-Grade Glioma with Self-Supervised Transfer Learning.

Purpose To develop and externally test a scan-to-prediction deep learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pediatric low-grade glioma. Materials and Methods This retrospective study included two pediatric low-grade glioma datasets with linked genomic and diagnostic T2-weighted MRI data of patients: Dana-Farber/Boston Children's Hospital (development dataset, n = 214 [113 (52.8%) male; 104 (48.6%) BRAF wild type, 60 (28.0%) BRAF fusion, and 50 (23.4%) BRAF V600E]) and the Children's Brain Tumor Network (external testing, n = 112 [55 (49.1%) male; 35 (31.2%) BRAF wild type, 60 (53.6%) BRAF fusion, and 17 (15.2%) BRAF V600E]). A deep learning pipeline was developed to classify BRAF mutational status (BRAF wild type vs BRAF fusion vs BRAF V600E) via a two-stage process: (a) three-dimensional tumor segmentation and extraction of axial tumor images and (b) section-wise, deep learning-based classification of mutational status. Knowledge-transfer and self-supervised approaches were investigated to prevent model overfitting, with a primary end point of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, a novel metric, center of mass distance, was developed to quantify the model attention around the tumor. Results A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest classification performance with an AUC of 0.82 (95% CI: 0.72, 0.91), 0.87 (95% CI: 0.61, 0.97), and 0.85 (95% CI: 0.66, 0.95) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively, on internal testing. On external testing, the pipeline yielded an AUC of 0.72 (95% CI: 0.64, 0.86), 0.78 (95% CI: 0.61, 0.89), and 0.72 (95% CI: 0.64, 0.88) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively. Conclusion Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pediatric low-grade glioma mutational status prediction in a limited data scenario. Keywords: Pediatrics, MRI, CNS, Brain/Brain Stem, Oncology, Feature Detection, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024.

Trends in Intracranial and Cerebral Volumes of Framingham Heart Study Participants Born 1930 to 1970.

Importance: Human brain development and maintenance is under both genetic and environmental influences that likely affect later-life dementia risk. Objective: To examine environmental influences by testing whether time-dependent secular differences occurred in cranial and brain volumes and cortical thickness over birth decades spanning 1930 to 1970. Design, Setting, and Participants: This cross-sectional study used data from the community-based Framingham Heart Study cohort for participants born in the decades 1930 to 1970. Participants did not have dementia or history of stroke and had magnetic resonance imaging (MRI) obtained from March 18, 1999, to November 15, 2019. The final analysis dataset was created in October 2023. Exposure: Years of birth ranging from 1925 to 1968. Main Measures: Cross-sectional analysis of intracranial, cortical gray matter, white matter, and hippocampal volumes as well as cortical surface area and cortical thickness. The secular measure was the decade in which the participant was born. Covariates included age at MRI and sex. Results: The main study cohort consisted of 3226 participants with a mean (SD) age of 57.7 (7.8) years at the time of their MRI. A total of 1706 participants were female (53%) and 1520 (47%) were male. The birth decades ranged from the 1930s to 1970s. Significant trends for larger intracranial, hippocampal, and white matter volumes and cortical surface area were associated with progressive birth decades. Comparing the 1930s birth decade to the 1970s accounted for a 6.6% greater volume (1234 mL; 95% CI, 1220-1248, vs 1321 mL; 95% CI, 1301-1341) for ICV, 7.7% greater volume (441.9 mL; 95% CI, 435.2-448.5, vs 476.3 mL; 95% CI, 467.0-485.7) for white matter, 5.7% greater value (6.51 mL; 95% CI, 6.42-6.60, vs 6.89 mL; 95% CI, 6.77-7.02) for hippocampal volume, and a 14.9% greater value (1933 cm2; 95% CI, 1908-1959, vs 2222 cm2; 95% CI, 2186-2259) for cortical surface area. Repeat analysis applied to a subgroup of 1145 individuals of similar age range born in the 1940s (mean [SD] age, 60.0 [2.8] years) and 1950s (mean [SD] age, 59.0 [2.8] years) resulted in similar findings. Conclusion and Relevance: In this study, secular trends for larger brain volumes suggested improved brain development among individuals born between 1930 and 1970. Early life environmental influences may explain these results and contribute to the declining dementia incidence previously reported in the Framingham Heart Study cohort.