Segmentation Analysis Research Articles

Deep Learning–Based Pediatric Brain Region Segmentation and Volumetric Analysis for General Growth Pattern in Healthy Children

Deep Learning–Based Pediatric Brain Region Segmentation and Volumetric Analysis for General Growth Pattern in Healthy Children

Abstract 4124677: Left ventricular function and myocardial longitudinal strain analysis in patients with Chagas disease: case series and systematic literature review.

Introduction: Chagas disease is a significant cause of tropical disease-related mortality. It presents in acute, indeterminate, and chronic phases, with chronic cardiomyopathy being the most severe form, leading to heart failure, arrhythmias, and sudden cardiac death. Conventional echocardiography often fails to detect early subclinical dysfunction, whereas Global longitudinal strain (GLS) may provide earlier detection of myocardial strain abnormalities. Left ventricular dysfunction is an independent predictor of mortality and GLS is an emerging modality that may aid early detection of cardiac involvement. Objective: This study aims to compare left ventricular function using multiple echocardiographic parameters between patients with indeterminate and chronic forms of Chagas disease and to perform a systematic literature review. Methods: The observational study involved 11 patients (mean age 76.36 years) from a tertiary hospital in Brazil, classified as indeterminate (45%) or chronic (55%). Serological confirmation and detailed echocardiographic evaluations, including GLS, were performed. A systematic literature review was also conducted on GLS in Chagas cardiomyopathy. Results: Patients with chronic Chagas disease showed significantly lower LVEF and GLS compared to those with the indeterminate form. Segmental strain analysis revealed consistent contractility reductions across specific ventricular segments in both groups. Discussion: Chagas cardiomyopathy often leads to dilated cardiomyopathy with significant arrhythmias and heart failure. GLS can detect early myocardial changes even before a significant drop in LVEF, indicating its potential for early diagnosis and better management of Chagas cardiomyopathy. Literature review supports the use of GLS for detecting early cardiac involvement and predicting adverse outcomes. Conclusion: Incorporating GLS with conventional echocardiography offers enhanced early detection of myocardial changes in Chagas disease. While promising, further research is needed to establish the clinical significance and impact of these techniques in routine practice.

CNSC-64. BEYOND THE LOCAL TUMOR MICROENVIRONMENT: CHARACTERIZING CHANGES TO NEURONAL ACTIVITY INDUCED BY PEDIATRIC HIGH-GRADE GLIOMA

Abstract Bidirectional electrochemical signaling between neurons and tumor cells is emerging as a critical regulator of pediatric high-grade glioma (HGG) pathology. Neuron-tumor interactions are known to induce local neuronal hyperactivity. However, recent work tracing the projections of these neuron-tumor networks revealed that HGG neuronal recruitment extends beyond the local tumor microenvironment (TME). These findings suggest that tumor-induced hyperexcitability may spread beyond the local TME and drive brain-wide circuit-level changes. To elucidate how non-tumor innervated brain regions are affected by TME hyperactivity we first characterized neuronal hyperactivity induced by a cortical patient-derived pediatric high-grade cell line in vitro on human iPSC-derived neurons. In vitro calcium imaging experiments demonstrated an increase in the number of calcium fluctuations in glioma co-cultured neurons. In parallel, multi-electrode recordings revealed increased population spiking activity and amplitude in neurons co-cultured with glioma cells. We then xenografted these HGG cells into the prefrontal cortex of mice and performed whole brain-clearing and cFos staining on tumor-bearing vs saline-injected control samples. As cFos is an immediate early gene activated by neuronal activity, we utilized the density of cFos expression as a readout-out of neuronal activation in our atlas-aligned segmented brain section analyses. We expectedly observed increased cFos expression within the ipsilateral primary and secondary motor region, which collectively comprise the local TME. Interestingly, we additionally observed elevated cFos in non-tumor bearing brain regions on both the ipsilateral and contralateral hemispheres, largely in layer 2/3 cortical neurons. These neurons form extensive cortico-cortical projections, and we coincidingly observed increased cFos expression in known cortical projection targets of the prefrontal xenograft location, such as somatosensory, visual, and retrosplenial cortices. Our findings suggest that tumor-induced neuronal hyperactivity extends beyond the local TME in a brain-wide manner and potentially follows established neuronal circuits, rendering these connected regions vulnerable to alterations in neuronal activity.

NCOG-48. CT SCAN COMPOSITE SCORE CAN IDENTIFY GLIOBLASTOMA PATIENTS WITH WORSE OUTCOMES

Abstract OBJECTIVE Obesity is a risk factor for many cancer types including glioblastoma multiforme (GBM). We used CT body composition analyses to construct a sex-specific composite score that would optimally predict overall survival in GBM. METHODS Using a retrospective institutional cohort, we performed single slice (L3) and volumetric (L1-L5) automated body segmentation analyses on abdominal and pelvic computed tomography (CT) scans performed within 1 month of diagnosis of GBM. Multivariable Cox proportional hazards models were then used to identify variables that were independently associated with GBM overall survival. Lastly, a learning-tree algorithm was implemented to identify the relative importance of body composition metrics using a XGBoost-powered learning model. These weights were used to create sex-specific composite CT scan scores of protective and predisposing factor with relation to GBM survival. A log-rank pairwise t-test was used to compared GBM survival across patient groups stratified based on these CT composite scores. RESULTS Higher relative inter/intramuscular adipose tissue volume (HR(95%CI):1.9(1.01-3.06), p=0.02), visceral adipose tissue volume (HR(95%CI):2.1(1.04-4.1), p=0.04) and aortic calcification volume (HR(95%CI):2.6(1.2-5.5), p<0.001) were associated with lower GBM overall survival, while higher subcutaneous adipose tissue volume (HR(95%CI):0.4(0.2-0.8), p=0.02), iliopsoas muscle volume (HR(95%CI):0.4(0.2-0.9), p<0.001), and trabecular bone density (HR(95%CI):0.4(0.1-0.8), p=0.003) were predictive of higher GBM OS (p-value of all tests <0.05). Using quartiles of the CT scan composite predisposing and protective scores, we were able to stratify male and female participants with significantly different outcomes with regards to GBM OS (Figure). Male and female participants with higher burden of predisposing factors had significantly lower chances of survival compared to those with lower cumulative burden of these factors (Figure, p-value Q4 vs. Q1 males< 0.01 and 0.001 in females) CONCLUSION Using automated body segmentation analysis we optimized a CT scan composite score that was able to stratify GBM patients with worse overall survival.

Young Icelanders and popular culture: An empirical study of Anglicisms in conversation

Abstract The aim of the study is to investigate how young Icelanders use Anglicisms in conversation that is shaped by popular culture. The data comprises 4 hours and 30 minutes of recordings: spoken interaction between two fifteen-year-old boys that are playing a computer game, and a conversation between two young women hosting a podcast on fashion, lifestyle, and entertainment. The methodological approach applied in the study is interactional linguistics. The research questions are as follows: 1) What kind of Anglicisms occur in the data in respect to parts-of-speech? 2) What interactional functions do these items have in their context? The study begins by addressing the frequency and distribution of Anglicisms in the data, but the main emphasis is on the qualitative analysis of segments of talk. The study shows that speakers use Anglicisms in a systematic and meaningful way. In the analysis, the functions were categorised as follows: Anglicisms that appear on the screen, Anglicisms that index an international identity, Anglicisms as assessments and comments, and Anglicisms in rituals such as greetings and farewells.

A new strategy based on multi-source remote sensing data for improving the accuracy of land use/cover change classification.

Land Use/Cover Change (LUCC) plays a crucial role in sustainable land management and regional planning. However, contemporary feature extraction approaches often prove inefficient at capturing critical data features, thereby complicating land cover categorization. In this research, we introduce a new feature extraction algorithm alongside a Segmented and Stratified Principal Component Analysis (SS-PCA) dimensionality reduction method based on correlation grouping. These methods are applied to UAV LiDAR and UAV HSI data collected from land use types (e.g., residential areas, agricultural lands) and specific species (e.g., tree species) in urban, agricultural, and natural environments to reflect the diversity of the study area and to demonstrate the ability of our methods to be applied in different classification scenarios. We utilize LiDAR and HSI data to extract 157 features, including intensity, height, Normalized Digital Surface Model (nDSM), spectral, texture, and index features, to identify the optimal feature subset. Subsequently, the best feature subset is inputted into a random forest classifier to classify the features. Our findings demonstrate that the SS-PCA method successfully enhances downscaled feature bands, reduces hyperspectral data noise, and improves classification accuracy (Overall Accuracy = 91.17%). Additionally, the CFW method effectively screens appropriate features, thereby increasing classification accuracy for LiDAR (Overall Accuracy = 78.10%), HIS (Overall Accuracy = 89.87%), and LiDAR + HIS (Overall Accuracy = 97.17%) data across various areas. Moreover, the integration of LiDAR and HSI data holds promise for significantly improving ground fine classification accuracy while mitigating issues such as the 'salt and pepper noise'. Furthermore, among individual features, the LiDAR intensity feature emerges as critical for enhancing classification accuracy, while among single-class features, the HSI feature proves most influential in improving classification accuracy.

Integrated Deep Learning Model for the Detection, Segmentation, and Morphologic Analysis of Intracranial Aneurysms Using CT Angiography.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a deep learning model for the morphologic measurement of unruptured intracranial aneurysms (UIAs) based on CT angiography (CTA) data and validate its performance using a multicenter dataset. Materials and Methods In this retrospective study, patients with CTA examinations, including those with and without UIAs, in a tertiary referral hospital from February 2018 to February 2021 were included as the training dataset. Patients with UIAs who underwent CTA at multiple centers between April 2021 to December 2022 were included as the multicenter external testing set. An integrated deep-learning (IDL) model was developed for UIA detection, segmentation and morphologic measurement using an nnU-net algorithm. Model performance was evaluated using the Dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC), with measurements by senior radiologists serving as the reference standard. The ability of the IDL model to improve performance of junior radiologists in measuring morphologic UIA features was assessed. Results The study included 1182 patients with UIAs and 578 controls without UIAs as the training dataset (55 years [IQR, 47-62], 1,012 [57.5%] females) and 535 patients with UIAs as the multicenter external testing set (57 years [IQR, 50-63], 353 [66.0%] females). The IDL model achieved 97% accuracy in detecting UIAs and achieved a DSC of 0.90 (95%CI, 0.88-0.92) for UIA segmentation. Model-based morphologic measurements showed good agreement with reference standard measurements (all ICCs > 0.85). Within the multicenter external testing set, the IDL model also showed agreement with reference standard measurements (all ICCs > 0.80). Junior radiologists assisted by the IDL model showed significantly improved performance in measuring UIA size (ICC improved from 0.88 [0.80-0.92] to 0.96 [0.92-0.97], P < .001). Conclusion The developed integrated deep learning model using CTA data showed good performance in UIA detection, segmentation and morphologic measurement and may be used to assist less experienced radiologists in morphologic analysis of UIAs. ©RSNA, 2024.

A "silent storm": uncovering the escalating crisis in mental healthcare for children and adolescents in Slovenia during and after the COVID-19 pandemic.

Our aim was to assess the burden of children and adolescents' mental health problems on the Slovenian outpatient healthcare system before, during and after the pandemic. In a retrospective analysis of healthcare indicators from 2008 to 2023, we analysed data from the National Institute of Public Health. Key domains included initial visits for mental and behavioural disorders (MBDs) to primary care for the population aged 0-19; the number of referrals to an initial assessment with a child and adolescent psychiatrist (CAP) at the secondary level for the population aged 0-17 along with the corresponding waiting times; and the number of urgent referrals for the population aged 0-17 to emergency mental health centres at the tertiary level. The calculations included rates per 1000 people. Descriptive statistics and diagrams were used to compare the data. Segmented linear regression analysis (SLR) was conducted on the primary healthcare data to identify the distinct temporal point indicating an increase. Comparing the average rates of the 2020-2022 period to those of the 2018-2019 period, there was a 20% increase in initial visits to primary care, a 23% increase in the referral rate to a CAP at the secondary level, and a 41% increase to the tertiary level of care. In secondary care, a four- to sevenfold increase in waiting times for the initial CAP assessment was observed between 2019 and 2023. The incidence of initial visits to primary healthcare services for MBD increased from 2008 to 2019 (average annual growth rate of 4.5%). The average annual growth rate for the 2020-2022 period tripled to 13.9%. The SLR showed that the trend of accelerating growth could have begun in 2017 for the 0-5 age group and possibly for the 15-19 age group as well. After the initial decline in 2020, all levels of the Slovenian healthcare system faced an increased burden of MBD in children and adolescents from 2021 to 2022 compared to pre-pandemic levels. Nevertheless, a portion of this increase aligns with longitudinal growing trends from 2008 onwards. Tackling the crisis requires urgent national action, significant improvement in organization, and investments in mental health.

AlGrow: a graphical interface for easy, fast and accurate area and growth analysis of heterogeneously colored targets.

AlGrow software provides a graphical interface to define target color volumes as hulls in color space and applies them to image segmentation and growth rate analysis across a multiplexed image series.

Effect of smoking on meibomian gland among Nepalese population

Purpose of study: To investigate the effects of cigarette smoking on meibomian gland and tear function test. Methods: It was a hospital-based cross-sectional study, which enrolled examined 30 subjects with a smoking history of at least 1 year (study group) alongside 25 healthy non-smokers (control group). Each participant’s symptoms were assessed using the Ocular Surface Disease Index (OSDI) questionnaire. A comprehensive ophthalmological evaluation followed, which included the non-invasive tear breakup time (NITBUT) and Schirmer test (with anesthesia). Additionally, we conducted a detailed analysis of the meibomian glands in both the upper and lower eyelids using meibography, employing the advanced Sirius anterior segment analysis system. Results: Participants in the study group averaged a smoking history of 6.94 ± 6.73 pack years. The mean OSDI score was 36.45 ± 10.60 in the study group, compared to 31.41 ± 8.12 in the control group (P = 0.05). For the NITBUT and Schirmer test, the study group recorded values of 9.54 ± 5.89 seconds and 14.77 ± 9.39 mm, respectively, while the control group showed 9.95 ± 6.15 seconds and 19.08 ± 7.08 mm (P = 0.85 and P = 0.03, respectively). Upper lid meibography revealed a 55.40 ± 10.10% gland loss in the study group, significantly higher than the 46.33 ± 14.70% observed in the control group (P = 0.01). However, no statistically significant difference was found in lower lid meibomian gland loss between the groups, with the study group at 54.08 ± 9.71% and the control group at 51.41 ± 17.24% (P = 0.49). Conclusion: Smoking results in meibomian gland damage which may be a risk factor for dry eye. In cases of ocular surface disorders related to chronic smoking, meibomian gland damage should be taken into consideration.

Prediction of femoral head collapse in osteonecrosis using deep learning segmentation and radiomics texture analysis of MRI

BackgroundFemoral head collapse is a critical pathological change and is regarded as turning point in disease progression in osteonecrosis of the femoral head (ONFH). In this study, we aim to build an automatic femoral head collapse prediction pipeline for ONFH based on magnetic resonance imaging (MRI) radiomics.MethodsIn the segmentation model development dataset, T1-weighted MRI of 222 hips from two hospitals were retrospectively collected and randomly split into training (n = 190) and test (n = 32) sets. In the prognosis prediction model development dataset, 206 hips were also retrospectively collected from two hospitals and divided into training set (n = 155) and external test set (n = 51) according to data source. A deep learning model for automatic lesion segmentation was trained with nnU-Net, from which three-dimensional regions of interest were segmented and a total of 107 radiomics features were extracted. After intra-class correlation coefficients screening, feature correlation coefficient screening and Least Absolute Shrinkage and Selection Operator regression feature selection, a machine learning model for ONFH prognosis prediction was trained with Logistic Regression (LR) and Light Gradient Boosting Machine (LightGBM) algorithm.ResultsThe segmentation model achieved an average dice similarity coefficient of 0.848 and an average 95% Hausdorff distance of 3.794 in the test set, compared to the manual segmentation results. After feature selection, nine radiomics features were included in the prognosis prediction model. External test showed that the LightGBM model exhibited acceptable predictive performance. The area under the curve (AUC) of the prediction model was 0.851 (95% CI: 0.7268–0.9752), with an accuracy of 0.765, sensitivity of 0.833, and specificity of 0.727. Decision curve analysis showed that the LightGBM model exhibited favorable clinical utility.ConclusionThis study presents an automated pipeline for predicting femoral head collapse in ONFH with acceptable performance. Further research is necessary to determine the clinical applicability of this radiomics-based approach and to assess its potential to assist in treatment decision-making for ONFH.

축제 방문 동기에 따른 축제방문객 시장세분화 연구: 설악문화제 중심으로

The purpose of this study was to find out what the motivation factors for visiting the festival are for visitors who participated in the Gangwon State Seorak cultural festival and to divide festival visitors based on the derived motivation factors for visiting the festival. Factor analysis, cluster analysis, and ANOVA analysis were used as research analysis. As a result of performing factor analysis on 14 festival visit motivation items, four factors (novelty, escape, family affinity, and sociability) were derived. Through market segmentation analysis, visitors who attended the festival were classified into three groups. Cluster 1 was a group of 88 people (25.7%) out of the total survey respondents of 349, and was a group of general festival visitors who showed a little curiosity about the festival. It called as ‘common festival visitor’. Cluster 2 was 131 people (38.3%) and had strong ties with families. It called as ‘family festival visitor’. Cluster 3 was an enthusiastic festival visitor 123 people (36.0%) that actively accepts all parts of tourism motivation. It called as ‘enthusiastic festival visitor’. In result, cluster 2, and Cluster 3 were derived as major target to developing marketing strategies and several recommendation were suggested.

Examining the Potential Impact of Recreational Cannabis Legalization on Individuals Receiving Treatment for Substance Use Disorder: An Interrupted Time Series Study in Guelph, Ontario, Canada

Objective: The present research evaluated the impact of legalizing recreational cannabis among individuals with substance use disorders (SUDs) who may already use cannabis at high rates. Method: Using an interrupted time series study design, we evaluated the potential impact of legalizing recreational cannabis among individuals seeking treatment for SUD within a hospital-based treatment setting in Guelph, Ontario. We examined 2,925 individuals who entered an inpatient SUD treatment program between April 2017 and December 2021. We performed segmented regression analyses using both the date of cannabis legalization and the date of edibles legalization as the interruption time point. We also performed stratified analyses to examine potential sex differences. Results: We found no significant changes in the frequency of cannabis use using either of the interruption time points. However, among the subsample who had used cannabis, there was evidence of increasing CUD severity post-legalization of edibles, as well as an overall decreasing trend in readiness to quit over time. Stratified analyses also suggested possible sex differences in frequency of cannabis use, CUD severity, and readiness to quit. Conclusions: Results point to some small but potentially important impacts of recreational cannabis legalization that may only continue with time. Nevertheless, there is a need to continue to monitor cannabis use trends over time to understand any potential lagged effects.

FONDUE: Robust resolution-invariant denoising of MR Images using Nested UNets

Abstract Recent human magnetic resonance imaging (MRI) studies continually push the boundaries of spatial resolution as a means to enhance levels of neuroanatomical detail and increase the accuracy and sensitivity of derived brain morphometry measures. However, acquisitions required to achieve these resolutions have a higher noise floor, potentially impacting segmentation and morphometric analysis results. This study proposes a novel, fast, robust, and resolution-invariant deep learning method to denoise structural human brain MRIs. We explore denoising of T1-weighted (T1w) brain images from varying field strengths (1.5T to 7T), voxel sizes (1.2mm to 250µm), scanner vendors (Siemens, GE, and Phillips), and diseased and healthy participants from a wide age range (young adults to aging individuals). Our proposed Fast-Optimized Network for Denoising through residual Unified Ensembles (FONDUE) method demonstrated stable denoising capabilities across multiple resolutions with performance on par or superior to the state-of-the-art methods while being several orders of magnitude faster at low relative cost when using a dedicated Graphics Processing Unit (GPU). FONDUE achieved the best performance on at least one of the four denoising-performance metrics on all the test datasets used, showing its generalization capabilities and stability. Due to its high-quality performance, robustness, fast execution times, and relatively low-GPU memory requirements, as well as its open-source public availability, FONDUE can be widely used for structural MRI denoising, especially in large-cohort studies. We have made the FONDUE repository and all training and evaluation scripts as well as the trained weights available at https://github.com/waadgo/FONDUE.

Combined Conjoint Analysis and Cluster Analysis in Segmentation of College Student Housing Preferences (Study of Statistics Students at Universitas Brawijaya Class of 2020-2023)

Combined Conjoint Analysis and Cluster Analysis in Segmentation of College Student Housing Preferences (Study of Statistics Students at Universitas Brawijaya Class of 2020-2023)

Morphometric analysis and tortuosity typing of the large intestine segments on computed tomography colonography with artificial intelligence

Background:Morphological properties such as length and tortuosity of the large intestine segments play important roles, especially in interventional procedures like colonoscopy. Objective:Using computed tomography (CT) colonoscopy images, this study aimed to examine the morphological features of the colon's anatomical sections and investigate the relationship of these sections with each other or with age groups. The shapes of the transverse colon were analyzed using artificial intelligence. Materials and Methods:The study was conducted as a two- and three-dimensional examination of CT colonography images of people between 40 and 80 years old, which were obtained retrospectively. An artificial intelligence algorithm (YOLOv8) was used for shape detection on 3D colon images. Results:160 people with a mean age of 89 men and 71 women included in the study was 57.79±8.55 and 56.55±6.60, respectively, and there was no statistically significant difference (p=0.24). The total colon length was 166.11±25.07 cm for men and 158.73±21.92 cm for women, with no significant difference between groups (p=0.12). As a result of the training of the model Precision, Recall, and mAP were found to be 0.8578, 0.7940, and 0.9142, respectively. Conclusion:The study highlights the importance of understanding the type and morphology of the large intestine for accurate interpretation of CT colonography results and effective clinical management of patients with suspected large intestine abnormalities. Furthermore, this study showed that 88.57% of the images in the test data set were detected correctly and that AI can play an important role in colon typing.

The correlation between left atrium voltage mapping and 3D late gadolinium enhancement cardiac magnetic resonance imaging findings in naive AF ablation candidate

Abstract Introduction The extent of the efficacy of late gadolinium enhancement cardiac MR (LGE-CMR) in depicting left atrial (LA) fibrosis in atrial fibrillation (AF) patients, compared to invasive Electroanatomical Mapping (EAM), is ongoing research field, while the highest degree of accuracy found when using ADAS program. Earlier studies focused mainly on post-ablation patients, employing segmentation (quality) and point-by-point (PBP) comparison methods. The non-invasive LGE-CMR-based fibrosis map shows promise for preprocedural planning and real-time guidance. Aim Evaluate LGE-CMR-based LA fibrosis precision in ablation-naïve AF patients using ADAS software, comparing it to the gold standard EAM using CARTO-3, in both qualitative and quantitative methods. Methods Patients planned for first CARTO-based AF ablation, undergoing pre-ablation LGE-CMR. 3D substrate atrial maps were generated via ADAS based on LGE-CMR (CMR-fib) and via CARTO as EAM. Normal range LA voltage was defined by Image Intensity Ratio of 1.2-1.32 on ADAS and by 0.2-0.5mV on Carto. Comparison methods, qualitative segmentation and PBP quantitative, with EAM serving as the gold standard. Results 24 naive patients included in the study (mean age 63.5 ± 10.9 yrs; 7 females, 15 paroxysmal AF, 17 maps during sinus). Segmental qualitative analysis (384 segments) showed 77% scarred segments, predominantly small scars (up to ⅓ segment). Compared with EAM, the CMR had 68.4% agreement, with 80.4% sensitivity, 78% PPV, 36.6% specificity, 32.6% NPV , kappa 0.139 AUC 0.567. Better agreement was found for dense scar. PBP quantitative comparison (41,345 points) demonstrated 50% scarred points, with 89% accuracy between EAM and CMR, with 49.6% sensitivity, 99.7% specificity, 99.5% PPV, and 73.5% NPV kappa 0.53, AUC 0.747. In both methods, agreement was worse for LA roof and best for AP and septal wall. Conclusion LGE-CMR tends to underestimate scar presence in naive patients compared to EAM, potentially due to baseline voltage scars, which are less dense compared to iatrogenic scar, the voltage criteria for scar in literature. Sensitivity is higher in segmental comparison, while specificity is superior in PBP, consistent with expectations of minimizing the size of comparison (from a segment to point). Hence, qualitative segmental method is better when assessing overall scarring, while PBP for assessing smaller specific areas. PBP comparisons exhibit less bias than segmental comparisons, which are overly sensitive to small scars. The diminished reliability of the LA roof is probably due to the margin of the CMR scan. Our study result regarding low sensitivity and high specificity of PBP aligns with a prior study investigating naïve patients through PBP comparisons, highlighting the need for a larger-scale study to assess LGE-CMR accuracy, considering various wall thicknesses and establishing scar thresholds on ADAS and CARTO software, for ablation-naïve patients with LA body scars.PBP projection on LA bodyAUC for PBP comprasion

Aortic integral distensibility based on the auto-segmented dynamic motion of the aortic wall

Abstract Background Aortic stiffness is important in cardiovascular diseases and predicting outcomes. Echocardiography is a widely used noninvasive imaging modality for assessing aortic stiffness, but its accuracy can be limited by the low spatial resolution of ultrasound-based images and the subjectivity of manual measurements of aortic dimensions. Automated segmentation analysis can provide a more accurate and objective measure. Objective An automated algorithm and software have been developed for segmenting the aortic wall. A new measurement technique called "Aortic Integral Distensibility (AID)" has been formulated using this framework. This method overcomes limitations of traditional method focusing solely on the two positions of Aortic Distensibility (AD). Method In this particular investigation, 112 participants were subjected to echocardiography in order to quantify the dynamics of the aortic wall. An automated algorithm was devised to delineate the aortic wall by utilizing an M-mode echocardiography scan. The statistical analysis encompassed the measurement of AD and AID before and after the age of 65 group. This analysis was conducted considering various risk factors, including age, gender, weight, BMI, smoking, and blood pressure. Additionally, clinical parameters, specifically AIx @75 (Augmentation Index) and Framingham Risk Score (FRS), were evaluated as well. Inter-rater reliability was conducted between the traditional AD and the newly implemented AID. Results The results indicate that the group under 65 had more distensibility than the group over 65, and AID measurements were slightly higher than AD measurements. SBP showed a strong correlation with AID, rather than AD. AIx @75 and FRS had a negative relationship with distensibility. In the 65 years or older group, there was a significant negative correlation observed between AIx @75 and AID (r = -0.4, p = 0.012). Furthermore, a strong correlation was also observed between FRS and AID (r = -0.53, p = 0.002). Bland-Altman analysis demonstrated that the automated methodology had better reproducibility and less variability in distensibility measurements than the manual methodology. Conclusion The study suggests that AID could be valuable for assessing aortic stiffness. AID could help clinicians diagnose and manage cardiovascular diseases more accurately. The automatic approach provides reliable measurements for aortic distensibility and strain, which has clinical implications.Schematic Chart of the Study Process

Identification and validation of ventricular rhythmic risk subgroups in hypertrophic cardiomyopathy by clustering analysis including left ventricular strain analysis

Abstract Background The excess mortality in hypertrophic cardiomyopathy (HCM) patients is mainly attributed to the occurrence of ventricular arrhythmia (VA).The prediction of VA remains challenging and could be improved. Purpose The study aimed to characterize the VA risk profile in HCM patients through clustering analysis combining conventional parameters with information derived from left ventricular longitudinal strain analysis (LV-LS). Methods 434 HCM patients (65% men, mean age 56 years) were retrospectively included from two referral centers and followed longitudinally (mean duration 6 years). The validation cohort included 177 HCM patients from an other tertiary French center. Mechanical and temporal parameters were automatically extracted from the LV-LS segmental curves of each patient in addition to conventional clinical and imaging data. A total of 287 features were analyzed using a clustering approach (k-means). The first endpoint for VA included suspected SCD, aborted cardiac arrest, appropriate ICD therapy (AIT), sustained ventricular tachycardia (SVT) and non-sustained ventricular tachycardia (NSVT) during follow-up. Results From the derivation cohort, 4 clusters were identified with a higher rhythmic risk for clusters 1 and 4 (VA rates of 26%(28/108), 13%(13/97), 12%(14/120), and 31%(34/109) for cluster 1,2,3 and 4 respectively) (Figure 1). These 4 clusters differed mainly by the LV mechanics. Patients from cluster 4 had a severe and homogeneous decrease of myocardial deformation (global longitudinal strain (GLS) -11%, normal value ≥ -20%) associated with LV and left atrium (LA) remodeling (left atrial volume index (LAVI) 46.6 vs. 41.5 ml/m², p=0.04 and LVEF 59.7 vs. 66.3%, p &amp;lt; 0.001) and impaired exercise capacity (% predicted peak work 58.6 vs. 69.5%; p= 0.025). Patients from cluster 1 showed a marked deformation delay and temporal dispersion on the segmental analysis associated with a moderate decrease of the GLS (-15.3%; p &amp;lt;0.0001 for GLS comparison between clusters). Patients from clusters 2 and 3 had a small GLS decrease (GLS -17.2 and -16.3%, respectively) with a less severe phenotype for cluster 2 and older patients for cluster 3 (mean age 62.1 vs. 54.1 years; p &amp;lt; 0.0001). The clustering analysis in the validation population resulted in the creation of 4 clusters overlapping the derivation cohort with similar characteristics (Figure 2). Clusters 1’ and 4’ had a higher incidence of ventricular arrhythmia with a VA rate of 22%(5/23), 18%(16/88), 0%(0/17), and 20%(10/49) for clusters 1’,2’,3’ and 4’ respectively. Conclusion Machine-learning-based cluster analysis processing LV-LS parameters in HCM patients identified 4 clusters with specific LV-strain patterns and different rhythmic risk levels. In the future, the automatic extraction and analysis of LV strain parameters could help to improve the risk stratification for SCD in HCM patients.Clustering analysisExternal validation

Non-linear relationship between soluble interleukin-2 receptor and prognosis of diffuse large B-cell lymphoma.

Despite an emphasis on the prognostic impact of serum soluble interleukin-2 receptor (sIL-2R) at diagnosis in patients with diffuse large B-cell lymphoma (DLBCL), whether the prognostic impact of elevated sIL-2R is linear remains unclear. To verify the presence of a non-linear association between sIL-2R level at diagnosis and overall survival (OS) in patients with newly diagnosed DLBCL, we conducted a multi-center, observational retrospective study. Among 488 analyzable patients, Cox proportional hazards modeling identified serum sIL-2R level at diagnosis as an independent predictor of OS. Multivariate Cox hazard modeling with restricted cubic spline model demonstrated that the relationship between serum sIL-2R level and OS was clearly non-linear (P for effect of sIL-2R = 0.002; P for non-linearity = 0.015). Mortality risk increased gradually as sIL-2R levels increased and plateaued at approximately 5,000 U/mL. Segmented regression analysis revealed that the trend in negative prognostic impact from a gradual increase in serum sIL-2R level changed significantly, with a breakpoint at approximately 2,000 U/mL. Multivariate receiver operating characteristic curves showed a significant improvement in prediction ability when serum sIL-2R level was added to the International Prognostic Index (IPI). Serum sIL-2R level at diagnosis was not only a prognostic factor, but also improved predictive accuracy for OS when incorporated with the IPI. However, the negative correlation between increasing sIL-2R and prognosis was non-linear.