Segmentation Analysis Research Articles

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)

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 < 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 <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 < 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.

Detecting anomalies in currency market of BRICS countries: insights into emerging economies

PurposeThe primary motive of the research paper is to investigate the efficiency of currency market of emerging economies (BRICS countries), by analyzing the presence and consistency of calendar anomalies – specifically the day-of-the-week (DOW) effect, the January effect and the Turn-of-the-month (TOM) effect. Daily data of around 23 years and 4 months were examined for the purpose of study. Segmented data of 8-year intervals were also analyzed to observe the changes in the pattern over a period. The findings are intended to offer insights into market behaviors and potential trading strategies for astute traders.Design/methodology/approachThe study employed a quantitative research design utilizing ordinary least squares regression with dummy variables and Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) (1,1) model. To study the calendar anomalies, the daily closing price of five currency pairs has been taken from Bloomberg’s software. The Kruskal–Wallis test was conducted to validate and check the robustness of analysis.FindingsThere are mixed results regarding calendar anomalies in the BRICS currency markets. Analysis of aggregate data revealed that DOW effect is present in all the currencies except USDZAR, with Monday showing positive return. The segmented analysis showed the presence of DOW effect in USDCNY and USDINR, while other currencies lacked consistent patterns. The January effect was evident for Indian Rupees and Chinese Yuan but not for other currencies. TOM effect was present only in Chinese Yuan. Overall, the Indian Rupee and Chinese Yuan displayed inefficiencies, indicating potential for trading strategies, while other currencies appeared efficient and lacked consistent patterns.Originality/valueThe literature on currency pricing anomalies is sparse, particularly in the context of developing and underdeveloped economies. While some research exists on anomalies within the currencies of developed nations, there is a significant gap in studies focusing on emerging economies. This paper seeks to address this deficiency by investigating the presence of calendar anomalies in the currencies of BRICS countries, providing new insights into the behaviors of these emerging economies.

Pretrained U-Net: in-depth analysis of binary image segmentation in underwater marine environment

Pretrained U-Net: in-depth analysis of binary image segmentation in underwater marine environment

Defining modern iatrogenic flatback syndrome: examination of segmental lordosis in short lumbar fusion patients undergoing thoracolumbar deformity correction.

Understanding the mechanism and extent of preoperative deformity in revision procedures may provide data to prevent future failures in lumbar spinal fusion patients. ASD patients without prior spine surgery (PRIMARY) and with prior short (SHORT) and long (LONG) fusions were included. SHORT patients were stratified into modes of failure: implant, junctional, malalignment, and neurologic. Baseline demographics, spinopelvic alignment, offset from alignment targets, and patient-reported outcome measures (PROMs) were compared across PRIMARY and SHORT cohorts. Segmental lordosis analyses, assessing under-, match, or over-correction to segmental and global lordosis targets, were performed by SRS-Schwab coronal curve type and construct length. Among 785 patients, 430 (55%) were PRIMARY and 355 (45%) were revisions. Revision procedures included 181 (23%) LONG and 174 (22%) SHORT corrections. SHORT modes of failure included 27% implant, 40% junctional, 73% malalignment, and/or 28% neurologic. SHORT patients were older, frailer, and had worse baseline deformity (PT, PI-LL, SVA) and PROMs (NRS, ODI, VR-12, SRS-22) compared to primary patients (p < 0.001). Segmental lordosis analysis identified 93%, 88%, and 62% undercorrected patients at LL, L1-L4, and L4-S1, respectively. SHORT patients more often underwent 3-column osteotomies (30% vs. 12%, p < 0.001) and had higher ISSG Surgical Invasiveness Score (87.8 vs. 78.3, p = 0.006). Nearly half of adult spinal deformity surgeries were revision fusions. Revision short fusions were associated with sagittal malalignment, often due to undercorrection of segmental lordosis goals, and frequently required more invasive procedures. Further initiatives to optimize alignment in lumbar fusions are needed to avoid costly and invasive deformity corrections. IV: Diagnostic: individual cross-sectional studies with consistently applied reference standard and blinding.

Anthropometric Profile and Position-Specific Changes in Segmental Body Composition of Professional Football Players Throughout a Training Period.

Body and anthropometric profiles of football players vary depending on the physiological and technical demands imposed by different positions. The aim of this study was to evaluate the body composition of professional soccer players in relation to their position on the field during a training macrocycle. The Direct Segmental Multi-Frequency Bioelectrical Impedance Analysis method was used to analyze 58 players at six key moments of the macrocycle. The results show that body profiles are adjusted to the specific demands of each position. Midfielders showed the lowest muscle mass, while defenders showed many notable changes. In general, as the season progressed, all field players experienced an increase in trunk body fat. Fat and lean mass values of goalkeepers differed greatly from the rest. The greatest variations in body composition were observed during pre-season and transition in relation to variations in training load and competitive intensity. The results suggest that the phase of the macrocycle has a greater influence on these variations, although the physical characteristics of each position are relevant. Understanding these dynamics allows for the design of more personalized and efficient training programs to optimize the performance of footballers according to their roles and each stage of the season.

The U.S. Carbonated Beverages Market: A Competitive Profile

This is the twenty-second paper—and the 23rd and 24th studies--that follow the footsteps of twenty-two studies that have tried to analyze the competitive profiles of U.S. consumer markets: Men’s Shaving Cream, Beer, Shampoo, Shredded/Grated Cheese, Refrigerated Orange Juice, Men’s Razor-Blades, Women’s Razor-Blades, Toothpaste, Canned Soup, Coffee, Potato Chips, Alkaline AA Battery, Facial Tissue, Toilet Paper, Paper Towel, Disposable Diapers, Sanitary Pads, Automatic-Dishwasher Detergent, Hand-Dishwashing Detergent, Household Liquid Non-Disinfectant Cleaner, Heavy-Duty Liquid Laundry Detergent, and Deodorant.Michael Porter associates high market share with cost leadership strategy, which is based on the idea of competing on a price that is lower than that of the competition.However, customer-perceived quality—not low cost—should be the underpinning of competitive strategy, because it is far more vital to long-term competitive position and profitability than any other factor. So, a superior alternative is to offer better quality vs. the competition.In most consumer markets, a business seeking market share leadership should try to serve the middle class by competing in the mid-price segment; and offering quality better than that of the competition: at a price somewhat higher to signify an image of quality, and to ensure that the strategy is both profitable and sustainable in the long run. The middle class is the socio-economic segment that represents about 40% of households in America.Quality, however, is a complex concept, consumers generally find difficult to understand. So, they often use relative price, and a brand’s reputation, as a symbol of quality.The U.S. Carbonated Beverages is a mega-market that had retail sales of $14,178 million in 2008. It had six segments: Cola Regular, Cola Diet, Non-Cola Regular, Non-Cola Diet, Lemon-Lime Regular, and Lemon-Lime Diet. We have combined them in two studies: Cola Regular and Diet Carbonated Beverages, and Non-Cola--Lemon-Lime Regular Carbonated Beverages, with 2008 retail sales, respectively, of $6,639 million, and $5,415 million.For both markets we have focused our analysis on the 12-Oz size because it was the most popular.Using Hierarchical Cluster Analysis, we tested two hypotheses: (I) That the market leader is likely to compete in the mid-price segment, and that (II) Its unit price is likely to be higher than that of the nearest competition.For the Cola Carbonated Beverages market, the data did not support Hypothesis I for both 2008 and 2007, because Coca-Cola Classic Regular, the market leader, was a member of the super-premium segment.Similarly, the data did not support Hypothesis II for both 2008 and 2007 either, because Pepsi Regular, the runner-up, had a unit price that was higher than that of the market leader, Coca-Cola Classic Regular.For the Regular Non-Cola--Lemon-Lime Carbonated Beverages market the data also did not support Hypothesis I because Mountain Dew, the market leader, was a member of the premium segment for both 2008 and 2007.However, the data did support Hypothesis II, because, Dr. Pepper, the runner-up, had a unit price that was lower than that of the market leader, Mountain Dew for 2008 and 2007.We found that relative price was a strategic variable, as we have hypothesized.We also discovered two strategic groups in the Cola Carbonated Beverages market, and four in the Non-Cola--Lemon-Lime Regular Carbonated Beverages market. A pattern is emerging in price-quality segmentation analysis. In thirteen of the twenty-four studies—that exclude Men’s Razor-Blades, Women’s Razor-Blades, Coffee, Toilet Paper, Paper Towels, Disposable Diapers, Sanitary Pads, Liquid Heavy-Duty Laundry Detergent, Deodorants, Cola Carbonated Beverages, and Regular Non-Cola--Lemon-Lime Carbonated Beverages—the market leader was found to be a member of the mid-price segment, as we have hypothesized.Also, results in eleven markets supported Hypothesis II.

Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation.

- Accurate detection, segmentation, and volumetric analysis of brain lesions are essential in neuro-oncology. Artificial intelligence (AI)-based models have improved the efficiency of these processes. This study evaluated an AI-based module for detecting and segmenting brain metastases, comparing it with manual detection and segmentation. - MRIs from 51 patients treated with Gamma Knife radiosurgery for brain metastases were analyzed. Manual lesion identification and contouring on Leksell Gamma Plan at the time of treatment served as the gold standard. The same MRIs were processed through an AI-based module (Brainlab Smart Brush), and lesion detection and volumes were compared. Discrepancies were analyzed to identify possible sources of error. - Among 51 patients, 359 brain metastases were identified. The AI module achieved a sensitivity of 79.2% and a positive predictive value of 95.6%, compared to a 93.3% sensitivity for manual detection. However, for lesions > 0.1cc, the AI's sensitivity rose to 97.5%, surpassing manual detection at 93%. Volumetric agreement between AI and manual segmentations was high (Spearman's ρ = 0.997, p < 0.001). Most lesions missed by the AI (53.8%) were near anatomical structures that complicated detection. - The AI module demonstrated higher sensitivity than manual detection for metastases larger than 0.1cc, with robust volumetric accuracy. However, human expertise remains critical for detecting smaller lesions, especially near complex anatomical areas. AI offers significant potential to enhance neuro-oncology practice by improving the efficiency and accuracy of lesion management.

Towards imagined speech: Identification of brain states from EEG signals for BCI-based communication systems

BackgroundThe electroencephalogram (EEG) based brain-computer interface (BCI) system employing imagined speech serves as a mechanism for decoding EEG signals to facilitate control over external devices or communication with the external world at the moment the user desires. To effectively deploy such BCIs, it is imperative to accurately discern various brain states from continuous EEG signals when users initiate word imagination. New methodThis study involved the acquisition of EEG signals from 15 subjects engaged in four states: resting, listening, imagined speech, and actual speech, each involving a predefined set of 10 words. The EEG signals underwent preprocessing, segmentation, spatio-temporal and spectral analysis of each state, and functional connectivity analysis using the phase locking value (PLV) method. Subsequently, five features were extracted from the frequency and time-frequency domains. Classification tasks were performed using four machine learning algorithms in both pair-wise and multiclass scenarios, considering subject-dependent and subject-independent data. ResultsIn the subject-dependent scenario, the random forest (RF) classifier achieved a maximum accuracy of 94.60 % for pairwise classification, while the artificial neural network (ANN) classifier achieved a maximum accuracy of 66.92 % for multiclass classification. In the subject-independent scenario, the random forest (RF) classifier achieved maximum accuracies of 81.02 % for pairwise classification and 55.58 % for multiclass classification. Moreover, EEG signals were classified based on frequency bands and brain lobes, revealing that the theta (θ) and delta (δ) bands, as well as the frontal and temporal lobes, are sufficient for distinguishing between brain states. ConclusionThe findings promise to develop a system capable of automatically segmenting imagined speech segments from continuous EEG signals.

Foundation model for efficient biological discovery in single-molecule data.

Modern data-intensive techniques offer ever deeper insights into biology, but render the process of discovery increasingly complex. For example, exploiting the unique ability of single-molecule fluorescence microscopy (SMFM)1-5. to uncover rare but critical intermediates often demands manual inspection of time traces and iterative ad hoc approaches that are difficult to systematize. To facilitate systematic and efficient discovery from SMFM data, we introduce META-SiM, a transformer-based foundation model pre-trained on diverse SMFM analysis tasks. META-SiM achieves high performance-rivaling best-in-class algorithms-on a broad range of analysis tasks including trace selection, classification, segmentation, idealization, and stepwise photobleaching analysis. Additionally, the model produces high-dimensional embedding vectors that encapsulate detailed information about each trace, which the web-based META-SiM Projector (https://www.simol-projector.org) casts into lower-dimensional space for efficient whole-dataset visualization, labeling, comparison, and sharing. Combining this Projector with the objective metric of Local Shannon Entropy enables rapid identification of condition-specific behaviors, even if rare or subtle. As a result, by applying META-SiM to an existing single-molecule Förster resonance energy transfer (smFRET) dataset6, we discover a previously unobserved intermediate state in pre-mRNA splicing. META-SiM thus removes bottlenecks, improves objectivity, and both systematizes and accelerates biological discovery in complex single-molecule data.

Feasibility of shortening scan duration of 18F-FDG myocardial metabolism imaging using a total-body PET/CT scanner

PurposeTo evaluate 18F-FDG myocardial metabolism imaging (MMI) using a total-body PET/CT scanner and explore the feasible scan duration to guide the clinical practice.MethodsA retrospective analysis was conducted on 41 patients who underwent myocardial perfusion-metabolism imaging to assess myocardial viability. The patients underwent 18F-FDG MMI with a total-body PET/CT scanner using a list-mode for 600 s. PET data were trimmed and reconstructed to simulate images of 600-s, 300-s, 120-s, 60-s, and 30-s acquisition time (G600-G30). Images among different groups were subjectively evaluated using a 5-point Likert scale. Semi-quantitative evaluation was performed using standardized uptake value (SUV), myocardial to background activity ratio (M/B), signal to noise ratio (SNR), contrast to noise ratio (CNR), contrast ratio (CR), and coefficient of variation (CV). Myocardial viability analysis included indexes of Mismatch and Scar. G600 served as the reference.ResultsSubjective visual evaluation indicated a decline in the scores of image quality with shortening scan duration. All the G600, G300, and G120 images were clinically acceptable (score ≥ 3), and their image quality scores were 4.9 ± 0.3, 4.8 ± 0.4, and 4.5 ± 0.8, respectively (P > 0.05). Moreover, as the scan duration reduced, the semi-quantitative parameters M/B, SNR, CNR, and CR decreased, while SUV and CV increased, and significant difference was observed in G300-G30 groups when comparing to G600 group (P < 0.05). For myocardial viability analysis of left ventricular and coronary segments, the Mismatch and Scar values of G300-G30 groups were almost identical to G600 group (ICC: 0.968-1.0, P < 0.001).ConclusionSufficient image quality for clinical diagnosis could be achieved at G120 for MMI using a total-body PET/CT scanner, while the image quality of G30 was acceptable for myocardial viability analysis.

Knot data analysis using multiscale Gauss link integral

In the past decade, topological data analysis has emerged as a powerful algebraic topology approach in data science. Although knot theory and related subjects are a focus of study in mathematics, their success in practical applications is quite limited due to the lack of localization and quantization. We address these challenges by introducing knot data analysis (KDA), a paradigm that incorporates curve segmentation and multiscale analysis into the Gauss link integral. The resulting multiscale Gauss link integral (mGLI) recovers the global topological properties of knots and links at an appropriate scale and offers a multiscale geometric topology approach to capture the local structures and connectivities in data. By integration with machine learning or deep learning, the proposed mGLI significantly outperforms other state-of-the-art methods across various benchmark problems in 13 intricately complex biological datasets, including protein flexibility analysis, protein-ligand interactions, human Ether-à-go-go-Related Gene potassium channel blockade screening, and quantitative toxicity assessment. Our KDA opens a research area-knot deep learning-in data science.

Tectonic Activity Analysis of the Laji-Jishi Shan Fault Zone: Insights from Geomorphic Indices and Crustal Deformation Data

Fault segmentation plays a critical role in assessing seismic hazards, particularly in tectonically complex regions. The Laji-Jishi Shan Fault Zone (LJSFZ), located on the northeastern margin of the Tibetan Plateau, is a key structure that accommodates regional tectonic stress. This study integrates geomorphic indices, cross-fault deformation rate profiles, and 3D crustal electrical structure data to analyze the varying levels of tectonic activity across different segments of the LJSFZ. We extracted 160 drainage basins along the strike of the LJSFZ from a 30 m resolution digital elevation model and calculated geomorphic indices, including the hypsometric integral (HI), stream length-gradient index (SL), and channel steepness index (ksn), to assess the variations in tectonic activity intensity along the strike of the LJSFZ. The basins were categorized based on river flow directions to capture potential differences across the fault zone. Our results show that the eastern basins of the LJSFZ exhibit the strongest tectonic activity, demonstrated by significantly higher SL and ksn values compared to other regions. A detailed segmentation analysis along the northern Laji Shan Fault and eastern Jishi Shan Fault identified distinct fault segments characterized by variations in SL and ksn indices. Segments with high SL values (&gt;500) correspond to higher crustal uplift rates (~3 mm/year), while segments with lower SL values exhibit lower uplift rates (~2 mm/year), as confirmed by cross-fault deformation profiles derived from GNSS and InSAR data. This correlation demonstrates that geomorphic indices effectively reflect fault activity intensity. Additionally, 3D crustal electrical structure data further indicate that highly conductive mid- to lower-crustal materials originating from the interior of the Tibetan Plateau are obstructed at segment L3 of the LJSFZ. This obstruction leads to localized intense uplift and enhanced fault activity. These findings suggest that while the regional stress–strain pattern of the northeastern Tibetan Plateau is the primary driver of the segmented activity along the Laji-Jishi Shan belt, the direction of localized crustal flow is a critical factor influencing fault activity segmentation.