Meta-analysis of machine learning models for the diagnosis of central precocious puberty based on clinical, hormonal (laboratory) and imaging data.

Background: Central precocious puberty (CPP) is a common endocrine disorder in children, and its diagnosis primarily relies on the gonadotropin-releasing hormone (GnRH) stimulation test, which is expensive and time-consuming. With the widespread application of artificial intelligence in medicine, some studies have utilized clinical, hormonal (laboratory) and imaging data-based machine learning (ML) models to identify CPP. However, the results of these studies varied widely and were challenging to directly compare, mainly due to diverse ML methods. Therefore, the diagnostic value of clinical, hormonal (laboratory) and imaging data-based ML models for CPP remains elusive. The aim of this study was to investigate the diagnostic value of ML models based on clinical, hormonal (laboratory) and imaging data for CPP through a meta-analysis of existing studies. Methods: We conducted a comprehensive search for relevant English articles on clinical, hormonal (laboratory) and imaging data-based ML models for diagnosing CPP, covering the period from the database creation date to December 2023. Pooled sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), summary receiver operating characteristic (SROC) curve, and area under the curve (AUC) were calculated to assess the diagnostic value of clinical, hormonal (laboratory) and imaging data-based ML models for diagnosing CPP. The I2 test was employed to evaluate heterogeneity, and the source of heterogeneity was investigated through meta-regression analysis. Publication bias was assessed using the Deeks funnel plot asymmetry test. Results: Six studies met the eligibility criteria. The pooled sensitivity and specificity were 0.82 (95% confidence interval (CI) 0.62-0.93) and 0.85 (95% CI 0.80-0.90), respectively. The LR+ was 6.00, and the LR- was 0.21, indicating that clinical, hormonal (laboratory) and imaging data-based ML models exhibited an excellent ability to confirm or exclude CPP. Additionally, the SROC curve showed that the AUC of the clinical, hormonal (laboratory) and imaging data-based ML models in the diagnosis of CPP was 0.90 (95% CI 0.87-0.92), demonstrating good diagnostic value for CPP. Conclusion: Based on the outcomes of our meta-analysis, clinical and imaging data-based ML models are excellent diagnostic tools with high sensitivity, specificity, and AUC in the diagnosis of CPP. Despite the geographical limitations of the study findings, future research endeavors will strive to address these issues to enhance their applicability and reliability, providing more precise guidance for the differentiation and treatment of CPP.

Baseline phenotypes with preserved ß-cell function and high insulin concentrations have the best improvements in glucose tolerance after weight loss: results from the prospective DEXLIFE and EGIR-RISC studies.

BACKGROUND: Weight loss and lifestyle intervention improve glucose tolerance delaying the onset of type 2 diabetes (T2D), but individual responses are highly variable. Determining the predictive factors linked to the beneficial effects of weight loss on glucose tolerance could provide tools for individualized prevention plans. Thus, the aim was to investigate the relationship between pre-intervention values of insulin sensitivity and secretion and the improvement in glucose metabolism after weight loss. METHODS: In the DEXLIFE cohort (373 individuals at high risk of T2D, assigned 3:1 to a 12-week lifestyle intervention or a control arm, Trial Registration: ISRCTN66987085), K-means clustering and logistic regression analysis were performed based on pre-intervention indices of insulin sensitivity, insulin secretion (AUC-I), and glucose-stimulated insulin response (ratio of incremental areas of insulin and glucose, iAUC I/G). The response to the intervention was evaluated in terms of reduction of OGTT-glucose concentration. Clusters' validation was done in the prospective EGIR-RISC cohort (n = 1538). RESULTS: Four replicable clusters with different glycemic and metabolomic profiles were identified. Individuals had similar weight loss, but improvement in glycemic profile and ß-cell function was different among clusters, highly depending on pre-intervention insulin response to OGTT. Pre-intervention high insulin response was associated with the best improvement in AUC-G, while clusters with low AUC-I and iAUC I/G showed no beneficial effect of weight loss on glucose control, as also confirmed by the logistic regression model. CONCLUSIONS: Individuals with preserved ß-cell function and high insulin concentrations at baseline have the best improvement in glucose tolerance after weight loss.

A generalizable and easy-to-use COVID-19 stratification model for the next pandemic via immune-phenotyping and machine learning.

Introduction: The coronavirus disease 2019 (COVID-19) pandemic has affected billions of people worldwide, and the lessons learned need to be concluded to get better prepared for the next pandemic. Early identification of high-risk patients is important for appropriate treatment and distribution of medical resources. A generalizable and easy-to-use COVID-19 severity stratification model is vital and may provide references for clinicians. Methods: Three COVID-19 cohorts (one discovery cohort and two validation cohorts) were included. Longitudinal peripheral blood mononuclear cells were collected from the discovery cohort (n = 39, mild = 15, critical = 24). The immune characteristics of COVID-19 and critical COVID-19 were analyzed by comparison with those of healthy volunteers (n = 16) and patients with mild COVID-19 using mass cytometry by time of flight (CyTOF). Subsequently, machine learning models were developed based on immune signatures and the most valuable laboratory parameters that performed well in distinguishing mild from critical cases. Finally, single-cell RNA sequencing data from a published study (n = 43) and electronic health records from a prospective cohort study (n = 840) were used to verify the role of crucial clinical laboratory and immune signature parameters in the stratification of COVID-19 severity. Results: Patients with COVID-19 were determined with disturbed glucose and tryptophan metabolism in two major innate immune clusters. Critical patients were further characterized by significant depletion of classical dendritic cells (cDCs), regulatory T cells (Tregs), and CD4+ central memory T cells (Tcm), along with increased systemic interleukin-6 (IL-6), interleukin-12 (IL-12), and lactate dehydrogenase (LDH). The machine learning models based on the level of cDCs and LDH showed great potential for predicting critical cases. The model performances in severity stratification were validated in two cohorts (AUC = 0.77 and 0.88, respectively) infected with different strains in different periods. The reference limits of cDCs and LDH as biomarkers for predicting critical COVID-19 were 1.2% and 270.5 U/L, respectively. Conclusion: Overall, we developed and validated a generalizable and easy-to-use COVID-19 severity stratification model using machine learning algorithms. The level of cDCs and LDH will assist clinicians in making quick decisions during future pandemics.

Computational identification and experimental verification of a novel signature based on SARS-CoV-2-related genes for predicting prognosis, immune microenvironment and therapeutic strategies in lung adenocarcinoma patients.

Background: Early research indicates that cancer patients are more vulnerable to adverse outcomes and mortality when infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Nonetheless, the specific attributes of SARS-CoV-2 in lung Adenocarcinoma (LUAD) have not been extensively and methodically examined. Methods: We acquired 322 SARS-CoV-2 infection-related genes (CRGs) from the Human Protein Atlas database. Using an integrative machine learning approach with 10 algorithms, we developed a SARS-CoV-2 score (Cov-2S) signature across The Cancer Genome Atlas and datasets GSE72094, GSE68465, and GSE31210. Comprehensive multi-omics analysis, including assessments of genetic mutations and copy number variations, was conducted to deepen our understanding of the prognosis signature. We also analyzed the response of different Cov-2S subgroups to immunotherapy and identified targeted drugs for these subgroups, advancing personalized medicine strategies. The expression of Cov-2S genes was confirmed through qRT-PCR, with GGH emerging as a critical gene for further functional studies to elucidate its role in LUAD. Results: Out of 34 differentially expressed CRGs identified, 16 correlated with overall survival. We utilized 10 machine learning algorithms, creating 101 combinations, and selected the RFS as the optimal algorithm for constructing a Cov-2S based on the average C-index across four cohorts. This was achieved after integrating several essential clinicopathological features and 58 established signatures. We observed significant differences in biological functions and immune cell statuses within the tumor microenvironments of high and low Cov-2S groups. Notably, patients with a lower Cov-2S showed enhanced sensitivity to immunotherapy. We also identified five potential drugs targeting Cov-2S. In vitro experiments revealed a significant upregulation of GGH in LUAD, and its knockdown markedly inhibited tumor cell proliferation, migration, and invasion. Conclusion: Our research has pioneered the development of a consensus Cov-2S signature by employing an innovative approach with 10 machine learning algorithms for LUAD. Cov-2S reliably forecasts the prognosis, mirrors the tumor's local immune condition, and supports clinical decision-making in tumor therapies.

The Role of Attention in Category Representation.

Numerous studies have found that selective attention affects category learning. However, previous research did not distinguish between the contribution of focusing and filtering components of selective attention. This study addresses this issue by examining how components of selective attention affect category representation. Participants first learned a rule-plus-similarity category structure, and then were presented with category priming followed by categorization and recognition tests. Additionally, to evaluate the involvement of focusing and filtering, we fit models with different attentional mechanisms to the data. In Experiment 1, participants received rule-based category training, with specific emphasis on a single deterministic feature (D feature). Experiment 2 added a recognition test to examine participants' memory for features. Both experiments indicated that participants categorized items based solely on the D feature, showed greater memory for the D feature, were primed exclusively by the D feature without interference from probabilistic features (P features), and were better fit by models with focusing and at least one type of filtering mechanism. The results indicated that selective attention distorted category representation by highlighting the D feature and attenuating P features. To examine whether the distorted representation was specific to rule-based training, Experiment 3 introduced training, emphasizing all features. Under such training, participants were no longer primed by the D feature, they remembered all features well, and they were better fit by the model assuming only focusing but no filtering process. The results coupled with modeling provide novel evidence that while both focusing and filtering contribute to category representation, filtering can also result in representational distortion.

Federated Fuzzy Clustering for Decentralized Incomplete Longitudinal Behavioral Data.

The use of medical data for machine learning, including unsupervised methods such as clustering, is often restricted by privacy regulations such as the Health Insurance Portability and Accountability Act (HIPAA). Medical data is sensitive and highly regulated and anonymization is often insufficient to protect a patient's identity. Traditional clustering algorithms are also unsuitable for longitudinal behavioral health trials, which often have missing data and observe individual behaviors over varying time periods. In this work, we develop a new decentralized federated multiple imputation-based fuzzy clustering algorithm for complex longitudinal behavioral trial data collected from multisite randomized controlled trials over different time periods. Federated learning (FL) preserves privacy by aggregating model parameters instead of data. Unlike previous FL methods, this proposed algorithm requires only two rounds of communication and handles clients with varying numbers of time points for incomplete longitudinal data. The model is evaluated on both empirical longitudinal dietary health data and simulated clusters with different numbers of clients, effect sizes, correlations, and sample sizes. The proposed algorithm converges rapidly and achieves desirable performance on multiple clustering metrics. This new method allows for targeted treatments for various patient groups while preserving their data privacy and enables the potential for broader applications in the Internet of Medical Things.

Stress responses in surgical trainees during simulation-based training courses in laparoscopy.

BACKGROUND: Simulation-based training courses in laparoscopy have become a fundamental part of surgical training programs. Surgical skills in laparoscopy are challenging to master, and training in these skills induces stress responses in trainees. There is limited data on trainees' stress levels, the stress responses related to training on different laparoscopic simulators, and how previous experiences influence trainees' stress response during a course. This study investigates physiologic, endocrine and self-reported stress responses during simulation-based surgical skills training in a course setting. METHODS: We conducted a prospective observational study of trainees attending basic laparoscopic skills training courses at a national training centre. During the three-day course, participants trained on different laparoscopic simulators: Two box-trainers (the D-box and P.O.P. trainer) and a virtual reality simulator (LAPMentor™). Participants' stress responses were examined through heart rate variability (HRV), saliva cortisol, and the State Trait Anxiety Inventory-6 (STAI-6). The correlation between previous laparoscopic experiences and stress response measurements was explored. RESULTS: Twenty-four surgical trainees were included in the study. Compared to resting conditions, stress measures were significantly higher during simulation-training activity (the D-box (SDNN = 58.5 ± 23.4; LF/HF-ratio = 4.58 ± 2.71; STAI-6 = 12.3 ± 3.9, P < 0.05), the P.O.P trainer (SDNN = 55.7 ± 7.4; RMSSD = 32.4 ± 17.1; STAI-6 = 12.1 ± 3.9, P < 0.05), and the LAPMentor™ (SDNN = 59.1 ± 18.5; RMSSD = 34.3 ± 19.7; LF/HF-ratio = 4.71 ± 2.64; STAI-6 = 9.9 ± 3.0, P < 0.05)). A significant difference in endocrine stress response was seen for the simulation-training activity on the D-box (saliva cortisol: 3.48 ± 1.92, P < 0.05), however, no significant differences were observed between the three simulators. A moderate correlation between surgical experience, and physiologic and endocrine stress response was observed (RMSSD: r=-0.31; SDNN: r=-0.42; SD2/SD1 ratio: r = 0.29; Saliva cortisol: r = 0.46; P < 0.05), and a negative moderate correlation to self-reported stress (r=-0.42, P < 0.05). CONCLUSION: Trainees have a significant higher stress response during simulation-training compared to resting conditions, with no difference in stress response between the simulators. Significantly higher cortisol levels were observed on the D-box, indicating that simulation tasks with time pressure stress participants the most. Trainees with more surgical experience are associated with higher physiologic stress measures, but lower self-reported stress scores, demonstrating that surgical experience influences trainees' stress response during simulation-based skills training courses.

SCB-YOLOv5: a lightweight intelligent detection model for athletes' normative movements.

Intelligent detection of athlete behavior is beneficial for guiding sports instruction. Existing mature target detection algorithms provide significant support for this task. However, large-scale target detection algorithms often encounter more challenges in practical application scenarios. We propose SCB-YOLOv5, to detect standardized movements of gymnasts. First, the movements of aerobics athletes were captured, labeled using the labelImg software, and utilized to establish the athlete normative behavior dataset, which was then enhanced by the dataset augmentation using Mosaic9. Then, we improved the YOLOv5 by (1) incorporating the structures of ShuffleNet V2 and convolutional block attention module to reconstruct the Backbone, effectively reducing the parameter size while maintaining network feature extraction capability; (2) adding a weighted bidirectional feature pyramid network into the multiscale feature fusion, to acquire precise channel and positional information through the global receptive field of feature maps. Finally, SCB-YOLOv5 was lighter by 56.9% than YOLOv5. The detection precision is 93.7%, with a recall of 99% and mAP value of 94.23%. This represents a 3.53% improvement compared to the original algorithm. Extensive experiments have verified that our method. SCB-YOLOv5 can meet the requirements for on-site athlete action detection. Our code and models are available at https://github.com/qingDu1/SCB-YOLOv5 .

Multi-feature, Chinese-Western medicine-integrated prediction model for diabetic peripheral neuropathy based on machine learning and SHAP.

BACKGROUND: Clinical studies have shown that diabetic peripheral neuropathy (DPN) has been on the rise, with most patients presenting with severe and progressive symptoms. Currently, most of the available prediction models for DPN are derived from general clinical information and laboratory indicators. Several Traditional Chinese medicine (TCM) indicators have been utilised to construct prediction models. In this study, we established a novel machine learning-based multi-featured Chinese-Western medicine-integrated prediction model for DPN using clinical features of TCM. MATERIALS AND METHODS: The clinical data of 1581 patients with Type 2 diabetes mellitus (T2DM) treated at the Department of Endocrinology of the First Affiliated Hospital of Anhui University of Chinese Medicine were collected. The data (including general information, laboratory parameters and TCM features) of 1142 patients with T2DM were selected after data cleaning. After baseline description analysis of the variables, the data were divided into training and validation sets. Four prediction models were established and their performance was evaluated using validation sets. Meanwhile, the accuracy, precision, recall, F1 score and area under the curve (AUC) of ROC were calculated using ten-fold cross-validation to further assess the performance of the models. An explanatory analysis of the results of the DPN prediction model was carried out using the SHAP framework based on machine learning-based prediction models. RESULTS: Of the 1142 patients with T2DM, 681 had a comorbidity of DPN, while 461 did not. There was a significant difference between the two groups in terms of age, cause of disease, systolic pressure, HbA1c, ALT, RBC, Cr, BUN, red blood cells in the urine, glucose in the urine, and protein in the urine (p < 0.05). T2DM patients with a comorbidity of DPN exhibited diverse TCM symptoms, including limb numbness, limb pain, hypodynamia, thirst with desire for drinks, dry mouth and throat, blurred vision, gloomy complexion, and unsmooth pulse, with statistically significant differences (p < 0.05). Our results showed that the proposed multi-featured Chinese-Western medicine-integrated prediction model was superior to conventional models without characteristic TCM indicators. The model showed the best performance (accuracy = 0.8109, precision = 0.8029, recall = 0.9060, F1 score = 0.8511, and AUC = 0.9002). SHAP analysis revealed that the dominant risk factors that caused DPN were TCM symptoms (limb numbness, thirst with desire for drinks, blurred vision), age, cause of disease, and glycosylated haemoglobin. These risk factors were exerted positive effects on the DPN prediction models. CONCLUSIONS: A multi-feature, Chinese-Western medicine-integrated prediction model for DPN was established and validated. The model improves early-stage identification of high-risk groups for DPN in the diagnosis and treatment of T2DM, while also providing informative support for the intelligent management of chronic conditions such as diabetes.

Tuberculosis Chest X-Ray Image Retrieval System Using Deep Learning Based Biomarker Predictions.

The world health organization's global tuberculosis (TB) report for 2022 identifies TB, with an estimated 1.6 million, as a leading cause of death. The number of new cases has risen since 2020, particularly the number of new drug-resistant cases, estimated at 450,000 in 2021. This is concerning, as treatment of patients with drug resistant TB is complex and may not always be successful. The NIAID TB Portals program is an international consortium with a primary focus on patient centric data collection and analysis for drug resistant TB. The data includes images, their associated radiological findings, clinical records, and socioeconomic information. This work describes a TB Portals' Chest X-ray based image retrieval system which enables precision medicine. An input image is used to retrieve similar images and the associated patient specific information, thus facilitating inspection of outcomes and treatment regimens from comparable patients. Image similarity is defined using clinically relevant biomarkers: gender, age, body mass index (BMI), and the percentage of lung affected per sextant. The biomarkers are predicted using variations of the DenseNet169 convolutional neural network. A multi-task approach is used to predict gender, age and BMI incorporating transfer learning from an initial training on the NIH Clinical Center CXR dataset to the TB portals dataset. The resulting gender AUC, age and BMI mean absolute errors were 0.9854, 4.03years and 1.67kgm2. For the percentage of sextant affected by lesions the mean absolute errors ranged between 7% to 12% with higher error values in the middle and upper sextants which exhibit more variability than the lower sextants. The retrieval system is currently available from https://rap.tbportals.niaid.nih.gov/find_similar_cxr.

Machine learning models using symptoms and clinical variables to predict coronary artery disease on coronary angiography.

Introduction: Coronary angiography (CAG) is invasive and expensive, while numbers of patients suspected of coronary artery disease (CAD) undergoing CAG results have no coronary lesions. Aim: To develop machine learning algorithms using symptoms and clinical variables to predict CAD. Material and methods: This study was conducted as a cross-sectional study of patients undergoing CAG. We randomly chose 2082 patients from 2602 patients suspected of CAD as the training set, and 520 patients as the test set. We utilized LASSO regression to do feature selection. The area under the receiver operating characteristic curve (AUC), confusion matrix of different thresholds, positive predictive value (PPV) and negative predictive value (NPV) were shown. Support vector machine algorithm performances in 10 folds were conducted in the training set for detecting severe CAD, while XGBoost algorithm performances were conducted in the test set for detecting severe CAD. Results: The algorithm of logistic regression achieved an average AUC of 0.77 in the training set during 10-fold validation and an AUC of 0.75 in the test set. When probability predicted by the model was less than 0.1, 11 patients in the test set (520 patients) were screened out, and NPV reached 90.9%. When probability predicted by the model was less than 0.2, 110 patients in the test set were screened out, and reached 83.6%. Meanwhile, when threshold was set to 0.9, PPV reached 97.4%. When the threshold was set to 0.8, PPV reached 91.5%. Conclusions: Machine learning algorithm using data from hospital information systems could assist in severe CAD exclusion and confirmation, and thus help patients avoid unnecessary CAG.

A review of machine learning-based methods for predicting drug-target interactions.

The prediction of drug-target interactions (DTI) is a crucial preliminary stage in drug discovery and development, given the substantial risk of failure and the prolonged validation period associated with in vitro and in vivo experiments. In the contemporary landscape, various machine learning-based methods have emerged as indispensable tools for DTI prediction. This paper begins by placing emphasis on the data representation employed by these methods, delineating five representations for drugs and four for proteins. The methods are then categorized into traditional machine learning-based approaches and deep learning-based ones, with a discussion of representative approaches in each category and the introduction of a novel taxonomy for deep neural network models in DTI prediction. Additionally, we present a synthesis of commonly used datasets and evaluation metrics to facilitate practical implementation. In conclusion, we address current challenges and outline potential future directions in this research field.

Fully automated deep learning system for osteoporosis screening using chest computed tomography images.

Background: Osteoporosis, a disease stemming from bone metabolism irregularities, affects approximately 200 million people worldwide. Timely detection of osteoporosis is pivotal in grappling with this public health challenge. Deep learning (DL), emerging as a promising methodology in the field of medical imaging, holds considerable potential for the assessment of bone mineral density (BMD). This study aimed to propose an automated DL framework for BMD assessment that integrates localization, segmentation, and ternary classification using various dominant convolutional neural networks (CNNs). Methods: In this retrospective study, a cohort of 2,274 patients underwent chest computed tomography (CT) was enrolled from January 2022 to June 2023 for the development of the integrated DL system. The study unfolded in 2 phases. Initially, 1,025 patients were selected based on specific criteria to develop an automated segmentation model, utilizing 2 VB-Net networks. Subsequently, a distinct cohort of 902 patients was employed for the development and testing of classification models for BMD assessment. Then, 3 distinct DL network architectures, specifically DenseNet, ResNet-18, and ResNet-50, were applied to formulate the 3-classification BMD assessment model. The performance of both phases was evaluated using an independent test set consisting of 347 individuals. Segmentation performance was evaluated using the Dice similarity coefficient; classification performance was appraised using the receiver operating characteristic (ROC) curve. Furthermore, metrics such as the area under the curve (AUC), accuracy, and precision were meticulously calculated. Results: In the first stage, the automatic segmentation model demonstrated excellent segmentation performance, with mean Dice surpassing 0.93 in the independent test set. In the second stage, both the DenseNet and ResNet-18 demonstrated excellent diagnostic performance in detecting bone status. For osteoporosis, and osteopenia, the AUCs were as follows: DenseNet achieved 0.94 [95% confidence interval (CI): 0.91-0.97], and 0.91 (95% CI: 0.87-0.94), respectively; ResNet-18 attained 0.96 (95% CI: 0.92-0.98), and 0.91 (95% CI: 0.87-0.94), respectively. However, the ResNet-50 model exhibited suboptimal diagnostic performance for osteopenia, with an AUC value of only 0.76 (95% CI: 0.69-0.80). Alterations in tube voltage had a more pronounced impact on the performance of the DenseNet. In the independent test set with tube voltage at 100 kVp images, the accuracy and precision of DenseNet decreased on average by approximately 14.29% and 18.82%, respectively, whereas the accuracy and precision of ResNet-18 decreased by about 8.33% and 7.14%, respectively. Conclusions: The state-of-the-art DL framework model offers an effective and efficient approach for opportunistic osteoporosis screening using chest CT, without incurring additional costs or radiation exposure.

Evaluation of four computed tomography reconstruction algorithms using a coronary artery phantom.

Background: Despite advancements in coronary computed tomography angiography (CTA), challenges in positive predictive value and specificity remain due to limited spatial resolution. The purpose of this experimental study was to investigate the effect of 2nd generation deep learning-based reconstruction (DLR) on the quantitative and qualitative image quality in coronary CTA. Methods: A vessel model with stepwise non-calcified plaque was scanned using 320-detector CT. Image reconstruction was performed using four techniques: hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), DLR, and 2nd generation DLR. The luminal peak CT number, contrast-to-noise ratio (CNR), and edge rise slope (ERS) were quantitatively evaluated via profile curve analysis. Two observers qualitatively graded the graininess, lumen sharpness, and overall lumen visibility on the basis of the degree of confidence for the stenosis severity using a five-point scale. Results: The image noise with HIR, MBIR, DLR, and 2nd generation DLR was 23.0, 21.0, 16.9, and 9.5 HU, respectively. The corresponding CNR (25% stenosis) was 15.5, 15.9, 22.1, and 38.3, respectively. The corresponding ERS (25% stenosis) was 203.2, 198.6, 228.9, and 262.4 HU/mm, respectively. Among the four reconstruction methods, the 2nd generation DLR achieved the significantly highest CNR and ERS values. The score of 2nd generation DLR in all evaluation points (graininess, sharpness, and overall lumen visibility) was higher than those of the other methods (overall vessel visibility score, 2.6±0.5, 3.8±0.6, 3.7±0.5, and 4.6±0.5 with HIR, MBIR, DLR, and 2nd generation DLR, respectively). Conclusions: 2nd generation DLR provided better CNR and ERS in coronary CTA than HIR, MBIR, and previous-generation DLR, leading to the highest subjective image quality in the assessment of vessel stenosis.

White matter biomarker for predicting de novo Parkinson's disease using tract-based spatial statistics: a machine learning-based model.

Background: Parkinson's disease (PD) is an irreversible, chronic degenerative disease of the central nervous system, potentially associated with cerebral white matter (WM) lesions. Investigating the microstructural alterations within the WM in the early stages of PD can help to identify the disease early and enable intervention to reduce the associated serious threats to health. Methods: This study selected 227 cases from the Parkinson's Progression Markers Initiative (PPMI) database, including 152 de novo PD patients and 75 normal controls (NC). Whole-brain voxel analysis of the WM was performed using the tract-based spatial statistics (TBSS) method. The WM regions with statistically significant differences (P<0.05) between the PD and NC groups were identified and used as masks. The mask was applied to each case's fractional anisotropy (FA) image to extract voxel values as feature vectors. Geometric dimensionality reduction was then applied to eliminate redundant values in the feature vectors. Subsequently, the cases were randomly divided into a training group (158 cases, including 103 PD patients and 55 NC) and a test group (69 cases, including 49 PD patients and 20 NC). The least absolute shrinkage and selection operator (LASSO) regression algorithm was employed to extract the minimal set of relevant features, then the random forest (RF) algorithm was utilized for classification using 5-fold cross validation. The resulting model was further integrated with clinical factors to create a comprehensive prediction model. Results: In comparison to the NC group, the FA values in PD patients exhibited a statistically significant decrease (P<0.05), indicating the presence of widespread WM lesions across multiple brain regions. Moreover, the PD prediction model, constructed based on these WM lesion regions, yielded prediction accuracy (ACC) and area under the receiver operating characteristic (ROC) curve (AUC) values of 0.778 and 0.865 in the validation set, and 0.783 and 0.831 in the test set, respectively. Furthermore, the performance of the integrated model showed some improvement, with ACC and AUC values in the test set reaching 0.804 and 0.844, respectively. Conclusions: The quantitative calculation of WM lesion area on FA images using the TBSS method can serve as a neuroimaging biomarker for diagnosing and predicting early PD at the individual level. When integrated with clinical variables, the predictive performance improves.

Hemodynamic property incorporated brain tumor segmentation by deep learning and density-based analysis of dynamic susceptibility contrast-enhanced magnetic resonance imaging (MRI).

Background: Magnetic resonance imaging (MRI) is a primary non-invasive imaging modality for tumor segmentation, leveraging its exceptional soft tissue contrast and high resolution. Current segmentation methods typically focus on structural MRI, such as T1-weighted post-contrast-enhanced or fluid-attenuated inversion recovery (FLAIR) sequences. However, these methods overlook the blood perfusion and hemodynamic properties of tumors, readily derived from dynamic susceptibility contrast (DSC) enhanced MRI. This study introduces a novel hybrid method combining density-based analysis of hemodynamic properties in time-dependent perfusion imaging with deep learning spatial segmentation techniques to enhance tumor segmentation. Methods: First, a U-Net convolutional neural network (CNN) is employed on structural images to delineate a region of interest (ROI). Subsequently, Hierarchical Density-Based Scans (HDBScan) are employed within the ROI to augment segmentation by exploring intratumoral hemodynamic heterogeneity through the investigation of tumor time course profiles unveiled in DSC MRI. Results: The approach was tested and evaluated using a cohort of 513 patients from the open-source University of Pennsylvania glioblastoma database (UPENN-GBM) dataset, achieving a 74.83% Intersection over Union (IoU) score when compared to structural-only segmentation. The algorithm also exhibited increased precision and localized predictions of heightened segmentation boundary complexity, resulting in a 146.92% increase in contour complexity (ICC) compared to the reference standard provided by the UPENN-GBM dataset. Importantly, segmenting tumors with the developed new approach uncovered a negative correlation of the tumor volume with the scores in the Karnofsky Performance Scale (KPS) clinically used for assessing the functional status of patients (-0.309), which is not observed with the prevailing segmentation standard. Conclusions: This work demonstrated that including hemodynamic properties of tissues from DSC MRI can improve existing structural or morphological feature-based tumor segmentation techniques with additional information on tumor biology and physiology. This approach can also be applied to other clinical indications that use perfusion MRI for diagnosis or treatment monitoring.

The application value of a vendor-specific deep learning image reconstruction algorithm in "triple low" head and neck computed tomography angiography.

Background: Head and neck computed tomography angiography (CTA) technology has become the noninvasive imaging method of choice for the diagnosis and long-term follow-up of vascular lesions of the head and neck. However, issues of radiation safety and contrast nephropathy associated with CTA examinations remain concerns. In recent years, deep learning image reconstruction (DLIR) algorithms have been increasingly used in clinical studies, demonstrating their potential for dose optimization. This study aimed to investigate the value of using a DLIR algorithm to reduce radiation and contrast doses in head and neck CTA. Methods: A total of 100 patients were prospectively enrolled and randomly divided into two groups. Group A (50 patients) consisted of those who underwent 70-kVp CTA with a low contrast volume and injection rate and who were classified according to the reconstruction algorithm into subgroups A1 [DLIR at high weighting (DLIR-H)], A2 [DLIR at low weighting (DLIR-L)], and A3 [volume-based adaptive statistical iterative reconstruction with 50% weighting (ASIR-V50%)]. Meanwhile, group B (50 patients) consisted of those who underwent standard radiation and contrast doses at 100 kVp with ASIR-V50% reconstruction. The computed tomography (CT) attenuation, background noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and subjective image quality score (SIQS) were statistically compared for several vessels among the four groups. Results: Group A showed significant reductions in contrast dosage, injection rate, and radiation dose of 36.09%, 20.88%, and 47.80%, respectively, compared to group B (all P<0.001). The four groups differed significantly in terms of background noise (all P<0.05) with group A1 having the lowest value. Group A1 also had significantly higher SNR and CNR values compared to group B in all vessels (all P<0.05) except the M1 of the middle cerebral artery for the SNR. Group A1 also had the highest SIQS, followed by the A2, B, and A3 groups. The SIQS showed good agreement between the two reviewers in all groups, with κ values between 0.88 and 1. Conclusions: Compared to the standard-dose protocol using 100 kVp and ASIR-V50%, a protocol of 70 kVp combined with DLIR-H significantly reduces the radiation dose, contrast dose, and injection rate in head and neck CTA while still significantly improving image quality for patients with a standard body size.

Compare deep learning model and conventional logistic regression model for the identification of unstable saccular intracranial aneurysms in computed tomography angiography.

Background: It is crucial to distinguish unstable from stable intracranial aneurysms (IAs) as early as possible to derive optimal clinical decision-making for further treatment or follow-up. The aim of this study was to investigate the value of a deep learning model (DLM) in identifying unstable IAs from computed tomography angiography (CTA) images and to compare its discriminatory ability with that of a conventional logistic regression model (LRM). Methods: From August 2011 to May 2021, a total of 1,049 patients with 681 unstable IAs and 556 stable IAs were retrospectively analyzed. IAs were randomly divided into training (64%), internal validation (16%), and test sets (20%). Convolutional neural network (CNN) analysis and conventional logistic regression (LR) were used to predict which IAs were unstable. The area under the curve (AUC), sensitivity, specificity and accuracy were calculated to evaluate the discriminating ability of the models. One hundred and ninety-seven patients with 229 IAs from Banan Hospital were used for external validation sets. Results: The conventional LRM showed 11 unstable risk factors, including clinical and IA characteristics. The LRM had an AUC of 0.963 [95% confidence interval (CI): 0.941-0.986], a sensitivity, specificity and accuracy on the external validation set of 0.922, 0.906, and 0.913, respectively, in predicting unstable IAs. In predicting unstable IAs, the DLM had an AUC of 0.771 (95% CI: 0.582-0.960), a sensitivity, specificity and accuracy on the external validation set of 0.694, 0.929, and 0.782, respectively. Conclusions: The CNN-based DLM applied to CTA images did not outperform the conventional LRM in predicting unstable IAs. The patient clinical and IA morphological parameters remain critical factors for ensuring IA stability. Further studies are needed to enhance the diagnostic accuracy.

Deep learning-based reconstruction enhances image quality and improves diagnosis in magnetic resonance imaging of the shoulder joint.

Background: Accelerated magnetic resonance imaging sequences reconstructed using the vendor-provided Recon deep learning algorithm (DL-MRI) were found to be more likely than conventional magnetic resonance imaging (MRI) sequences to detect subacromial (SbA) bursal thickening. However, the extent of this thickening was not extensively explored. This study aimed to compare the image quality of DL-MRI with conventional MRI sequences reconstructed via conventional pipelines (Conventional-MRI) for shoulder examinations and evaluate the effectiveness of DL-MRI in accurately demonstrating the degree of SbA bursal and subcoracoid (SC) bursal thickening. Methods: This prospective cross-sectional study enrolled 41 patients with chronic shoulder pain who underwent 3-T MRI (including both Conventional-MRI and accelerated MRI sequences) of the shoulder between December 2022 and April 2023. Each protocol consisted of oblique axial, coronal, and sagittal images, including proton density-weighted imaging (PDWI) with fat suppression (FS) and oblique coronal T1-weighted imaging (T1WI) with FS. The image quality and degree of artifacts were assessed using a 5-point Likert scale for both Conventional-MRI and DL-MRI. Additionally, the degree of SbA and SC bursal thickening, as well as the relative signal-to-noise ratio (rSNR) and relative contrast-to-noise ratio (rCNR) were analyzed using the paired Wilcoxon test. Statistical significance was defined as P<0.05. Results: The utilization of accelerated sequences resulted in a remarkable 54.7% reduction in total scan time. Overall, DL-MRI exhibited superior image quality scores and fewer artifacts compared to Conventional-MRI. Specifically, DL-MRI demonstrated significantly higher measurements of SC bursal thickenings in the oblique sagittal PDWI sequence compared to Conventional-MRI [3.92 (2.83, 5.82) vs. 3.74 (2.92, 5.96) mm, P=0.028]. Moreover, DL-MRI exhibited higher detection of SbA bursal thickenings in the oblique coronal PDWI sequence [2.61 (1.85, 3.46) vs. 2.48 (1.84, 3.25) mm], with a notable trend towards significant differences (P=0.071). Furthermore, the rSNRs of the muscle in DL-MRI images were significantly higher than those in Conventional-MRI images across most sequences (P<0.001). However, the rSNRs of bone on Conventional-MRI of oblique axial and oblique coronal PDWI sequences showed adverse results [oblique axial: 1.000 (1.000, 1.000) vs. 0.444 (0.367, 0.523); and oblique coronal: 1.000 (1.000, 1.000) vs. 0.460 (0.387, 0.631); all P<0.001]. Additionally, all DL-MRI images exhibited significantly greater rSNRs and rCNRs compared to accelerated MRI sequences reconstructed using traditional pipelines (P<0.001). Conclusions: In conclusion, the utilization of DL-MRI enhances image quality and improves diagnostic capabilities, making it a promising alternative to Conventional-MRI for shoulder imaging.

Accelerated four-dimensional free-breathing whole-liver water-fat magnetic resonance imaging with deep dictionary learning and chemical shift modeling.

Background: Multi-echo chemical-shift-encoded magnetic resonance imaging (MRI) has been widely used for fat quantification and fat suppression in clinical liver examinations. Clinical liver water-fat imaging typically requires breath-hold acquisitions, with the free-breathing acquisition method being more desirable for patient comfort. However, the acquisition for free-breathing imaging could take up to several minutes. The purpose of this study is to accelerate four-dimensional free-breathing whole-liver water-fat MRI by jointly using high-dimensional deep dictionary learning and model-guided (MG) reconstruction. Methods: A high-dimensional model-guided deep dictionary learning (HMDDL) algorithm is proposed for the acceleration. The HMDDL combines the powers of the high-dimensional dictionary learning neural network (hdDLNN) and the chemical shift model. The neural network utilizes the prior information of the dynamic multi-echo data in spatial respiratory motion, and echo dimensions to exploit the features of images. The chemical shift model is used to guide the reconstruction of field maps, R2∗ maps, water images, and fat images. Data acquired from ten healthy subjects and ten subjects with clinically diagnosed nonalcoholic fatty liver disease (NAFLD) were selected for training. Data acquired from one healthy subject and two NAFLD subjects were selected for validation. Data acquired from five healthy subjects and five NAFLD subjects were selected for testing. A three-dimensional (3D) blipped golden-angle stack-of-stars multi-gradient-echo pulse sequence was designed to accelerate the data acquisition. The retrospectively undersampled data were used for training, and the prospectively undersampled data were used for testing. The performance of the HMDDL was evaluated in comparison with the compressed sensing-based water-fat separation (CS-WF) algorithm and a parallel non-Cartesian recurrent neural network (PNCRNN) algorithm. Results: Four-dimensional water-fat images with ten motion states for whole-liver are demonstrated at several R values. In comparison with the CS-WF and PNCRNN, the HMDDL improved the mean peak signal-to-noise ratio (PSNR) of images by 9.93 and 2.20 dB, respectively, and improved the mean structure similarity (SSIM) of images by 0.058 and 0.009, respectively, at R=10. The paired t-test shows that there was no significant difference between HMDDL and ground truth for proton-density fat fraction (PDFF) and R2∗ values at R up to 10. Conclusions: The proposed HMDDL enables features of water images and fat images from the highly undersampled multi-echo data along spatial, respiratory motion, and echo dimensions, to improve the performance of accelerated four-dimensional (4D) free-breathing water-fat imaging.