Prediction of Osteoporosis and Fragility Fracture Risk Using Proximal Humerus CT Value from Chest CT: A Development and Validation Study.

Use of Multiphase CT Protocols in 18 Countries: Appropriateness and Radiation Doses.

Comprehensive clinical examination can be compromised in patients on veno-venous extracorporeal membrane oxygenation (VV-ECMO). Adjunctive diagnostic imaging strategies range from bedside imaging only to routine computed tomography (CT). The risk-benefit of either approach remains to be evaluated. Patients retrieved to the Royal Brompton Hospital (RBH) on VV-ECMO routinely undergo admission CT imaging of head, chest, abdomen and pelvis. This study aimed to identify how frequently changes in therapy or adverse events could be attributed to routine CT scanning. Demographic and clinical data were gathered retrospectively from patients retrieved to RBH on VV-ECMO (January 2014-2016). Scans were categorized as 'routine' or requested to clarify a specific clinical uncertainty. Clinical records were reviewed to identify attributable management changes and CT- related adverse events. Seventy-two patients were retrieved on VV-ECMO (median age 44 years) and 65 scanned on admission (mean radiation dose 2344mGy-cm). Routine head CT head yielded novel clinical information in 11 patients, 10 of whom had unexpected intracranial haemorrhage and, subsequently, had their anticoagulation withheld. Routine thoracic CT identified unexpected positive findings in three patients (early fibrosis, pulmonary vasculitis, pneumomediastinum), eliciting management variation in one (steroid administration). Routine abdomen/pelvis CT identified new information in three patients (adrenal haemorrhage, hepatosteatosis, splenic infarction), changing the management in one (withholding anticoagulation). CT scanning was not associated with consequential adverse events (e.g. accidental decannulation, gas entrainment into the circuit, hypoxia, hypotension). Median transfer/scan time was 78 minutes, requiring five ITU staff-members. In our cohort, a policy of routine head CT changed the management in 17% of patients; the yield from routine chest, abdomen and pelvis CT was modest. CT transfer was safe, but resource intensive. Prospective studies should evaluate whether routine CT impacts outcome.

Machine Learning Methods Based on Chest CT for Predicting the Risk of COVID-19-Associated Pulmonary Aspergillosis.

Predicting Osteoporosis and Osteopenia by Fusing Deep Transfer Learning Features and Classical Radiomics Features Based on Single-Source Dual-energy CT Imaging

BackgroundCerebral microbleeds (CMBs) are common in the hypertensive population and can only be detected with magnetic resonance imaging (MRI). The anticoagulation and thrombolytic regimens for patients with >5 CMBs are different from those for patients with ≤ 5 CMBs. However, MRI is not suitable for evaluating CMBs in patients with MRI contraindications or acute ischemic stroke urgently requiring thrombolysis. We aimed to develop and validate a nomogram combining clinical and brain computed tomography (CT) characteristics for predicting >5 CMBs in a hypertensive population.Materials and methodsIn total, 160 hypertensive patients from 2016 to 2020 who were confirmed by MRI to have >5 (77 patients) and ≤ 5 CMBs (83) were retrospectively analyzed as the training cohort. Sixty-four hypertensive patients from January 2021 to February 2022 were included in the validation cohort. Multivariate logistic regression was used to evaluate >5 CMBs. A combined nomogram was constructed based on the results, while clinical and CT models were established according to the corresponding characteristics. Receiver operating characteristic (ROC) and calibration curves and decision curve analysis (DCA) were used to verify the models.ResultsIn the multivariable analysis, the duration of hypertension, level of homocysteine, the number of lacunar infarcts (LIs), and leukoaraiosis (LA) score were included as factors associated with >5 CMBs. The clinical model consisted of the duration of hypertension and level of homocysteine, while the CT model consisted of the number of LIs and LA. The combined model consisted of the duration of hypertension, level of homocysteine, LI, and LA. The combined model achieved an area under the curve (AUC) of 0.915 (95% confidence interval [CI]: 0.860–0.953) with the training cohort and 0.887 (95% CI: 0.783–0.953) with the validation cohort, which were higher than those of the clinical model [training cohort: AUC, 0.797 (95% CI: 0.726, 0.857); validation cohort: AUC, 0.812 (95% CI: 0.695, 0.899)] and CT model [training cohort: AUC, 0.884 (95% CI: 0.824, 0.929); validation cohort: AUC, 0.868 (95% CI: 0.760, 0.940)]. DCA showed that the clinical value of the combined model was superior to that of the clinical model and CT model.ConclusionA combined model based on clinical and CT characteristics showed good diagnostic performance for predicting >5 CMBs in hypertensive patients.

Individualized Prediction and Risk Factors of Recurrence in Chinese Patients with Sebaceous Carcinoma: A Multicenter Study of 418 Patients

IntroductionStroke remains a leading cause of death and disability worldwide. Effective and prompt prognostic evaluation is vital for determining the appropriate management strategy. Radiomics is an emerging noninvasive method used to identify the quantitative imaging indicators for predicting important clinical outcomes. This study was conducted to investigate and validate a radiomics nomogram for predicting ischemic stroke prognosis using the modified Rankin scale (mRS).MethodsA total of 598 consecutive patients with subacute infarction confirmed by diffusion-weighted imaging (DWI), from January 2018 to December 2019, were retrospectively assessed. They were assigned to the good (mRS ≤ 2) and poor (mRS > 2) functional outcome groups, respectively. Then, 399 patients examined by MR scanner 1 and 199 patients scanned by MR scanner 2 were assigned to the training and validation cohorts, respectively. Infarction lesions underwent manual segmentation on DWI, extracting 402 radiomic features. A radiomics nomogram encompassing patient characteristics and the radiomics signature was built using a multivariate logistic regression model. The performance of the nomogram was evaluated in the training and validation cohorts. Ultimately, decision curve analysis was implemented to assess the clinical value of the nomogram. The performance of infarction lesion volume was also evaluated using univariate analysis.ResultsStroke lesion volume showed moderate performance, with an area under the curve (AUC) of 0.678. The radiomics signature, including 11 radiomics features, exhibited good prediction performance. The radiomics nomogram, encompassing clinical characteristics (age, hemorrhage, and 24 h National Institutes of Health Stroke Scale score) and the radiomics signature, presented good discriminatory potential in the training cohort [AUC = 0.80; 95% confidence interval (CI) 0.75–0.86], which was validated in the validation cohort (AUC = 0.73; 95% CI 0.63–0.82). In addition, it demonstrated good calibration in the training (p = 0.55) and validation (p = 0.21) cohorts. Decision curve analysis confirmed the clinical value of this nomogram.ConclusionThis novel noninvasive clinical-radiomics nomogram shows good performance in predicting ischemic stroke prognosis.Supplementary InformationThe online version contains supplementary material available at 10.1007/s40120-021-00263-2.

To predict the epidermal growth factor receptor (EGFR) T790M status of patients with advanced non-small cell lung cancer (NSCLC) following the first-line first-/second-generation EGFR-tyrosine kinase inhibitor (EGFR-TKI) therapy, the related clinical features and chest computed tomography (CT) images of patients with advanced NSCLC in our hospital were retrospectively collected. All patients who met the criteria were randomly divided into training and validation cohorts. Then, a clinical model with the filtered clinical characteristics and a deep-learning model (DLM) were constructed. The area under the curve (AUC), specificity, sensitivity, accuracy, and decision curve analysis were used to evaluate model performance. In total, 66 patients met the inclusion criteria of the study (training cohort, n = 40; validation cohort, n = 26). EGFR19del and the use of gefitinib were significant (P < 0.05), and then, the clinical model was established using multivariate logistic regression analysis. The AUCs of the clinical model were 0.862 (95% confidence interval [CI], 0.570 – 0.966) and 0.755 (0.566 – 0.943) in the training and validation cohorts, respectively. The AUCs of the DLM from the chest CT image analysis were 0.839 (95% CI, 0.708 – 0.970) and 0.842 (0.680 – 1.000) in the training and validation cohorts, respectively. In the validation cohort, the DLM and clinical model exhibited an accuracy of 0.7308 and 0.5000, specificity of 0.6667 and 0.2000, positive probability values of 0.6429 and 0.4545, and negative probability values of 0.8333 and 0.7500, respectively. The DLM was developed using chest CT images to predict the EGFR T790M status following the first-line first- and second-generation EGFR-TKI treatment of advanced EGFR-positive NSCLC.

This study extracted radiomics features of blood clots from computed tomography pulmonary angiography (CTPA) images of acute pulmonary embolism (APE) patients, and constructs a predictive model for APE patient risk stratification by comparing multiple machine learning (ML) algorithms. This retrospective study analyzed patients with APE, documenting their clinical characteristics (clinical and hematological indicators), conventional CTPA imaging parameters. Patients are stratified into low-risk group and high-risk group based on risk stratification. The data were randomly divided into a training cohort and a validation cohort in a 7:3 ratio. We developed 2 distinct models: nomogram model based on clinical characteristics and an image parameter model based on conventional CTPA imaging parameters. Features were screened by the least absolute shrinkage and selection operator (LASSO) method. The radiomics predictive model was constructed using 7 ML algorithms and selected the one with the best performance.The combined model was constructed by integrating radiomics features with clinical characteristics and image parameter using an optimal algorithm. Model performance was evaluated using receiver operating characteristic curves and decision curves analysis, with the area under the curve (AUC) compared via the DeLong test. A total of 202 patients were included. The training cohort contained 141 cases, while the validation cohort included 61 cases. Multivariate logistic analysis revealed that the pulmonary embolism severity index, dyspnea, troponin, and right ventricle/ left ventricle short-axis maximum diameter ratio were independent clinical predictors (P < .05). A total of 12 radiomics features were selected through LASSO screening. Logistic regression demonstrated the best performance among the 7 ML algorithms. In the validation cohort, the combined model demonstrated significantly superior predictive performance (AUC = 0.935) compared to the nomogram model (AUC = 0.805), the image parameter model (AUC = 0.788), and the radiomics model (AUC = 0.860) (P < .05). Decision curve analysis indicated that the combined model demonstrated higher clinical net benefit when the risk threshold exceeded 0.04. Calibration curves and Hosmer-Lemeshow test further confirmed the combined model’s goodness of fit in both the training and validation cohorts. The combined model combining clinical characteristics, conventional CTPA imaging parameters, and radiomics features demonstrated outstanding predictive performance and clinical applicability in risk stratification for APE patients.

To develop and validate a combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT. One hundred sixty-five patients with vertebral compression fractures were allocated to training (n = 110 [62 acute benign and 48 malignant fractures]) and validation (n = 55 [30 acute benign and 25 malignant fractures]) cohorts. Radiomics features (n = 144) were extracted from non-contrast-enhanced CT images. Radiomics score was constructed by applying least absolute shrinkage and selection operator regression to reproducible features. A combined radiomics-clinical model was constructed by integrating significant clinical parameters with radiomics score using multivariate logistic regression analysis. Model performance was quantified in terms of discrimination and calibration. The model was internally validated on the independent data set. The combined radiomics-clinical model, composed of two significant clinical predictors (age and history of malignancy) and the radiomics score, showed good calibration (Hosmer-Lemeshow test, p > 0.05) and discrimination in both training (AUC, 0.970) and validation (AUC, 0.948) cohorts. Discrimination performance of the combined model was higher than that of either the radiomics score (AUC, 0.941 in training cohort and 0.852 in validation cohort) or the clinical predictor model (AUC, 0.924 in training cohort and 0.849 in validation cohort). The model stratified patients into groups with low and high risk of malignant fracture with an accuracy of 98.2% in the training cohort and 90.9% in the validation cohort. The combined radiomics-clinical model integrating clinical parameters with radiomics score could predict malignancy in vertebral compression fractures on CT with high discriminatory ability. • A combined radiomics-clinical model was constructed to predict malignancy of vertebral compression fractures on CT by combining clinical parameters and radiomics features. • The model showed good calibration and discrimination in both training and validation cohorts. • The model showed high accuracy in the stratification of patients into groups with low and high risk of malignant vertebral compression fractures.

BACKGROUNDEsophageal varices (EV) are the most fatal complication of chronic hepatitis B (CHB) related cirrhosis. The prognosis is poor, especially after the first upper gastrointestinal hemorrhage.AIMTo construct nomograms to predict the risk and severity of EV in patients with CHB related cirrhosis.METHODSBetween 2016 and 2018, the patients with CHB related cirrhosis were recruited and divided into a training or validation cohort at The First Affiliated Hospital of Wenzhou Medical University. Clinical and ultrasonic parameters that were closely related to EV risk and severity were screened out by univariate and multivariate logistic regression analyses, and integrated into two nomograms, respectively. Both nomograms were internally and externally validated by calibration, concordance index (C-index), receiver operating characteristic curve, and decision curve analyses (DCA).RESULTSA total of 307 patients with CHB related cirrhosis were recruited. The independent risk factors for EV included Child-Pugh class [odds ratio (OR) = 7.705, 95% confidence interval (CI) = 2.169-27.370, P = 0.002], platelet count (OR = 0.992, 95%CI = 0.984-1.000, P = 0.044), splenic portal index (SPI) (OR = 3.895, 95%CI = 1.630-9.308, P = 0.002), and liver fibrosis index (LFI) (OR = 3.603, 95%CI = 1.336-9.719, P = 0.011); those of EV severity included Child-Pugh class (OR = 5.436, 95%CI = 2.112-13.990, P < 0.001), mean portal vein velocity (OR = 1.479, 95%CI = 1.043-2.098, P = 0.028), portal vein diameter (OR = 1.397, 95%CI = 1.021-1.912, P = 0.037), SPI (OR = 1.463, 95%CI = 1.030-2.079, P = 0.034), and LFI (OR = 3.089, 95%CI = 1.442-6.617, P = 0.004). Two nomograms (predicting EV risk and severity, respectively) were well-calibrated and had a favorable discriminative ability, with C-indexes of 0.916 and 0.846 in the training cohort, respectively, higher than those of other predictive indexes, like LFI (C-indexes = 0.781 and 0.738), SPI (C-indexes = 0.805 and 0.714), ratio of platelet count to spleen diameter (PSR) (C-indexes = 0.822 and 0.726), King’s score (C-indexes = 0.694 and 0.609), and Lok index (C-indexes = 0.788 and 0.700). The areas under the curves (AUCs) of the two nomograms were 0.916 and 0.846 in the training cohort, respectively, higher than those of LFI (AUCs = 0.781 and 0.738), SPI (AUCs = 0.805 and 0.714), PSR (AUCs = 0.822 and 0.726), King’s score (AUCs = 0.694 and 0.609), and Lok index (AUCs = 0.788 and 0.700). Better net benefits were shown in the DCA. The results were validated in the validation cohort.CONCLUSIONNomograms incorporating clinical and ultrasonic variables are efficient in noninvasively predicting the risk and severity of EV.

To develop and validate a computed tomography (CT) radiomics nomogram from multicentre datasets for preoperative prediction of perineural invasion (PNI) in colorectal cancer. A total of 299 patients with histologically confirmed colorectal cancer from three hospitals were enrolled in this retrospective study. Radiomic features were extracted from the whole tumour volume. The least absolute shrinkage and selection operator logistic regression was applied for feature selection and radiomics signature construction. Finally, a radiomics nomogram combining the radiomics score and clinical predictors was established. The receiver operating characteristic curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the radiomics nomogram in the training cohort, internal validation and external validation cohorts. Twelve radiomics features extracted from the whole tumour volume were used to construct the radiomics model. The area under the curve (AUC) values of the radiomics model in the training cohort, internal validation cohort, external validation cohort 1, and external validation cohort 2 were 0.82 (0.75-0.90), 0.77 (0.62-0.92), 0.71 (0.56-0.85), and 0.73 (0.60-0.85), respectively. The nomogram, which combined the radiomics score with T category and N category by CT, yielded better performance in the training cohort (AUC = 0.88), internal validation cohort (AUC = 0.80), external validation cohort 1 (AUC = 0.75), and external validation cohort 2 (AUC = 0.76). DCA confirmed the clinical utility of the nomogram. The CT-based radiomics nomogram has the potential to accurately predict PNI in patients with colorectal cancer.

BackgroundAccording to the World Health Organization (WHO) Classification of Thoracic Tumors published in 2021, lung adenocarcinoma (LUAD) includes minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC). The invasive component of MIA is ≤5 mm, while IAC is, on the contrary. This difference in the extent of invasion leads to distinct biological behaviors, which correspond to different treatment approaches and prognostic outcomes. Therefore, this study aimed to construct and validate a radiomics-based nomogram for preoperatively predicting the invasiveness of LUAD appearing as pulmonary nodules.MethodsFrom January 2020 to June 2024, data of a total of 611 pulmonary nodule patients who underwent preoperative computed tomography (CT) examinations at three centers were retrospectively analyzed. All patients were pathologically diagnosed with LUAD, including IAC and MIA. Individuals from the primary center were randomly divided into a training cohort and an internal validation cohort at a ratio of 7:3, while patients from the other two centers were included in an external validation cohort. Firstly, univariable and multivariable logistic regression (LR) analyses were performed to develop a clinical model. Secondly, three representative machine learning classifiers were used to construct radiomics models, and their performances were compared to select the optimal one. Finally, with the integration of the clinical and radiomics signatures, a combined model was established, and a nomogram was generated to visualize the risk scores. The diagnostic performance was evaluated with the receiver operating characteristic (ROC) curves, the goodness-of-fit was verified through the calibration curves, and the clinical utility was assessed by the decision curve analysis (DCA).ResultsSix hundred and eleven patients were recruited, with 356 individuals in the training cohort (IAC, 227; MIA, 129), 153 in the validation cohort (IAC, 108; MIA, 45), and 102 in the test cohort (IAC, 70; MIA, 32). The combined model worked robustly and effectively, with areas under the curves (AUCs) of 0.968 [95% confidence interval (CI), 0.953–0.984], 0.902 (95% CI, 0.856–0.949), and 0.899 (95% CI, 0.839–0.959) in the training, validation, and test cohorts, respectively, demonstrating an excellent predictive power, a good model fit, and a significant clinical utility.ConclusionsThis radiomics-based nomogram could serve as a clinical predictive model for preoperatively predicting the invasiveness of LUAD, which contributes to the future development of more individualized therapeutic strategies.

BackgroundThere is lack of discrimination as to traditional imaging diagnostic methods of cystic renal lesions (CRLs). This study aimed to evaluate the value of machine learning models based on clinical data and contrast-enhanced computed tomography (CECT) radiomics features in the differential diagnosis of benign and malignant CRL.MethodsThere were 192 patients with CRL (Bosniak class ≥ II) enrolled through histopathological examination, including 144 benign cystic renal lesions (BCRLs) and 48 malignant cystic renal lesions (MCRLs). Radiomics features were extracted from CECT images taken during the medullary phase. Using the light gradient boosting machine (LightGBM) algorithm, the clinical, radiomics and combined models were constructed. A comprehensive nomogram was developed by integrating the radiomics score (Rad-score) with independent clinical factors. Receiver operating characteristic (ROC) curves were plotted. The corresponding area under the curve (AUC) value was worked out to quantify the discrimination performance of the three models in training and validation cohorts. Calibration curves were worked out to assess the accuracy of the probability values predicted by the models. Decision curve analysis (DCA) was worked out to assess the performance of models at different thresholds.ResultsMaximum diameter and Bosniak class were independent risk factors of patients with MCRL in the clinical model. Twenty-one radiomics features were extracted to work out a Rad-score. The performance of the clinical model in the training cohort was AUC =0.948, 95% confidence interval (CI): 0.917–0.980, and the performance in the validation cohort was AUC =0.936, 95% CI: 0.859–1.000 (P<0.05). The performance of the radiomics model in the training cohort was AUC =0.990, 95% CI: 0.979–1.000, and the performance in the validation cohort was AUC =0.959, 95% CI: 0.903–1.000 (P<0.05). Compared with the above models, the combined radiomics nomogram had an AUC of 0.989 (95% CI: 0.977–1.000) in the training cohort and an AUC of 0.962 (95% CI: 0.905–1.000) in the validation cohort (P<0.05), showing the best diagnostic efficacy.ConclusionsThe radiomics nomogram integrating clinical independent risk factors and radiomics signature improved the diagnostic accuracy in differentiating between BCRL and MCRL, which can provide a reference for clinical decision-making and help clinicians develop individualized treatment strategies for patients.

The purpose of this study was to distinguish pneumonic-type mucinous adenocarcinoma (PTMA) from lobar pneumonia (LP) by pre-treatment CT radiological and clinical or radiological parameters. A total of 199 patients (patients diagnosed with LP = 138, patients diagnosed with PTMA = 61) were retrospectively evaluated and assigned to either the training cohort (n = 140) or the validation cohort (n = 59). Radiomics features were extracted from chest CT plain images. Multivariate logistic regression analysis was conducted to develop a radiomics model and a nomogram model, and their clinical utility was assessed. The performance of the constructed models was assessed with the receiver operating characteristic (ROC) curve and the area under the curve (AUC). The clinical application value of the models was comprehensively evaluated using decision curve analysis (DCA). The radiomics signature, consisting of 14 selected radiomics features, showed excellent performance in distinguishing between PTMA and LP, with an AUC of 0.90 (95% CI, 0.83-0.96) in the training cohort and 0.88 (95% CI, 0.79-0.97) in the validation cohort. A nomogram model was developed based on the radiomics signature and clinical features. It had a powerful discriminative ability, with the highest AUC values of 0.94 (95% CI, 0.90-0.98) and 0.91 (95% CI, 0.84-0.99) in the training cohort and validation cohort, respectively, which were significantly superior to the clinical model alone. There were no significant differences in calibration curves from Hosmer-Lemeshow tests between training and validation cohorts (p = 0.183 and p = 0.218), which indicated the good performance of the nomogram model. DCA indicated that the nomogram model exhibited better performance than the clinical model. The nomogram model based on radiomics signatures of CT images and clinical risk factors could help to differentiate PTMA from LP, which can provide appropriate therapy decision support for clinicians, especially in situations where differential diagnosis is difficult.