Nomogram using intratumoral and peritumoral radiomics for the preoperative prediction of visceral pleural invasion in clinical stage IA lung adenocarcinoma.

BACKGROUND: Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical operation and postoperative treatment. We investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting the status of VPI in patients diagnosed with clinical stage IA lung adenocarcinoma. METHODS: A total of 404 patients from our hospital were randomly assigned to a training set (n = 283) and an internal validation set (n = 121) using a 7:3 ratio, while 81 patients from two other hospitals constituted the external validation set. We extracted 1218 CT-based radiomics features from the gross tumor volume (GTV) as well as the gross peritumoral tumor volume (GPTV5, 10, 15), respectively, and constructed radiomic models. Additionally, we developed a nomogram based on relevant CT features and the radscore derived from the optimal radiomics model. RESULTS: The GPTV10 radiomics model exhibited superior predictive performance compared to GTV, GPTV5, and GPTV15, with area under the curve (AUC) values of 0.855, 0.842, and 0.842 in the three respective sets. In the clinical model, the solid component size, pleural indentation, solid attachment, and vascular convergence sign were identified as independent risk factors among the CT features. The predictive performance of the nomogram, which incorporated relevant CT features and the GPTV10-radscore, outperformed both the radiomics model and clinical model alone, with AUC values of 0.894, 0.828, and 0.876 in the three respective sets. CONCLUSIONS: The nomogram, integrating radiomics features and CT morphological features, exhibits good performance in predicting VPI status in lung adenocarcinoma.

Predicting major adverse cardiovascular events within 3 years by optimization of radiomics model derived from pericoronary adipose tissue on coronary computed tomography angiography: a case-control study.

BACKGROUND: Coronary inflammation induces changes in pericoronary adipose tissue (PCAT) can be detected by coronary computed tomography angiography (CCTA). Our aim was to investigate whether different PCAT radiomics model based on CCTA could improve the prediction of major adverse cardiovascular events (MACE) within 3 years. METHODS: This retrospective study included 141 consecutive patients with MACE and matched to patients with non-MACE (n = 141). Patients were randomly assigned into training and test datasets at a ratio of 8:2. After the robust radiomics features were selected by using the Spearman correlation analysis and the least absolute shrinkage and selection operator, radiomics models were built based on different machine learning algorithms. The clinical model was then calculated according to independent clinical risk factors. Finally, an overall model was established using the radiomics features and the clinical factors. Performance of the models was evaluated for discrimination degree, calibration degree, and clinical usefulness. RESULTS: The diagnostic performance of the PCAT model was superior to that of the RCA-model, LAD-model, and LCX-model alone, with AUCs of 0.723, 0.675, 0.664, and 0.623, respectively. The overall model showed superior diagnostic performance than that of the PCAT-model and Cli-model, with AUCs of 0.797, 0.723, and 0.706, respectively. Calibration curve showed good fitness of the overall model, and decision curve analyze demonstrated that the model provides greater clinical benefit. CONCLUSION: The CCTA-based PCAT radiomics features of three major coronary arteries have the potential to be used as a predictor for MACE. The overall model incorporating the radiomics features and clinical factors offered significantly higher discrimination ability for MACE than using radiomics or clinical factors alone.

Lesion-specific pericoronary adipose tissue CT attenuation improves risk prediction of major adverse cardiovascular events in coronary artery disease.

OBJECTIVES: To determine whether lesion-specific pericoronary adipose tissue CT attenuation (PCATa) is superior to PCATa around the proximal right coronary artery (PCATa-RCA) and left anterior descending artery (PCATa-LAD) for major adverse cardiovascular events (MACE) prediction in coronary artery disease (CAD). METHODS: Six hundred and eight CAD patients who underwent coronary CTA from January 2014 to December 2018 were retrospectively included, with clinical risk factors, plaque features, lesion-specific PCATa, PCATa-RCA, and PCATa-LAD collected. MACE was defined as cardiovascular death, non-fatal myocardial infarction, unplanned revascularization, and hospitalization for unstable angina. Four models were established, encapsulating traditional factors (Model A), traditional factors and PCATa-RCA (Model B), traditional factors and PCATa-LAD (Model C), and traditional factors and lesion-specific PCATa (Model D). Prognostic performance was evaluated with C-statistic, area under receiver operator characteristic curve (AUC), and net reclassification index (NRI). RESULTS: Lesion-specific PCATa was an independent predictor for MACE (adjusted hazard ratio = 1.108, P < .001). The C-statistic increased from 0.750 for model A to 0.762 for model B (P = .078), 0.773 for model C (P = .046), and 0.791 for model D (P = .005). The AUC increased from 0.770 for model A to 0.793 for model B (P = .027), 0.793 for model C (P = .387), and 0.820 for model D (P = .019). Compared with model A, the NRIs for models B, C, and D were 0.243 (-0.323 to 0.792, P = .392), 0.428 (-0.012 to 0.835, P = .048), and 0.708 (0.152-1.016, P = .001), respectively. CONCLUSIONS: Lesion-specific PCATa improves risk prediction of MACE in CAD, which is better than PCATa-RCA and PCATa-LAD. ADVANCES IN KNOWLEDGE: Lesion-specific PCATa was superior to PCATa-RCA and PCATa-LAD for MACE prediction.

Preoperative Prediction of Meningioma Subtype by Constructing a Clinical-Radiomics Model Nomogram Based on Magnetic Resonance Imaging.

OBJECTIVE: We sought to investigate the value of a clinical-radiomics model based on magnetic resonance imaging in differentiating fibroblastic meningiomas from non-fibroblastic meningiomas. METHODS: Clinical, imaging, and postoperative pathologic data of 423 patients (128 fibroblastic meningiomas and 295 non-fibroblastic meningiomas) were randomly categorized into training (n = 296) and validation (n = 127) groups at a 7:3 ratio. The Selectpercentile and LASSO were used to selected the highly correlated features from 3376 radiomics features. Different classifiers were used to train and verify the model. The receiver operating characteristic curves, accuracy (ACC), sensitivity (SEN), and specificity (SPE) were drawn to evaluate the performance. The optimal radiomics model was selected. Calibration curves and decision curve analysis were used to verify the clinical utility and consistency of the nomogram constructed from the radiomics features and clinical factors. RESULTS: Thirteen radiomics features were selected from contrast-enhanced T1-weighted imaging and T2-weighted imaging after dimensionality reduction. The prediction performance of random forest radiomics model is slightly lower than that of the clinical-radiomics model. The area under the curve, SEN, SPE, and ACC of the clinical-radiomics model training set were 0.836 (95% confidence interval, 0.795-0.878), 0.922, 0.583, and 0.686, respectively. The area under the curve, SEN, SPE, and ACC of the validation set were 0.756 (95% confidence interval, 0.660-0.846), 0.816, 0.596, and 0.661, respectively. CONCLUSIONS: The diagnostic efficacy of the clinical-radiomics model of fibroblastic meningioma and non-fibroblastic meningioma was better than that of the radiomics prediction model alone and can be used as a potential tool for clinical surgical planning and evaluation of patient prognosis.

Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task.

The black-box nature of machine learning models hinders the deployment of some high-accuracy medical diagnosis algorithms. It is risky to put one's life in the hands of models that medical researchers do not fully understand or trust. However, through model interpretation, black-box models can promptly reveal significant biomarkers that medical practitioners may have overlooked due to the surge of infected patients in the COVID-19 pandemic. This research leverages a database of 92 patients with confirmed SARS-CoV-2 laboratory tests between 18th January 2020 and 5th March 2020, in Zhuhai, China, to identify biomarkers indicative of infection severity prediction. Through the interpretation of four machine learning models, decision tree, random forests, gradient boosted trees, and neural networks using permutation feature importance, partial dependence plot, individual conditional expectation, accumulated local effects, local interpretable model-agnostic explanations, and Shapley additive explanation, we identify an increase in N-terminal pro-brain natriuretic peptide, C-reaction protein, and lactic dehydrogenase, a decrease in lymphocyte is associated with severe infection and an increased risk of death, which is consistent with recent medical research on COVID-19 and other research using dedicated models. We further validate our methods on a large open dataset with 5644 confirmed patients from the Hospital Israelita Albert Einstein, at São Paulo, Brazil from Kaggle, and unveil leukocytes, eosinophils, and platelets as three indicative biomarkers for COVID-19.

Magnetic Resonance Deep Learning Radiomic Model Based on Distinct Metastatic Vascular Patterns for Evaluating Recurrence-Free Survival in Hepatocellular Carcinoma.

BACKGROUND: The metastatic vascular patterns of hepatocellular carcinoma (HCC) are mainly microvascular invasion (MVI) and vessels encapsulating tumor clusters (VETC). However, most existing VETC-related radiological studies still focus on the prediction of VETC status. PURPOSE: This study aimed to build and compare VETC-MVI related models (clinical, radiomics, and deep learning) associated with recurrence-free survival of HCC patients. STUDY TYPE: Retrospective. POPULATION: 398 HCC patients (349 male, 49 female; median age 51.7 years, and age range: 22-80 years) who underwent resection from five hospitals in China. The patients were randomly divided into training cohort (n = 358) and test cohort (n = 40). FIELD STRENGTH/SEQUENCE: 3-T, pre-contrast T1-weighted imaging spoiled gradient recalled echo (T1WI SPGR), T2-weighted imaging fast spin echo (T2WI FSE), and contrast enhanced arterial phase (AP), delay phase (DP). ASSESSMENT: Two radiologists performed the segmentation of HCC on T1WI, T2WI, AP, and DP images, from which radiomic features were extracted. The RFS related clinical characteristics (VETC, MVI, Barcelona stage, tumor maximum diameter, and alpha fetoprotein) and radiomic features were used to build the clinical model, clinical-radiomic (CR) nomogram, deep learning model. The follow-up process was done 1 month after resection, and every 3 months subsequently. The RFS was defined as the date of resection to the date of recurrence confirmed by radiology or the last follow-up. Patients were followed up until December 31, 2022. STATISTICAL TESTS: Univariate COX regression, least absolute shrinkage and selection operator (LASSO), Kaplan-Meier curves, log-rank test, C-index, and area under the curve (AUC). P < 0.05 was considered statistically significant. RESULTS: The C-index of deep learning model achieved 0.830 in test cohort compared with CR nomogram (0.731), radiomic signature (0.707), and clinical model (0.702). The average RFS of the overall patients was 26.77 months (range 1-80 months). DATA CONCLUSION: MR deep learning model based on VETC and MVI provides a potential tool for survival assessment. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.

Prediction of meningioma grade by constructing a clinical radiomics model nomogram based on magnetic resonance imaging.

PURPOSE: To explore the clinical value of a clinical radiomics model nomogram based on magnetic resonance imaging (MRI) for preoperative meningioma grading. MATERIALS AND METHODS: We collected retrospectively 544 patients with pathological diagnosis of meningiomas were categorized into training (n = 380) and validation (n = 164) groups at the ratio of 7∶ 3. There were 3,376 radiomics features extracted from T2WI and T1C by shukun technology platform after manual segmentation using an independent blind method by two radiologists. The Selectpercentile and Lasso are used to filter the most strongly correlated features. Random forest (RF) radiomics model and clinical radiomics model nomogram were constructed respectively. The calibration, discrimination, and clinical validity were evaluated by using the calibration curve and decision analysis curve (DCA). RESULTS: The RF radiomics model based on T1C and T2WI was the most effective to predict meningioma grade before surgery among the six different classifiers. The predictive ability of clinical radiomics model was slightly higher than that of RF model alone. The AUC, SEN, SPE, and ACC of the training set were 0.949, 0.976, 0.785, and 0.826, and the AUC, SEN, SPE, and ACC of the validation set were 0.838, 0.829, 0.783, and 0.793, respectively. The calibration curve and Hosmer-Lemeshow test showed the predictive probability of the fusion model was similar to the actual differentiated LGM and HGM. The analysis of the decision curve showed that the clinical radiomics model could obtain the best clinical net profit. CONCLUSIONS: The clinical radiomics model nomogram based on T1C and T2WI has high accuracy and sensitivity for predicting meningioma grade.

Baseline whole-lung CT features deriving from deep learning and radiomics: prediction of benign and malignant pulmonary ground-glass nodules.

Objective: To develop and validate the model for predicting benign and malignant ground-glass nodules (GGNs) based on the whole-lung baseline CT features deriving from deep learning and radiomics. Methods: This retrospective study included 385 GGNs from 3 hospitals, confirmed by pathology. We used 239 GGNs from Hospital 1 as the training and internal validation set; 115 and 31 GGNs from Hospital 2 and Hospital 3 as the external test sets 1 and 2, respectively. An additional 32 stable GGNs from Hospital 3 with more than five years of follow-up were used as the external test set 3. We evaluated clinical and morphological features of GGNs at baseline chest CT and extracted the whole-lung radiomics features simultaneously. Besides, baseline whole-lung CT image features are further assisted and extracted using the convolutional neural network. We used the back-propagation neural network to construct five prediction models based on different collocations of the features used for training. The area under the receiver operator characteristic curve (AUC) was used to compare the prediction performance among the five models. The Delong test was used to compare the differences in AUC between models pairwise. Results: The model integrated clinical-morphological features, whole-lung radiomic features, and whole-lung image features (CMRI) performed best among the five models, and achieved the highest AUC in the internal validation set, external test set 1, and external test set 2, which were 0.886 (95% CI: 0.841-0.921), 0.830 (95%CI: 0.749-0.893) and 0.879 (95%CI: 0.712-0.968), respectively. In the above three sets, the differences in AUC between the CMRI model and other models were significant (all P < 0.05). Moreover, the accuracy of the CMRI model in the external test set 3 was 96.88%. Conclusion: The baseline whole-lung CT features were feasible to predict the benign and malignant of GGNs, which is helpful for more refined management of GGNs.

Automatic differentiation of ruptured and unruptured intracranial aneurysms on computed tomography angiography based on deep learning and radiomics.

OBJECTIVES: Rupture of intracranial aneurysm is very dangerous, often leading to death and disability. In this study, deep learning and radiomics techniques were used to automatically detect and differentiate ruptured and unruptured intracranial aneurysms. MATERIALS AND METHODS: 363 ruptured aneurysms and 535 unruptured aneurysms from Hospital 1 were included in the training set. 63 ruptured aneurysms and 190 unruptured aneurysms from Hospital 2 were used for independent external testing. Aneurysm detection, segmentation and morphological features extraction were automatically performed with a 3-dimensional convolutional neural network (CNN). Radiomic features were additionally computed via pyradiomics package. After dimensionality reduction, three classification models including support vector machines (SVM), random forests (RF), and multi-layer perceptron (MLP) were established and evaluated via area under the curve (AUC) of receiver operating characteristics. Delong tests were used for the comparison of different models. RESULTS: The 3-dimensional CNN automatically detected, segmented aneurysms and calculated 21 morphological features for each aneurysm. The pyradiomics provided 14 radiomics features. After dimensionality reduction, 13 features were found associated with aneurysm rupture. The AUCs of SVM, RF and MLP on the training dataset and external testing dataset were 0.86, 0.85, 0.90 and 0.85, 0.88, 0.86, respectively, for the discrimination of ruptured and unruptured intracranial aneurysms. Delong tests showed that there was no significant difference among the three models. CONCLUSIONS: In this study, three classification models were established to distinguish ruptured and unruptured aneurysms accurately. The aneurysms segmentation and morphological measurements were performed automatically, which greatly improved the clinical efficiency. CLINICAL RELEVANCE STATEMENT: Our fully automatic models could rapidly process the CTA data and evaluate the status of aneurysms in one minute.

Diagnosis of coronary artery disease in patients with type 2 diabetes mellitus based on computed tomography and pericoronary adipose tissue radiomics: a retrospective cross-sectional study.

BACKGROUND: Patients with type 2 diabetes mellitus (T2DM) are highly susceptible to cardiovascular disease, and coronary artery disease (CAD) is their leading cause of death. We aimed to assess whether computed tomography (CT) based imaging parameters and radiomic features of pericoronary adipose tissue (PCAT) can improve the diagnostic efficacy of whether patients with T2DM have developed CAD. METHODS: We retrospectively recruited 229 patients with T2DM but no CAD history (146 were diagnosed with CAD at this visit and 83 were not). We collected clinical information and extracted imaging manifestations from CT images and 93 radiomic features of PCAT from all patients. All patients were randomly divided into training and test groups at a ratio of 7:3. Four models were constructed, encapsulating clinical factors (Model 1), clinical factors and imaging indices (Model 2), clinical factors and Radscore (Model 3), and all together (Model 4), to identify patients with CAD. Receiver operating characteristic curves and decision curve analysis were plotted to evaluate the model performance and pairwise model comparisons were performed via the DeLong test to demonstrate the additive value of different factors. RESULTS: In the test set, the areas under the curve (AUCs) of Model 2 and Model 4 were 0.930 and 0.929, respectively, with higher recognition effectiveness compared to the other two models (each p < 0.001). Of these models, Model 2 had higher diagnostic efficacy for CAD than Model 1 (p < 0.001, 95% CI [0.129-0.350]). However, Model 4 did not improve the effectiveness of the identification of CAD compared to Model 2 (p = 0.776); similarly, the AUC did not significantly differ between Model 3 (AUC = 0.693) and Model 1 (AUC = 0.691, p = 0.382). Overall, Model 2 was rated better for the diagnosis of CAD in patients with T2DM. CONCLUSIONS: A comprehensive diagnostic model combining patient clinical risk factors with CT-based imaging parameters has superior efficacy in diagnosing the occurrence of CAD in patients with T2DM.

Fine-Grained Assessment of COVID-19 Severity Based on Clinico-Radiological Data Using Machine Learning.

BACKGROUND: The severe and critical cases of COVID-19 had high mortality rates. Clinical features, laboratory data, and radiological features provided important references for the assessment of COVID-19 severity. The machine learning analysis of clinico-radiological features, especially the quantitative computed tomography (CT) image analysis results, may achieve early, accurate, and fine-grained assessment of COVID-19 severity, which is an urgent clinical need. OBJECTIVE: To evaluate if machine learning algorithms using CT-based clinico-radiological features could achieve the accurate fine-grained assessment of COVID-19 severity. METHODS: The clinico-radiological features were collected from 78 COVID-19 patients with different severities. A neural network was developed to automatically measure the lesion volume from CT images. The severity was clinically diagnosed using two-type (severe and non-severe) and fine-grained four-type (mild, regular, severe, critical) classifications, respectively. To investigate the key features of COVID-19 severity, statistical analyses were performed between patients' clinico-radiological features and severity. Four machine learning algorithms (decision tree, random forest, SVM, and XGBoost) were trained and applied in the assessment of COVID-19 severity using clinico-radiological features. RESULTS: The CT imaging features (CTscore and lesion volume) were significantly related with COVID-19 severity (p < 0.05 in statistical analysis for both in two-type and fine-grained four-type classifications). The CT imaging features significantly improved the accuracy of machine learning algorithms in assessing COVID-19 severity in the fine-grained four-type classification. With CT analysis results added, the four-type classification achieved comparable performance to the two-type one. CONCLUSIONS: CT-based clinico-radiological features can provide an important reference for the accurate fine-grained assessment of illness severity using machine learning to achieve the early triage of COVID-19 patients.

Baseline MRI-based radiomics model assisted predicting disease progression in nasopharyngeal carcinoma patients with complete response after treatment.

BACKGROUND: Accurate pretreatment prediction for disease progression of nasopharyngeal carcinoma is key to intensify therapeutic strategies to high-risk individuals. Our aim was to evaluate the value of baseline MRI-based radiomics machine-learning models in predicting the disease progression in nasopharyngeal carcinoma patients who achieved complete response after treatment. METHODS: In this retrospective study, 171 patients with pathologically confirmed nasopharyngeal carcinoma were included. Using hold-out cross validation scheme (7:3), relevant radiomic features were selected with the least absolute shrinkage and selection operator method based on baseline T2-weighted fat suppression and contrast-enhanced T1-weighted images in the training cohort. After Pearson's correlation analysis of selected radiomic features, multivariate logistic regression analysis was applied to radiomic features and clinical characteristics selection. Logistic regression analysis and support vector machine classifier were utilized to build the predictive model respectively. The predictive accuracy of the model was evaluated by ROC analysis along with sensitivity, specificity and AUC calculated in the validation cohort. RESULTS: A prediction model using logistic regression analysis comprising 4 radiomics features (HGLZE_T2H, HGLZE_T1, LDLGLE_T1, and GLNU_T1) and 5 clinical features (histology, T stage, N stage, smoking history, and age) showed the best performance with an AUC of 0.75 in the training cohort (95% CI: 0.66-0.83) and 0.77 in the validation cohort (95% CI: 0.64-0.90). The nine independent impact factors were entered into the nomogram. The calibration curves for probability of 3-year disease progression showed good agreement. The features of this prediction model showed satisfactory clinical utility with decision curve analysis. CONCLUSIONS: A radiomics model derived from pretreatment MR showed good performance for predicting disease progression in nasopharyngeal carcinoma and may help to improve clinical decision making.

Vertebral MRI-based radiomics model to differentiate multiple myeloma from metastases: influence of features number on logistic regression model performance.

OBJECTIVES: This study aimed to use the most frequent features to establish a vertebral MRI-based radiomics model that could differentiate multiple myeloma (MM) from metastases and compare the model performance with different features number. METHODS: We retrospectively analyzed conventional MRI (T1WI and fat-suppression T2WI) of 103 MM patients and 138 patients with metastases. The feature selection process included four steps. The first three steps defined as conventional feature selection (CFS), carried out 50 times (ten times with 5-fold cross-validation), included variance threshold, SelectKBest, and least absolute shrinkage and selection operator. The most frequent fixed features were selected for modeling during the last step. The number of events per independent variable (EPV) is the number of patients in a smaller subgroup divided by the number of radiomics features considered in developing the prediction model. The EPV values considered were 5, 10, 15, and 20. Therefore, we constructed four models using the top 16, 8, 6, and 4 most frequent features, respectively. The models constructed with features selected by CFS were also compared. RESULTS: The AUCs of 20EPV-Model, 15EPV-Model, and CSF-Model (AUC = 0.71, 0.81, and 0.78) were poor than 10EPV-Model (AUC = 0.84, p < 0.001). The AUC of 10EPV-Model was comparable with 5EPV-Model (AUC = 0.85, p = 0.480). CONCLUSIONS: The radiomics model constructed with an appropriate small number of the most frequent features could well distinguish metastases from MM based on conventional vertebral MRI. Based on our results, we recommend following the 10 EPV as the rule of thumb for feature selection. KEY POINTS: • The developed radiomics model could distinguish metastases from multiple myeloma based on conventional vertebral MRI. • An accurate model based on just a handful of the most frequent features could be constructed by utilizing multiple feature reduction techniques. • An event per independent variable value of 10 is recommended as a rule of thumb for modeling feature selection.

A distributed fMRI-based signature for the subjective experience of fear.

The specific neural systems underlying the subjective feeling of fear are debated in affective neuroscience. Here, we combine functional MRI with machine learning to identify and evaluate a sensitive and generalizable neural signature predictive of the momentary self-reported subjective fear experience across discovery (n = 67), validation (n = 20) and generalization (n = 31) cohorts. We systematically demonstrate that accurate fear prediction crucially requires distributed brain systems, with important contributions from cortical (e.g., prefrontal, midcingulate and insular cortices) and subcortical (e.g., thalamus, periaqueductal gray, basal forebrain and amygdala) regions. We further demonstrate that the neural representation of subjective fear is distinguishable from the representation of conditioned threat and general negative affect. Overall, our findings suggest that subjective fear, which exhibits distinct neural representation with some other aversive states, is encoded in distributed systems rather than isolated 'fear centers'.

Differentiating Parkinson's disease motor subtypes: A radiomics analysis based on deep gray nuclear lesion and white matter.

OBJECTIVE: To investigate the feasibility of radiomics analysis of brain MR images to differentiate Parkinson's disease motor subtypes. METHODS: 42 postural instability gait difficulty (PIGD) patients, 92 tremor-dominant (TD) patients and 96 healthy controls were included from the Parkinson's Progressive Marker Initiative public database. For each subject, 4850 radiomic features from 148 cortical and 14 subcortical brain regions were extracted. The variance threshold and the least absolute shrinkage and selection operator were used to select the optimal features. Classification models based on Support Vector Machine, Logistic Regrcession, and Multi-Layer Perceptron were constructed to assess the performance of optimal features in the discrimination of the two subtypes. Correlations between radiomic features and clinical scores of the two subtypes were estimated. RESULTS: The Support Vector Machine demonstrated the best performance in discriminating between the two subtypes, and the mean area under the curve was 0.833 (specificity = 83.3%, sensitivity = 75.0%, and accuracy = 80.7%). For the postural instability gait difficulty patients, these optimal features in the hippocampal showed closed correlations with the Montreal Cognitive Assessment scores (P < 0.05). CONCLUSION: The results of our study provide preliminary evidence that radiomics analysis of brain MR images could allow discrimination between patients with TD, PIGD and control subjects and has great potential value in the clinical practice.

Establishment of a Clinical Nomogram Model to Predict the Progression of COVID-19 to Severe Disease.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a worldwide public health pandemic with a high mortality rate, among severe cases. The disease is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. It is important to ensure early detection of the virus to curb disease progression to severe COVID-19. This study aims to establish a clinical-nomogram model to predict the progression to severe COVID-19 in a timely and efficient manner. METHODS: This retrospective study included 202 patients with COVID-19 who were admitted to the Fifth Affiliated Hospital of Sun Yat-sen University and Shiyan Taihe Hospital from January 17 to April 30, 2020. The patients were randomly assigned to the training dataset (n = 163, with 43 progressing to severe COVID-19) or the validation dataset (n = 39, with 10 progressing to severe COVID-19) at a ratio of 8:2. The optimal subset algorithm was applied to filter for the clinical factors most relevant to the disease progression. Based on these factors, the logistic regression model was fit to distinguish severe (including severe and critical cases) from non-severe (including mild and moderate cases) COVID-19. Sensitivity, specificity, and area under the curve (AUC) were calculated using the R software package to evaluate prediction performance. A clinical nomogram was established and performance assessed using the discrimination curve. RESULTS: Risk factors, including demographic data, symptoms, laboratory and image findings, were recorded for the 202 patients. Eight of the 53 variables that were entered into the selection process were selected via the best subset algorithm to establish the predictive model; they included gender, age, BMI, CRP, D-dimer, TP, ALB, and involved-lobe. AUC, sensitivity, and specificity were 0.91, 0.84 and 0.86 for the training dataset, and 0.87, 0.66, and 0.80 for the validation dataset. CONCLUSION: We established an efficient and reliable clinical nomogram model which showed that gender, age, and initial indexes including BMI, CRP, D-dimer, involved-lobe, TP, and ALB could predict the risk of progression to severe COVID-19.

Early prediction of severity in coronavirus disease (COVID-19) using quantitative CT imaging.

PURPOSE: To evaluate whether the extent of COVID-19 pneumonia on CT scans using quantitative CT imaging obtained early in the illness can predict its future severity. METHODS: We conducted a retrospective single-center study on confirmed COVID-19 patients between January 18, 2020 and March 5, 2020. A quantitative AI algorithm was used to evaluate each patient's CT scan to determine the proportion of the lungs with pneumonia (VR) and the rate of change (RAR) in VR from scan to scan. Patients were classified as being in the severe or non-severe group based on their final symptoms. Penalized B-splines regression modeling was used to examine the relationship between mean VR and days from onset of symptoms in the two groups, with 95% and 99% confidence intervals. RESULTS: Median VR max was 18.6% (IQR 9.1-32.7%) in 21 patients in the severe group, significantly higher (P < 0.0001) than in the 53 patients in non-severe group (1.8% (IQR 0.4-5.7%)). RAR was increasing with a median RAR of 2.1% (IQR 0.4-5.5%) in severe and 0.4% (IQR 0.1-0.9%) in non-severe group, which was significantly different (P < 0.0001). Penalized B-spline analyses showed positive relationships between VR and days from onset of symptom. The 95% confidence limits of the predicted means for the two groups diverged 5 days after the onset of initial symptoms with a threshold of 11.9%. CONCLUSION: Five days after the initial onset of symptoms, CT could predict the patients who later developed severe symptoms with 95% confidence.

Radiomics Nomograms Based on Non-enhanced MRI and Clinical Risk Factors for the Differentiation of Chondrosarcoma from Enchondroma.

BACKGROUND: Differentiating chondrosarcoma from enchondroma using conventional MRI remains challenging. An effective method for accurate preoperative diagnosis could affect the management and prognosis of patients. PURPOSE: To validate and evaluate radiomics nomograms based on non-enhanced MRI and clinical risk factors for the differentiation of chondrosarcoma from enchondroma. STUDY TYPE: Retrospective. POPULATION: A total of 103 patients with pathologically confirmed chondrosarcoma (n = 53) and enchondroma (n = 50) were randomly divided into training (n = 68) and validation (n = 35) groups. FIELD STRENGTH/SEQUENCE: Axial non-contrast-enhanced T1-weighted images (T1WI) and fat-suppressed T2-weighted images (T2WI-FS) were acquired at 3.0 T. ASSESSMENT: Clinical risk factors (sex, age, and tumor location) and diagnosis assessment based on morphologic MRI by three radiologists were recorded. Three radiomics signatures were established based on the T1WI, T2WI-FS, and T1WI + T2WI-FS sequences. Three clinical radiomics nomograms were developed based on the clinical risk factors and three radiomics signatures. STATISTICAL TESTS: The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of radiomics signatures and clinical radiomics nomograms. RESULTS: Tumor location was an important clinical risk factor (P < 0.05). The radiomics signature based on T1WI and T1WI + T2WI-FS features performed better than that based on T2WI-FS in the validation group (AUC in the validation group: 0.961, 0.938, and 0.833, respectively; P < 0.05). In the validation group, the three clinical radiomics nomograms (T1WI, T2WI-FS, and T1WI + T2WI-FS) achieved AUCs of 0.938, 0.935, and 0.954, respectively. In all patients, the clinical radiomics nomogram based on T2WI-FS (AUC = 0.967) performed better than that based on T2WI-FS (AUC = 0.901, P < 0.05). DATA CONCLUSION: The proposed clinical radiomics nomogram showed promising performance in differentiating chondrosarcoma from enchondroma. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 2.

Prediction of High-Risk Cytogenetic Status in Multiple Myeloma Based on Magnetic Resonance Imaging: Utility of Radiomics and Comparison of Machine Learning Methods.

BACKGROUND: Radiomics has shown promising results in the diagnosis, efficacy, and prognostic assessments of multiple myeloma (MM). However, little evidence exists on the utility of radiomics in predicting a high-risk cytogenetic (HRC) status in MM. PURPOSE: To develop and test a magnetic resonance imaging (MRI)-based radiomics model for predicting an HRC status in MM patients. STUDY TYPE: Retrospective. POPULATION: Eighty-nine MM patients (HRC [n: 37] and non-HRC [n: 52]). FIELD STRENGTH/SEQUENCE: A 3.0 T; fast spin-echo (FSE): T1-weighted image (T1WI) and fat-suppression T2WI (FS-T2WI). ASSESSMENT: Overall, 1409 radiomics features were extracted from each volume of interest drawn by radiologists. Three sequential feature selection steps-variance threshold, SelectKBest, and least absolute shrinkage selection operator-were repeated 10 times with 5-fold cross-validation. Radiomics models were constructed with the top three frequency features of T1 WI/T2 WI/two-sequence MRI (T1 WI and FS-T2 WI). Radiomics models, clinical data (age and visually assessed MRI pattern), or radiomics combined with clinical data were used with six classifiers to distinguish between HRC and non-HRC statuses. Six classifiers used were support vector machine, random forest, logistic regression (LR), decision tree, k-nearest neighbor, and XGBoost. Model performance was evaluated with area under the curve (AUC) values. STATISTICAL TESTS: Mann-Whitney U-test, Chi-squared test, Z test, and DeLong method. RESULTS: The LR classifier performed better than the other classifiers based on different data (AUC: 0.65-0.82; P < 0.05). The two-sequence MRI models performed better than the other data models using different classifiers (AUC: 0.68-0.82; P < 0.05). Thus, the LR two-sequence model yielded the best performance (AUC: 0.82 ± 0.02; sensitivity: 84.1%; specificity: 68.1%; accuracy: 74.7%; P < 0.05). CONCLUSION: The LR-based machine learning method appears superior to other classifier methods for assessing HRC in MM. Radiomics features based on two-sequence MRI showed good performance in differentiating HRC and non-HRC statuses in MM. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Intrinsic, dynamic and effective connectivity among large-scale brain networks modulated by oxytocin.

The neuropeptide oxytocin is a key modulator of social-emotional behavior and its intranasal administration can influence the functional connectivity of brain networks involved in the control of attention, emotion and reward reported in humans. However, no studies have systematically investigated the effects of oxytocin on dynamic or directional aspects of functional connectivity. The present study employed a novel computational framework to investigate these latter aspects in 15 oxytocin-sensitive regions using data from randomized placebo-controlled between-subject resting state functional MRI studies incorporating 200 healthy subjects. In order to characterize the temporal dynamics, the 'temporal state' was defined as a temporal segment of the whole functional MRI signal which exhibited a similar functional interaction pattern among brain regions of interest. Results showed that while no significant effects of oxytocin were found on brain temporal state related characteristics (including temporal state switching frequency, probability of transitions between neighboring states, and averaged dwell time on each state) oxytocin extensively (n = 54 links) modulated effective connectivity among the 15 regions. The effects of oxytocin were primarily characterized by increased effective connectivity both between and within emotion, reward, salience, attention and social cognition processing networks and their interactions with the default mode network. Top-down control over emotional processing regions such as the amygdala was particularly affected. Oxytocin also increased effective homotopic interhemispheric connectivity in almost all these regions. Additionally, the effects of oxytocin on effective connectivity were sex-dependent, being more extensive in males. Overall, these findings suggest that modulatory effects of oxytocin on both within- and between-network interactions may underlie its functional influence on social-emotional behaviors, although in a sex-dependent manner. These findings may be of particular relevance to potential therapeutic use of oxytocin in psychiatric disorders associated with social dysfunction, such as autism spectrum disorder and schizophrenia, where directionality of treatment effects on causal interactions between networks may be of key importance .