Quantitative parameters of CT texture analysis as potential markersfor early prediction of spontaneous intracranial hemorrhage enlargement

Quantitative imaging for predicting hematoma expansion in intracerebral hemorrhage: A multimodel comparison

BACKGROUND

Several studies report that radiomics provides additional information for predicting hematoma expansion in intracerebral hemorrhage (ICH). However, the comparison of diagnostic performance of radiomics for predicting revised hematoma expansion (RHE) remains unclear.

METHODS

The cohort comprised 312 consecutive patients with ICH. A total of 1106 radiomics features from seven categories were extracted using Python software. Support vector machines achieved the best performance in both the training and validation datasets. Clinical factors models were constructed to predict RHE. Receiver operating characteristic curve analysis was used to assess the abilities of non-contrast computed tomography (NCCT) signs, radiomics features, and combined models to predict RHE.

RESULTS

We finally selected the top 21 features for predicting RHE. After univariate analysis, 4 clinical factors and 5 NCCT signs were selected for inclusion in the prediction models. In the training and validation dataset, radiomics features had a higher predictive value for RHE (AUC = 0.83) than a single NCCT sign and expansion-prone hematoma. The combined prediction model including radiomics features, clinical factors, and NCCT signs achieved higher predictive performances for RHE (AUC = 0.88) than other combined models.

CONCLUSIONS

NCCT radiomics features have a good degree of discrimination for predicting RHE in ICH patients. Combined prediction models that include quantitative imaging significantly improve the prediction of RHE, which may assist in the risk stratification of ICH patients for anti-expansion treatments.

Establishment and validation of a CT-based prediction model for the good dissolution of mild chronic subdural hematoma with atorvastatin treatment

PURPOSE

To develop and validate a prediction model based on imaging data for the prognosis of mild chronic subdural hematoma undergoing atorvastatin treatment.

METHODS

We developed the prediction model utilizing data from patients diagnosed with CSDH between February 2019 and November 2021. Demographic characteristics, medical history, and hematoma characteristics in non-contrast computed tomography (NCCT) were extracted upon admission to the hospital. To reduce data dimensionality, a backward stepwise regression model was implemented to build a prognostic prediction model. We calculated the area under the receiver operating characteristic curve (AUC) of the prognostic prediction model by a tenfold cross-validation procedure.

RESULTS

Maximum thickness, volume, mean density, morphology, and kurtosis of the hematoma were identified as the most significant predictors of good hematoma dissolution in mild CSDH patients undergoing atorvastatin treatment. The prediction model exhibited good discrimination, with an area under the curve (AUC) of 0.82 (95% confidence interval [CI], 0.74-0.90) and good calibration (p = 0.613). The validation analysis showed the AUC of the final prognostic prediction model is 0.80 (95% CI 0.71-0.86) and it has good prediction performance.

CONCLUSION

The imaging data-based prediction model has demonstrated great prediction accuracy for good hematoma dissolution in mild CSDH patients undergoing atorvastatin treatment. The study results emphasize the importance of imaging data evaluation in the management of CSDH patients.

A Comparative Study of a Nomogram and Machine Learning Models in Predicting Early Hematoma Expansion in Hypertensive Intracerebral Hemorrhage

RATIONALE AND OBJECTIVES

Early identification for hematoma expansion can help improve patient outcomes. Presently, there are many methods to predict hematoma expansion. This study compared a variety of models to find a model suitable for clinical promotion.

MATERIALS AND METHODS

Non-contrast head CT images and clinical data were collected from 203 patients diagnosed with hypertensive intracerebral hemorrhage. Radiomics features were extracted from all CT images, and the dataset was randomly divided into training and validation sets (7:3 ratio) after applying the synthetic minority oversampling method. The radiomics score (Radscore) was calculated using least absolute shrinkage and selection operator (LASSO) regression, combined with selected clinical predictors, to develop a nomogram and four machine learning (ML) models: logistic regression, random forest, support vector machine, and extreme gradient boosting (XGBoost). Discrimination, calibration and clinical usefulness of the nomogram and ML models were assessed.

RESULTS

The nomogram and ML models were integrated with Radscore and clinical predictors. The nomogram demonstrated favorable discriminatory ability in the training set with an AUC of 0.80, which was confirmed in the validation set (AUC=0.76). Among the ML models, the XGBoost model achieved the highest AUC (training set=0.89 and validation set=0.85), surpassing that of the nomogram. The XGBoost model exhibited good clinical usefulness.

CONCLUSION

Both the nomogram and ML models constructed by non-contrast head CT image-based Radscore integrated with clinical predictors can predict early hematoma expansion of hypertensive intracerebral hemorrhage, and the XGBoost model had the highest prediction performance and best clinical usefulness.

Prediction of early hematoma expansion of spontaneous intracerebral hemorrhage based on deep learning radiomics features of noncontrast computed tomography

OBJECTIVES

Aimed to develop a nomogram model based on deep learning features and radiomics features for the prediction of early hematoma expansion.

METHODS

A total of 561 cases of spontaneous intracerebral hemorrhage (sICH) with baseline Noncontrast Computed Tomography (NCCT) were included. The metrics of hematoma detection were evaluated by Intersection over Union (IoU), Dice coefficient (Dice), and accuracy (ACC). The semantic features of sICH were judged by EfficientNet-B0 classification model. Radiomics analysis was performed based on the region of interest which was automatically segmented by deep learning. A combined model was constructed in order to predict the early expansion of hematoma using multivariate binary logistic regression, and a nomogram and calibration curve were drawn to verify its predictive efficacy by ROC analysis.

RESULTS

The accuracy of hematoma detection by segmentation model was 98.2% for IoU greater than 0.6 and 76.5% for IoU greater than 0.8 in the training cohort. In the validation cohort, the accuracy was 86.6% for IoU greater than 0.6 and 70.0% for IoU greater than 0.8. The AUCs of the deep learning model to judge semantic features were 0.95 to 0.99 in the training cohort, while in the validation cohort, the values were 0.71 to 0.83. The deep learning radiomics model showed a better performance with higher AUC in training cohort (0.87), internal validation cohort (0.83), and external validation cohort (0.82) than either semantic features or Radscore.

CONCLUSION

The combined model based on deep learning features and radiomics features has certain efficiency for judging the risk grade of hematoma.

CLINICAL RELEVANCE STATEMENT

Our study revealed that the deep learning model can significantly improve the work efficiency of segmentation and semantic feature classification of spontaneous intracerebral hemorrhage. The combined model has a good prediction efficiency for early hematoma expansion.

KEY POINTS

• We employ a deep learning algorithm to perform segmentation and semantic feature classification of spontaneous intracerebral hemorrhage and construct a prediction model for early hematoma expansion. • The deep learning radiomics model shows a favorable performance for the prediction of early hematoma expansion. • The combined model holds the potential to be used as a tool in judging the risk grade of hematoma.

CT texture analysis for differentiating between peritoneal carcinomatosis and peritoneal tuberculosis: a cross-sectional study

PURPOSE

Peritoneal carcinomatosis (PC) and peritoneal tuberculosis (PTB) have similar clinical and radiologic imaging features, which make it very difficult to differentiate between the two entities clinically. Our aim was to determine if the CT textural parameters of omental lesions among patients with PC were different from those with PTB.

METHODS

All patients who had undergone omental biopsy at our institution from January 2010 to December 2018 and had a tissue diagnosis of PC or PTB were eligible for inclusion. Patients who did not have a contrast-enhanced CT abdomen within one month of the omental biopsy were excluded. A region of interest (ROI) was manually drawn over omental lesions and radiomic features were extracted using open-source LIFEx software. Statistical analysis was performed to compare mean differences in CT texture parameters between the PC and PTB groups.

RESULTS

A total of 66 patients were included in the study of which 38 and 28 had PC and PTB, respectively. Omental lesions in patients with PC had higher mean radiodensity (mean difference: +32.4; p = 0.001), higher mean entropy (mean difference: +0.11; p < 0.001), and lower mean energy (mean difference: -0.024; p = 0.001) compared to those in PTB. Additionally, omental lesions in the PC group had lower gray-level co-occurrence matrix (GLCM) homogeneity (mean difference: -0.073; p < 0.001) and higher GLCM dissimilarity (mean difference: +0.480; p < 0.001) as compared to the PTB group.

CONCLUSION

CT texture parameters of omental lesions differed significantly between patients with PTB and those with PC, which may help clinicians in differentiating between the two entities.

Comparative evaluation of multiparametric lumbar MRI radiomic models for detecting osteoporosis

BACKGROUND

Osteoporosis is a serious global public health issue. Currently, there are few studies that explore the use of multiparametric MRI radiomics for osteoporosis detection. The purpose of this study was to compare the performance of radiomics features from multiple MRI sequences (T1WI, T2WI and T1WI combined with T2WI) for detecting osteoporosis in patients.

METHODS

A retrospective analysis was performed on 160 patients who had undergone dual-energy X-ray absorptiometry(DXA) and lumbar magnetic resonance imaging (MRI) at our hospital. Among them, 86 patients were diagnosed with abnormal bone mass (osteoporosis or low bone mass), and 74 patients were diagnosed with normal bone mass based on the DXA results. Sagittal T1-and T2-weighted images of all patients were imported into the uAI Research Portal (United Imaging Intelligence) for image delineation and radiomics analysis, where a series of radiomic features were obtained. A radiomic model that included T1WI, T2WI, and T1WI+T2WI was established using features selected by LASSO regression. We used ROC curve analysis to evaluate the predictive efficacy of each model for identifying bone abnormalities and conducted decision curve analysis (DCA) to evaluate the net benefit of each model. Finally, we validated the model in a sample of 35 patients from different health care institution.

RESULTS

The T1WI + T2WI radiomics model showed better screening performance for patients with abnormal bone mass. In the training group, the sensitivity was 0.758, the specificity was 0.78, and the accuracy was 0.768 (AUC =0.839, 95% CI=0.757-0.901). In the validation group, the sensitivity was 0.792, the specificity was 0.875, and the accuracy was 0.833 (AUC =0.86, 95% CI=0.73-0.943).The DCA also showed that the combined model had better net benefits. In the external validation group, the sensitivity was 0.764, the specificity was 0.833, and the accuracy was 0.8 (AUC =0.824, 95% CI 0.678-0.969).

CONCLUSIONS

Radiomics-based multiparametric MRI can be used for the quantitative analysis of lumbar MRI and for accurately screening patients with abnormal bone mass.

CT-based radiomics models predict spontaneous intracerebral hemorrhage expansion and are comparable with CT angiography spot sign

Background and purpose

This study aimed to investigate the efficacy of radiomics, based on non-contrast computed tomography (NCCT) and computed tomography angiography (CTA) images, in predicting early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (SICH). Additionally, the predictive performance of these models was compared with that of the established CTA spot sign.

Materials and methods

A retrospective analysis was conducted using CT images from 182 patients with SICH. Data from the patients were divided into a training set (145 cases) and a testing set (37 cases) using random stratified sampling. Two radiomics models were constructed by combining quantitative features extracted from NCCT images (the NCCT model) and CTA images (the CTA model) using a logistic regression (LR) classifier. Additionally, a univariate LR model based on the CTA spot sign (the spot sign model) was established. The predictive performance of the two radiomics models and the spot sign model was compared according to the area under the receiver operating characteristic (ROC) curve (AUC).

Results

For the training set, the AUCs of the NCCT, CTA, and spot sign models were 0.938, 0.904, and 0.726, respectively. Both the NCCT and CTA models demonstrated superior predictive performance compared to the spot sign model (all P < 0.001), with the performance of the two radiomics models being comparable (P = 0.068). For the testing set, the AUCs of the NCCT, CTA, and spot sign models were 0.925, 0.873, and 0.720, respectively, with only the NCCT model exhibiting significantly greater predictive value than the spot sign model (P = 0.041).

Conclusion

Radiomics models based on NCCT and CTA images effectively predicted HE in patients with SICH. The predictive performances of the NCCT and CTA models were similar, with the NCCT model outperforming the spot sign model. These findings suggest that this approach has the potential to reduce the need for CTA examinations, thereby reducing radiation exposure and the use of contrast agents in future practice for the purpose of predicting hematoma expansion.

The value of computed tomography texture analysis in identifying chronic subdural hematoma patients with a good response to polytherapy

This study aimed to investigate the predictive factors of therapeutic efficacy for chronic subdural hematoma (CSDH) patients receiving atorvastatin combined with dexamethasone therapy by using clinical imaging characteristics in conjunction with computed tomography (CT) texture analysis (CTTA). Clinical imaging characteristics and CT texture parameters at admission were retrospectively investigated in 141 CSDH patients who received atorvastatin combined with dexamethasone therapy from June 2019 to December 2022. The patients were divided into a training set (n = 81) and a validation set (n = 60). Patients in the training data were divided into two groups based on the effectiveness of the treatment. Univariate and multivariate analyses were performed to assess the potential factors that could indicate the prognosis of CSDH patients in the training set. The receiver operating characteristic (ROC) curve was used to analyze the predictive efficacy of the significant factors in predicting the prognosis of CSDH patients and was validated using a validation set. The multivariate analysis showed that the hematoma density to brain parenchyma density ratio, singal min (minimum) and singal standard deviation of the pixel distribution histogram, and inhomogeneity were independent predictors for the prognosis of CSDH patients based on atorvastatin and dexamethasone therapy. The area under the ROC curve between the two groups was between 0.716 and 0.806. As determined by significant factors, the validation's accuracy range was 0.816 to 0.952. Clinical imaging characteristics in conjunction with CTTA could aid in distinguishing patients with CSDH who responded well to atorvastatin combined with dexamethasone.

Machine-learning-based performance comparison of two-dimensional (2D) and three-dimensional (3D) CT radiomics features for intracerebral haemorrhage expansion

AIM

To investigate the value of non-contrast CT (NCCT)-based two-dimensional (2D) radiomics features in predicting haematoma expansion (HE) after spontaneous intracerebral haemorrhage (ICH) and compare its predictive ability with the three-dimensional (3D) signature.

MATERIALS AND METHODS

Three hundred and seven ICH patients who received baseline NCCT within 6 h of ictus from two stroke centres were analysed retrospectively. 2D and 3D radiomics features were extracted in the manner of one-to-one correspondence. The 2D and 3D models were generated by four different machine-learning algorithms (regularised L1 logistic regression, decision tree, support vector machine and AdaBoost), and the receiver operating characteristic (ROC) curve was used to compare their predictive performance. A robustness analysis was performed according to baseline haematoma volume.

RESULTS

Each feature type of 2D and 3D modalities used for subsequent analyses had excellent consistency (mean ICC >0.9). Among the different machine-learning algorithms, pairwise comparison showed no significant difference in both the training (mean area under the ROC curve [AUC] 0.858 versus 0.802, all p>0.05) and validation datasets (mean AUC 0.725 versus 0.678, all p>0.05), and the 10-fold cross-validation evaluation yielded similar results. The AUCs of the 2D and 3D models were comparable either in the binary or tertile volume analysis (all p>0.5).

CONCLUSION

NCCT-derived 2D radiomics features exhibited acceptable and similar performance to the 3D features in predicting HE, and this comparability seemed unaffected by initial haematoma volume. The 2D signature may be preferred in future HE-related radiomic works given its compatibility with emergency condition of ICH.

Radiomic markers of intracerebral hemorrhage expansion on non-contrast CT: independent validation and comparison with visual markers

Objective

To devise and validate radiomic signatures of impending hematoma expansion (HE) based on admission non-contrast head computed tomography (CT) of patients with intracerebral hemorrhage (ICH).

Methods

Utilizing a large multicentric clinical trial dataset of hypertensive patients with spontaneous supratentorial ICH, we developed signatures predictive of HE in a discovery cohort (n = 449) and confirmed their performance in an independent validation cohort (n = 448). In addition to n = 1,130 radiomic features, n = 6 clinical variables associated with HE, n = 8 previously defined visual markers of HE, the BAT score, and combinations thereof served as candidate variable sets for signatures. The area under the receiver operating characteristic curve (AUC) quantified signatures' performance.

Results

A signature combining select radiomic features and clinical variables attained the highest AUC (95% confidence interval) of 0.67 (0.61-0.72) and 0.64 (0.59-0.70) in the discovery and independent validation cohort, respectively, significantly outperforming the clinical (pdiscovery = 0.02, pvalidation = 0.01) and visual signature (pdiscovery = 0.03, pvalidation = 0.01) as well as the BAT score (pdiscovery < 0.001, pvalidation < 0.001). Adding visual markers to radiomic features failed to improve prediction performance. All signatures were significantly (p < 0.001) correlated with functional outcome at 3-months, underlining their prognostic relevance.

Conclusion

Radiomic features of ICH on admission non-contrast head CT can predict impending HE with stable generalizability; and combining radiomic with clinical predictors yielded the highest predictive value. By enabling selective anti-expansion treatment of patients at elevated risk of HE in future clinical trials, the proposed markers may increase therapeutic efficacy, and ultimately improve outcomes.

Prediction of Early Perihematomal Edema Expansion Based on Noncontrast Computed Tomography Radiomics and Machine Learning in Intracerebral Hemorrhage

OBJECTIVES

To investigate the predictive value of noncontrast computed tomography (NCCT) models based on radiomics features and machine learning for early perihematomal edema (PHE) expansion in patients with spontaneous intracerebral hemorrhage (ICH).

METHODS

We retrospectively reviewed NCCT data from 214 patients with spontaneous ICH. All radiomics features were extracted from volume of interest of hematomas on admission scans. A total of 8 machine learning methods were applied for constructing models in the training and the test set. Receiver operating characteristic analysis and the areas under the curve were used to evaluate the predictive value.

RESULTS

A total of 23 features were finally selected to establish models of early PHE expansion after feature screening. Patients were randomly assigned into training (n = 171) and test (n = 43) sets. The accuracy, sensitivity, and specificity in the test set were 72.1%, 90.0%, and 66.7% for the support vector machine model; 79.1%, 70.0%, and 84.4% for the k-nearest neighbor model; 88.4%, 90.0%, and 87.9% for the logistic regression model; 74.4%, 90.0%, and 69.7% for the extra tree model; 74.4%, 90.0%, and 69.7% for the extreme gradient boosting model; 83.7%, 100%, and 78.8% for the multilayer perceptron (MLP) model; 72.1%, 100%, and 65.6% for the light gradient boosting machine model; and 60.5%, 90.0%, and 53.1% for the random forest model, respectively.

CONCLUSIONS

The MLP model seemed to be the best model for prediction of PHE expansion in patients with ICH. NCCT models based on radiomics features and machine learning could predict early PHE expansion and improve the discrimination of identify spontaneous intracerebral hemorrhage patients at risk of early PHE expansion.

Prediction of poor outcome in stroke patients using radiomics analysis of intraparenchymal and intraventricular hemorrhage and clinical factors

PURPOSE

To build three prognostic models using radiomics analysis of the hemorrhagic lesions, clinical variables, and their combination, to predict the outcome of stroke patients with spontaneous intracerebral hemorrhage (sICH).

MATERIALS AND METHODS

Eighty-three sICH patients were included. Among them, 40 patients (48.2%) had poor prognosis with modified Rankin scale (mRS) of 5 and 6 at discharge, and the prognostic model was built to differentiate mRS ≤ 4 vs. 5 + 6. The region of interest (ROI) of intraparenchymal hemorrhage (IPH) and intraventricular hemorrhage (IVH) were separately segmented. Features were extracted using PyRadiomics, and the support vector machine was applied to select features and build radiomics models based on IPH and IPH + IVH. The clinical models were built using multivariate logistic regression, and then the radiomics scores were combined with clinical variables to build the combined model.

RESULTS

When using IPH, the AUC for radiomics, clinical, and combined model was 0.78, 0.82, and 0.87, respectively. When using IPH + IVH, the AUC was increased to 0.80, 0.84, and 0.90, respectively. The combined model had a significantly improved AUC compared to the radiomics by DeLong test. A clinical prognostic model based on the ICH score of 0-1 only achieved AUC of 0.71.

CONCLUSIONS

The combined model using the radiomics score derived from IPH + IVH and the clinical factors could achieve a high accuracy in prediction of sICH patients with poor outcome, which may be used to assist in making the decision about the optimal care.

Quality assessment of stroke radiomics studies: Promoting clinical application

PURPOSE

To evaluate the quality of radiomics studies on stroke using a radiomics quality score (RQS), Minimum Information for Medial AI reporting (MINIMAR) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to promote clinical application.

METHODS

PubMed MEDLINE and Embase were searched to identify radiomics studies on stroke. Of 464 articles, 52 relevant original research articles were included. The RQS, MINIMAR and TRIPOD were scored to evaluate the quality of the studies by neuroradiologists.

RESULTS

Only four studies (7.7 %) performed external validation. The mean RQS was 3.2 of 36 (8.9 %), and the basic adherence rate was 24.9 %. The adherence rate was low for conducting phantom study (1.9 %), stating comparison to 'gold standard' (1.9 %), offering potential clinical utility (13.5 %) and performing cost-effectiveness analysis (1.9 %). None of the studies performed a test-retest, stated biologic correlation, conducted prospective studies, or opened codes and data to the public, resulting in low RQS. The total MINIMAR adherence rate was 47.4 %. The overall adherence rate for TRIPOD was 54.6 %, with low scores for reporting the title (2.0 %), key elements of the study setting (6.1 %), and explaining the sample size (2.0 %).

CONCLUSIONS

The overall radiomics reporting quality and reporting of published radiomics studies on stoke was suboptimal. More thorough validation and open data are needed to increase clinical applicability of radiomics studies.

A Clinical-Radiomics Based Nomogram to Predict Progressive Intraparenchymal Hemorrhage in Mild to Moderate Traumatic Injury Patients

PURPOSE

To develop a non-contrast computed tomography(NCCT)based radiomics model for predicting intraparenchymal hemorrhage progression in patients with mild to moderate traumatic brain injury(TBI).

METHODS

We retrospectively analyzed 166 mild to moderate TBI patients with intraparenchymal hemorrhage from January 2018 to December 2021. The enrolled patients were divided into training cohort and test cohort with a ratio of 6:4. Uni- and multivariable logistic regression analyses were implemented to screen clinical-radiological factors and to establish a clinical-radiological model. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), the calibration curve, the decision curve analysis, sensitivity, and specificity.

RESULTS

Eleven radiomics features, presence with SDH, and D-dimer > 5 mg/l were selected to construct the combined clinical-radiomic model for the prediction of TICH in mild to moderate TBI patients. The AUC of the combined model was 0.81(95% confidence interval (CI), 0.72 to 0.90) in the training cohort and 0.88 (95% CI 0.79 to 0.96) in the test cohort, which were superior to the clinical model alone (AUC_training = 0.72, AUC_test = 0.74). The calibration curve demonstrated that the radiomics nomogram had a good agreement between prediction and observation. Decision curve analysis confirmed clinically useful.

CONCLUSIONS

The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors can serve as a reliable and powerful tool for Predicting intraparenchymal hemorrhage progression for patients with mild to moderate TBI.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Efficacy of non-enhanced computer tomography-based radiomics for predicting hematoma expansion: A meta-analysis

Background

This meta-analysis aimed to assess the efficacy of radiomics using non-enhanced computed tomography (NCCT) for predicting hematoma expansion in patients with spontaneous intracerebral hemorrhage.

Methods

Throughout the inception of the project to April 11, 2022, a comprehensive search was conducted on PubMed, Embase, and Cochrane Central Register of Controlled Trials. The methodological quality of studies in this analysis was assessed by the radiomics quality scoring system (RQS). A meta-analysis of radiomic studies based on NCCT for predicting hematoma expansion in patients with intracerebral hemorrhage was performed. The efficacy of the radiomics approach and non-contrast CT markers was compared using network meta-analysis (NMA).

Results

Ten articles comprising a total of 1525 patients were quantitatively analyzed for hematoma expansion after cerebral hemorrhage using radiomics. Based on the included studies, the mean RQS was 14.4. The AUC value (95% confidence interval) of the radiomics model was 0.80 (0.76-0.83). Five articles comprising 846 patients were included in the NMA. The results synthesized according to Bayesian NMA revealed that the predictive ability of the radiomics model outperformed most of the NCCT biomarkers.

Conclusions

The NCCT-based radiomics approach has the potential to predict hematoma expansion. Compared to NCCT biomarkers, we recommend a radiomics approach. Standardization of the radiomics approach is required for further clinical implementation.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=324034, identifier [CRD42022324034].

Cone-beam computed tomography texture analysis can help differentiate odontogenic and non-odontogenic maxillary sinusitis

Purpose

This study aimed to assess texture analysis (TA) of cone-beam computed tomography (CBCT) images as a quantitative tool for the differential diagnosis of odontogenic and non-odontogenic maxillary sinusitis (OS and NOS, respectively).

Materials and Methods

CBCT images of 40 patients diagnosed with OS (N=20) and NOS (N=20) were evaluated. The gray level co-occurrence (GLCM) matrix parameters, and gray level run length matrix texture (GLRLM) parameters were extracted using manually placed regions of interest on lesion images. Seven texture parameters were calculated using GLCM and 4 parameters using GLRLM. The Mann-Whitney test was used for comparisons between the groups, and the Levene test was performed to confirm the homogeneity of variance (α=5%).

Results

The results showed statistically significant differences (P<0.05) between the OS and NOS patients regarding 3 TA parameters. NOS patients presented higher values for contrast, while OS patients presented higher values for correlation and inverse difference moment. Greater textural homogeneity was observed in the OS patients than in the NOS patients, with statistically significant differences in standard deviations between the groups for correlation, sum of squares, sum of entropy, and entropy.

Conclusion

TA enabled quantitative differentiation between OS and NOS on CBCT images by using the parameters of contrast, correlation, and inverse difference moment.

The Added Value of Intraventricular Hemorrhage on the Radiomics Analysis for the Prediction of Hematoma Expansion of Spontaneous Intracerebral Hemorrhage

Background: Among patients undergoing head computed tomography (CT) scans within 3 h of spontaneous intracerebral hemorrhage (sICH), 28% to 38% have hematoma expansion (HE) on follow-up CT. This study aimed to predict HE using radiomics analysis and investigate the impact of intraventricular hemorrhage (IVH) compared with the conventional approach based on intraparenchymal hemorrhage (IPH) alone. Methods: This retrospective study enrolled 127 patients with baseline and follow-up non-contrast CT (NCCT) within 4~72 h of sICH. IPH and IVH were outlined separately for performing radiomics analysis. HE was defined as an absolute hematoma growth > 6 mL or percentage growth > 33% of either IPH (HEP) or a combination of IPH and IVH (HEP+V) at follow-up. Radiomic features were extracted using PyRadiomics, and then the support vector machine (SVM) was used to build the classification model. For each case, a radiomics score was generated to indicate the probability of HE. Results: There were 57 (44.9%) HEP and 70 (55.1%) non-HEP based on IPH alone, and 58 (45.7%) HEP+V and 69 (54.3%) non-HEP+V based on IPH + IVH. The majority (>94%) of HE patients had poor early outcomes (death or modified Rankin Scale > 3 at discharge). The radiomics model built using baseline IPH to predict HEP (RMP) showed 76.4% accuracy and 0.73 area under the ROC curve (AUC). The other model using IPH + IVH to predict HEP+V (RMP+V) had higher accuracy (81.9%) with AUC = 0.80, and this model could predict poor outcomes. The sensitivity/specificity of RMP and RMP+V for HE prediction were 71.9%/80.0% and 79.3%/84.1%, respectively. Conclusion: The proposed radiomics approach with additional IVH information can improve the accuracy in prediction of HE, which is associated with poor clinical outcomes. A reliable radiomics model may provide a robust tool to help manage ICH patients and to enroll high-risk ICH cases into anti-expansion or neuroprotection drug trials.

A non-contrast computed tomography-based radiomics nomogram for the prediction of hematoma expansion in patients with deep ganglionic intracerebral hemorrhage

Background and purpose

Hematoma expansion (HE) is a critical event following acute intracerebral hemorrhage (ICH). We aimed to construct a non-contrast computed tomography (NCCT) model combining clinical characteristics, radiological signs, and radiomics features to predict HE in patients with spontaneous ICH and to develop a nomogram to assess the risk of early HE.

Materials and methods

We retrospectively reviewed 388 patients with ICH who underwent initial NCCT within 6 h after onset and follow-up CT within 24 h after initial NCCT, between January 2015 and December 2021. Using the LASSO algorithm or stepwise logistic regression analysis, five models (clinical model, radiological model, clinical-radiological model, radiomics model, and combined model) were developed to predict HE in the training cohort (n = 235) and independently verified in the test cohort (n = 153). The Akaike information criterion (AIC) and the likelihood ratio test (LRT) were used for comparing the goodness of fit of the five models, and the AUC was used to evaluate their ability in discriminating HE. A nomogram was developed based on the model with the best performance.

Results

The combined model (AIC = 202.599, χ2 = 80.6) was the best fitting model with the lowest AIC and the highest LRT chi-square value compared to the clinical model (AIC = 232.263, χ2 = 46.940), radiological model (AIC = 227.932, χ2 = 51.270), clinical-radiological model (AIC = 212.711, χ2 = 55.490) or radiomics model (AIC = 217.647, χ2 = 57.550). In both cohorts, the nomogram derived from the combined model showed satisfactory discrimination and calibration for predicting HE (AUC = 0.900, sensitivity = 83.87%; AUC = 0.850, sensitivity = 80.10%, respectively).

Conclusion

The NCCT-based model combining clinical characteristics, radiological signs, and radiomics features could efficiently discriminate early HE, and the nomogram derived from the combined model, as a non-invasive tool, exhibited satisfactory performance in stratifying HE risks.

Development and Validation of a Clinical-Based Signature to Predict the 90-Day Functional Outcome for Spontaneous Intracerebral Hemorrhage

We aimed to develop and validate an objective and easy-to-use model for identifying patients with spontaneous intracerebral hemorrhage (ICH) who have a poor 90-day prognosis. This three-center retrospective study included a large cohort of 1,122 patients with ICH who presented within 6 h of symptom onset [training cohort, n = 835; internal validation cohort, n = 201; external validation cohort (center 2 and 3), n = 86]. We collected the patients’ baseline clinical, radiological, and laboratory data as well as the 90-day functional outcomes. Independent risk factors for prognosis were identified through univariate analysis and multivariate logistic regression analysis. A nomogram was developed to visualize the model results while a calibration curve was used to verify whether the predictive performance was satisfactorily consistent with the ideal curve. Finally, we used decision curves to assess the clinical utility of the model. At 90 days, 714 (63.6%) patients had a poor prognosis. Factors associated with prognosis included age, midline shift, intraventricular hemorrhage (IVH), subarachnoid hemorrhage (SAH), hypodensities, ICH volume, perihematomal edema (PHE) volume, temperature, systolic blood pressure, Glasgow Coma Scale (GCS) score, white blood cell (WBC), neutrophil, and neutrophil-lymphocyte ratio (NLR) (p < 0.05). Moreover, age, ICH volume, and GCS were identified as independent risk factors for prognosis. For identifying patients with poor prognosis, the model showed an area under the receiver operating characteristic curve of 0.874, 0.822, and 0.868 in the training cohort, internal validation, and external validation cohorts, respectively. The calibration curve revealed that the nomogram showed satisfactory calibration in the training and validation cohorts. Decision curve analysis showed the clinical utility of the nomogram. Taken together, the nomogram developed in this study could facilitate the individualized outcome prediction in patients with ICH.

Evaluation of Intracranial Hypertension in Patients With Hypertensive Intracerebral Hemorrhage Using Texture Analysis

Purpose

Texture analysis based on clinical images had been widely used in neurological diseases. This study aimed to achieve depth information of computed tomography (CT) images by texture analysis and to establish a model for noninvasive evaluation of intracranial pressure (ICP) in patients with hypertensive intracerebral hemorrhage (HICH).

Methods

Forty-seven patients with HICH were selected. Related CT images and ICP value were collected. The morphological features of hematoma volume, midline shift, and ventriculocranial ratio were measured. Forty textural features were extracted from regions of interest. Four models were established to predict intracranial hypertension with morphological features, textural features of anterior horn, textural features of temporal lobe, and textural features of posterior horn.

Results

Model of posterior horn had the highest ability to predict intracranial hypertension (AUC = 0.90, F1 score = 0.72), followed by model of anterior horn (AUC = 0.70, F1 score = 0.53) and model of temporal lobe (AUC = 0.70, F1 score = 0.58), and model of morphological features displayed the worst performance (AUC = 0.42, F1 score = 0.38).

Conclusion

Texture analysis can realize interpretation of CT images in depth, which has great potential in noninvasive evaluation of intracranial hypertension.

A Novel CT-based Radiomics-Clinical Nomogram for the Prediction of Short-Term Prognosis in Deep Intracerebral Hemorrhage

OBJECTIVE

To develop and validate a radiomics-clinical nomogram for the prediction of short-term prognosis in patients with deep intracerebral hemorrhage (DICH) on admission.

METHODS

A total of 326 patients with DICH (development cohort = 187; testing cohort = 81; validation cohort = 58) were retrospectively included. Radiomics features were extracted from computed tomography (CT) images and optimal features were selected using least absolute shrinkage and selection operator regression. A radiomics score (R-score) was developed using the optimal features. Univariate and multivariate analyses were used to determine independent risk factors for poor outcomes at 30 days. A radiomics-clinical (R-C) nomogram was developed and validated in the three cohorts. Receiver operating characteristic curve (ROC), calibration curve and decision curve analyses were conducted to evaluate the performances of the R-C nomogram.

RESULTS

Only 4 of 396 radiomics features were selected to develop R-scores. Age, onset-to-CT time, Glasgow Coma Scale score, midline shift, and R-score were detected as independent predictors of poor prognosis of DICH. The R-C nomogram was developed by the independent predictors and showed acceptable discrimination with areas under ROCs of 0.80, 0.79, and 0.70 in the development, testing and validation cohorts, respectively. The R-C nomogram showed good agreement between the predicted probability and the actual probability (all P > 0.05) and clinical applicability in each cohort.

CONCLUSIONS

The R-C nomogram is a stable and effective tool for predicting the short-term prognosis of DICH, which may help clinicians perform individual risk assessments and make decisions for patients with DICH.

Comparison of Radiomic Models Based on Different Machine Learning Methods for Predicting Intracerebral Hemorrhage Expansion

PURPOSE

The objective of this study was to predict hematoma expansion (HE) by radiomic models based on different machine learning methods and determine the best radiomic model through the comparison.

METHOD

A total of 108 patients with intracerebral hemorrhage were retrospectively evaluated. Images of baseline non-contrast computed tomography (NCCT) and follow-up NCCT scan within 24 h were retrospectively reviewed. An HE was defined as a volume increase of more than 33% or an increase greater than 12.5 mL from the volume of the baseline NCCT. Texture parameters of the baseline NCCT images were selected by the least absolute shrinkage and selection operator (LASSO) regression. We used support vector machine (SVM), decision tree (DT), conditional inference trees (CIT), random forest (RF), k‑nearest neighbors (KNN), back-propagation neural network (BPNet) and Bayes to build models. Receiver operating characteristic (ROC) analysis and decision curve analysis (DCA) was performed and compared among models.

RESULTS

Every model had a relatively high AUC (all > 0.75), SVM and KNN had the highest AUC of 0.91. There were significant differences between SVM and CIT (Z > 2.266, p = 0.02345), KNN and CIT (Z = 2.4834, p = 0.01301), RF and CIT (Z = 2.6956, p = 0.007027), KNN and BPNet (Z = 2.0122, p = 0.0442), RF and BPNet (Z = 1.9793, p = 0.04778). There was no significant difference among SVM, DT, RF, KNN and Bayes (p > 0.05). The SVM obtained the largest net benefit when the threshold probability was less than 0.33, while KNN obtained the largest net benefit when the threshold probability was greater than 0.33. Combined with ROC and DCA, SVM and KNN performed better in all the models for predicting HE.

CONCLUSION

Radiomic models based on different machine learning methods can be used to predict HE and the models generated by SVM and KNN performed best.

Evaluation of Intracranial Hypertension in Traumatic Brain Injury Patient: A Noninvasive Approach Based on Cranial Computed Tomography Features

BACKGROUND

Our purpose was to establish a noninvasive quantitative method for assessing intracranial pressure (ICP) levels in patients with traumatic brain injury (TBI) through investigating the Hounsfield unit (HU) features of computed tomography (CT) images.

METHODS

In this retrospective study, 47 patients with a closed TBI were recruited. Hounsfield unit features from the last cranial CT and the initial ICP value were collected. Three models were established to predict intracranial hypertension with Hounsfield unit (HU model), midline shift (MLS model), and clinical expertise (CE model) features.

RESULTS

The HU model had the highest ability to predict intracranial hypertension. In 34 patients with unilateral injury, the HU model displayed the highest performance. In three classifications of intracranial hypertension (ICP ≤ 22, 23-29, and ≥30 mmHg), the HU model achieved the highest F1 score.

CONCLUSIONS

This radiological feature-based noninvasive quantitative approach showed better performance compared with conventional methods, such as the degree of midline shift and clinical expertise. The results show its potential in clinical practice and further research.

Texture analysis of cone beam computed tomography images reveals dental implant stability

The aim of this study was to characterize the alveolar bone of edentulous maxillary sites using texture analysis (TA) of cone beam computed tomography (CBCT) images and to correlate the results to the insertion torque, thus verifying whether TA is a predictive tool of final implant treatment. This study was conducted on patients who had received single implants in the maxilla (46 implants) 1year earlier and whose torque values were properly recorded. Three cross-sections of the sites were selected on CBCT scans. Two regions of interest (ROIs) corresponding to the implant bone site and peri-implant bone were also outlined, according to virtual planning. The CBCT scans were exported to MaZda software, where the two ROIs were delimited following the previously demarcated contours. Values for the co-occurrence matrix were calculated for TA. With regard to the insertion torque value, there was a direct correlation with the contrast of the peri-implant bone (P<0.001) and an inverse correlation with the entropy of the implant bone site (P=0.006). A greater contrast indicates a greater torque value for insertion of the implants, and there is a possible association with a lower entropy value of the implant-bone interface.

Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model

We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were selected using the least absolute shrinkage and selection operator (LASSO) method and multivariate analysis. The radiomics score (Rad-score) was calculated through linear combination of selected features multiplied by their respective LASSO coefficients. The support vector machine (SVM) method was used to construct the model. IVH growth was experienced by 13.4% and 13.7% of patients in the training and testing cohorts, respectively. The Rad-score was associated with severe IVH and poor outcome. Independent predictors of IVH growth included hypercholesterolemia (odds ratio [OR], 0.12 [95%CI, 0.02-0.90]; p=0.039), baseline Graeb score (OR, 1.26 [95%CI, 1.16-1.36]; p<0.001), time to initial CT (OR, 0.70 [95%CI, 0.58-0.86]; p<0.001), international normalized ratio (OR, 4.27 [95%CI, 1.40, 13.0]; p=0.011), and Rad-score (OR, 2.3 [95%CI, 1.6-3.3]; p<0.001). In the training cohort, the model achieved an AUC of 0.78, sensitivity of 0.83, and specificity of 0.66. In the testing cohort, AUC, sensitivity, and specificity were 0.71, 0.81, and 0.64, respectively. This radiomics-clinical model thus has the potential to predict IVH growth.

Are computed-tomography-based hematoma radiomics features reproducible and predictive of intracerebral hemorrhage expansion? an in vitro experiment and clinical study

OBJECTIVES

To identify reproducible hematoma radiomics features (RFs) for use in predicting hematoma expansion (HE) in patients with acute intracerebral hemorrhage (ICH).

METHODS

For test-retest analysis, three syringes with different volumes of blood collected at the same time (to mimic homogeneous hematoma) and a phantom (FT/HK 2000; Huake, Szechwan, China) containing three cylindrical inserts were scanned seven times within 6 h on the same CT scanner. Three additional syringes with mixed blood collected at different time points (to mimic heterogeneous hematoma) were tied together with the first three syringes as well as the phantom were scanned using modified CT acquisition parameters for intra CT analysis. A coefficient of variation below 10% served as the cutoff value for reproducibility. Finally, reproducible and potentially useful RFs were used to predict HE in 144 acute ICH patients, with the area under the receiver operating characteristic curves (AUC) used to evaluate their diagnostic performance.

RESULTS

A total of 630 RFs including 18 first-order, 24 gray-level co-occurrence matrix (GLCM), 16 gray-level run length matrix (GLRLM), five neighborhood gray-tone difference matrix (NGTDM), 63 Laplacian of Gaussian (LoG), and 504 Wavelet features were evaluated. In the test-retest analysis, the percentages of reproducible RFs ranged from 42.54% (268/630) to 45.4% (286/630) for the three homogeneous hematoma samples and 79.05% (498/630) to 81.43% (513/630) for the phantom. In the intra-CT analysis, the percentages varied from 31.43% (198/630) to 42.38% (267/630) for the six hematoma samples and 48.89% (308/630) to 53.97% (340/630) for the phantom. In the in vitro experiment, 148 RFs were reproducible for all hematoma samples in both the test-retest and intra-CT analyses; however, only 80 were statistically different between homogeneous and heterogeneous hematoma samples. Finally, HE occurred in 25% (growth >6 ml, 36/144) to 31.94% (growth >3 ml or 33%, 46/144) of the patients. The AUCs in predicting HE ranged from 0.625 to 0.703.

CONCLUSIONS

Only a few CT-based RFs from the in vitro hematoma were reproducible and can distinguish between homogeneous and heterogeneous hematomas. The use of RFs alone to predict HE in acute ICH showed only a moderate performance.

ADVANCES IN KNOWLEDGE

Using an in vitro experiment and clinical validation, this study demonstrated for the first time that CT-based hematoma RFs can be used to predict HE in acute ICH; nonetheless, only a few RFs are reproducible and can be used for prediction.

Quantitative CT radiomics-based models for prediction of haematoma expansion and poor functional outcome in primary intracerebral haemorrhage

OBJECTIVES

To test radiomics-based features extracted from noncontrast CT of patients with spontaneous intracerebral haemorrhage for prediction of haematoma expansion and poor functional outcome and compare them with radiological signs and clinical factors.

MATERIALS AND METHODS

Seven hundred fifty-four radiomics-based features were extracted from 1732 scans derived from the TICH-2 multicentre clinical trial. Features were harmonised and a correlation-based feature selection was applied. Different elastic-net parameterisations were tested to assess the predictive performance of the selected radiomics-based features using grid optimisation. For comparison, the same procedure was run using radiological signs and clinical factors separately. Models trained with radiomics-based features combined with radiological signs or clinical factors were tested. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) score.

RESULTS

The optimal radiomics-based model showed an AUC of 0.693 for haematoma expansion and an AUC of 0.783 for poor functional outcome. Models with radiological signs alone yielded substantial reductions in sensitivity. Combining radiomics-based features and radiological signs did not provide any improvement over radiomics-based features alone. Models with clinical factors had similar performance compared to using radiomics-based features, albeit with low sensitivity for haematoma expansion. Performance of radiomics-based features was boosted by incorporating clinical factors, with time from onset to scan and age being the most important contributors for haematoma expansion and poor functional outcome prediction, respectively.

CONCLUSION

Radiomics-based features perform better than radiological signs and similarly to clinical factors on the prediction of haematoma expansion and poor functional outcome. Moreover, combining radiomics-based features with clinical factors improves their performance.

KEY POINTS

• Linear models based on CT radiomics-based features perform better than radiological signs on the prediction of haematoma expansion and poor functional outcome in the context of intracerebral haemorrhage. • Linear models based on CT radiomics-based features perform similarly to clinical factors known to be good predictors. However, combining these clinical factors with radiomics-based features increases their predictive performance.

Can perihaematomal radiomics features predict haematoma expansion?

AIM

To evaluate the association between perihaematomal radiomics features and haematoma expansion (HE).

MATERIALS AND METHODS

Clinical and radiological data were collected retrospectively. The 1:1 propensity score matching (PSM) method was used to balance the difference of baseline characteristics between patients with and without HE. Radiomics features were extracted from the intra- and perihaematomal regions. Top HE-associated features were selected using the minimum redundancy, maximum relevancy algorithm. Support vector machine models were used to predict HE. Predictive performance of radiomics features from different regions was evaluated by receiver operating characteristic curve and confusion matrix-derived metrics.

RESULTS

A total of 1,062 patients were enrolled. After PSM analysis, the propensity score-matched cohort (PSM cohort) included 314 patients (HE: n=157; non-HE: n=157). The PSM cohort was distributed into the training (n=218) and the validation cohorts (n=96). The predictive performance of intra- and perihaematomal features were comparable in the training (area under the receiver operating characteristic curve [AUC], 0.751 versus 0.757; p=0.867) and the validation cohorts (AUC, 0.724 versus 0.671; p=0.454). By incorporating intra- and perihaematomal features, the combined model outperformed the single intrahaematomal model in the training cohort (AUC, 0.872 versus 0.751; p<0.001). Decision curve analysis (DCA) further confirmed the clinical usefulness of the combined model.

CONCLUSION

Perihaematomal radiomics features can predict HE. The integration of intra- and perihaematomal signatures may provide additional benefit to the prediction of HE.

Radiomics for intracerebral hemorrhage: are all small hematomas benign?

OBJECTIVES

We hypothesized that not all small hematomas are benign and that radiomics could predict hematoma expansion (HE) and short-term outcomes in small hematomas.

METHODS

We analyzed 313 patients with small (<10 ml) intracerebral hemorrhage (ICH) who underwent baseline non-contrast CT within 6 h of symptom onset between September 2013 and February 2019. Poor outcome was defined as a Glasgow Outcome Scale score ≤3. A radiomic model and a clinical model were built using least absolute shrinkageand selection operator algorithm or multivariate analysis. A combined model that incorporated the developed radiomic score and clinical factors was then constructed. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of these models.

RESULTS

The addition of radiomics to clinical factors significantly improved the prediction performance of HE compared with the clinical model alone in both the training {AUC, 0.762 [95% CI (0.665-0.859)] versus AUC, 0.651 [95% CI (0.556-0.745)], p = 0.007} and test {AUC, 0.776 [95% CI (0.655-0.897) versus AUC, 0.631 [95% CI (0.451-0.810)], p = 0.001} cohorts. Moreover, the radiomic-based model achieved good discrimination ability of poor outcomes in the 3-10 ml group (AUCs 0.720 and 0.701).

CONCLUSION

Compared with clinical information alone, combined model had greater potential for discriminating between benign and malignant course in patients with small ICH, particularly 3-10 ml hematomas.

ADVANCES IN KNOWLEDGE

Radiomics can be used as a supplement to conventional medical imaging, improving clinical decision-making and facilitating personalized treatment in small ICH.

Clinical-radiomics Nomogram for Risk Estimation of Early Hematoma Expansion after Acute Intracerebral Hemorrhage

RATIONALE AND OBJECTIVES

Noncontrast CT-based radiomics signature has shown ability for detecting hematoma expansion (HE) in spontaneous intracerebral hemorrhage (ICH). We sought to compare its predictive performance with clinical risk factors and develop a clinical-radiomics nomogram to assess the risk of early HE.

MATERIALS AND METHODS

In total, 1153 patients with ICH who underwent baseline cranial CT within 6 hours and follow-up scans within 72 hours of stroke onset were enrolled, of whom 864 (75%) were assigned to the derivation cohort and 289 (25%) to the validation cohort. Based on LASSO algorithm or stepwise logistic regression analysis, three models (clinical model, radiomics model, and hybrid model) were constructed to predict HE. The Akaike information criterion (AIC) and likelihood ratio test (LRT) were used for comparing the goodness of fit of the three models, and the AUC was used to evaluate their discrimination ability for HE.

RESULTS

The hybrid model (AIC = 681.426; χ²= 128.779) was the optimal model with the lowest AIC and highest chi-square values compared to the radiomics model (AIC = 767.979; χ² = 110.234) or the clinical model (AIC = 753.757; χ² = 56.448). The radiomics model was superior in the prediction of HE to the clinical model in both derivation (p = 0.009) and validation (p = 0.022) cohorts. In both datasets, the clinical-radiomics nomogram showed satisfactory discrimination and calibration for detecting HE (AUC = 0.771, Sensitivity = 87.0%; AUC = 0.820, Sensitivity = 88.1%; respectively).

CONCLUSION

Among patients with acute ICH, noncontrast CT-based radiomics model outperformed the clinical-only model in the prediction of HE, and the established clinical-radiomics nomogram with favorable performance can offer a noninvasive tool for the risk stratification of HE.

The role of CT texture analysis in predicting the clinical outcomes of acute ischemic stroke patients undergoing mechanical thrombectomy

OBJECTIVES

To evaluate the performance of CT-based texture analysis (TA) for predicting clinical outcomes of mechanical thrombectomy (MT) in acute ischemic stroke (AIS).

METHODS

This single-center, retrospective study contained 64 consecutive patients with AIS who underwent MT for large anterior circulation occlusion between December 2016 and January 2020. Patients were divided into 2 groups according to the modified Rankin scale (mRS) scores at 3 months as good outcome (mRS ≤ 2) and bad outcome (mRS > 2). Two observers examined the early ischemic changes for TA on baseline non-contrast CT images independently. Demographic, clinical, periprocedural, and texture variables were compared between the groups and ROC curves were made. Logistic regression analysis was used and a model was created to determine the independent predictors of a bad outcome.

RESULTS

Sixty-four patients (32 female, 32 male; mean age 63.03 ± 14.42) were included in the study. Fourteen texture parameters were significantly different between patients with good and bad outcomes. The long-run high gray-level emphasis (LRHGE), which is a gray-level run-length matrix (GLRLM) feature, showed the highest sensitivity (80%) and specificity (70%) rates to predict disability. The GLRLM_LRHGE value of > 4885.0 and the time from onset to puncture of > 237.5 mi were found as independent predictors of the bad outcome. The diagnostic rate was 80.0% when using the combination of the GLRLM_LRHGE and the time from onset to puncture cutoff values.

CONCLUSION

CT-based TA might be a promising modality to predict clinical outcome after MT in patients with AIS.

KEY POINTS

• The gray-level run-length matrix parameters displayed higher diagnostic performance among the texture features. • The long-run high gray-level emphasis showed the highest sensitivity and specificity rates for predicting a bad outcome in stroke patients undergoing mechanical thrombectomy. • The gray-level run-length matrix_long-run high gray-level emphasis value of > 4885.0 (OR = 11.06; 95% CI = 2.51 - 48.77; p = 0.001) and the time from onset to puncture of > 237.5 min (OR = 8.55; 95% CI = 1.96 - 37.21; p = 0.004) were found as independent predictors of the bad outcome.

Radiomics in Stroke Neuroimaging: Techniques, Applications, and Challenges

Stroke is a leading cause of disability and mortality worldwide, resulting in substantial economic costs for post-stroke care each year. Neuroimaging, such as cranial computed tomography or magnetic resonance imaging, is the backbone of stroke management strategies, which can guide treatment decision-making (thrombolysis or hemostasis) at an early stage. With advances in computational technologies, particularly in machine learning, visual image information can now be converted into numerous quantitative features in an objective, repeatable, and high-throughput manner, in a process known as radiomics. Radiomics is mainly used in the field of oncology, which remains an area of active research. Over the past few years, investigators have attempted to apply radiomics to stroke in the hope of gaining benefits similar to those obtained in cancer management, i.e., in promoting the development of personalized precision medicine. Currently, radiomic analysis has shown promise for a variety of applications in stroke, including the diagnosis of stroke lesions, early prediction of outcomes, and evaluation for long-term prognosis. In this article, we elaborate the contributions of radiomics to stroke, as well as the subprocesses and techniques involved in radiomics studies. We also discuss the potential challenges facing its widespread implementation in routine practice and the directions for future research.

Noncontrast Computed Tomography-Based Radiomics Analysis in Discriminating Early Hematoma Expansion after Spontaneous Intracerebral Hemorrhage

Objective

To determine whether noncontrast computed tomography (NCCT) models based on multivariable, radiomics features, and machine learning (ML) algorithms could further improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH).

Materials and Methods

We retrospectively reviewed 261 patients with sICH who underwent initial NCCT within 6 hours of ictus and follow-up CT within 24 hours after initial NCCT, between April 2011 and March 2019. The clinical characteristics, imaging signs and radiomics features extracted from the initial NCCT images were used to construct models to discriminate early HE. A clinical-radiologic model was constructed using a multivariate logistic regression (LR) analysis. Radiomics models, a radiomics-radiologic model, and a combined model were constructed in the training cohort (n = 182) and independently verified in the validation cohort (n = 79). Receiver operating characteristic analysis and the area under the curve (AUC) were used to evaluate the discriminative power.

Results

The AUC of the clinical-radiologic model for discriminating early HE was 0.766. The AUCs of the radiomics model for discriminating early HE built using the LR algorithm in the training and validation cohorts were 0.926 and 0.850, respectively. The AUCs of the radiomics-radiologic model in the training and validation cohorts were 0.946 and 0.867, respectively. The AUCs of the combined model in the training and validation cohorts were 0.960 and 0.867, respectively.

Conclusion

NCCT models based on multivariable, radiomics features and ML algorithm could improve the discrimination of early HE. The combined model was the best recommended model to identify sICH patients at risk of early HE.

Artificial Intelligence Applications for Workflow, Process Optimization and Predictive Analytics

There is great potential for artificial intelligence (AI) applications, especially machine learning and natural language processing, in medical imaging. Much attention has been garnered by the image analysis tasks for diagnostic decision support and precision medicine, but there are many other potential applications of AI in radiology and have potential to enhance all levels of the radiology workflow and practice, including workflow optimization and support for interpretation tasks, quality and safety, and operational efficiency. This article reviews the important potential applications of informatics and AI related to process improvement and operations in the radiology department.

A Nomogram Combined Radiomics and Kinetic Curve Pattern as Imaging Biomarker for Detecting Metastatic Axillary Lymph Node in Invasive Breast Cancer

Objective: To construct and validate a nomogram model integrating the magnetic resonance imaging (MRI) radiomic features and the kinetic curve pattern for detecting metastatic axillary lymph node (ALN) in invasive breast cancer preoperatively. Materials and Methods: A total of 145 ALNs from two institutions were classified into negative and positive groups according to the pathologic or surgical results. One hundred one ALNs from institution I were taken as the training cohort, and the other 44 ALNs from institution II were taken as the external validation cohort. The kinetic curve was computed using dynamic contrast-enhanced MRI software. The preprocessed images were used for radiomic feature extraction. The LASSO regression was applied to identify optimal radiomic features and construct the Radscore. A nomogram model was constructed combining the Radscore and the kinetic curve pattern. The discriminative performance was evaluated by receiver operating characteristic analysis and calibration curve.

Results: Five optimal features were ultimately selected and contributed to the Radscore construction. The kinetic curve pattern was significantly different between negative and positive lymph nodes. The nomogram model showed a better performance in both training cohort [area under the curve (AUC) = 0.91, 95% CI = 0.83–0.96] and external validation cohort (AUC = 0.86, 95% CI = 0.72–0.94); the calibration curve indicated a better accuracy of the nomogram model for detecting metastatic ALN than either Radscore or kinetic curve pattern alone.

Conclusion: A nomogram model integrated the Radscore and the kinetic curve pattern could serve as a biomarker for detecting metastatic ALN in patients with invasive breast cancer.

Risk stratification of thymic epithelial tumors by using a nomogram combined with radiomic features and TNM staging

OBJECTIVES

To construct and validate a nomogram model that integrated the CT radiomic features and the TNM staging for risk stratification of thymic epithelial tumors (TETs).

METHODS

A total of 136 patients with pathology-confirmed TETs who underwent CT examination were collected from two institutions. According to the WHO pathological classification criteria, patients were classified into low-risk and high-risk groups. The TNM staging was determined in terms of the 8th edition AJCC/UICC staging criteria. LASSO regression was performed to extract the optimal features correlated to risk stratification among the 704 radiomic features calculated. A nomogram model was constructed by combining the Radscore and the TNM staging. The clinical performance was evaluated by ROC analysis, calibration curve, and decision curve analysis (DCA). The Kaplan-Meier (KM) analysis was employed for survival analysis.

RESULTS

Five optimal features identified by LASSO regression were employed to calculate the Radscore correlated to risk stratification. The nomogram model showed a better performance in both training cohort (AUC = 0.84, 95%CI 0.75-0.91) and external validation cohort (AUC = 0.79, 95%CI 0.69-0.88). The calibration curve and DCA analysis indicated a better accuracy of the nomogram model for risk stratification than either Radscore or the TNM staging alone. The KM analysis showed a significant difference between the two groups stratified by the nomogram model (p = 0.02).

CONCLUSIONS

A nomogram model that integrated the radiomic signatures and the TNM staging could serve as a reliable model of risk stratification in predicting the prognosis of patients with TETs.

KEY POINTS

• The radiomic features could be associated with the TET pathophysiology. • TNM staging and Radscore could independently stratify the risk of TETs. • The nomogram model is more objective and more comprehensive than previous methods.

A Nomogram Model of Radiomics and Satellite Sign Number as Imaging Predictor for Intracranial Hematoma Expansion

Background

We aimed to construct and validate a nomogram model based on the combination of radiomic features and satellite sign number for predicting intracerebral hematoma expansion.

Methods

A total of 129 patients from two institutions were enrolled in this study. The preprocessed initial CT images were used for radiomic feature extraction. The ANOVA-Kruskal–Wallis test and least absolute shrinkage and selection operator regression were applied to identify candidate radiomic features and construct the Radscore. A nomogram model was developed by integrating the Radscore with a satellite sign number. The discrimination performance of the proposed model was evaluated by receiver operating characteristic (ROC) analysis, and the predictive accuracy was assessed via a calibration curve. Decision curve analysis (DCA) and Kaplan–Meier (KM) survival analysis were performed to evaluate the clinical value of the model.

Results

Four optimal features were ultimately selected and contributed to the Radscore construction. A positive correlation was observed between the satellite sign number and Radscore (Pearson’s r: 0.451). The nomogram model showed the best performance with high area under the curves in both training cohort (0.881, sensitivity: 0.973; specificity: 0.787) and external validation cohort (0.857, sensitivity: 0.950; specificity: 0.766). The calibration curve, DCA, and KM analysis indicated the high accuracy and clinical usefulness of the nomogram model for hematoma expansion prediction.

Conclusion

A nomogram model of integrated radiomic signature and satellite sign number based on noncontrast CT images could serve as a reliable and convenient measurement of hematoma expansion prediction.

A Nomogram Combined Radiomic and Semantic Features as Imaging Biomarker for Classification of Ovarian Cystadenomas

Objective: To construct and validate a combined Nomogram model based on radiomic and semantic features to preoperatively classify serous and mucinous pathological types in patients with ovarian cystadenoma.

Methods: A total of 103 patients with pathology-confirmed ovarian cystadenoma who underwent CT examination were collected from two institutions. All cases divided into training cohort (N = 73) and external validation cohort (N = 30). The CT semantic features were identified by two abdominal radiologists. The preprocessed initial CT images were used for CT radiomic features extraction. The LASSO regression were applied to identify optimal radiomic features and construct the Radscore. A Nomogram model was constructed combining the Radscore and the optimal semantic feature. The model performance was evaluated by ROC analysis, calibration curve and decision curve analysis (DCA).

Result: Five optimal features were ultimately selected and contributed to the Radscore construction. Unilocular/multilocular identification was significant difference from semantic features. The Nomogram model showed a better performance in both training cohort (AUC = 0.94, 95%CI 0.86–0.98) and external validation cohort (AUC = 0.92, 95%CI 0.76–0.98). The calibration curve and DCA analysis indicated a better accuracy of the Nomogram model for classification than either Radscore or the loculus alone.

Conclusion: The Nomogram model combined radiomic and semantic features could be used as imaging biomarker for classification of serous and mucinous types of ovarian cystadenomas.

Noncontrast computer tomography-based radiomics model for predicting intracerebral hemorrhage expansion: preliminary findings and comparison with conventional radiological model

OBJECTIVES

To develop a radiomics model for predicting hematoma expansion in patients with intracerebral hemorrhage (ICH) and to compare its predictive performance with a conventional radiological feature-based model.

METHODS

We retrospectively analyzed 251 consecutive patients with acute ICH. Two radiologists independently assessed baseline noncontrast computed tomography (NCCT) images. For each radiologist, a radiological model was constructed from radiological variables; a radiomics score model was constructed from high-dimensional quantitative features extracted from NCCT images; and a combined model was constructed using both radiological variables and radiomics score. Development of models was constructed in a primary cohort (n = 177). We then validated the results in an independent validation cohort (n = 74). The primary outcome was hematoma expansion. We compared the three models for predicting hematoma expansion. Predictive performance was assessed with the receiver operating characteristic (ROC) curve analysis.

RESULTS

In the primary cohort, combined model and radiomics model showed greater AUCs than radiological model for both readers (all p < .05). In the validation cohort, combined model and radiomics model showed greater AUCs, sensitivities, and accuracies than radiological model for reader 2 (all p < .05). Combined model showed greater AUC than radiomics model for reader 1 only in the primary cohort (p = .03). Performance of three models was comparable between reader 1 and reader 2 in both cohorts (all p > .05).

CONCLUSIONS

NCCT-based radiomics model showed high predictive performance and outperformed radiological model in the prediction of early hematoma expansion in ICH patients.

KEY POINTS

• Radiomics model showed better performance for prediction of hematoma expansion in patients with intracerebral hemorrhage than radiological feature-based model. • Hematomas which expanded in follow-up NCCT tended to be larger in baseline volume, more irregular in shape, more heterogeneous in composition, and coarser in texture. • A radiomics model provides a convenient and objective tool for prediction of hematoma expansion that helps to define subsets of patients who would benefit from anti-expansion therapy.

Radiomics: an Introductory Guide to What It May Foretell

PURPOSE OF REVIEW

To briefly review the radiomics concept, its applications, and challenges in oncology in the era of precision medicine.

RECENT FINDINGS

Over the last 5 years, more than 500 studies have evaluated the role of radiomics to predict tumor diagnosis, genetic pattern, tumor response to therapy, and survival in multiple cancers. This new post-processing method is aimed at extracting multiple quantitative features from the image and converting them into mineable data. Radiomics models developed have shown promising results and may play a role in the near future in the daily patient management especially to assess tumor heterogeneity acting as a whole tumor virtual biopsy. For now, radiomics is limited by its lack of standardization; future challenges will be to provide robust and reproducible metrics extracted from large multicenter databases.

CT texture analysis: a potential tool for predicting the Fuhrman grade of clear-cell renal carcinoma

Background

The purpose of this study was to analyze the image heterogeneity of clear-cell renal-cell carcinoma (ccRCC) by computer tomography texture analysis and to provide new objective quantitative imaging parameters for the pre-operative prediction of Fuhrman-grade ccRCC.

Methods

A retrospective analysis of 131 cases of ccRCCs was performed by manually depicting tumor areas. Then, histogram-based texture parameters were calculated. The texture-feature values between Fuhrman low- (Grade I-II) and high-grade (Grade III-IV) ccRCCs were compared by two independent sample t-tests (False Discovery Rate correction), and receiver operating characteristic curve (ROC) was used to evaluate the efficacy of using texture features to predict Fuhrman high- and low-grade ccRCCs.

Results

There were no statistical differences for any texture parameters without filtering (p > 0.05). There was a statistically significant difference between the entropy (fine) of the corticomedullary phase and the entropy (fine and coarse) of the nephrographic phase after Laplace of Gaussian filtering. The area under the ROC of the entropy was between 0.74 and 0.83.

Conclusions

Computer tomography texture features can predict the Fuhrman grading of ccRCC pre-operatively, with entropy being the most important imaging marker for clinical application.

Challenges Related to Artificial Intelligence Research in Medical Imaging and the Importance of Image Analysis Competitions

In recent years, there has been enormous interest in applying artificial intelligence (AI) to radiology. Although some of this interest may have been driven by exaggerated expectations that the technology can outperform radiologists in some tasks, there is a growing body of evidence that illustrates its limitations in medical imaging. The true potential of the technique probably lies somewhere in the middle, and AI will ultimately play a key role in medical imaging in the future. The limitless power of computers makes AI an ideal candidate to provide the standardization, consistency, and dependability needed to support radiologists in their mission to provide excellent patient care. However, important roadblocks currently limit the expansion of this field in medical imaging. This article reviews some of the challenges and potential solutions to advance the field forward, with focus on the experience gained by hosting image-based competitions.