High-order radiomics features based on T2 FLAIR MRI predict multiple glioma immunohistochemical features: A more precise and personalized gliomas management.
ABSTRACT: OBJECTIVE:To investigate the performance of high-order radiomics features and models based on T2-weighted fluid-attenuated inversion recovery (T2 FLAIR) in predicting the immunohistochemical biomarkers of glioma, in order to execute a non-invasive, more precise and personalized glioma disease management. METHODS:51 pathologically confirmed gliomas patients committed in our hospital from March 2015 to June 2018 were retrospective analysis, and Ki-67, vimentin, S-100 and CD34 immunohistochemical data were collected. The volumes of interest (VOIs) were manually sketched and the radiomics features were extracted. Feature reduction was performed by ANOVA+ Mann-Whiney, spearman correlation analysis, least absolute shrinkage and selection operator (LASSO) and Gradient descent algorithm (GBDT). SMOTE technique was used to solve the data bias between two groups. Comprehensive binary logistic regression models were established. Area under the ROC curves (AUC), sensitivity, specificity and accuracy were used to evaluate the predict performance of models. Models reliability were decided according to the standard net benefit of the decision curves. RESULTS:Four clusters of significant features were screened out and four predicting models were constructed. AUC of Ki-67, S-100, vimentin and CD34 models were 0.713, 0.923, 0.854 and 0.745, respectively. The sensitivities were 0.692, 0.893, 0.875 and 0.556, respectively. The specificities were: 0.667, 0.905, 0.722, and 0.875, with accuracy of 0.660, 0.898, 0.738, and 0.667, respectively. According to the decision curves, the Ki-67, S-100 and vimentin models had reference values. CONCLUSION:The radiomics features based on T2 FLAIR can potentially predict the Ki-67, S-100, vimentin and CD34 expression. Radiomics model were expected to be a computer-intelligent, non-invasive, accurate and personalized management method for gliomas.
Project description:OBJECTIVE:To identify glioma radiomic features associated with proliferation-related Ki-67 antigen and cellular tumour antigen p53 levels, common immunohistochemical markers for differentiating benign from malignant tumours, and to generate radiomic prediction models. METHODS:Patients with glioma, who were scanned before therapy using standard brain magnetic resonance imaging (MRI) protocols on T1 and T2 weighted imaging, were included. For each patient, regions-of-interest (ROI) were drawn based on tumour and peritumoral areas (5/10/15/20 mm), and features were identified using feature calculations, and used to create and assess logistic regression models for Ki-67 and p53 levels. RESULTS:A total of 92 patients were included. The best area under the curve (AUC) for the Ki-67 model was 0.773 for T2 weighted imaging in solid glioma (sensitivity, 0.818; specificity, 0.833), followed by a less reliable AUC of 0.773 (sensitivity, 0.727; specificity 0.667) in 20-mm peritumoral areas. The highest AUC for the p53 model was 0.709 (sensitivity, 1; specificity, 0.4) for T2 weighted imaging in 10-mm peritumoral areas. CONCLUSION:Using T2-weighted imaging, the prediction model for Ki-67 level in solid glioma tissue was better than the p53 model. The 20-mm and 10-mm peritumoral areas in the Ki-67 and p53 model, respectively, showed predictive effects, suggesting value in further research into areas without conventional MRI features.
Project description:BACKGROUND:This study aims to establish a radiomics analysis system for the diagnosis and clinical behaviour prediction of hepatocellular carcinoma (HCC) based on multi-parametric ultrasound imaging. METHODS:A total of 177 patients with focal liver lesions (FLLs) were included in the study. Every patient underwent multi-modal ultrasound examination, including B-mode ultrasound (BMUS), shear wave elastography (SWE), and shear wave viscosity (SWV) imaging. The radiomics analysis system was built on sparse representation theory (SRT) and support vector machine (SVM) for asymmetric data. Through the sparse regulation from the SRT, the proposed radiomics system can effectively avoid over-fitting issues that occur in regular radiomics analysis. The purpose of the proposed system includes differential diagnosis between benign and malignant FLLs, pathologic diagnosis of HCC, and clinical prognostic prediction. Three biomarkers, including programmed cell death protein 1 (PD-1), antigen Ki-67 (Ki-67) and microvascular invasion (MVI), were included and analysed. We calculated the accuracy (ACC), sensitivity (SENS), specificity (SPEC) and area under the receiver operating characteristic curve (AUC) to evaluate the performance of the radiomics models. RESULTS:A total of 2560 features were extracted from the multi-modal ultrasound images for each patient. Five radiomics models were built, and leave-one-out cross-validation (LOOCV) was used to evaluate the models. In LOOCV, the AUC was 0.94 for benign and malignant classification (95% confidence interval [CI]: 0.88 to 0.98), 0.97 for malignant subtyping (95% CI: 0.93 to 0.99), 0.97 for PD-1 prediction (95% CI: 0.89 to 0.98), 0.94 for Ki-67 prediction (95% CI: 0.87 to 0.97), and 0.98 for MVI prediction (95% CI: 0.93 to 0.99). The performance of each model improved when the viscosity modality was included. CONCLUSIONS:Radiomics analysis based on multi-modal ultrasound images could aid in comprehensive liver tumor evaluations, including diagnosis, differential diagnosis, and clinical prognosis.
Project description:Objectives: To investigate the ability of radiomics features from MRI in differentiating anaplastic oligodendroglioma (AO) from atypical low-grade oligodendroglioma using machine-learning algorithms. Methods: A total number of 101 qualified patients (50 participants with AO and 51 with atypical low-grade oligodendroglioma) were enrolled in this retrospective, single-center study. Forty radiomics features of tumor images derived from six matrices were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images. Three selection methods were performed to select the optimal features for classifiers, including distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT). Then three machine-learning classifiers were adopted to generate discriminative models, including linear discriminant analysis, support vector machine, and random forest (RF). Receiver operating characteristic analysis was conducted to evaluate the discriminative performance of each model. Results: Nine predictive models were established based on radiomics features from T1C images and FLAIR images. All of the classifiers represented feasible ability in differentiation, with AUC more than 0.840 when combined with suitable selection method. For models based on T1C images, the combination of LASSO and RF classifier represented the highest AUC of 0.904 in the validation group. For models based on FLAIR images, the combination of GBDT and RF classifier showed the highest AUC of 0.861 in the validation group. Conclusion: Radiomics-based machine-learning approach could potentially serve as a feasible method in distinguishing AO from atypical low-grade oligodendroglioma.
Project description:Background: Normal-appearing white matter (NAWM) refers to the normal, yet diseased tissue around the white matter hyperintensities (WMH) on conventional MR images. Radiomics is an emerging quantitative imaging technique that provides more details than a traditional visual analysis. This study aims to explore whether WMH could be predicted during the early stages of NAWM, using a textural analysis in the general elderly population. Methods: Imaging data were obtained from PACS between 2012 and 2017. The subjects (?60 years) received two or more MRI exams on the same scanner with time intervals of more than 1 year. By comparing the baseline and follow-up images, patients with noted progression of WMH were included as the case group (n = 51), while age-matched subjects without WMH were included as the control group (n = 51). Segmentations of the regions of interest (ROIs) were done with the ITK software. Two ROIs of developing NAWM (dNAWM) and non-developing NAWM (non-dNAWM) were drawn separately on the FLAIR images of each patient. dNAWM appeared normal on the baseline images, yet evolved into WMH on the follow-up images. Non-dNAWM appeared normal on both the baseline and follow-up images. A third ROI of normal white matter (NWM) was extracted from the control group, which was normal on both baseline and follow-up images. Textural features were dimensionally reduced with ANOVA+MW, correlation analysis, and LASSO. Three models were built based on the optimal parameters of dimensional reduction, including Model 1 (NWM vs. dNAWM), Model 2 (non-dNAWM vs. dNAWM), and Model 3 (NWM vs. non-dNAWM). The ROC curve was adopted to evaluate the classification validity of these models. Results: Basic characteristics of the patients and controls showed no significant differences. The AUC of Model 1 in training and test groups were 0.967 (95% CI: 0.831-0.999) and 0.954 (95% CI: 0.876-0.989), respectively. The AUC of Model 2 were 0.939 (95% CI: 0.856-0.982) and 0.846 (95% CI: 0.671-0.950). The AUC of Model 3 were 0.713 (95% CI: 0.593-0.814) and 0.667 (95% CI: 0.475-0.825). Conclusion: Radiomics textural analysis can distinguish dNAWM from non-dNAWM on FLAIR images, which could be used for the early detection of NAWM lesions before they develop into visible WHM.
Project description:PURPOSE:This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS:The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS:For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS:The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.
Project description:OBJECTIVES: To assess the immunohistochemical expression of Ki-67 and Proliferating Cell Nuclear Antigen (PCNA) as proliferative markers to study proliferative activity and CD34 as an endothelial cell marker in order to study vascular proliferation in astrocytomas in correlation with some clinicopathological parameters (age, gender, site of the tumor, and tumor grade). METHODS: A retrospective study wherein a total of 51 formalin-fixed paraffin-embedded brain astrocytoma excisional biopsies covering the period of June 2009 to February 2011 were retrieved from the archival materials of the Specialized Surgical Hospital in Medical City in Baghdad, Iraq. The histopathological diagnosis had been revised and all cases were stained by immunohistochemical technique with Ki-67, PCNA, and CD34 tumor markers. Values were considered statistically significant when p<0.05. RESULTS: Fibrillary astrocytoma (WHO grade II) was found to be the most common type among astrocytic tumors with the peak age incidence of astrocytomas found in the second and fifth decades of life, and a slight male predominance had been identified. There was a significant correlation between the age of the patients and the grade of the tumor, Ki-67 and PCNA labeling indices, and microvessel density (MVD) detected by CD34 (p<0.05). There was a highly significant correlation between Ki-67 and PCNA labeling indices in astrocytomas (p<0.001). CONCLUSION: A significant correlation was found between Ki-67, PCNA labeling indices, and MVD (microvessel density) detected by CD34, and between the clinicopathological variables of astrocytomas (age and grade of tumor). Hence, Ki-67 and PCNA, as markers for proliferation, and MVD as a marker of angiogenesis, could be used as ancillary methods in the differentiation of borderline grades of astrocytomas.
Project description:Background:Grading of gliomas is critical information related to prognosis and survival. We aimed to apply a radiomics approach using various machine learning classifiers to determine the glioma grading. Methods:We considered 285 (high grade n = 210, low grade n = 75) cases obtained from the Brain Tumor Segmentation 2017 Challenge. Manual annotations of enhancing tumors, non-enhancing tumors, necrosis, and edema were provided by the database. Each case was multi-modal with T1-weighted, T1-contrast enhanced, T2-weighted, and FLAIR images. A five-fold cross validation was adopted to separate the training and test data. A total of 468 radiomics features were calculated for three types of regions of interest. The minimum redundancy maximum relevance algorithm was used to select features useful for classifying glioma grades in the training cohort. The selected features were used to build three classifier models of logistics, support vector machines, and random forest classifiers. The classification performance of the models was measured in the training cohort using accuracy, sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic curve. The trained classifier models were applied to the test cohort. Results:Five significant features were selected for the machine learning classifiers and the three classifiers showed an average AUC of 0.9400 for training cohorts and 0.9030 (logistic regression 0.9010, support vector machine 0.8866, and random forest 0.9213) for test cohorts. Discussion:Glioma grading could be accurately determined using machine learning and feature selection techniques in conjunction with a radiomics approach. The results of our study might contribute to high-throughput computer aided diagnosis system for gliomas.
Project description:As a cell proliferation biomarker, Ki-67 is principally used in ER+/HER2- breast cancer. However, the importance and the best cutoff point of Ki-67 in triple-negative breast cancer (TNBC) remains unclear and was evaluated in this study.A total of 1800 patients with early invasive TNBC between 2011 and 2016 at Fudan University Shanghai Cancer Center were consecutively recruited for this study. The optimal cutoff for Ki-67 was assessed by Cutoff Finder. Propensity score matching (PSM, ratio?=?1:2) was performed to match the Ki-67low group with the Ki-67high group. Overall survival (OS) and disease-free survival (DFS) were compared between the two groups using the Kaplan-Meier method and Cox regression model. The most relevant cutoff value for Ki-67 for prognosis was 30% (p?=?0.008). At the cutoff point of 30%, worse DFS and OS were observed in the Ki-67high group. In multivariate analyses, N-stage (p?<?0.001), T-stage (p?=?0.038), and Ki-67 at the 30% threshold (p?=?0.020) were independently linked to OS. In subgroup analysis, Ki-67 cutoff at 30% had prognostic and predictive potential for DFS with either tumor size ?2?cm (p?=?0.008) or lymph node-negative (N-) (p?=?0.038) and especially with T1N0M0 (stage I) TNBCs. For 945 N- TNBC patients, adjuvant chemotherapy (CT) was associated with better OS in the Ki-67high group (p?=?0.017) than in the Ki-67low group (p?=?0.875). For stage I/Ki-67low patients, adjuvant CT did not affect DFS (p?=?0.248). Thus, Ki-67 cutoff at 30% had early independent prognostic and predictive potential for OS and DFS in TNBCs, and Ki-67?>?30% was significantly associated with worse prognosis, especially for stage I patients. For stage I/Ki-67low TNBC patients, the advantage of CT is unclear, providing the basis for future de-escalation therapy.
Project description:Radiomics relies on the extraction of a wide variety of quantitative image-based features to provide decision support. Magnetic resonance imaging (MRI) contributes to the personalization of patient care but suffers from being highly dependent on acquisition and reconstruction parameters. Today, there are no guidelines regarding the optimal pre-processing of MR images in the context of radiomics, which is crucial for the generalization of published image-based signatures. This study aims to assess the impact of three different intensity normalization methods (Nyul, WhiteStripe, Z-Score) typically used in MRI together with two methods for intensity discretization (fixed bin size and fixed bin number). The impact of these methods was evaluated on first- and second-order radiomics features extracted from brain MRI, establishing a unified methodology for future radiomics studies. Two independent MRI datasets were used. The first one (DATASET1) included 20 institutional patients with WHO grade II and III gliomas who underwent post-contrast 3D axial T1-weighted (T1w-gd) and axial T2-weighted fluid attenuation inversion recovery (T2w-flair) sequences on two different MR devices (1.5 T and 3.0 T) with a 1-month delay. Jensen-Shannon divergence was used to compare pairs of intensity histograms before and after normalization. The stability of first-order and second-order features across the two acquisitions was analysed using the concordance correlation coefficient and the intra-class correlation coefficient. The second dataset (DATASET2) was extracted from the public TCIA database and included 108 patients with WHO grade II and III gliomas and 135 patients with WHO grade IV glioblastomas. The impact of normalization and discretization methods was evaluated based on a tumour grade classification task (balanced accuracy measurement) using five well-established machine learning algorithms. Intensity normalization highly improved the robustness of first-order features and the performances of subsequent classification models. For the T1w-gd sequence, the mean balanced accuracy for tumour grade classification was increased from 0.67 (95% CI 0.61-0.73) to 0.82 (95% CI 0.79-0.84, P?=?.006), 0.79 (95% CI 0.76-0.82, P?=?.021) and 0.82 (95% CI 0.80-0.85, P?=?.005), respectively, using the Nyul, WhiteStripe and Z-Score normalization methods compared to no normalization. The relative discretization makes unnecessary the use of intensity normalization for the second-order radiomics features. Even if the bin number for the discretization had a small impact on classification performances, a good compromise was obtained using the 32 bins considering both T1w-gd and T2w-flair sequences. No significant improvements in classification performances were observed using feature selection. A standardized pre-processing pipeline is proposed for the use of radiomics in MRI of brain tumours. For models based on first- and second-order features, we recommend normalizing images with the Z-Score method and adopting an absolute discretization approach. For second-order feature-based signatures, relative discretization can be used without prior normalization. In both cases, 32 bins for discretization are recommended. This study may pave the way for the multicentric development and validation of MR-based radiomics biomarkers.