Magnetic Resonance Imaging Radiomic Features Research Articles

Prediction of recurrence of ischemic stroke within 1 year of discharge based on machine learning MRI radiomics.

This study aimed to investigate the value of a machine learning-based magnetic resonance imaging (MRI) radiomics model in predicting the risk of recurrence within 1 year following an acute ischemic stroke (AIS). The MRI and clinical data of 612 patients diagnosed with AIS at the Second Affiliated Hospital of Nanchang University from March 1, 2019, to March 5, 2021, were obtained. The patients were divided into recurrence and non-recurrence groups according to whether they had a recurrent stroke within 1 year after discharge. Randomized splitting was used to divide the data into training and validation sets using a ratio of 7:3. Two radiologists used the 3D-slicer software to label the lesions on brain diffusion-weighted (DWI) MRI sequences. Radiomics features were extracted from the annotated images using the pyradiomics software package, and the features were filtered using the Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis. Four machine learning algorithms, logistic regression (LR), Support Vector Classification (SVC), LightGBM, and Random forest (RF), were used to construct a recurrence prediction model. For each algorithm, three models were constructed based on the MRI radiomics features, clinical features, and combined MRI radiomics and clinical features. The sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were used to compare the predictive efficacy of the models. Twenty features were selected from 1,037 radiomics features extracted from DWI images. The LightGBM model based on data with three different features achieved the best prediction accuracy from all 4 models in the validation set. The LightGBM model based solely on radiomics features achieved a sensitivity, specificity, and AUC of 0.65, 0.671, and 0.647, respectively, and the model based on clinical data achieved a sensitivity, specificity, and AUC of 0.7, 0.799, 0.735, respectively. The sensitivity, specificity, and AUC of the LightGBM model base on both radiomics and clinical features achieved the best performance with a sensitivity, specificity, and AUC of 0.85, 0.805, 0.789, respectively. The ischemic stroke recurrence prediction model based on LightGBM achieved the best prediction of recurrence within 1 year following an AIS. The combination of MRI radiomics features and clinical data improved the prediction performance of the model.

Intra- and peri-tumoral MRI radiomics features for preoperative lymph node metastasis prediction in early-stage cervical cancer

BackgroundNoninvasive and accurate prediction of lymph node metastasis (LNM) is very important for patients with early-stage cervical cancer (ECC). Our study aimed to investigate the accuracy and sensitivity of radiomics models with features extracted from both intra- and peritumoral regions in magnetic resonance imaging (MRI) with T2 weighted imaging (T2WI) and diffusion weighted imaging (DWI) for predicting LNM.MethodsA total of 247 ECC patients with confirmed lymph node status were enrolled retrospectively and randomly divided into training (n = 172) and testing sets (n = 75). Radiomics features were extracted from both intra- and peritumoral regions with different expansion dimensions (3, 5, and 7 mm) in T2WI and DWI. Radiomics signature and combined radiomics models were constructed with selected features. A nomogram was also constructed by combining radiomics model with clinical factors for predicting LNM.ResultsThe area under curves (AUCs) of radiomics signature with features from tumors in T2WI and DWI were 0.841 vs. 0.791 and 0.820 vs. 0.771 in the training and testing sets, respectively. Combining radiomics features from tumors in the T2WI, DWI and peritumoral 3 mm expansion in T2WI achieved the best performance with an AUC of 0.868 and 0.846 in the training and testing sets, respectively. A nomogram combining age and maximum tumor diameter (MTD) with radiomics signature achieved a C-index of 0.884 in the prediction of LNM for ECC.Conclusions Radiomics features extracted from both intra- and peritumoral regions in T2WI and DWI are feasible and promising for the preoperative prediction of LNM for patients with ECC.

Magnetic resonance imaging radiomic features for recurrent prostate cancer following proton radiation therapy-A pilot study.

The role of multiparametric MRI (mp-MRI) for postproton radiation evaluation is unclear. In this pilot study, we characterize the mp-MRI features using the Prostate Imaging-Reporting and Data System (PI-RADS) for recurrent prostate cancer (PCa) following proton radiation therapy. After obtaining IRB approval, we identified 163 consecutive cases who underwent MRI-fusion prostate biopsy at our institution from November 2017 to May 2020. This study evaluated patients with prostate cancer (PCa) with biochemical recurrence following proton radiation. Patients were excluded if they had grossly metastatic disease, metal fragments, implanted devices, or with surgically removed prostates. The mpMRI studies were reviewed in depth and scored by 2 fellowship-trained radiologists. Following MRI-fusion biopsy of lesions of interest (LOI), slides were read by fellowship-trained pathologists. We found 14 patients with 16 lesions who met the study inclusion criteria. The median age was 69 years (range 57-79) and median time to biochemical recurrence was 7.3 years (range 3-13). On post-treatment imaging, decreases in prostate size and diffusely decreased T2 signal intensity were observed, making the use of apparent diffusion coefficient (ADC) and early enhancement at dynamic contrast enhanced (DCE) imaging often necessary for diagnosis of disease recurrence. We identified a total of 16 lesions with PIRADS scores of 3 or higher. Of these lesions, there were 5 PIRADS 3 lesions (4/5 (80%) without prostate cancer), 7 PIRADS 4-5 lesions (6 (86%) had high risk Pca), and 4 lesions with unassigned PIRADS scores (100% had high risk cancers). Among the MRI variables, diffusion weighted imaging (DWI) heterogeneity had the strongest association with recurrence of PCa (P < 0.001). Results of our pilot study showed that the PIRADS scoring system in the postproton radiation therapy setting has some correlations with prostate cancer recurrence; However, the clinical value of these findings are unclear. While definitive PIRADS categorization of lesions demonstrated expected frequency of cancer consistent with the scoring system, all unassigned lesions also harbored malignancy suggesting a cautious approach to PIRADS scoring system in postproton radiation setting. The findings from this study may be validated using a larger cohort.

Preoperative prediction of tumor deposits in rectal cancer with clinical-magnetic resonance deep learning-based radiomic models.

This study aimed to establish an effective model for preoperative prediction of tumor deposits (TDs) in patients with rectal cancer (RC). In 500 patients, radiomic features were extracted from magnetic resonance imaging (MRI) using modalities such as high-resolution T2-weighted (HRT2) imaging and diffusion-weighted imaging (DWI). Machine learning (ML)-based and deep learning (DL)-based radiomic models were developed and integrated with clinical characteristics for TD prediction. The performance of the models was assessed using the area under the curve (AUC) over five-fold cross-validation. A total of 564 radiomic features that quantified the intensity, shape, orientation, and texture of the tumor were extracted for each patient. The HRT2-ML, DWI-ML, Merged-ML, HRT2-DL, DWI-DL, and Merged-DL models demonstrated AUCs of 0.62 ± 0.02, 0.64 ± 0.08, 0.69 ± 0.04, 0.57 ± 0.06, 0.68 ± 0.03, and 0.59 ± 0.04, respectively. The clinical-ML, clinical-HRT2-ML, clinical-DWI-ML, clinical-Merged-ML, clinical-DL, clinical-HRT2-DL, clinical-DWI-DL, and clinical-Merged-DL models demonstrated AUCs of 0.81 ± 0.06, 0.79 ± 0.02, 0.81 ± 0.02, 0.83 ± 0.01, 0.81 ± 0.04, 0.83 ± 0.04, 0.90 ± 0.04, and 0.83 ± 0.05, respectively. The clinical-DWI-DL model achieved the best predictive performance (accuracy 0.84 ± 0.05, sensitivity 0.94 ± 0. 13, specificity 0.79 ± 0.04). A comprehensive model combining MRI radiomic features and clinical characteristics achieved promising performance in TD prediction for RC patients. This approach has the potential to assist clinicians in preoperative stage evaluation and personalized treatment of RC patients.

Reproducibility of 2D versus 3D radiomics for quantitative assessment of fetal lung development: a retrospective fetal MRI study

PurposeTo investigate the reproducibility of radiomics features extracted from two-dimensional regions of interest (2D ROIs) versus whole lung (3D) ROIs in repeated in-vivo fetal magnetic resonance imaging (MRI) acquisitions.MethodsThirty fetal MRI scans including two axial T2-weighted acquisitions of the lungs were analysed. 2D (lung at the level of the carina) and 3D (whole lung) ROIs were manually segmented using ITK-Snap. Ninety-five radiomics features were extracted from 2 and 3D ROIs in initial and repeat acquisitions using Pyradiomics. Radiomics feature intra-class correlation coefficients (ICC) were calculated between 2 and 3D ROIs in the initial acquisition, and between 2 and 3D ROIs in repeated acquisitions, respectively.ResultsMRI data of 11 (36.7%) female and 19 (63.3%) male fetuses acquired at a median 25 + 0 gestational weeks plus days (GW) (interquartile range [IQR] 23 + 4 − 27 + 0 GW) were assessed. Median radiomics feature ICC between 2 and 3D ROIs in the initial MRI acquisition was 0.733 (IQR 0.313–0.814, range 0.018–0.970). ICCs between radiomics features extracted using 3D ROIs in initial and repeat acquisitions (median 0.908 [IQR 0.824–0.929, range 0.335–0.996]) were significantly higher compared to 2D ROIs (0.771 [0.699–0.835, 0.048–0.965]) (p < 0.001).ConclusionFetal MRI radiomics features extracted from 3D whole lung segmentation masks showed significantly higher reproducibility across repeat acquisitions compared to 2D ROIs. Therefore, fetal MRI whole lung radiomics features are robust diagnostic and potentially prognostic tools in the image-based in-vivo quantitative assessment of lung development.

Radiomic-based machine learning model for the accurate prediction of prostate cancer risk stratification.

To precisely predict prostate cancer (PCa) risk stratification, we constructed a machine learning (ML) model based on magnetic resonance imaging (MRI) radiomic features. Between August 2016 and May 2021, patients with histologically proven PCa who underwent pre-operative MRI and prostate-specific antigen screening were included. The patients were grouped into different risk categories as defined by the European Association of Urology-European Association of Nuclear Medicine-European Society for Radiotherapy and Oncology-European Society of Urogenital Radiology-International Society of Geriatric Oncology guidelines. Using Artificial Intelligence Kit software, PCa regions of interest were delineated and radiomic features were extracted. Subsequently, predictable models were built by utilising five traditional ML approaches: support vector machine, logistic regression, gradient boosting decision tree, k-nearest neighbour and random forest (RF) classifiers. The classification capacity of the developed models was assessed by area under the receiver operating characteristic curve (AUC) analysis. A total of 213 patients were enrolled, including 16 low-risk, 65 intermediate-risk, and 132 high-risk PCa patients. The risk stratification of PCa could be revealed by MRI radiomic features, and second-order features accounted for most of the selected features. Among the five established ML models, the RF model showed the best overall predictive performance (AUC = 0.87). After further analysis of the subgroups based on the RF model, the prediction of the high-risk group was the best (AUC = 0.89). This study demonstrated that the MR radiomics-based ML method could be a promising tool for predicting PCa risk stratification precisely. The ML models have valuable prospect for accurate PCa risk assessment, which might contribute to customize treatment and surveillance strategies.

18F-FDG PET/CT Parameters Enhance MRI Radiomics for Predicting Human Papilloma Virus Status in Oropharyngeal Squamous Cell Carcinoma.

Predicting human papillomavirus (HPV) status is critical in oropharyngeal squamous cell carcinoma (OPSCC) radiomics. In this study, we developed a model for HPV status prediction using magnetic resonance imaging (MRI) radiomics and 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) parameters in patients with OPSCC. Patients with OPSCC who underwent 18F-FDG PET/CT and contrast-enhanced MRI before treatment between January 2012 and February 2020 were enrolled. Training and test sets (3:2) were randomly selected. 18F-FDG PET/CT parameters and MRI radiomics feature were extracted. We developed three light-gradient boosting machine prediction models using the training set: Model 1, MRI radiomics features; Model 2, 18F-FDG PET/CT parameters; and Model 3, combination of MRI radiomics features and 18F-FDG PET/CT parameters. Area under the receiver operating characteristic curve (AUROC) values were used to analyze the performance of the models in predicting HPV status in the test set. A total of 126 patients (118 male and 8 female; mean age: 60 years) were included. Of these, 103 patients (81.7%) were HPV-positive, and 23 patients (18.3%) were HPV-negative. AUROC values in the test set were 0.762 [95% confidence interval (CI), 0.564-0.959], 0.638 (95% CI, 0.404-0.871), and 0.823 (95% CI, 0.668-0.978) for Models 1, 2, and 3, respectively. The net reclassification improvement of Model 3, compared with that of Model 1, in the test set was 0.119. When combined with an MRI radiomics model, 18F-FDG PET/CT exhibits incremental value in predicting HPV status in patients with OPSCC.

MRI and CT Radiomics Features to Predict Overall Survival of Locally Advanced Esophageal Cancer after Definite Chemoradiotherapy

<h3>Purpose/Objective(s)</h3> We establish prediction models to predict 2-year overall survival and stratify patients with different risks based on the radiomics features extracted from machine learning method using magnetic resonance imaging (MRI) and computed tomography (CT) before definite chemoradiotherapy (dCRT) in locally advanced esophageal cancer. <h3>Materials/Methods</h3> A total of 192 patients receiving the definite chemoradiotherapy were enrolled. The inclusion criteria were as follows 1) ≥18 years old; 2) Clinical stages T1-4, N0-1, M0-1B (AJCC version 6, M1b is limited to lymph node metastasis in the supraclavicular or celiac trunk area); 3) Radiation dose EQD2≥40Gy. 4)Minimum follow-up time is 2 years. We extracted 547 radiomics features from MRI and CT images respectively. The least absolute shrinkage and selection operator (LASSO) for COX algorithm was used to obtain features highly correlated with survival outcomes. Based on MRI, CT and the hybrid image data, three prediction models were built. In each hold-out experiment, patients were randomized into the training and validation cohorts at a ratio of 7:3. The predictive performance was evaluated in the training cohort and verified in the validation cohort using the concordance index (C-index). <h3>Results</h3> The median age of the patients was 63 years, and 78% were males. The clinical stages were stage ⅡA in 7 patients (3.6%), ⅡB in 10 patients (5.2%), Ⅲ in 131 patients (68.2%), Ⅳa in 16 patients (8.3%) and Ⅳb in 28 patients (14.6%). The median survival time was 20.9 months and the median follow-up time was 28.3 months. The predictive performances of MRI-based model were tested in the training sets and validation sets with the C-index of 0.725 (95%CI:0.617-0.834) and 0.603 (95%CI:0.399-0.808). For the prediction of 2-year OS, the AUC values were 0.822 for the training sets and 0.578 for the validation sets. We also created a CT radiomics-based model and a similar performance as MRI radiomics-based model was observed with an average C-index of 0.679 (95%CI:0.565-0.794) in the training sets and 0.629 (95%CI:0.417-0.840) in the validation sets. The hybrid model combining MRI and CT radiomics features were furtherly investigated, and the best performances were shown among three models with an average C-index of 0.721(95%CI:0.621-0.833) in the training cohorts and 0.689 (95%CI:0.497-0.881) in the validation cohorts. It showed significant differences (p<0.0001) of 2-year OS in the high-risk and low-risk groups divided by the best cutoff value of the receiver operator characteristic (ROC) curve in the hybrid radiomics-based model. The median survival of high-risk and low-risk groups were 11.3 VS 19.5 months in training cohorts and 13.3 VS 30.0 months in validation cohorts, and 2-year OS of high-risk and low-risk was 17.1% VS 69.2% in training groups compared to 26.2% VS 48.4% in validation groups. <h3>Conclusion</h3> The hybrid radiomics-based model has the best performances of predicting 2-year overall survival and can differentiate the high-risk and low-risk patients.

Differentiating Primary Tumors for Brain Metastasis with Integrated Radiomics from Multiple Imaging Modalities

Objectives To differentiate the primary site of brain metastases (BMs) is of high clinical value for the successful management of patients with BM. The purpose of this study is to investigate a combined radiomics model with computer tomography (CT) and magnetic resonance imaging (MRI) images in differentiating BMs originated from lung and breast cancer. Methods Pretreatment cerebral contrast enhanced CT and T1-weighted MRI images of 78 patients with 179 BMs from primary lung and breast cancer were retrospectively analyzed. Radiomic features were extracted from contoured BM lesions and selected using the Mann–Whitney U test and the least absolute shrinkage and selection operator (LASSO) logistic regression. Binary logistic regression (BLR) and support vector machine (SVM) models were built and evaluated based on selected radiomic features from CT alone, MRI alone, and combined images to differentiate BMs originated from lung and breast cancer. Results A total of 10 and 6 optimal radiomic features were screened out of 1288 CT and 1197 MRI features, respectively. The mean area under the curves (AUCs) of the BLR and SVM models using fivefolds cross-validation were 0.703 vs. 0.751, 0.718 vs. 0.754, and 0.781 vs. 0.803 in the training dataset and 0.708 vs. 0.763, 0.715 vs. 0.717, and 0.771 vs. 0.805 in the testing dataset for models with CT alone, MRI alone, and combined CT and MRI radiomic features, respectively. Conclusions Radiomics model based on combined CT and MRI features is feasible and accurate in the differentiation of the primary site of BMs from lung and breast cancer.

Impact of Parallel Acquisition Technology on the Robustness of Magnetic Resonance Imaging Radiomic Features.

The aim of this study was to investigate the impact of integrated parallel acquisition technology (iPAT) on the robustness of magnetic resonance imaging radiomic features. A phantom and 6 healthy volunteers were scanned on a clinical 3-T system using T1-weighted (S1), T1-weighted fluid-attenuated (S2), T2-weighted fluid-attenuated (S3), and T2-weighted (S4); 2 iPAT flavors (generalized autocalibration partially parallel acquisitions and modified sensitivity encoding [mSENSE]) and their different acceleration factors R. Radiomic features were extracted, and their robustness was assessed using coefficient of variation (CV), and differences between sequences and region of interest (ROI) were evaluated using the χ2 test. One volunteer was excluded because of movement during imaging acquisition. Generalized autocalibration partially parallel acquisitions provided more radiomic features with excellent robustness than mSENSE. Radiomic features with excellent robustness, unaffected by iPAT across different sequences and ROIs, in 92 radiomic features for phantom and healthy volunteers are 6.5% and 2.2%. For phantom, difference in the robustness degree between 4 sequences/P-ROIs was significant according to χ2 test; S2 and S3 could provide more excellent robust radiomic features than S1 and S4, and P-ROI3 filled with the biggest polystyrene particles could provide the most radiomic features with excellent robustness than the other P-ROIs. For healthy volunteers, only the difference in the degree of robustness between the 4 V-ROIs was significant, and V-ROI3 in white matter region of the left frontal lobe, which was located at periphery in image, could provide the most robust radiomic features compared with other V-ROIs. Integrated parallel acquisition technology had a significant impact on the robustness of radiomic features. Generalized autocalibration partially parallel acquisitions delivered a more robust substrate for radiomic analyses than mSENSE.

Brain magnetic resonance imaging radiomics features associated with hepatic encephalopathy in adult cirrhotic patients

PurposeHepatic encephalopathy (HE) is a potential complication of cirrhosis. Magnetic resonance imaging (MRI) may demonstrate hyperintense T1 signal in the globi pallidi. The purpose of this study was to evaluate the performance of MRI-based radiomic features for diagnosing and grading chronic HE in adult patients affected by cirrhosis.MethodsAdult patients with and without cirrhosis underwent brain MRI with identical imaging protocol on a 3T scanner. Patients without history of chronic liver disease were the control population. HE grading was based on underlying liver disease, severity of clinical manifestation, and number of encephalopathic episodes. Texture analysis was performed on axial T1-weighted images on bilateral lentiform nuclei at the level of the foramina of Monro. Diagnostic performance of texture analysis for the diagnosis and grading of HE was assessed by calculating the area under the receiver operating characteristics (AUROC) with 95% confidence interval (CI).ResultsThe final study population consisted of 124 patients, 70 cirrhotic patients, and 54 non-cirrhotic controls. Thirty-eight patients had history of HE with 22 having an HE grade > 1. The radiomic features predicted the presence of HE with an AUROC of 0.82 (95% CI: 0.73, 0.90; P < .0001; 82% sensitivity, 66% specificity). Radiomic features predicted grade 1 HE (AUROC 0.75; 95% CI: 0.61, 0.89; P < .0001; 94% sensitivity, 60% specificity) and grade ≥ 2 HE (AUROC 0.82; 95% CI: 0.71, 0.93; P < .0001, 95% sensitivity, 57% specificity).ConclusionIn cirrhotic patients, MR radiomic is effective in predicting the presence of chronic HE and in grading its severity.

Acquisition repeatability of MRI radiomics features in the head and neck: a dual-3D-sequence multi-scan study

Radiomics has increasingly been investigated as a potential biomarker in quantitative imaging to facilitate personalized diagnosis and treatment of head and neck cancer (HNC), a group of malignancies associated with high heterogeneity. However, the feature reliability of radiomics is a major obstacle to its broad validity and generality in application to the highly heterogeneous head and neck (HN) tissues. In particular, feature repeatability of radiomics in magnetic resonance imaging (MRI) acquisition, which is considered a crucial confounding factor of radiomics feature reliability, is still sparsely investigated. This study prospectively investigated the acquisition repeatability of 93 MRI radiomics features in ten HN tissues of 15 healthy volunteers, aiming for potential magnetic resonance-guided radiotherapy (MRgRT) treatment of HNC. Each subject underwent four MRI acquisitions with MRgRT treatment position and immobilization using two pulse sequences of 3D T1-weighed turbo spin-echo and 3D T2-weighed turbo spin-echo on a 1.5 T MRI simulator. The repeatability of radiomics feature acquisition was evaluated in terms of the intraclass correlation coefficient (ICC), whereas within-subject acquisition variability was evaluated in terms of the coefficient of variation (CV). The results showed that MRI radiomics features exhibited heterogeneous acquisition variability and uncertainty dependent on feature types, tissues, and pulse sequences. Only a small fraction of features showed excellent acquisition repeatability (ICC > 0.9) and low within-subject variability. Multiple MRI scans improved the accuracy and confidence of the identification of reliable features concerning MRI acquisition compared to simple test-retest repeated scans. This study contributes to the literature on the reliability of radiomics features with respect to MRI acquisition and the selection of reliable radiomics features for use in modeling in future HNC MRgRT applications.

Gd-EOB-DTPA-enhanced MRI radiomic features for predicting histological grade of hepatocellular carcinoma.

Prediction models for the histological grade of hepatocellular carcinoma (HCC) remain unsatisfactory. The purpose of this study is to develop preoperative models to predict histological grade of HCC based on gadolinium-ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) radiomics. And to compare the performance between artificial neural network (ANN) and logistic regression model. A total of 122 HCCs were randomly assigned to the training set (n=85) and the test set (n=37). There were 242 radiomic features extracted from volumetric of interest (VOI) of arterial and hepatobiliary phases images. The radiomic features and clinical parameters [gender, age, alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen 19-9 (CA19-9), alanine aminotransferase (ALT), aspartate transaminase (AST)] were selected by permutation test and decision tree. ANN of arterial phase (ANN-AP), logistic regression model of arterial phase (LR-AP), ANN of hepatobiliary phase (ANN-HBP), logistic regression mode of hepatobiliary phase (LR-HBP), ANN of combined arterial and hepatobiliary phases (ANN-AP + HBP), and logistic regression model of combined arterial and hepatobiliary phases (LR-AP + HBP) were built to predict HCC histological grade. Those prediction models were assessed and compared. ANN-AP and LR-AP were composed by AST and radiomic features based on arterial phase. ANN-HBP and LR-HBP were composed by AFP and radiomic features based on hepatobiliary phase. ANN-AP + HBP and LR-AP + HBP were composed by AST and radiomic features based on arterial and hepatobiliary phases. The prediction models could distinguish between high-grade tumors [Edmondson-Steiner (E-S) grade III and IV] and low-grade tumors (E-S grade I and II) in both training set and test set. In the test set, the AUCs of ANN-AP, LR-AP, ANN-HBP, LR-HBP, ANN-AP + HBP and LR-AP + HBP were 0.889, 0.777, 0.941, 0.819, 0.944 and 0.792 respectively. The ANN-HBP was significantly superior to LR-HBP (P=0.001). And the ANN-AP + HBP was significantly superior to LR-AP + HBP (P=0.007). Prediction models consisting of clinical parameters and Gd-EOB-DTPA-enhanced MRI radiomic features (based on arterial phase, hepatobiliary phase, and combined arterial and hepatobiliary phases) could distinguish between high-grade HCCs and low-grade HCCs. And the ANN was superior to logistic regression model in predicting histological grade of HCC.

Changes in Magnetic Resonance Imaging Radiomic Features in Response to Androgen Deprivation Therapy in Patients with Intermediate- and High-risk Prostate Cancer

AimsThe benefits of neoadjuvant androgen deprivation therapy (nADT) in the management of intermediate- and high-risk prostate cancer patients have been well-established. The aim of this study was to identify radiomic prognostic features derived from routine anatomic magnetic resonance imaging (MRI) sequences that can predict the response of the prostate cancer to nADT. Materials and methodsPatients with intermediate- and high-risk prostate cancer (with one of clinical stage ≥ T2c, Gleason score ≥7 or presenting prostate-specific antigen ≥10) who received 3 months of ADT prior to radical external beam radiotherapy were enrolled into this study. The relative blood volume and the relative blood flow were used as dynamic MRI kinetic parameters to quantify vascular changes as responses to nADT. For all pre- and post-nADT data sets, a combination of T2-weighted and contrast-enhanced T1-weighted anatomic images were used to define regions of interest (ROI) as the dominant malignant nodules (DMNs) and the benign prostate (the entire prostate with the summed DMNs being subtracted). MRI textural radiomic features associated with prostate cancer response in the literature of energy and homogeneity were selected. Pyradiomics was used to extract textural features of the ROIs. A Wilcoxon signed-rank test was carried out to investigate if there were statistically significant differences in values of radiomic features between: (i) benign prostate ROI and DMN pre-nADT; (ii) pre- and post-nADT of benign prostate ROI; (iii) pre- and post-nADT of DMN. Changes in radiomic features and dynamic MRI kinetic parameters were correlated using the Spearman correlation test. ResultsTwenty prostate cancer patients were recruited into the study. The median time between the first baseline scan and the first on-treatment scan was 91.5 days (range 82–105). One patient had no discernible tumour visible, leaving 19 patients with evaluable data for the analysis. Baseline homogeneity and energy values differed significantly between benign and malignant tissue (P < 0.01). In response to nADT, homogeneity and energy showed reciprocal changes, significantly increased in benign prostate while decreasing in the DMN. The reduction in tumour homogeneity and energy feature values showed a positive association with the decline in tumour blood flow and tumour blood volume induced by androgen deprivation as derived from dynamic MRI parameters. ConclusionEnergy and homogeneity radiomic features derived from MRI of benign and malignant prostate showed significant reciprocal changes in response to nADT. This study confirms the potential of these radiomic features to act as surrogate markers of tumour androgen sensitivity due to their strong association with ADT-induced physiological effects in prostate tumours.

RtNet: a deep hybrid neural network for the identification of acute rejection and chronic allograft nephropathy after renal transplantation using multiparametric MRI.

Reliable diagnosis of the cause of renal allograft dysfunction is of clinical importance. The aim of this study is to develop a hybrid deep-learning approach for determining acute rejection (AR), chronic allograft nephropathy (CAN) and renal function in kidney-allografted patients by multimodality integration. Clinical and magnetic resonance imaging (MRI) data of 252 kidney-allografted patients who underwent post-transplantation MRI between December 2014 and November 2019 were retrospectively collected. An end-to-end convolutional neural network, namely RtNet, was designed to discriminate between AR, CAN and stable renal allograft recipient (SR), and secondarily, to predict the impaired renal graft function [estimated glomerular filtration rate (eGFR) ≤50 mL/min/1.73 m2]. Specially, clinical variables and MRI radiomics features were integrated into the RtNet, resulting in a hybrid network (RtNet+). The performance of the conventional radiomics model RtRad, RtNet and RtNet+ was compared to test the effect of multimodality interaction. Out of 252 patients, AR, CAN and SR was diagnosed in 20/252 (7.9%), 92/252 (36.5%) and 140/252 (55.6%) patients, respectively. Of all MRI sequences, T2-weighted imaging and diffusion-weighted imaging with stretched exponential analysis showed better performance than other sequences. On pairwise comparison of resulting prediction models, RtNet+ produced significantly higher macro-area-under-curve (macro-AUC) (0.733 versus 0.745; P = 0.047) than RtNet in discriminating between AR, CAN and SR. RtNet+ performed similarly to the RtNet (macro-AUC, 0.762 versus 0.756; P > 0.05) in discriminating between eGFR ≤50 mL/min/1.73 m2 and >50 mL/min/1.73 m2. With decision curve analysis, adding RtRad and RtNet to clinical variables resulted in more net benefits in diagnostic performance. Our study revealed that the proposed RtNet+ model owned a stable performance in revealing the cause of renal allograft dysfunction, and thus might offer important references for individualized diagnostics and treatment strategy.

Predicting survival in patients with glioblastoma using MRI radiomic features extracted from radiation planning volumes.

Quantitative image analysis using pre-operative magnetic resonance imaging (MRI) has been able to predict survival in patients with glioblastoma (GBM). The study explored the role of postoperative radiation (RT) planning MRI-based radiomics to predict the outcomes, with features extracted from the gross tumor volume (GTV) and clinical target volume (CTV). Patients with IDH-wildtype GBM treated with adjuvant RT having MRI as a part of RT planning process were included in the study. 546 features were extracted from each GTV and CTV. A LASSO Cox model was applied, and internal validation was performed using leave-one-out cross-validation with overall survival as endpoint. Cross-validated time-dependent area under curve (AUC) was constructed to test the efficacy of the radiomics model, and clinical features were used to generate a combined model. Analysis was done for the entire group and in individual surgical groups-gross total excision (GTR), subtotal resection (STR), and biopsy. 235 patients were included in the study with 57, 118, and 60 in the GTR, STR, and biopsy subgroup, respectively. Using the radiomics model, binary risk groups were feasible in the entire cohort (p < 0.01) and biopsy group (p = 0.04), but not in the other two surgical groups individually. The integrated AUC (iAUC) was 0.613 for radiomics-based classification in the biopsy subgroup, which improved to 0.632 with the inclusion of clinical features. Imaging features extracted from the GTV and CTV regions can lead to risk-stratification of GBM undergoing biopsy, while the utility in other individual subgroups needs to be further explored.

Magnetic Resonance Radiomics and Machine-learning Models: An Approach for Evaluating Tumor-stroma Ratio in Patients with Pancreatic Ductal Adenocarcinoma

To develop and validate a magnetic resonance imaging (MRI)-based machine learning classifier for evaluating the tumor-stroma ratio (TSR) in patients with pancreatic ductal adenocarcinoma (PDAC). In this retrospective study, 148 patients with PDAC underwent an MR scan and surgical resection. We used hematoxylin and eosin to quantify the TSR. For each patient, we extracted 1,409 radiomics features and reduced them using the least absolute shrinkage and selection operator logistic regression algorithm. The extreme gradient boosting (XGBoost) classifier was developed using a training set comprising 110 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 38 consecutive patients, admitted between January 2018 and April 2018. We determined the performance of the XGBoost classifier based on its discriminative ability, calibration, and clinical utility. A log-rank test revealed significantly longer survival in the TSR-low group. The prediction model displayed good discrimination in the training (area under the curve [AUC], 0.82) and validation set (AUC, 0.78). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 77.14%, 75.00%, 0.76%, 0.84%, and 0.65%, respectively, those for the validation set were 58.33%, 92.86%, 0.71%, 0.93%, and 0.57%, respectively. We developed an XGBoost classifier based on MRI radiomics features, a non-invasive prediction tool that can evaluate the TSR of patients with PDAC. Moreover, it will provide a basis for interstitial targeted therapy selection and monitoring.

FLAIR and ADC Image-Based Radiomics Features as Predictive Biomarkers of Unfavorable Outcome in Patients With Acute Ischemic Stroke.

At present, it is still challenging to predict the clinical outcome of acute ischemic stroke (AIS). In this retrospective study, we explored whether radiomics features extracted from fluid-attenuated inversion recovery (FLAIR) and apparent diffusion coefficient (ADC) images can predict clinical outcome of patients with AIS. Patients with AIS were divided into a training (n = 110) and an external validation (n = 80) sets. A total of 753 radiomics features were extracted from each FLAIR and ADC image of the 190 patients. Interquartile range (IQR), Wilcoxon rank sum test, and least absolute shrinkage and selection operator (LASSO) were used to reduce the feature dimension. The six strongest radiomics features were related to an unfavorable outcome of AIS. A logistic regression analysis was employed for selection of potential predominating clinical and conventional magnetic resonance imaging (MRI) factors. Subsequently, we developed several models based on clinical and conventional MRI factors and radiomics features to predict the outcome of AIS patients. For predicting unfavorable outcome [modified Rankin scale (mRS) > 2] in the training set, the area under the receiver operating characteristic curve (AUC) of ADC radiomics model was 0.772, FLAIR radiomics model 0.731, ADC and FLAIR radiomics model 0.815, clinical model 0.791, and clinical and conventional MRI model 0.782. In the external validation set, the AUCs for the prediction with ADC radiomics model was 0.792, FLAIR radiomics model 0.707, ADC and FLAIR radiomics model 0.825, clinical model 0.763, and clinical and conventional MRI model 0.751. When adding radiomics features to the combined model, the AUCs for predicting unfavorable outcome in the training and external validation sets were 0.926 and 0.864, respectively. Our results indicate that the radiomics features extracted from FLAIR and ADC can be instrumental biomarkers to predict unfavorable clinical outcome of AIS and would additionally improve predictive performance when adding to combined model.

MRI-Radiomics Prediction for Cytokeratin 19-Positive Hepatocellular Carcinoma: A Multicenter Study.

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and has poor prognosis. Cytokeratin (CK)19-positive (CK19+) HCC is especially aggressive; early identification of this subtype and timely intervention can potentially improve clinical outcomes. In the present study, we developed a preoperative gadoxetic acid-enhanced magnetic resonance imaging (MRI)-based radiomics model for noninvasive and accurate classification of CK19+ HCC. A multicenter and time-independent cohort of 257 patients were retrospectively enrolled (training cohort, n = 143; validation cohort A, n = 75; validation cohort B, n = 39). A total of 968 radiomics features were extracted from preoperative multisequence MR images. The maximum relevance minimum redundancy algorithm was applied for feature selection. Multiple logistic regression, support vector machine, random forest, and artificial neural network (ANN) algorithms were used to construct the radiomics model, and the area under the receiver operating characteristic (AUROC) curve was used to evaluate the diagnostic performance of corresponding classifiers. The incidence of CK19+ HCC was significantly higher in male patients. The ANN-derived combined classifier comprising 12 optimal radiomics features showed the best diagnostic performance, with AUROCs of 0.857, 0.726, and 0.790 in the training cohort and validation cohorts A and B, respectively. The combined model based on multisequence MRI radiomics features can be used for preoperative noninvasive and accurate classification of CK19+ HCC, so that personalized management strategies can be developed.

Magnetic resonance radiomics features and prognosticators in different molecular subtypes of pediatric Medulloblastoma.

PurposeMedulloblastoma (MB) is a highly malignant pediatric brain tumor. In the latest classification, medulloblastoma is divided into four distinct groups: wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. We analyzed the magnetic resonance imaging radiomics features to find the imaging surrogates of the 4 molecular subgroups of MB.Material and methodsFrozen tissue, imaging data, and clinical data of 38 patients with medulloblastoma were included from Taipei Medical University Hospital and Taipei Veterans General Hospital. Molecular clustering was performed based on the gene expression level of 22 subgroup-specific signature genes. A total 253 magnetic resonance imaging radiomic features were generated from each subject for comparison between different molecular subgroups.ResultsOur cohort consisted of 7 (18.4%) patients with WNT medulloblastoma, 12 (31.6%) with SHH tumor, 8 (21.1%) with Group 3 tumor, and 11 (28.9%) with Group 4 tumor. 8 radiomics gray-level co-occurrence matrix texture (GLCM) features were significantly different between 4 molecular subgroups of MB. In addition, for tumors with higher values in a gray-level run length matrix feature—Short Run Low Gray-Level Emphasis, patients have shorter survival times than patients with low values of this feature (p = 0.04). The receiver operating characteristic analysis revealed optimal performance of the preliminary prediction model based on GLCM features for predicting WNT, Group 3, and Group 4 MB (area under the curve = 0.82, 0.72, and 0.78, respectively).ConclusionThe preliminary result revealed that 8 contrast-enhanced T1-weighted imaging texture features were significantly different between 4 molecular subgroups of MB. Together with the prediction models, the radiomics features may provide suggestions for stratifying patients with MB into different risk groups.