Multiparametric MRI radiomics improves preoperative diagnostic performance for local staging in patients with endometrial cancer.

PURPOSE: To determine whether multiparametric magnetic resonance imaging (MRI) radiomics-based machine learning methods can improve preoperative local staging in patients with endometrial cancer (EC). METHODS: Data of patients with histologically confirmed EC who underwent preoperative MRI were retrospectively analyzed and divided into a training or test set. Radiomic features extracted from multiparametric MR images were used to train and test the prediction of deep myometrial invasion (DMI) and cervical stromal invasion (CSI). Two radiologists assessed the presence of DMI and CSI on conventional MR images. A combined model incorporating a radiomic signature and conventional MR images was constructed and presented as a nomogram. Performance of the predictive models was assessed using the area under curve (AUC) in the receiver operating curve analysis and pairwise comparison using DeLong's test with Bonferroni correction. RESULTS: This study included 198 women (training set = 138, test set = 60). Conventional MRI achieved AUCs of 0.837 and 0.799 for detecting DMI and 0.825 and 0.858 for detecting CSI in the training and test sets, respectively. The nomogram achieved AUCs of 0.928 and 0.869 for detecting DMI and 0.913 and 0.937 for detecting CSI in the training and test sets, respectively. The ability of the nomogram to detect DMI and CSI in the two sets was superior to that of conventional MRI (adjusted p < 0.05), except for the ability to detect CSI in the test set (adjusted p > 0.05). CONCLUSION: A nomogram incorporating radiomics signature into conventional MRI improved the efficacy of preoperative local staging of EC.

A Radiomics Nomogram for Preoperative Prediction of Early Recurrence of Small Hepatocellular Carcinoma After Surgical Resection or Radiofrequency Ablation.

BACKGROUND: Patients with small hepatocellular carcinoma (HCC) (3 cm) still have a poor prognosis. The purpose of this study was to develop a radiomics nomogram to preoperatively predict early recurrence (ER) (2 years) of small HCC. METHODS: The study population included 111 patients with small HCC who underwent surgical resection (SR) or radiofrequency ablation (RFA) between September 2015 and September 2018 and were followed for at least 2 years. Radiomic features were extracted from the entire tumor by using the MaZda software. The least absolute shrinkage and selection operator (LASS0) method was applied for feature selection, and radiomics signature construction. A rad-score was then calculated. Multivariable logistic regression analysis was used to establish a prediction model including independent clinical risk factors, radiologic features and rad-score, which was ultimately presented as a radiomics nomogram. The predictive ability of the nomogram was evaluated using the area under the receiver operating characteristic (ROC) curve and internal validation was performed via bootstrap resampling and 5-fold cross-validation method. RESULTS: A total of 53 (53/111, 47.7%) patients had confirmed ER according to the final clinical outcomes. In univariate logistic regression analysis, cirrhosis and hepatitis B infection (P=0.015 and 0.083, respectively), hepatobiliary phase hypointensity (P=0.089), Child-Pugh score (P=0.083), the preoperative platelet count (P=0.003), and rad-score (P<0.001) were correlated with ER. However, after multivariate logistic regression analysis, only the preoperative platelet count and rad-score were included as predictors in the final model. The area under ROC curve (AUC) of the radiomics nomogram to predict ER of small HCC was 0.981 (95% CI: 0.957, 1.00), while the AUC verified by bootstrap is 0.980 (95% CI: 0.962, 1.00), indicating the goodness-of-fit of the final model. CONCLUSIONS: The radiomics nomogram containing the clinical risk factors and rad-score can be used as a quantitative tool to preoperatively predict individual probability of ER of small HCC.

Hepatobiliary phase hypointensity on gadobenate dimeglumine-enhanced magnetic resonance imaging may improve the diagnosis of hepatocellular carcinoma.

BACKGROUND: To determine the clinical value of hepatobiliary phase (HBP) hypointensity for noninvasive diagnosis of hepatocellular carcinoma (HCC). METHODS: A total of 246 high-risk patients with 263 selected nodules (126 HCCs, 137 non-HCCs) undergoing gadobenate dimeglumine (Gd-BOPTA)-enhanced magnetic resonance imaging (MRI) were included in the study. Imaging-based diagnoses of small (≤3 cm) and large (>3 cm) HCCs were made using the following 4 criteria: (I) non-rim arterial phase hyper-enhancement (APHE) plus hypointensity on the portal venous phase (PVP); (II) non-rim APHE plus hypointensity on the PVP and/or transitional phase (TP); (III) non-rim APHE plus hypointensity on the PVP and/or TP and/or HBP; (IV) criterion 3 plus non-LR-1/2/M. Based on typical imaging features, LR-1, LR-2, or LR-M (if definitely benign, probably benign, malignant but not HCC specific, respectively) were defined according to the Liver Imaging Reporting and Data System (LI-RADS). Sensitivities and specificities of imaging criteria were calculated and compared using McNemar's test. RESULTS: Among the diagnostic criteria for small HCCs, criterion 3 and 4, which included HBP hypointensity, showed significantly higher sensitivities (96.4% and 94.6%, respectively) than criterion 1 (58.9%, P<0.001 for both). Moreover, criterion 4, which included HBP hypointensity and ancillary features, showed significantly higher specificity (94.7%) than criterion 3 (66.7%, P<0.001) and comparable specificity to criterion 1 (97.4%, P=0.375), achieving the highest accuracies (94.7%). The diagnostic performance of criterion 4 for large HCCs was similar to that for small HCCs. CONCLUSIONS: HBP hypointensity acquired from Gd-BOPTA-MRI can improve sensitivity and maintain high specificity in the diagnosis of both small and large HCCs after excluding benignities or non-HCC malignancies according to characteristic imaging features.

A radiomics nomogram based on contrast-enhanced MRI for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma.

BACKGROUND: Macrotrabecular-massive hepatocellular carcinoma (MTM-HCC) represents an aggressive form of hepatocellular carcinoma and is associated with poor survival outcomes. AIMS: This study aimed to develop a radiomics nomogram based on contrast-enhanced MRI for preoperative prediction of MTM-HCC. METHODS: This study enrolled 88 patients with histologically confirmed HCC, including 32 MTM-HCCs and 56 Non-MTM-HCCs. The clinical and gadobenate dimeglumine (Gd)-enhanced MRI features were retrospectively reviewed by two abdominal radiologists. The regions of interest (ROIs) on the largest cross-sectional image and two adjacent images of the tumor, from which radiomics features were extracted via MaZda software and a radiomics score (Rad-score) was calculated via Python software. Combined with the Rad-score and independent imaging factors, a radiomics nomogram was constructed using R software. Nomogram performance was estimated with calibration curve. RESULTS: A total of eleven top weighted radiomics features were selected among five sequences of MR images. There was a significant difference in Rad-score between MTM-HCC and non-MTM-HCC patients (P < 0.001), where patients with MTM-HCC generally had higher Rad-scores (absolute value). After multivariate analysis, radiomics score (OR = 7.794, P < 0.001) and intratumor fat (OR = 9.963, P = 0.014) were determined as independent predictors associated with MTM-HCC. The area under the receiver operating characteristic (ROC) curve of the selected model was 0.813 (95% CI 0.714-0.912) and the optimal cutoff value was 0.60. The nomogram showed overall satisfactory prediction performance (AUC = 0.785 [95% CI 0.684-0.886]). CONCLUSIONS: A contrast-enhanced MRI-based radiomics nomogram may be useful for preoperative prediction of MTM-HCC in primary HCC patients, allowing opportunity to improve the treatment course and patient outcomes.

Texture Analysis of Three-Dimensional MRI Images May Differentiate Borderline and Malignant Epithelial Ovarian Tumors.

OBJECTIVE: To explore the value of magnetic resonance imaging (MRI)-based whole tumor texture analysis in differentiating borderline epithelial ovarian tumors (BEOTs) from FIGO stage I/II malignant epithelial ovarian tumors (MEOTs). MATERIALS AND METHODS: A total of 88 patients with histopathologically confirmed ovarian epithelial tumors after surgical resection, including 30 BEOT and 58 MEOT patients, were divided into a training group (n = 62) and a test group (n = 26). The clinical and conventional MRI features were retrospectively reviewed. The texture features of tumors, based on T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging, were extracted using MaZda software and the three top weighted texture features were selected by using the Random Forest algorithm. A non-texture logistic regression model in the training group was built to include those clinical and conventional MRI variables with p value < 0.10. Subsequently, a combined model integrating non-texture information and texture features was built for the training group. The model, evaluated using patients in the training group, was then applied to patients in the test group. Finally, receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of the models. RESULTS: The combined model showed superior performance in categorizing BEOTs and MEOTs (sensitivity, 92.5%; specificity, 86.4%; accuracy, 90.3%; area under the ROC curve [AUC], 0.962) than the non-texture model (sensitivity, 78.3%; specificity, 84.6%; accuracy, 82.3%; AUC, 0.818). The AUCs were statistically different (p value = 0.038). In the test group, the AUCs, sensitivity, specificity, and accuracy were 0.840, 73.3%, 90.1%, and 80.8% when the non-texture model was used and 0.896, 75.0%, 94.0%, and 88.5% when the combined model was used. CONCLUSION: MRI-based texture features combined with clinical and conventional MRI features may assist in differentitating between BEOT and FIGO stage I/II MEOT patients.

Quantitative analysis of multiphase magnetic resonance images may assist prediction of histopathological grade of small hepatocellular carcinoma.

BACKGROUND: The aim of the study was to investigate whether preoperative quantitative analysis of multiphase magnetic resonance images may assist in predicting the pathological grade of small hepatocellular carcinoma (HCC). METHODS: A total of 49 patients with small HCCs (≤3 cm) underwent multiphase magnetic resonance imaging (MRI) and were retrospectively reviewed. Routine unenhanced and post gadobenate dimeglumine (Gd-BOPTA)-enhanced MRI were preoperatively performed. Signal intensity (SI) was measured within the designated region of interest (ROI) including those of the lesion and paraspinous muscles. The lesion-to-paraspinous muscle relative contrast ratio (RCR) on T2-weighted (T2W) imaging, diffusion-weighted (DW) imaging, and dynamic phase Gd-BOPTA-enhanced T1W (T1-weighted) imaging were calculated, and statistical analysis was performed to determine the predictive power for the histological grade. RESULTS: In all, 49 cases were included comprising 3 well-differentiated (WD) HCCs, 36 moderately differentiated (MD) HCCs, and 10 poorly differentiated (PD) HCCs. There was a negative correlation between the RCR and pathological grade of small HCC in the arterial phase [correlation coefficient (ρ)=-0.305, P<0.05]. However, there was no correlation between RCR in other phases and pathological grade (P>0.05 for all). There was also no correlation between tumor margin, tumor location, cystic/necrotic change, intratumoral fat, enhancement pattern, tumor capsule, tumor boundary or tumor size, and any of the differentiation categories (P>0.05 for all). CONCLUSIONS: The lesion-to-paraspinous muscle RCR on arterial phase Gd-BOPTA-enhanced T1W imaging may be useful for the prediction of the histological characteristics of small HCC.

CT Image-Based Texture Analysis to Predict Microvascular Invasion in Primary Hepatocellular Carcinoma.

The objective of this study was to determine the clinical value of computed tomography (CT) image-based texture analysis in predicting microvascular invasion of primary hepatocellular carcinoma (HCC). CT images of patients with HCC from May 2017 to May 2019 confirmed by surgery and histopathology were retrospectively analyzed. Image features including tumor margin, tumor capsule, peritumoral enhancement, hypoattenuating halo, intratumoral arteries, and tumor-liver differences were assessed. All patients were divided into microvascular invasion (MVI)-negative group (n = 34) and MVI-positive group (n = 68). Preoperative CT images were further imported into MaZda software, where the regions of interest of the lesions were manually delineated. Texture features of lesions based on pre-contrast, arterial, portal, and equilibrium phase CT images were extracted. Thirty optimal texture parameters were selected from each phase by Fisher's coefficient (Fisher), classification error probability combined with average correlation coefficient (POE+ACC), and mutual information (MI). Finally, receiver operating characteristic curve analysis was performed. The results showed that the Edmonson-Steiner grades, tumor size, tumor margin, and intratumoral artery characteristics were significantly different between the two groups (P = 0.012, < 0.001, < 0.001, = 0.003, respectively). There were 58 parameters with significant differences between the MVI-negative and MVI-positive groups (P < 0.001 for all). Among them, 12, 14, 17, and 15 parameters were derived from the pre-contrast phase, arterial phase, portal phase, and equilibrium phase respectively. According to the ROC analysis, optimal texture parameters based on the pre-contrast, arterial, portal, and equilibrium phases were 135dr_GLevNonU (AUC, 0.766; the cutoff value, 1055.00), Vertl_RLNonUni (AUC, 0.764; the cutoff value, 5974.38), 45dgr_GLevNonU (AUC, 0.762; the cutoff value, 924.34), and Vertl_RLNonUni (AUC, 0.754; the cutoff value, 4868.80), respectively. Texture analysis of preoperative CT images may be used as a non-invasive method to predict microvascular invasion in patients with primary hepatocellular carcinomas, and further to guide the treatment and evaluate prognosis. The most valuable parameters were derived from the gray-level run-length matrix.

Early Diffusion-Weighted Imaging and Proton Magnetic Resonance Spectroscopy Features of Liver Transplanted Tumors Treated with Radiation in Rabbits: Correlation with Histopathology.

In this study, we sought to determine how diffusion-weighted imaging (DWI) and proton magnetic resonance spectroscopy (1H-MRS) features are associated with histopathological results, and explored the cellular mechanisms of DWI and 1H-MRS in early radiosensitivity of transplanted liver tumors. VX2 tumors were implanted into the hind leg muscles of 60 New Zealand White Rabbits. All rabbits were randomly divided into ten subgroups according to treatment: irradiated or nonirradiated and according to different times postirradiation. Magnetic resonance scanning was then performed one day before irradiation and on days 1, 3, 5 and 7 postirradiation. Differences in tumor volume, apparent diffusion coefficient (ADC) value, choline/creatine ratio and lipid/creatine ratio, and their associations with histopathological findings, were assessed. Tumor volumes in the irradiated groups were smaller than control values, while ADC values increased gradually with time postirradiation; choline/creatine ratios were reduced while lipid/creatine ratios were larger compared to control values. Bax protein levels after irradiation increased with time. Interestingly, the ADC value and Bax-positive grade showed the same increasing trend (r = 0.900, P < 0.001). Additionally, choline/creatine and lipid/creatine ratios were respectively significantly associated with Bax-positive grade. Furthermore, significant associations of tumor volume with ADC value, choline/creatine ratio and lipid/creatine ratio were observed. These findings demonstrated that ADC value, choline/creatine ratio and lipid/creatine ratio, indicators of early radiosensitivity, are related to cell apoptosis.