Multi-Parametric Magnetic Resonance Imaging-Based Radiomics Analysis of Cervical Cancer for Preoperative Prediction of Lymphovascular Space Invasion.

BACKGROUND: Detection of lymphovascular space invasion (LVSI) in early cervical cancer (CC) is challenging. To date, no standard clinical markers or screening tests have been used to detect LVSI preoperatively. Therefore, non-invasive risk stratification tools are highly desirable. OBJECTIVE: To train and validate a multi-parametric magnetic resonance imaging (mpMRI)-based radiomics model to detect LVSI in patients with CC and investigate its potential as a complementary tool to enhance the efficiency of risk assessment strategies. MATERIALS AND METHODS: The model was developed from the tumor volume of interest (VOI) of 125 patients with CC. A total of 1037 radiomics features obtained from conventional magnetic resonance imaging (MRI), including a small field-of-view (sFOV) high-resolution (HR)-T2-weighted MRI (T2WI), apparent diffusion coefficient (ADC), T2WI, fat-suppressed (FS)-T2WI, as well as axial and sagittal contrast-enhanced T1-weighted MRI (T1c). We conducted a radiomics-based characterization of each tumor region using pretreatment image data. Feature selection was performed using the least absolute shrinkage and selection operator method on the training set. The predictive performance was compared with single variates (clinical data and single-layer radiomics signatures) analyzed using a receiver operating characteristic (ROC) curve. Three-fold cross-validation performed 20 times was used to evaluate the accuracy of the trained classifiers and the stability of the selected features. The models were validated by using a validation set. RESULTS: Feature selection extracted the six most important features (3 from sFOV HR-T2WI, 1 T2WI, 1 FS-T2WI, and 1 T1c) for model construction. The mpMRI-combined radiomics model (area under the curve [AUC]: 0.940) reached a significantly higher performance (better than the clinical parameters [AUC: 0.730]), including any single-layer model using sFOV HR-T2WI (AUC: 0.840), T2WI (AUC: 0.770), FS-T2WI (AUC: 0.710), ADC maps (AUC: 0.650), sagittal, and axial T1c values (AUC: 0.710, 0.680) in the validation set. CONCLUSION: Biomarkers using multi-parametric radiomics features derived from preoperative MR images could predict LVSI in patients with CC.

Diffusion Kurtosis MR Imaging versus Conventional Diffusion-Weighted Imaging for Distinguishing Hepatocellular Carcinoma from Benign Hepatic Nodules.

Objectives: To assess the efficacy of diffusion kurtosis imaging (DKI) and compare DKI-derived parameters with conventional diffusion-weighted imaging (DWI) for distinguishing hepatocellular carcinoma (HCC) from benign hepatic nodules including focal nodular hyperplasia (FNH), hemangioma, and hepatocellular adenoma (HCA). Materials and Methods: 151 patients with 182 hepatic nodules (114 HCCs and 68 benign nodules including 33 FNHs, 29 hemangiomas, and 6 HCAs) were analyzed. Preoperative MRI examinations including DKI (b values: 0, 200, 500, 800, 1500, and 2000 sec/mm2) were performed, and kurtosis (K), diffusivity (D), and apparent diffusion coefficient (ADC) were calculated. The efficacy of DKI-derived parameters K, D, and ADC for distinguishing HCC from these benign nodules was analyzed. Results: ROC (receiver operating characteristic curve) analysis showed the optimal cutoff values of ADC, D, and K for identification of these benign nodules, and HCCs were 1.295 (area under the curve (AUC): 0.826; sensitivity 80.6%; specificity 70.8%), 1.787 (AUC: 0.770; sensitivity 83.6%; specificity 59.6%), and 1.002 (AUC: 0.761; sensitivity 65.5%; specificity 79.0%), respectively. Statistically significant differences were found in ADC, D, and K values between groups of HCC-FNH and HCC-hemangioma (P < 0.05). There were significant differences in K and ADC values between groups of FNH-hemangioma and HCA-hemangioma (P < 0.05), respectively. Using logistic regression analysis, a regression equation was obtained: Logit(P)=-1.982X 1+1.385X 3+1.948(X 1: ADC; X 3: K), and odds ratios (OR) were 0.138 (95% confidence interval (CI): 0.052, 0.367), and 8.996 (95% CI: 0.970, 16.460), respectively. Conclusion: Both ADC value and DKI-derived parameters K and D values have demonstrated a higher preoperative efficacy in distinguishing HCC from FNH, hemangioma, and HCA. No evidence was shown to suggest D or K value was superior to the ADC value.

Imaging biomarkers for well and moderate hepatocellular carcinoma: preoperative magnetic resonance image and histopathological correlation.

BACKGROUND: Our aim of the study is to investigate the feasibility of preoperative prediction for hepatocellular carcinoma (HCC) histological grading using gadoxetic acid-enhanced magnetic resonance imaging (MRI). METHODS: This study included one hundred and fifty-six patients with solitary HCC. Preoperative gadoxetic acid-enhanced MRI findings were retrospectively analyzed. MRI qualitative features such as tumor size, margin, capsule status, signal homogeneity, intratumoral vessels, peritumoral enhancement during mid-arterial phase, peritumoral hypointensity during the hepatobiliary phase (HBP) were investigated. Apparent diffusion coefficients (ADCs), T1 reduction ratio of pre- and post-contrast enhanced images of the tumors were calculated. HCC histological grading in surgical specimens were confirmed by Edmonson's criteria. Correlations between these MRI features and HCC histological grading were analyzed using multivariate logistic regression. The receiver operating characteristic (ROC) curve was used to assess the predictive efficacy of the model. RESULTS: Univariate analysis showed that maximum tumor diameter (p = 0.004), tumor margin (p = 0.006), intratumoral vessels (p = 0.001) and peritumoral hypointensity during HBP (p = 0.000), were significantly correlated with HCC histological grading. There was no relationship between capsule, tumor signal, venous thrombosis, peritumoral enhancement during mid-arterial phase, ADC value, T1 reduction ratio, and HCC histological grading. Multivariate logistic regression analysis demonstrated that the maximum tumor diameter (p = 0.012, odds ratio = 1.002, 95% confidence interval: 1.007-1.046)) was an independent risk factor for high grade HCC. CONCLUSIONS: Greater tumor size, a more irregular margin, presence of intratumoral vessels, and peritumoral hypointensity during HBP were indicators for high grade HCC. The maximum tumor diameter was an independent risk factor for high grade HCC.

MRI T2-Weighted Imaging and Fat-Suppressed T2-Weighted Imaging Image Fusion Technology Improves Image Discriminability for the Evaluation of Anal Fistulas.

OBJECTIVE: To explore whether MRI fusion technology (combined T2-weighted imaging [T2WI] and fat-suppressed T2WI [T2WI-FS]) improves signal differences between anal fistulas and surrounding structures. MATERIALS AND METHODS: A total of 32 patients with confirmed diagnoses of anal fistula were retrospectively studied. All available T2WI and T2WI-FS images for each patient were used to generate fusion image (T2WI-Fusion) based on the addition of gray values obtained from each pixel via an MR post-processing work station. The discriminability of fistula, perianal sphincter, and perianal fat in T2WI, T2WI-FS, and T2WI-Fusion images was quantified with Fisher's scoring algorithm. For subjective visual image assessment by researchers, five-point scale scores were determined using a modified double-stimulus continuous quality-scale test to evaluate T2WI-FS, T2WI, enhanced axial three-dimensional-volumetric interpolated breath-hold examination (3D-VIBE), and T2WI-Fusion sequence images. The differences were subsequently compared. RESULTS: Mean Fisher scores for fistulas vs. sphincters obtained from T2WI-Fusion (FFusion-fistula = 6.56) were significantly higher than those from T2WI (FT2WI-fistula = 3.35) (p = 0.001). Mean Fisher scores for sphincters vs. fat from T2WI-Fusion (FFusion-sphincter = 10.84) were significantly higher than those from T2WI-FS (FSFS-sphincter = 2.57) (p = 0.001). In human assessment, T2WI-Fusion showed the same fistula discriminability as T2WI-FS, and better sphincter discriminability than T2WI. Overall, T2WI-Fusion showed better discriminability than T2WI, T2WI-FS, and enhanced 3D-VIBE images. CONCLUSION: T2WI and T2WI-FS fusion technology improves signal differences between anal fistulas and surrounding structures, and may facilitate better evaluation of anal fistulas and sphincters.

Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI.

OBJECTIVES: Preoperative prediction of microvascular invasion (MVI) in patients with hepatocellular cancer (HCC) is important for surgery strategy making. We aimed to develop and validate a combined intratumoural and peritumoural radiomics model based on gadolinium-ethoxybenzyl-diethylenetriamine (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) for preoperative prediction of MVI in primary HCC patients. METHODS: This study included a training cohort of 110 HCC patients and a validating cohort of 50 HCC patients. All the patients underwent preoperative Gd-EOB-DTPA-enhanced MRI examination and curative hepatectomy. The volumes of interest (VOIs) around the hepatic lesions including intratumoural and peritumoural regions were manually delineated in the hepatobiliary phase of MRI images, from which quantitative features were extracted and analysed. In the training cohort, machine-learning method was applied for dimensionality reduction and selection of the extracted features. RESULTS: The proportion of MVI-positive patients was 38.2% and 40.0% in the training and validation cohort, respectively. Supervised machine learning selected ten features to establish a predictive model for MVI. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity of the combined intratumoural and peritumoural radiomics model in the training and validation cohort were 0.85 (95% confidence interval (CI), 0.77-0.93), 88.2%, 76.2%, and 0.83 (95% CI, 0.71-0.95), 90.0%, 75.0%, respectively. CONCLUSIONS: We evaluate quantitative Gd-EOB-DTPA-enhanced MRI image features of both intratumoural and peritumoural regions and provide an effective radiomics-based model for the prediction of MVI in HCC patients, and may therefore help clinicians make precise decisions regarding treatment before the surgery. KEY POINTS: • An effective radiomics model for prediction of microvascular invasion in HCC patients is established. • The radiomics model is superior to the radiologist in prediction of MVI. • The radiomics model can help clinicians in pretreatment decision making.

Pretreatment prediction of immunoscore in hepatocellular cancer: a radiomics-based clinical model based on Gd-EOB-DTPA-enhanced MRI imaging.

OBJECTIVES: Immunoscore evaluates the density of CD3+ and CD8+ T cells in both the tumor core and invasive margin. Pretreatment prediction of immunoscore in hepatocellular cancer (HCC) is important for precision immunotherapy. We aimed to develop a radiomics model based on gadolinium-ethoxybenzyl-diethylenetriamine (Gd-EOB-DTPA)-enhanced MRI for pretreatment prediction of immunoscore (0-2 vs. 3-4) in HCC. MATERIALS AND METHODS: The study included 207 (training cohort: n = 150; validation cohort: n = 57) HCC patients with hepatectomy who underwent preoperative Gd-EOB-DTPA-enhanced MRI. The volumes of interest enclosing hepatic lesions including intratumoral and peritumoral regions were manually delineated in the hepatobiliary phase of MRI images, from which 1044 quantitative features were extracted and analyzed. Extremely randomized tree method was used to select radiomics features for building radiomics model. Predicting performance in immunoscore was compared among three models: (1) using only intratumoral radiomics features (intratumoral radiomics model); (2) using combined intratumoral and peritumoral radiomics features (combined radiomics model); (3) using clinical data and selected combined radiomics features (combined radiomics-based clinical model). RESULTS: The combined radiomics model showed a better predicting performance in immunoscore than intratumoral radiomics model (AUC, 0.904 (95% CI 0.855-0.953) vs. 0.823 (95% CI 0.747-0.899)). The combined radiomics-based clinical model showed an improvement over the combined radiomics model in predicting immunoscore (AUC, 0·926 (95% CI 0·884-0·967) vs. 0·904 (95% CI 0·855-0·953)), although differences were not statistically significant. Results were confirmed in validation cohort and calibration curves showed good agreement. CONCLUSION: The MRI-based combined radiomics nomogram is effective in predicting immunoscore in HCC and may help making treatment decisions. KEY POINTS: • Radiomics obtained from Gd-EOB-DTPA-enhanced MRI help predicting immunoscore in hepatocellular carcinoma. • Combined intratumoral and peritumoral radiomics are superior to intratumoral radiomics only in predicting immunoscore. • We developed a combined clinical and radiomicsnomogram to predict immunoscore in hepatocellular carcinoma.

Prediction of sorafenib treatment-related gene expression for hepatocellular carcinoma: preoperative MRI and histopathological correlation.

PURPOSE: To investigate the feasibility of prediction for targeted therapy-related gene expression in hepatocellular carcinoma (HCC) using preoperative gadoxetic acid-enhanced magnetic resonance imaging (MRI). MATERIALS AND METHODS: Ninety-one patients (81 men, mean age 53.9 ± 12 years) with solitary HCC who underwent preoperative enhanced MRI were retrospectively analyzed. Features including tumor size, signal homogeneity, tumor capsule, tumor margin, intratumoral vessels, peritumor enhancement, peritumor hypointensity, signal intensity ratio on DWI, T1 relaxation times, and the reduction rate between pre- and post-contrast enhancement images were assessed. The operation and histopathological evaluation were performed within 2 weeks after MRI examination (mean time 7 days). The expression levels of BRAF, RAF1, VEGFR2, and VEGFR3 were evaluated. The associations between these imaging features and gene expression levels were investigated. RESULTS: Tumor incomplete capsules or non-capsules (p = 0.001) and intratumoral vessels (p = 0.002) were significantly associated with BRAF expression, and tumor incomplete capsules or non-capsules (p = 0.001) and intratumoral vessels (p = 0.013) with RAF1 expression. There was no significant association between the expression of VEGFR2, VEGFR3, and all examined MRI features. Multivariate logistic regression showed that incomplete tumor capsule (p = 0.002) and non-capsule (p = 0.004) were independent risk factors of HCC with high BRAF expression; incomplete tumor capsule (p < 0.001) and non-capsule (p = 0.040) were independent risk factors of HCC with high RAF1 expression. CONCLUSION: The presence of incomplete capsule or intratumoral vessels and the absence of capsule are potential indicators of high BRAF and RAF1 expression. Gadoxetic acid-enhanced MRI may facilitate the choice of gene therapy for patients with HCC. KEY POINTS: • Incomplete tumor capsule and non-capsule were independent risk factors of HCC with high BRAF and RAF1 expression. • The presence of intratumoral vessels was a potential indicator of high BRAF and RAF1 expression. • Gadoxetic acid-enhanced MRI may be a predictor of efficacy of treatment with sorafenib.

Combined Volumetric and Density Analyses of Contrast-Enhanced CT Imaging to Assess Drug Therapy Response in Gastroenteropancreatic Neuroendocrine Diffuse Liver Metastasis.

Objective: We propose a computer-aided method to assess response to drug treatment, using CT imaging-based volumetric and density measures in patients with gastroenteropancreatic neuroendocrine tumors (GEP-NETs) and diffuse liver metastases. Methods: Twenty-five patients with GEP-NETs with diffuse liver metastases were enrolled. Pre- and posttreatment CT examinations were retrospectively analyzed. Total tumor volume (volume) and mean volumetric tumor density (density) were calculated based on tumor segmentation on CT images. The maximum axial diameter (tumor size) for each target tumor was measured on pre- and posttreatment CT images according to Response Evaluation Criteria In Solid Tumors (RECIST). Progression-free survival (PFS) for each patient was measured and recorded. Results: Correlation analysis showed inverse correlation between change of volume and density (Δ(V + D)), change of volume (ΔV), and change of tumor size (ΔS) with PFS (r = -0.653, P=0.001; r = -0.617, P=0.003; r = -0.548, P=0.01, respectively). There was no linear correlation between ΔD and PFS (r = -0.226, P=0.325). Conclusion: The changes of volume and density derived from CT images of all lesions showed a good correlation with PFS and may help assess treatment response.

CT Enterography score: a potential predictor for severity assessment of active ulcerative colitis.

BACKGROUND: Evaluate the possibility of CT enterography (CTE) score system as a predictor in assessing active ulcerative colitis (UC) severity. METHODS: Forty-six patients with active UC with CTE and colonoscopy were enrolled. Based on modified Mayo score, patients were divided into three groups: mild (n = 10), moderate (n = 17) and severe (n = 19). A cumulative CTE score was calculated in each patient and its correlation with modified Mayo score was analyzed. The optimal cutoff values of CTE score were determined by receiver operating characteristic (ROC) curves analysis. RESULTS: Significant between-group differences were observed in CTE spectrums of mucosal bubbles, mural stratification, loss of haustration, enlarged mesenteric lymph nodes and engorged mesenteric vessels (P < 0.05). The cumulative CTE scores were significant difference between three groups (CTE score:4.9 ± 2.3, 7.6 ± 2.6, and 10.9 ± 2.0, respectively, P < 0.01). The cumulative CTE score showed a positive correlation with modified Mayo score (r = 0.835, P < 0.05). The optimal cut-off value for CTE score predicting moderate and severe UC was 9.5 (area under the curve [AUC]:0.847, sensitivity:78.9%, specificity:82.4%). CONCLUSION: Disease severity assessment by CTE score demonstrates strong positive correlation with severity established modified Mayo score. CTE score system maybe a potential predictor for active UC severity assessment.

[Changes in diameter of superior mesenteric vein and gastrocolic trunk in patients with cecum-ascending colon cancer].

OBJECTIVE: To compare the difference of the diameters of superior mesenteric vein (SMV) and gastrocolic trunk (GCT) between patients with cecum-ascending colon cancer and normal individuals, and to assess the diagnostic value of the diameters of SMV and GCT in cecum-ascending colon cancer. METHODS: Preoperative imaging data of 60 patients with primary cecum-ascending colon cancer confirmed by postoperative pathology at the First Affiliated Hospital of Sun Yat-sen University from June 2014 to December 2016 were retrospectively analyzed. The diameters of SMV and GCT were measured on preoperative CT images. SMV was measured at about 2 cm below the junction of SMV and splenic vein. GCT was measured at 1 cm near the proximal junction of right colon vein, right gastroepiploic vein and anterior pancreaticoduodenal vein. Another 60 people receiving pelvic CT examination without organ illness were collected as control. The diameter differences of SMV and GCT between cancer group and control group were compared. The diagnostic value of the diameters of SMV and GCT in cecum-ascending colon cancer was evaluated by receiver operating characteristic (ROC) curves. RESULTS: Among 60 cases of cecum-ascending colon cancer, 36 were males and 24 were females with median age of 48 years (range 28-84); 13 were cecum cancer, 47 were ascending colon cancer; 11 had no lymph node and liver metastasis, 40 had lymph node metastasis, 9 had liver metastasis (all with lymph node metastasis). Compared to control group, the diameters of SMV and GCT in cancer group were significantly longer [SMV:(11.2±1.3) mm vs. (9.5±1.7) mm, t=6.04, P<0.001; GCT:(5.5±0.9) mm vs. (3.5±1.0) mm, t=11.51, P<0.001]. However, there were no statistically significant differences in diameters of SMV and GCT among hepatic metastasis, lymph node metastasis and no metastasis cancer groups (all P>0.05). The ROC curve analysis showed that the area under the curve of SMV diameter was 0.777, and the optimal cut-off point was 10.5 mm in the diagnosis of cecum-ascending colon cancer, with the sensitivity and specificity of 95.0%(57/60) and 46.7%(28/60) respectively. The area under the curve of GCT diameter was 0.923, and the optimal cut-off point was 4.5 mm in the diagnosis of cecum-ascending colon cancer, with sensitivity and specificity of 88.3%(53/60) and 85.0%(51/60) respectively. CONCLUSION: The dilation of the SMV and GCT may be used as warning factors for cecum-ascending colon cancer, especially the diameter of GCT.

Pancreatic schwannoma: a case report and an updated 40-year review of the literature yielding 68 cases.

BACKGROUND: Pancreatic schwannoma is a rare tumor. Preoperative diagnosis of pancreatic schwannoma is challenging due to its tendency to mimic other lesions of the pancreas. We describe a case of pancreatic schwannoma and present a review of the cases currently reported in the English literature to identify characteristics of pancreatic schwannoma on imaging. CASE PRESENTATION: A 53-year-old male presented with a history of intermittent periumbilical abdominal pain and lower back pain for 1 week. Based on ultrasound (US) and computed tomography (CT) findings, we made a preoperative diagnosis of solid pseudopapillary tumor and performed a standard pancreaticoduodenectomy. Pathological examination showed that the tumor was composed of spindle cells with a palisading arrangement, and immunohistochemistry revealed strong positive staining for S-100 protein, which was consistent with a diagnosis of pancreatic schwannoma. At the 8-month follow-up visit, the patient was doing well without recurrent disease, and his abdominal pain had resolved. CONCLUSIONS: Although pancreatic schwannoma is rare, it should be included in the list of differential diagnoses of pancreatic masses, both solid and cystic. A tumor size larger than 6.90 cm, vascular encasement, or visceral invasion should elicit suspicion of malignant transformation.