A Transfer Learning Radiomics Nomogram for Preoperative Prediction of Borrmann Type IV Gastric Cancer From Primary Gastric Lymphoma

ObjectiveThis study aims to differentiate preoperative Borrmann type IV gastric cancer (GC) from primary gastric lymphoma (PGL) by transfer learning radiomics nomogram (TLRN) with whole slide images of GC as source domain data.Materials and MethodsThis study retrospectively enrolled 438 patients with histopathologic diagnoses of Borrmann type IV GC and PGL. They received CT examinations from three hospitals. Quantitative transfer learning features were extracted by the proposed transfer learning radiopathomic network and used to construct transfer learning radiomics signatures (TLRS). A TLRN, which integrates TLRS, clinical factors, and CT subjective findings, was developed by multivariate logistic regression. The diagnostic TLRN performance was assessed by clinical usefulness in the independent validation set.ResultsThe TLRN was built by TLRS and a high enhanced serosa sign, which showed good agreement by the calibration curve. The TLRN performance was superior to the clinical model and TLRS. Its areas under the curve (AUC) were 0.958 (95% confidence interval [CI], 0.883–0.991), 0.867 (95% CI, 0.794–0.922), and 0.921 (95% CI, 0.860–0.960) in the internal and two external validation cohorts, respectively. Decision curve analysis (DCA) showed that the TLRN was better than any other model. TLRN has potential generalization ability, as shown in the stratification analysis.ConclusionsThe proposed TLRN based on gastric WSIs may help preoperatively differentiate PGL from Borrmann type IV GC.Borrmann type IV gastric cancer, primary gastric lymphoma, transfer learning, whole slide image, deep learning.

Preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma based on kupffer phase radiomic features of sonazoid contrast-enhanced ultrasound (SCEUS): A prospective study

OBJECTIVES: To establish and evaluate a machine learning radiomics model based on grayscale and Sonazoid contrast enhanced ultrasound images for the preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. METHODS: 100 cases of histopathological confirmed HCC lesions were prospectively included. Regions of interest were segmented on both grayscale and Kupffer phase of Sonazoid contrast enhanced (CEUS) images. Radiomic features were extracted from tumor region and region containing 5 mm of peritumoral liver tissues. Maximum relevance minimum redundancy (MRMR) and Least Absolute Shrinkage and Selection Operator (LASSO) were used for feature selection and Support Vector Machine (SVM) classifier was trained for radiomic signature calculation. Radiomic signatures were incorporated with clinical variables using univariate-multivariate logistic regression for the final prediction of MVI. Receiver operating characteristic curves, calibration curves and decision curve analysis were used to evaluate model’s predictive performance of MVI. RESULTS: Age were the only clinical variable significantly associated with MVI. Radiomic signature derived from Kupffer phase images of peritumoral liver tissues (kupfferPT) displayed a significantly better performance with an area under the receiver operating characteristic curve (AUROC) of 0.800 (95% confidence interval: 0.667, 0.834), the final prediction model using Age and kupfferPT achieved an AUROC of 0.804 (95% CI: 0.723, 0.878), accuracy of 75.0%, sensitivity of 87.5% and specificity of 69.1%. CONCLUSIONS: Radiomic model based on Kupffer phase ultrasound images of tissue adjacent to HCC lesions showed an observable better predictive value compared to grayscale images and has potential value to facilitate preoperative identification of HCC patients at higher risk of MVI.

Radiomics nomogram for the preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma

Purpose To develop and validate a radiomics nomogram for the preoperative prediction of lymph node (LN) metastasis in pancreatic ductal adenocarcinoma (PDAC). Materials and methods In this retrospective study, 225 patients with surgically resected, pathologically confirmed PDAC underwent multislice computed tomography (MSCT) between January 2014 and January 2017. Radiomics features were extracted from arterial CT scans. The least absolute shrinkage and selection operator method was used to select the features. Multivariable logistic regression analysis was used to develop the predictive model, and a radiomics nomogram was built and internally validated in 45 consecutive patients with PDAC between February 2017 and December 2017. The performance of the nomogram was assessed in the training and validation cohort. Finally, the clinical usefulness of the nomogram was estimated using decision curve analysis (DCA). Results The radiomics signature, which consisted of 13 selected features of the arterial phase, was significantly associated with LN status (p < 0.05) in both the training and validation cohorts. The multivariable logistic regression model included the radiomics signature and CT-reported LN status. The individualized prediction nomogram showed good discrimination in the training cohort [area under the curve (AUC), 0.75; 95% confidence interval (CI), 0.68–0.82] and in the validation cohort (AUC, 0.81; 95% CI, 0.69–0.94) and good calibration. DCA demonstrated that the radiomics nomogram was clinically useful. Conclusions The presented radiomics nomogram that incorporates the radiomics signature and CT-reported LN status is a noninvasive, preoperative prediction tool with favorable predictive accuracy for LN metastasis in patients with PDAC.

Preoperative sonographic prediction of intra-abdominal adhesions using sliding sign at repeat caesarean section at the University of Maiduguri Teaching Hospital, Nigeria: a prospective observational study

ObjectiveTo determine if the presence or absence of sonographic sliding sign preoperatively is a good predictor of the presence and type of intra-abdominal adhesions; and to determine the time taken to demonstrate this sign.DesignA prospective, observational, triple-blind study using tests of diagnostic accuracy.SettingSingle-centre tertiary health institution in north-east Nigeria.Participants67 women in the third trimester scheduled for repeat elective caesarean sections (CS) had transabdominal sonography to determine the absence or presence and degree of sliding sign. The time taken to make these decisions were noted. Surgeons blinded to the ultrasound findings graded adhesions intraoperatively and comparison between sonographic and intraoperative findings made. Women who were scheduled for emergency CS were excluded.Main outcome measuresAccuracy of preoperative ultrasound to determine no/mild, moderate and severe adhesions. Secondary outcomes were interobserver correlations and time taken to determine sliding.ResultsWhen classified as adhesion and no adhesion, the sliding sign demonstrated a sensitivity of 100.00% (CI95 85.18% to 100.00%), specificity of 100.00% (CI95 92.13% to 100.00%). In predicting presence of moderate intra-abdominal adhesions, a sensitivity of 65.0% (CI95 40.78% to 84.61%) and specificity of 82.98% (CI95 69.19% to 92.35%) was found. For predicting severe intra-abdominal adhesions, it had a sensitivity of 25.00% (CI95 0.63% to 80.59%) and specificity of 98.41 (CI95 91.47 to 99.96). Disease prevalence for mild, moderate and severe adhesions was 33.82% (CI95 22.79% to 46.32%), 29.85% (CI95 19.28% to 42.27%) and 5.97% (CI95 1.65% to 14.59%), respectively. Interobserver Cohen’s kappa coefficient and PPA were 0.58 (CI95 0.39 to 0.76) and 58.82 (CI95 52.82 to 64.82), respectively. The mean duration to determine sliding sign was 7.56±2.86 s.ConclusionThis study supports the role of transabdominal sliding sign in preoperative prediction of intra-abdominal adhesions in women with previous CS without significant increase in sonography duration. This information can encourage planning for CS by ensuring that surgeons of appropriate seniority are deployed to undertake anticipated complex operations.

MRI-Based Radiomics Nomogram To Predict Intraoperative Hemorrhage of Placenta Previa

Background: Placenta previa is associated with higher percentage of intraoperative and postpartum hemorrhage, increased obstetric hysterectomy, significant maternal morbidity and mortality. We aimed to develop and validate a magnetic resonance imaging (MRI)-based nomogram to preoperative prediction of intraoperative hemorrhage (IPH) for placenta previa, which might contribute to adequate assessment and preoperative preparation for the obstetricians.Methods: Between May 2015 and December 2019, a total of 125 placenta previa pregnant women were divided into a training set (n = 80) and a validation set (n = 45). Radiomics features were extracted from MRI images of each patient. A MRI-based model comprising seven features was built for the classification of patients into IPH and non-IPH groups in a training set and validation set. Multivariate nomograms based on logistic regression analyses were built according to radiomics features. Receiver operating characteristic (ROC) curve was used to assess the model. Predictive accuracy of nomogram were assessed by calibration plots and decision curve analysis. Results: In multivariate analysis, placenta position, placenta thickness, cervical blood sinus and placental signals in the cervix were signifcantly independent predictors for IPH (all p < 0.05). The MRI-based nomogram showed favorable discrimination between IPH and non-IPH groups. The calibration curve showed good agreement between the estimated and the actual probability of IPH. Decision curve analysis also showed a high clinical benefit across a wide range of probability thresholds. The AUC was 0.918 ( 95% CI, 0.857-0.979 ) in the training set and 0.866( 95% CI, 0.748-0.985 ) in the validation set by the combination of four MRI features.Conclusions: The MRI-based nomograms might be a useful tool for the preoperative prediction of IPH outcomes for placenta previa. Our study enables obstetricians to perform adequate preoperative evaluation to minimize blood loss and reduce the rate of caesarean hysterectomy.

Evaluation of microvascular invasion of hepatocellular carcinoma using whole-lesion histogram analysis with the stretched-exponential diffusion model

Objectives: To evaluate the potential role of histogram analysis of stretched exponential model (SEM) through whole-tumor volume for preoperative prediction of microvascular invasion (MVI) in single hepatocellular carcinoma (HCC). Methods: This study included 43 patients with pathologically proven HCCs by surgery who underwent multiple b-values diffusion-weighted imaging (DWI) and contrast-enhanced MRI.The histogram metrics of distributed diffusion coefficient (DDC) and heterogeneity index (α) from SEM were compared between HCCs with and without MVI, by using the independent t-test. Morphologic features of conventional MRI and clinical data were evaluated with chi-squared or Fisher’s exact tests. Receiver operating characteristic (ROC) and multivariable logistic regression analyses were performed to evaluate the diagnostic performance of different parameters for predicting MVI. Results: The tumor size and non-smooth tumor margin were significantly associated with MVI (all p < 0.05). The mean, fifth, 25th, 50th percentiles of DDC, and the fifth percentile of ADC between HCCs with and without MVI were statistically significant differences (all p < 0.05). The histogram parameters of α showed no statistically significant differences (all p > 0.05). At multivariate analysis,the fifth percentile of DDC was independent risk factor for MVI of HCC(p = 0.006). Conclusions: Histogram parameters DDC and ADC, but not the α value, are useful predictors of MVI. The fifth percentile of DDC was the most useful value to predict MVI of HCC. Advances in knowledge: There is limited literature addressing the role of SEM for evaluating MVI of HCC. Our findings suggest that histogram analysis of SEM based on whole-tumor volume can be useful for MVI prediction.