Arterial Phase CT Images Research Articles

A CT-based deep learning for segmenting tumors and predicting microsatellite instability in patients with colorectal cancers: a multicenter cohort study.

To develop and validate deep learning (DL) models using preoperative contrast-enhanced CT images for tumor auto-segmentation and microsatellite instability(MSI) prediction incolorectal cancer (CRC). Patients with CRC who underwent surgery or biopsy between January 2018 and April 2023 were retrospectively enrolled. Mismatch repair protein expression was determined via immunohistochemistry or fluorescence multiplex polymerase chain reaction-capillary electrophoresis. Manually delineated tumor contours using arterial and venous phase CT images by three abdominal radiologists are served as ground truth. Tumor auto-segmentation used nnU-Net. MSI prediction employed ViT or convolutional neural networks models, trained and validated with arterial and venous phase images (image model) or combined clinical-pathological factors (combined model). The segmentation model was evaluated using patch coverage ratio, Dice coefficient, recall, precision, and F1-score. The predictive models' efficacy was assessed using areas under the curves and decision curve analysis. Overall, 2180 patients (median age: 61years ± 17 [SD]; 1285 males) were divided into training (n = 1159), validation (n = 289), and independent external test (n = 732) groups. High-level MSI status was present in 435 patients (20%). In the external test set, the segmentation model performed well in the arterial phase, with patch coverage ratio, Dice coefficient, recall, precision, and F1-score values of 0.87, 0.71, 0.72, 0.74, and 0.71, respectively. For MSI prediction, the combined models outperformed the clinical model (AUC = 0.83 and 0.82 vs 0.67, p < 0.001) and two image models (AUC = 0.75 and 0.77, p < 0.001). Decision curve analysis confirmed the higher net benefit of the combined model compared to the other models across probability thresholds ranging from 0.1 to 0.45. DL enhances tumor segmentation efficiency and, when integrated with contrast-enhanced CT and clinicopathological factors, exhibits good diagnostic performance in predicting MSI in CRC.

Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT

PurposeThe purpose of this study was to develop a radiomics-based algorithm to identify small pancreatic neuroendocrine tumors (PanNETs) on CT and evaluate its robustness across manual and automated segmentations, exploring the feasibility of automated screening. Materials and methodsPatients with pathologically confirmed T1 stage PanNETs and healthy controls undergoing dual-phase CT imaging were retrospectively identified. Manual segmentation of pancreas and tumors was performed, then automated pancreatic segmentations were generated using a pretrained neural network. A total of 1223 radiomics features were independently extracted from both segmentation volumes, in the arterial and venous phases separately. Ten final features were selected to train classifiers to identify PanNETs and controls. The cohort was divided into training and testing sets, and performance of classifiers was assessed using area under the receiver operator characteristic curve (AUC), specificity and sensitivity, and compared against two radiologists blinded to the diagnoses. ResultsA total of 135 patients with 142 PanNETs, and 135 healthy controls were included. There were 168 women and 102 men, with a mean age of 55.4 ± 11.6 (standard deviation) years (range: 20–85 years). Median PanNET size was 1.3 cm (Q1, 1.0; Q3, 1.5; range: 0.5–1.9). The arterial phase LightGBM model achieved the best performance in the test set, with 90 % sensitivity (95 % confidence interval [CI]: 80–98), 76 % specificity (95 % CI: 62–88) and an AUC of 0.87 (95 % CI: 0.79–0.94). Using features from the automated segmentations, this model achieved an AUC of 0.86 (95 % CI: 0.79–0.93). In comparison, the two radiologists achieved a mean 50 % sensitivity and 100 % specificity using arterial phase CT images. ConclusionRadiomics features identify small PanNETs, with stable performance when extracted using automated segmentations. These models demonstrate high sensitivity, complementing the high specificity of radiologists, and could serve as opportunistic screeners.

Radiomics analysis in predicting vascular invasion in gastric cancer based on enhanced CT: a preliminary study

BackgroundVascular invasion (VI) is closely related to the metastasis, recurrence, prognosis, and treatment of gastric cancer. Currently, predicting VI preoperatively using traditional clinical examinations alone remains challenging. This study aims to explore the value of radiomics analysis based on preoperative enhanced CT images in predicting VI in gastric cancer.MethodsWe retrospectively analyzed 194 patients with gastric adenocarcinoma who underwent enhanced CT examination. Based on pathology analysis, patients were divided into the VI group (n = 43) and the non-VI group (n = 151). Radiomics features were extracted from arterial phase (AP) and portal venous phase (PP) CT images. The radiomics score (Rad-score) was then calculated. Prediction models based on image features, clinical factors, and a combination of both were constructed. The diagnostic efficiency and clinical usefulness of the models were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA).ResultsThe combined prediction model included the Rad-score of AP, the Rad-score of PP, Ki-67, and Lauren classification. In the training group, the area under the curve (AUC) of the combined prediction model was 0.83 (95% CI 0.76–0.89), with a sensitivity of 64.52% and a specificity of 92.45%. In the validation group, the AUC was 0.80 (95% CI 0.67–0.89), with a sensitivity of 66.67% and a specificity of 88.89%. DCA indicated that the combined prediction model might have a greater net clinical benefit than the clinical model alone.ConclusionThe integrated models, incorporating enhanced CT radiomics features, Ki-67, and clinical factors, demonstrate significant predictive capability for VI. Moreover, the radiomics model has the potential to optimize personalized clinical treatment selection and patient prognosis assessment.

Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images

ObjectivesThis study aims to develop an innovative, deep model for thymoma risk stratification using preoperative CT images. Current algorithms predominantly focus on radiomic features or 2D deep features and require manual tumor segmentation by radiologists, limiting their practical applicability.MethodsThe deep model was trained and tested on a dataset comprising CT images from 147 patients (82 female; mean age, 54 years ± 10) who underwent surgical resection and received subsequent pathological confirmation. The eligible participants were divided into a training cohort (117 patients) and a testing cohort (30 patients) based on the CT scan time. The model consists of two stages: 3D tumor segmentation and risk stratification. The radiomic model and deep model (2D) were constructed for comparative analysis. Model performance was evaluated through dice coefficient, area under the curve (AUC), and accuracy.ResultsIn both the training and testing cohorts, the deep model demonstrated better performance in differentiating thymoma risk, boasting AUCs of 0.998 and 0.893 respectively. This was compared to the radiomic model (AUCs of 0.773 and 0.769) and deep model (2D) (AUCs of 0.981 and 0.760). Notably, the deep model was capable of simultaneously identifying lesions, segmenting the region of interest (ROI), and differentiating the risk of thymoma on arterial phase CT images. Its diagnostic prowess outperformed that of the baseline model.ConclusionsThe deep model has the potential to serve as an innovative decision-making tool, assisting on clinical prognosis evaluation and the discernment of suitable treatments for different thymoma pathological subtypes.Key Points• This study incorporated both tumor segmentation and risk stratification.• The deep model, using clinical and 3D deep features, effectively predicted thymoma risk.• The deep model improved AUCs by 16.1pt and 17.5pt compared to radiomic model and deep model (2D) respectively.

CT-based radiomics research for discriminating the risk stratification of pheochromocytoma using different machine learning models: a multi-center study.

The purpose of this study was to explore and verify the value of various machine learning models in preoperative risk stratification of pheochromocytoma. A total of 155 patients diagnosed with pheochromocytoma through surgical pathology were included in this research (training cohort: n = 105; test cohort: n = 50); the risk stratification scoring system classified a PASS score of < 4 as low risk and a PASS score of ≥ 4 as high risk. From CT images captured during the non-enhanced, arterial, and portal venous phase, radiomic features were extracted. After reducing dimensions and selecting features, Logistic Regression (LR), Extra Trees, and K-Nearest Neighbor (KNN) were utilized to construct the radiomics models. By adopting ROC curve analysis, the optimal radiomics model was selected. Univariate and multivariate logistic regression analyses of clinical radiological features were used to determine the variables and establish a clinical model. The integration of radiomics and clinical features resulted in the creation of a combined model. ROC curve analysis was used to evaluate the performance of the model, while decision curve analysis (DCA) was employed to assess its clinical value. 3591 radiomics features were extracted from the region of interest in unenhanced and dual-phase (arterial and portal venous phase) CT images. 13 radiomics features were deemed to be valuable. The LR model demonstrated the highest prediction efficiency and robustness among the tested radiomics models, with an AUC of 0.877 in the training cohort and 0.857 in the test cohort. Ultimately, the composite of clinical features was utilized to formulate the clinical model. The combined model demonstrated the best discriminative ability (AUC, training cohort: 0.887; test cohort: 0.874). The DCA of the combined model showed the best clinical efficacy. The combined model integrating radiomics and clinical features had an outstanding performance in differentiating the risk of pheochromocytoma and could offer a non-intrusive and effective approach for making clinical decisions.

Texture Analysis of Adenomatous and Metastatic Adrenal Lesions on Native and Contrast-enhanced Computed Tomography

Differentiating lipid-poor adrenal adenomas from adrenal metastases is not possible without performing a dedicated contrast-enhanced CT (CECT) protocol. Our purpose is to evaluate the possible role of texture analysis in classifying adrenal lesions.&#x0D; This is a retrospective study. We evaluated 33 patients with 47 metastases and 43 patients with 47 adenomas. Seven of the adenomas were lipid-poor, and the rest – lipid-rich adenomas. We used commercially available software for lesion segmentation and texture analysis on native and arterial phase CT images with a slice thickness of 2 mm. The segmentation was semi-automated, and features were computed on the resulting regions of interest (ROI) for each lesion on both native and arterial phases. Two conventional (HU standard deviation, Histogram Entropy) and six second-order texture features (GLCM – Homogeneity, Energy, Entropy log 10, Contrast, Dissimilarity, NGDLM–Busyness) were calculated. For statistical analysis the IBM SPSS 19 package was used to compare the following groups in both phases: 1. Adenomas--Metastasis; 2. Lipid-rich adenomas (LRA)--metastases; 3. Lipid-rich--lipid-poor adenomas (LPA); 4. Lipid-poor adenomas--metastases.&#x0D; There was a statistically significant difference in the distribution of some conventional (Histogram Entropy) and second-order features (GLCM – Homogeneity, Energy, Entropy log 10, Dissimilarity) in the first group on the native as well as on the enhanced images. The results were similar when comparing lipid-rich adenomas to metastases. Only native phase derived features were discriminative between lipid-rich and lipid-poor adenomas, with no difference between parameters on CECT. No difference was found between any of the texture features in lipid-poor adenomas and metastases for both phases.&#x0D; First- and second-order texture features were graded based on their potential for serving as classifier tools. Unenhanced features ranked higher. Further research and validation are needed to discover the most robust set of features for differentiating between lipid-poor adenomas and metastases.

Decoding tumor stage by peritumoral and intratumoral radiomics in resectable esophageal squamous cell carcinoma

PurposeTo evaluate the potential application of radiomics in predicting Tumor-Node-Metastasis (TNM) stage in patients with resectable esophageal squamous cell carcinoma (ESCC).MethodsThis retrospective study included 122 consecutive patients (mean age, 57 years; 27 women). Corresponding tumor of interest was identified on axial arterial-phase CT images with manual annotation. Radiomics features were extracted from intra- and peritumoral regions. Features were pruned to train LASSO regression model with 93 patients to construct a radiomics signature, whose performance was validated in a test set of 29 patients. Prognostic value of radiomics-predicted TNM stage was estimated by survival analysis in the entire cohort.ResultsThe radiomics signature incorporating one intratumoral and four peritumoral features was significantly associated with TNM stage. This signature discriminated tumor stage with an area under curve (AUC) of 0.823 in the training set, with similar performance in the test set (AUC 0.813). Recurrence-free survival (RFS) was significantly different between different radiomics-predicted TNM stage groups (Low-risk vs high-risk, log-rank P = 0.004). Univariate and multivariate Cox regression analyses revealed that radiomics-predicted TNM stage was an independent preoperative factor for RFS.ConclusionsThe proposed radiomics signature combing intratumoral and peritumoral features was predictive of TNM stage and associated with prognostication in ESCC.Graphical abstract

Development and Validation of Multi-Omics Thymoma Risk Classification Model Based on Transfer Learning.

The paper aims to develop prediction model that integrates clinical, radiomics, and deep features using transfer learning to stratifying between high and low risk of thymoma. Our study enrolled 150 patients with thymoma (76 low-risk and 74 high-risk) who underwent surgical resection and pathologically confirmed in Shengjing Hospital of China Medical University from January 2018 to December 2020. The training cohort consisted of 120 patients (80%) and the test cohort consisted of 30 patients (20%). The 2590 radiomics and 192 deep features from non-enhanced, arterial, and venous phase CT images were extracted and ANOVA, Pearson correlation coefficient, PCA, and LASSO were used to select the most significant features. A fusion model that integrated clinical, radiomics, and deep features was developed with SVM classifiers to predict the risk level of thymoma, and accuracy, sensitivity, specificity, ROC curves, and AUC were applied to evaluate the classification model. In both the training and test cohorts, the fusion model demonstrated better performance in stratifying high and low risk of thymoma. It had AUCs of 0.99 and 0.95, and an accuracy of 0.93 and 0.83, respectively. This was compared to the clinical model (AUCs of 0.70 and 0.51, accuracy of 0.68 and 0.47), the radiomics model (AUCs of 0.97 and 0.82, accuracy of 0.93 and 0.80), and the deep model (AUCs of 0.94 and 0.85, accuracy of 0.88 and 0.80). The fusion model integrating clinical, radiomics and deep features based on transfer learning was efficient for noninvasively stratifying high risk and low risk of thymoma. The models could help to determine surgery strategy for thymoma cancer.

Machine Learning Improves the Prediction of Responses to Immune Checkpoint Inhibitors in Metastatic Melanoma.

Pretreatment LDH is a standard prognostic biomarker for advanced melanoma and is associated with response to ICI. We assessed the role of machine learning-based radiomics in predicting responses to ICI and in complementing LDH for prognostication of metastatic melanoma. From 2008-2022, 79 patients with 168 metastatic hepatic lesions were identified. All patients had arterial phase CT images 1-month prior to initiation of ICI. Response to ICI was assessed on follow-up CT at 3 months using RECIST criteria. A machine learning algorithm was developed using radiomics. Maximum relevance minimum redundancy (mRMR) was used to select features. ROC analysis and logistic regression analyses evaluated performance. Shapley additive explanations were used to identify the variables that are the most important in predicting a response. mRMR selection revealed 15 features that are associated with a response to ICI. The machine learning model combining both radiomics features and pretreatment LDH resulted in better performance for response prediction compared to models that included radiomics or LDH alone (AUC of 0.89 (95% CI: [0.76-0.99]) vs. 0.81 (95% CI: [0.65-0.94]) and 0.81 (95% CI: [0.72-0.91]), respectively). Using SHAP analysis, LDH and two GLSZM were the most predictive of the outcome. Pre-treatment CT radiomic features performed equally well to serum LDH in predicting treatment response.

Computed tomography texture analysis combined with preoperative clinical factors serve as a predictor of early efficacy of transcatheter arterial chemoembolization in hepatocellular carcinoma.

To investigate a pre-therapeutic radiomics nomogram to accurately predict hepatocellular carcinoma (HCC) lesion responses to transcatheter arterial chemoembolization (TACE). This retrospective study from January 2012 to 2022 included 92 TACE-treated patients who underwent liver contrast-enhanced CT scan 7days before treatment, having complete clinical information. We extracted quantitative texture parameters and clinical factors for the largest tumors on the baseline arterial and portal venous phase CT images. An adaptive least absolute shrinkage and selection operator (LASSO)-penalized logistic regression identified independent predictors of tumor activity after TACE. We fitted an adaptive LASSO regression model to narrow down the texture features and clinical risk factors of the tumor activity status. The selected texture features were used to construct radiomic scores (RadScore), which demonstrated superior performance in predicting tumor activity on both the training (area under the curve (AUC): 0.881, 95% CI: 0.799-0.963) and testing sets (AUC: 0.88, 95% CI: 0.726-1). A logistic regression-based nomogram was developed using RadScore and four selected clinical features. In the testing set, nomogram total points were significant predictors (P = 0.034), and the training set showed no departure from perfect fit (P = 0.833). Internal validation of the nomogram was obtained for the training (AUC: 0.91, 95% CI: 0.837-0.984) and testing (AUC: 0.889, 95% CI: 0.746-1) sets. We propose a nomogram to predict the early response of HCC lesions to TACE treatment with high accuracy, which may serve as an additional criterion in multidisciplinary decision-making treatment.

Radiomics analysis of contrast-enhanced CT for staging liver fibrosis: an update for image biomarker

BackgroundTo establish and validate a radiomics-based model for staging liver fibrosis at contrast-enhanced CT images.Materials and methodsThis retrospective study developed two radiomics-based models (R-score: radiomics signature; R-fibrosis: integrate radiomic and serum variables) in a training cohort of 332 patients (median age, 59 years; interquartile range, 51–67 years; 256 men) with biopsy-proven liver fibrosis who underwent contrast-enhanced CT between January 2017 and December 2020. Radiomic features were extracted from non-contrast, arterial and portal phase CT images and selected using the least absolute shrinkage and selection operator (LASSO) logistic regression to differentiate stage F3–F4 from stage F0–F2. Optimal cutoffs to diagnose significant fibrosis (stage F2–F4), advanced fibrosis (stage F3–F4) and cirrhosis (stage F4) were determined by receiver operating characteristic curve analysis. Diagnostic performance was evaluated by area under the curve, Obuchowski index, calibrations and decision curve analysis. An internal validation was conducted in 111 randomly assigned patients (median age, 58 years; interquartile range, 49–66 years; 89 men).ResultsIn the validation cohort, R-score and R-fibrosis (Obuchowski index, 0.843 and 0.846, respectively) significantly outperformed aspartate transaminase-to-platelet ratio (APRI) (Obuchowski index, 0.651; p < .001) and fibrosis-4 index (FIB-4) (Obuchowski index, 0.676; p < .001) for staging liver fibrosis. Using the cutoffs, R-fibrosis and R-score had a sensitivity range of 70–87%, specificity range of 71–97%, and accuracy range of 82–86% in diagnosing significant fibrosis, advanced fibrosis and cirrhosis.ConclusionRadiomic analysis of contrast-enhanced CT images can reach great diagnostic performance of liver fibrosis.

Arterial enhancing local tumor progression detection on CT images using convolutional neural network after hepatocellular carcinoma ablation: a preliminary study

To evaluate the performance of a deep convolutional neural network (DCNN) in detecting local tumor progression (LTP) after tumor ablation for hepatocellular carcinoma (HCC) on follow-up arterial phase CT images. The DCNN model utilizes three-dimensional (3D) patches extracted from three-channel CT imaging to detect LTP. We built a pipeline to automatically produce a bounding box localization of pathological regions using a 3D-CNN trained for classification. The performance metrics of the 3D-CNN prediction were analyzed in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), area under the receiver operating characteristic curve (AUC), and average precision. We included 34 patients with 49 LTP lesions and randomly selected 40 patients without LTP. A total of 74 patients were randomly divided into three sets: training (n = 48; LTP: no LTP = 21:27), validation (n = 10; 5:5), and test (n = 16; 8:8). When used with the test set (160 LTP positive patches, 640 LTP negative patches), our proposed 3D-CNN classifier demonstrated an accuracy of 97.59%, sensitivity of 96.88%, specificity of 97.65%, and PPV of 91.18%. The AUC and precision–recall curves showed high average precision values of 0.992 and 0.96, respectively. LTP detection on follow-up CT images after tumor ablation for HCC using a DCNN demonstrated high accuracy and incorporated multichannel registration.

CT-based radiomics model for preoperative prediction of hepatic encephalopathy after transjugular intrahepatic portosystemic shunt.

To develop and evaluate a machine learning-based CT radiomics model for the prediction of hepatic encephalopathy (HE) after transjugular intrahepatic portosystemic shunt (TIPS). A total of 106 patients who underwent TIPS placement were consecutively enrolled in this retrospective study. Regions of interest (ROIs) were drawn on unenhanced, arterial phase, and portal venous phase CT images, and radiomics features were extracted, respectively. A radiomics model was established to predict the occurrence of HE after TIPS by using random forest algorithm and 10-fold cross-validation. Receiver operating characteristic (ROC) curves were performed to validate the capability of the radiomics model and clinical model on the training, test and original data sets, respectively. The radiomics model showed favorable discriminatory ability in the training cohort with an area under the curve (AUC) of 0.899 (95% CI, 0.848 to 0.951), while in the test cohort, it was confirmed with an AUC of 0.887 (95% CI, 0.760 to 1.00). After applying this model to original data set, it had an AUC of 0.955 (95% CI, 0.896 to 1.00). A clinical model was also built with an AUC of 0.649 (95% CI, 0.530 to 0.767) in the original data set, and a Delong test demonstrated its relative lower efficiency when compared with the radiomics model (p < 0.05). Machine learning-based CT radiomics model performed better than traditional clinical parameter-based models in the prediction of post-TIPS HE. Radiomics model for the prediction of post-TIPS HE was built based on feature extraction from routine acquired pre-operative CT images and feature selection by random forest algorithm, which showed satisfied performance and proved the advantages of machine learning in this field.

Preoperative assessment of cervical lymph node metastases in patients with papillary thyroid carcinoma: Incremental diagnostic value of dual-energy CT combined with ultrasound.

PurposeTo determine whether dual-energy CT (DECT) has incremental diagnostic value when combined with ultrasound (US) in the diagnosis of metastatic cervical lymph nodes (LNs) in patients with papillary thyroid carcinoma (PTC).MethodsThis was a single-center retrospective cohort study of patients diagnosed with PTC between October 2019 and August 2020. US features of LNs to include hyperechogenicity, round shape, microcalcification, cystic component, and homogeneous/peripheral vascularity were considered suggestive of metastasis. The HU of arterial phase (HUarterial) and DECT-derived CT images [contrast media (CM) and areas under the 100 keV monoenergetic curve (AUC100keV)] were measured. Effective atomic numbers (Zeff), iodine concentration (mg/mL), and slope of the HU curve (λHU) were also obtained. The values for metastatic and benign LNs were compared using Student’s t-test with false-discovery correction. Logistic regression with areas under the receiver operating characteristic curves (AUCs) were performed for predicting metastatic LNs.ResultsA total of 102 patients were included (49 metastatic and 53 benign LNs; mean age, 46±15 years). Metastatic LNs showed significantly higher values for HUarterial, CM, Zeff, λHU, AUC100keV, and iodine concentration (all, P = 0.001). In logistic regression, the HUarterial demonstrated the highest AUC (0.824; 95% confidence interval [CI], 0.751–0.897), followed by CM HU (0.762; 95% CI, 0.679–0.846). Combination of DECT parameters with US features improved the AUC from 0.890 to 0.941.ConclusionCompared to US features alone, combination with DECT-derived quantitative parameters improved diagnostic performance in predicting metastatic cervical LNs in patients with PTC.

Prediction of serosal invasion in gastric cancer: development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT images

BackgroundTo develop and validate multivariate models integrating endoscopic biopsy, tumor markers, and CT findings based on late arterial phase (LAP) to predict serosal invasion in gastric cancer (GC).MethodsThe preoperative differentiation degree, tumor markers, CT morphological characteristics, and CT value-related and texture parameters of 154 patients with GC were analyzed retrospectively. Multivariate models based on regression analysis and machine learning algorithms were performed to improve the diagnostic efficacy.ResultsThe differentiation degree, carbohydrate antigen (CA) 199, CA724, CA242, and multiple CT findings based on LAP differed significantly between T1–3 and T4 GCs in the primary cohort (all P < 0.05). Multivariate models based on regression analysis and random forest achieved AUCs of 0.849 and 0.865 in the primary cohort, respectively.ConclusionWe developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics, and CT value-related and texture parameters to predict serosal invasion in GCs and achieved favorable performance.

Computed tomography radiomics to predict EBER positivity in Epstein-Barr virus-associated gastric adenocarcinomas: a retrospective study.

The relevance of Epstein-Barr virus (EBV) in gastric carcinoma has been represented by the existence of EBV-encoded small RNA (EBER) in the tumor cells and has prognostic significance in gastric cancer, while gastric adenocarcinoma represents the most frequently occurring gastric malignancy. To observe the capacity of radiomic features extracted from contrast-enhanced computed tomography (CE-CT) images to differentiate EBER-positive gastric adenocarcinoma from EBER-negative ones. A total of 54 patients with gastric adenocarcinoma (EBER-positive: 27, EBER-negative: 27) were retrospectively examined. Radiomic imaging features were extracted from all regions of interest (ROI) delineated by two experienced radiologists on late arterial phase CT images. We distinguished related radiomic features through the two-tailed t test and applied them to construct a decision tree model to evaluate whether EBER in situ hybridization positive had appeared. Nine radiomics features were significantly related to EBER in situ hybridization status (P < 0.05), four of which were used to build the decision tree through backward elimination: Correlation_ AllDirection_offset7, Correlation_ angle135_offset7, RunLengthNonuniformity_ AllDirection_offset1_SD, and HighGreyLevelRunEmphasis_ AllDiretion_offset1_SD. The decision tree model consisted of seven decision nodes and six terminal nodes, three of which demonstrated positive EBER in situ hybridization. The specificity, sensitivity, and accuracy of the model were 84%, 80%, and 81.7%, respectively. The area under the curve of the decision tree model was 0.87. Radiomics based on CE-CT could be applied to predict EBER in situ hybridization status preoperatively in patients with gastric adenocarcinoma.

Radiomics analysis of CT imaging for differentiating gastric neuroendocrine carcinomas from gastric adenocarcinomas

PurposeTo develop and evaluate a CT-based radiomics nomogram for differentiating gastric neuroendocrine carcinomas (NECs) from gastric adenocarcinomas (ADCs). MethodsCT images of 63 patients with gastric NECs were collected retrospectively, and 63 patients with gastric ADCs were selected as the control group. Univariate analysis was used to identify the significant factors of clinical characteristics and CT findings for differentiating gastric NECs from ADCs. Radiomics analysis was applied to CT images of unenhanced, arterial phase and venous phase, respectively. A radiomics nomogram incorporating the radiomics signature and the subjective CT findings was developed and its diagnostic ability was evaluated. The diagnostic performances of CT findings model, radiomics signature and radiomics nomogram were compared using DeLong test. ResultsThe tumor margin and lymph node (LN) metastasis were independent predictors for differentiating gastric NECs from ADCs. The radiomics signature based on venous phase presented superior AUC of 0.798 [95 % confidence interval (CI), 0.657−0.938] in validation cohort. The nomogram incorporated the radiomics signature, tumor margin and LN metastasis showed AUCs of 0.821 (95 %CI: 0.725−0.895) in the primary cohort and 0.809 (95 %CI: 0.649−0.918) in the validation cohort. Moreover, the radiomics nomogram showed good discrimination and calibration. The diagnostic performance of CT findings model was significantly lower than that of radiomics nomogram (p = 0.001) and radiomics signature (p = 0.025). ConclusionsRadiomics analysis exhibited good performance in differentiating gastric NECs from ADCs, and the radiomics nomogram may have significant clinical implications on preoperative detection of gastric malignant tumors.

Gastric poorly cohesive carcinoma: differentiation from tubular adenocarcinoma using nomograms based on CT findings in the 40s late arterial phase.

To summarise the CT findings of gastric poorly cohesive carcinoma (PCC) in the 40s late arterial phase and differentiate it from tubular adenocarcinoma (TAC) using an integrative nomogram. A total of 241 patients including 59 PCCs, 109 TACs, and 73 other type gastric cancers were enrolled. Thirteen CT morphological characteristics of each lesion in the late arterial phase were evaluated. In addition, CT value-related parameters were extracted from ROIs encompassing the area of greatest enhancement on four-phase CT images. Nomograms based on regression models were built to discriminate PCCs from TACs and from non-PCCs. ROC curve analysis was performed to assess the diagnostic efficiency. Six morphological characteristics, 10 CT value-related parameters, and the enhanced curve types differed significantly among the above three groups in the primary cohort (all p < 0.05). The paired comparison revealed that 10 CT value-related parameters differed significantly between PCCs and TACs (all p < 0.05). The AUC of the nomogram based on the multivariate model for discriminating PCCs from TACs was 0.954, which was confirmed in the validation cohort (AUC = 0.895). The AUC of another nomogram for discriminating PCCs from non-PCCs was 0.938, which was confirmed in the validation cohort (AUC = 0.880). In the 40s late arterial phase, the morphological characteristics and CT value-related parameters were significantly different among PCCs, TACs, and other types. PCCs were prone to manifest mucosal line interruption, diffuse thickening, infiltrative growth, and slow-rising enhanced curve (Type A). Furthermore, multivariate models were useful in discriminating PCCs from TACs and other types. • Multiple morphological characteristics and CT value-related parameters differed significantly between gastric PCCs and TACs in the 40s late arterial phase. • The nomogram integrating morphological characteristics and CT value-related parameters in the 40s late arterial phase had favourable performance in discriminating PCCs from TACs. • More useful information can be derived from 40s late arterial phase CT images; thus, a more accurate evaluation can be made in clinical practice.

Development and validation of a CT-based nomogram for preoperative prediction of clear cell renal cell carcinoma grades.

Nuclear grades are proved to be one of the most significant prognostic factors for clear cell renal cell carcinoma (ccRCC). Radiomics nomogram is a widely used noninvasive tool that could predict tumor phenotypes. In this study, we performed radiomics analysis to develop and validate a CT-based nomogram for the preoperative prediction of nuclear grades in ccRCC. CT images and clinical data of 258 ccRCC patients were retrieved from the Cancer Imaging Archive (TCIA). Radiomics features were extracted from arterial-phase CT images using 3D Slicer software. LASSO regression model was performed to develop a radiomics signature in the training set (n= 143). A radiomics nomogram was constructed combining radiomics signature and selected clinical predictors. Receiver operating characteristic (ROC) curve and calibration curve were used to determine the performance of the radiomics nomogram in the training and validation set (n = 115). Decision curve analysis was used to assess the clinical usefulness of the CT-based nomogram. One thousand three hundred sixteen radiomics features were extracted from arterial-phase CT images. A radiomics signature, consisting of 20 features, was developed and showed a favorable performance in discriminating nuclear grades with an area under the curve (AUC) of 0.914 and 0.846 in the training and validation set, respectively. The CT-based nomogram, including the radiomics signature and theCT-determined T stage, achieved good calibration and discrimination in the training set (AUC, 0.929; 95% CI, 0.886-0.972) and validation set (AUC, 0.876; 95% CI, 0.812-0.939). Decision curve analysis demonstrated the clinical usefulness of the CT-based nomogram. The noninvasive CT-based nomogram, including radiomics signature and CT-determined T stage, could improve the accuracy of preoperative grading of ccRCC and provide individualized treatment for ccRCC patients. • Contrast-enhanced CT may help in preoperative grading of ccRCC. • The CT-based nomogram incorporated a radiomics signature and CT-determined T stage could preoperatively predict ccRCC grades. • The CT-based nomogram has the potential to improve individualized treatment and assist clinical decision making of ccRCC patients.

Radiomics Analysis of Contrast-Enhanced CT for Staging Liver Fibrosis: An Update for Image Biomarker

Background: To establish and validate a radiomics-based model for staging liver fibrosis at contrast-enhanced CT images. Materials and Methods: This retrospective study developed two radiomics-based models (R-score: radiomics signature; R-fibrosis: integrate radiomic and serum variables) in a training cohort of 332 patients (median age, 59 years; interquartile range, 51-67 years; 256 men) with biopsy-proven liver fibrosis who underwent contrast-enhanced CT between January 2017 and December 2020. Radiomic features were extracted from non-contrast, arterial and portal phase CT images and selected by using the least absolute shrinkage and selection operator (LASSO) logistic regression to differentiate stage F3-F4 from stage F0-F2. Optimal cutoffs to diagnose significant fibrosis (stage F2-F4), advanced fibrosis (stage F3-F4) and cirrhosis (stage F4) were determined by receiver operating characteristic curve analysis. Diagnostic performance was evaluated by area under the curve, Obuchowski index, calibrations and decision curve analysis. An internal validation was conducted in 111 randomly assigned patients (median age, 58 years; interquartile range, 49-66 years; 89 men). Results: In the validation cohort, R-score and R-fibrosis (Obuchowski index, 0.843 and 0.846, respectively) significantly outperformed aspartate transaminase-to-platelet ratio (APRI) (Obuchowski index, 0.651; P < .001) and fibrosis-4 index (FIB-4) (Obuchowski index, 0.676; P < .001) for staging liver fibrosis. By using the cutoffs, R-fibrosis and R-score had a sensitivity range of 70%-87%, specificity range of 71%-97%, and accuracy range of 82%-86% in diagnosing significant fibrosis, advanced fibrosis and cirrhosis. Conclusion: Radiomic analysis of contrast-enhanced CT images can reach great diagnostic performance of liver fibrosis. Funding Information: This work was supported by grants from the National Natural Science Youth Foundation (Grant Number 81902415 to Y.Y.), Natural Science Youth Foundation of Jiangsu Province (Grant Number BK20190116 to Y.Y.) and Key Laboratory of Imaging Diagnosis and Minimally Invasive Interventional Research of Zhejiang Province (No. YXJR202002, to J.W). Declaration of Interests: The authors declare that they have no competing interests. Ethics Approval Statement: This retrospective study was approved by the institutional review board of the Affiliated Drum Tower Hospital of Nanjing University Medical School. The requirement for written informed consent was waived due to its retrospective nature.