Venous Phase Computed Tomography Images Research Articles

Deep Learning–Based Prediction of Hepatic Decompensation in Patients With Primary Sclerosing Cholangitis With Computed Tomography

ObjectiveTo investigate a deep learning model for predicting hepatic decompensation using computed tomography (CT) imaging in patients with primary sclerosing cholangitis (PSC). Patients and MethodsRetrospective cohort study involving 277 adult patients with large-duct PSC who underwent an abdominal CT scan. The portal venous phase CT images were used as input to a 3D-DenseNet121 model, which was trained using 5-fold crossvalidation to classify hepatic decompensation. To further investigate the role of each anatomic region in the model’s decision-making process, we trained the model on different sections of 3-dimensional CT images. This included training on the right, left, anterior, posterior, inferior, and superior halves of the image data set. For each half, as well as for the entire scan, we performed area under the receiving operating curve (AUROC) analysis. ResultsHepatic decompensation occurred in 128 individuals after a median (interquartile range) of 1.5 years (142-1318 days) after the CT scan. The deep learning model exhibited promising results, with a mean ± SD AUROC of 0.89±0.04 for the baseline model. The mean ± SD AUROC for left, right, anterior, posterior, superior, and inferior halves were 0.83±0.03, 0.83±0.03, 0.82±0.09, 0.79±0.02, 0.78±0.02, and 0.76±0.04, respectively. ConclusionThe study illustrates the potential of examining CT imaging using 3D-DenseNet121 deep learning model to predict hepatic decompensation in patients with PSC.

Preoperative CT-based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors.

Gastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively. To establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively. The 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre-trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre-trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single-phase and dual-phase images. The arterial phase, venous phase and dual-phase machine learning models were built, respectively, and the morphological features were added to the dual-phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed. The area under the curve (AUC) of the dual-phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887-0.974) (p=0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357-0.891). In this study, we established a combined model that incorporated dual-phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

Automated segmentation of liver and hepatic vessels on portal venous phase computed tomography images using a deep learning algorithm.

CT-image segmentation for liver and hepatic vessels can facilitate liver surgical planning. However, time-consuming process and inter-observer variations of manual segmentation have limited wider application in clinical practice. Our study aimed to propose an automated deep learning (DL) segmentation algorithm for liver and hepatic vessels on portal venous phase CT images. This retrospective study was performed to develop a coarse-to-fine DL-based algorithm that was trained, validated, and tested using private 413, 52, and 50 portal venous phase CT images, respectively. Additionally, the performance of the DL algorithm was extensively evaluated and compared with manual segmentation using an independent clinical dataset of preoperative contrast-enhanced CT images from 44 patients with hepatic focal lesions. The accuracy of DL-based segmentation was quantitatively evaluated using the Dice Similarity Coefficient (DSC) and complementary metrics [Normalized Surface Dice (NSD) and Hausdorff distance_95 (HD95) for liver segmentation, Recall and Precision for hepatic vessel segmentation]. The processing time for DL and manual segmentation was also compared. Our DL algorithm achieved accurate liver segmentation with DSC of 0.98, NSD of 0.92, and HD95 of 1.52mm. DL-segmentation of hepatic veins, portal veins, and inferior vena cava attained DSC of 0.86, 0.89, and 0.94, respectively. Compared with the manual approach, the DL algorithm significantly outperformed with better segmentation results for both liver and hepatic vessels, with higher accuracy of liver and hepatic vessel segmentation (all p<0.001) in independent 44 clinical data. In addition, the DL method significantly reduced the manual processing time of clinical postprocessing (p<0.001). The proposed DL algorithm potentially enabled accurate and rapid segmentation for liver and hepatic vessels using portal venous phase contrast CT images.

Preoperative CT histogram analysis to predict the expression of Ki-67 in solid pseudopapillary tumours of the pancreas

To explore the value of preoperative computed tomography (CT) histogram features in predicting the expression status of Ki-67 in patients with solid pseudopapillary pancreatic tumours (SPTP). This retrospective study analysed venous phase CT images of 39 patients with SPTP confirmed at surgery and histopathology and measured using the Ki-67 proliferation index from November 2015 to February 2022. According to the Ki-67 proliferation index, they were divided into high expression (Ki-67≥4%) and low expression (Ki-67<4%) groups. The histogram features of quantitative parameters were extracted using MaZda software, and the quantitative parameters of CT histograms were compared between groups. The receiver operating characteristic (ROC) curves of the patients were plotted according to the parameters, with statistically significant differences. The area under the curve (AUC), sensitivity, and specificity were calculated, and the effectiveness of the histogram parameters in predicting Ki-67 expression was analysed and evaluated. In total, 27 SPTP patients were enrolled, including 11 with high expression of Ki-67 and 16 with low expression. Comparative analysis of the Ki-67 high- and low-expression groups revealed a statistically significant in necrosis and variance (p<0.05). ROC curve analysis showed that the AUC of necrosis and variance predicting Ki-67 expression status were 0.753 and 0.841, the sensitivities were 81.8% and 81.3%, and the specificities were 68.7% and 81.8%, respectively. Preoperative CT histogram features help predict Ki-67 expression status in patients with SPTP.

Deep learning imaging reconstruction of reduced-dose 40 keV virtual monoenergetic imaging for early detection of colorectal cancer liver metastases

ObjectiveTo explore whether reduced-dose (RD) gemstone spectral imaging (GSI) and deep learning image reconstruction (DLIR) of 40 keV virtual monoenergetic image (VMI) enhanced the early detection and diagnosis of colorectal cancer liver metastases (CRLM). MethodsThirty-five participants with pathologically confirmed colorectal cancer were prospectively enrolled from March to August 2022 after routine care abdominal computed tomography (CT). GSI mode was used for contrast-enhanced CT, and two portal venous phase CT images were obtained [standard-dose (SD) CT dose index (CTDIvol) = 15.51 mGy, RD CTDIvol = 7.95 mGy]. The 40 keV-VMI were reconstructed via filtered back projection (FBP) and iterative reconstruction (ASIR-V 60 %, AV60) of both SD and RD images. RD medium-strength deep learning image reconstruction (DLIR-M) and RD high-strength deep learning image reconstruction (DLIR-H) were used to reconstruct the 40 keV-VMI. The contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) of the liver and the lesions were objectively evaluated. The overall image quality, lesion conspicuity, and diagnostic confidence were subjectively evaluated, to compare the differences in evaluation results among the different images. ResultsAll 35 participants (mean age: 59.51 ± 11.01 years; 14 females) underwent SD and RD GSI portal venous-phase CT scans. The dose-length product of the RD GSI scan was reduced by 49–53 % lower than that of the SD GSI scan (420.22 ± 31.95) vs (817.58 ± 60.56). A total of 219 lesions were identified, including 55 benign lesions and 164 metastases, with an average size of 7.37 ± 4.14 mm. SD-FBP detected 207 lesions, SD-AV60 detected 201 lesions, and DLIR-M and DLIR-H detected 199 and 190 lesions, respectively. For lesions ≤ 5 mm, there was no statistical difference between SD-FBP vs DLIR-M (χ2McNemar = 1.00, P = 0.32) and SD-AV60 vs DLIR-M (χ2McNemar = 0.33, P = 0.56) in the detection rate. The CNR, SNR, and noise of DLIR-M and DLIR-H 40 keV-VMI images were better than those of SD-FBP images (P < 0.01) but did not differ significantly from those of SD-AV60 images (P > 0.05). When the lesions ≤ 5 mm, there were statistical differences in the overall diagnostic sensitivity of lesions compared with SD-FBP, SD-AV60, DLIR-M and DLIR-H (P＜0.01). There were no statistical differences in the sensitivity of lesions diagnosis between SD-FBP, SD-AV60 and DLIR-M (both P＞0.05). However, the DLIR-M subjective image quality and lesion diagnostic confidence were higher for SD-FBP (both P < 0.01). ConclusionReduced dose DLIR-M of 40 keV-VMI can be used for routine follow-up care of colorectal cancer patients, to optimize evaluations and ensure CT image quality. Meanwhile, the detection rate and diagnostic sensitivity and specificity of small lesions, early liver metastases is not obviously reduced.

Nomogram including tumor deposition count to noninvasively evaluate the prognosis of rectal cancer patients: A retrospective study

To build a nomogram model that includes tumor deposition (TDs) count to noninvasively evaluate the prognosis of patients with rectal cancer (RC). A total of 262 patients between January 2013 and December 2018 were recruited and divided into 2 cohorts: training (n = 171) and validation (n = 91). Axial portal venous phase computed tomography images were used to extract radiomic features, and the least absolute shrinkage and selection operator-Cox analysis was applied to develop an optimal radiomics model to derive the Rad-score. A Cox regression model combining clinicopathological factors and Rad-scores was constructed and visualized using a nomogram. And its ability to predict RC patients’ survival was tested by Kaplan–Meier survival analysis. The time-dependent concordance index curve was used to demonstrate the differentiation degree of model. Calibration and decision curve analyses were used to evaluate the calibration accuracy and clinical usefulness of the nomogram model, and the prediction performance of the nomogram model was compared with the clinical and radiomics models using the likelihood test. Computed tomography-based Rad-score, pathological tumor (pT) stageT4, and TDs count were independent risk factors affecting the prognosis of RC. The whole concordance index of the nomogram model for predicting the overall survival rates of RC was higher than that of the clinical and radiomics models in the training (0.812 vs 0.59, P = .019; 0.812 vs 0.714, P = .014) and validation groups (0.725 vs 0.585, P = .002; 0.725 vs 0.751, P = .256). The nomogram model could effectively predict patients’ overall survival rate (hazard ratio = 9.25, 95% CI = [1.17–72.99], P = .01). The nomogram model also showed a higher clinical net benefit than the clinical and radiomics models in the training and validation groups. The nomogram model developed in this study can be used to noninvasively evaluate the prognosis of RC patients. The TDs count is an independent risk factor for the prognosis of RC.

Virtual biopsy using CT radiomics for evaluation of disagreement in pathology between endoscopic biopsy and postoperative specimens in patients with gastric cancer: a dual-energy CT generalizability study

PurposeTo develop a noninvasive radiomics-based nomogram for identification of disagreement in pathology between endoscopic biopsy and postoperative specimens in gastric cancer (GC).Materials and methodsThis observational study recruited 181 GC patients who underwent pre-treatment computed tomography (CT) and divided them into a training set (n = 112, single-energy CT, SECT), a test set (n = 29, single-energy CT, SECT) and a validation cohort (n = 40, dual-energy CT, DECT). Radiomics signatures (RS) based on five machine learning algorithms were constructed from the venous-phase CT images. AUC and DeLong test were used to evaluate and compare the performance of the RS. We assessed the dual-energy generalization ability of the best RS. An individualized nomogram combined the best RS and clinical variables was developed, and its discrimination, calibration, and clinical usefulness were determined.ResultsRS obtained with support vector machine (SVM) showed promising predictive capability with AUC of 0.91 and 0.83 in the training and test sets, respectively. The AUC of the best RS in the DECT validation cohort (AUC, 0.71) was significantly lower than that of the training set (Delong test, p = 0.035). The clinical-radiomic nomogram accurately predicted pathologic disagreement in the training and test sets, fitting well in the calibration curves. Decision curve analysis confirmed the clinical usefulness of the nomogram.ConclusionCT-based radiomics nomogram showed potential as a clinical aid for predicting pathologic disagreement status between biopsy samples and resected specimens in GC. When practicability and stability are considered, the SECT-based radiomics model is not recommended for DECT generalization.Critical relevance statementRadiomics can identify disagreement in pathology between endoscopic biopsy and postoperative specimen.Graphical abstract

Differentiation of retroperitoneal paragangliomas and schwannomas based on computed tomography radiomics

The purpose of this study was to differentiate the retroperitoneal paragangliomas and schwannomas using computed tomography (CT) radiomics. This study included 112 patients from two centers who pathologically confirmed retroperitoneal pheochromocytomas and schwannomas and underwent preoperative CT examinations. Radiomics features of the entire primary tumor were extracted from non-contrast enhancement (NC), arterial phase (AP) and venous phase (VP) CT images. The least absolute shrinkage and selection operator method was used to screen out key radiomics signatures. Radiomics, clinical and clinical-radiomics combined models were built to differentiate the retroperitoneal paragangliomas and schwannomas. Model performance and clinical usefulness were evaluated by receiver operating characteristic curve, calibration curve and decision curve. In addition, we compared the diagnostic accuracy of radiomics, clinical and clinical-radiomics combined models with radiologists for pheochromocytomas and schwannomas in the same set of data. Three NC, 4 AP, and 3 VP radiomics features were retained as the final radiomics signatures for differentiating the paragangliomas and schwannomas. The CT characteristics CT attenuation value of NC and the enhancement magnitude at AP and VP were found to be significantly different statistically (P < 0.05). The NC, AP, VP, Radiomics and clinical models had encouraging discriminative performance. The clinical-radiomics combined model that combined radiomics signatures and clinical characteristics showed excellent performance, with an area under curve (AUC) values were 0.984 (95% CI 0.952–1.000) in the training cohort, 0.955 (95% CI 0.864–1.000) in the internal validation cohort and 0.871 (95% CI 0.710–1.000) in the external validation cohort. The accuracy, sensitivity and specificity were 0.984, 0.970 and 1.000 in the training cohort, 0.960, 1.000 and 0.917 in the internal validation cohort and 0.917, 0.923 and 0.818 in the external validation cohort, respectively. Additionally, AP, VP, Radiomics, clinical and clinical-radiomics combined models had a higher diagnostic accuracy for pheochromocytomas and schwannomas than the two radiologists. Our study demonstrated the CT-based radiomics models has promising performance in differentiating the paragangliomas and schwannomas.

Discrimination of Liver Metastases of Digestive System Neuroendocrine Tumors From Neuroendocrine Carcinoma by Computed Tomography-Based Radiomics Analysis.

The aim of the study is to investigate the value of computed tomography (CT) radiomics features to discriminate the liver metastases (LMs) of digestive system neuroendocrine tumors (NETs) from neuroendocrine carcinoma (NECs). Ninety-nine patients with LMs of digestive system neuroendocrine neoplasms from 2 institutions were included. Radiomics features were extracted from the portal venous phase CT images by the Pyradiomics and then selected by using the t test, Pearson correlation analysis, and least absolute shrinkage and selection operator method. The radiomics score (Rad score) for each patient was constructed by linear combination of the selected radiomics features. The radiological model was constructed by radiological features using the multivariable logistic regression. Then, the combined model was constructed by combining Rad score and the radiological model into logistic regression. The performance of all models was evaluated by the receiver operating characteristic curves with the area under curve (AUC). In the radiological model, only the enhancement degree (odds ratio, 8.299; 95% confidence interval, 2.070-32.703; P = 0.003) was an independent predictor for discriminating the LMs of digestive system NETs from those of NECs. The combined model constructed by the Rad score in combination with the enhancement degree showed good discrimination performance, with AUCs of 0.893, 0.841, and 0.740 in the training, testing, and external validation groups, respectively. In addition, it performed better than radiological model in the training and testing groups (AUC, 0.893 vs 0.726; AUC, 0.841 vs 0.621). The CT radiomics might be useful for discrimination LMs of digestive system NECs from NETs.

Clinical-radiomics nomogram for predicting esophagogastric variceal bleeding risk noninvasively in patients with cirrhosis.

Esophagogastric variceal bleeding (EGVB) is a serious complication of patients with decompensated cirrhosis and is associated with high mortality and morbidity. Early diagnosis and screening of cirrhotic patients at risk for EGVB is crucial. Currently, there is a lack of noninvasive predictive models widely available in clinical practice. To develop a nomogram based on clinical variables and radiomics to facilitate the noninvasive prediction of EGVB in cirrhotic patients. A total of 211 cirrhotic patients hospitalized between September 2017 and December 2021 were included in this retrospective study. Patients were divided into training (n = 149) and validation (n = 62) groups at a 7:3 ratio. Participants underwent three-phase computed tomography (CT) scans before endoscopy, and radiomic features were extracted from portal venous phase CT images. The independent sample t-test and least absolute shrinkage and selection operator logistic regression were used to screen out the best features and establish a radiomics signature (RadScore). Univariate and multivariate analyses were performed to determine the independent predictors of EGVB in clinical settings. A noninvasive predictive nomogram for the risk of EGVB was built using independent clinical predictors and RadScore. Receiver operating characteristic, calibration, clinical decision, and clinical impact curves were applied to evaluate the model's performance. Albumin (P = 0.001), fibrinogen (P = 0.001), portal vein thrombosis (P = 0.002), aspartate aminotransferase (P = 0.001), and spleen thickness (P = 0.025) were selected as independent clinical predictors of EGVB. RadScore, constructed with five CT features of the liver region and three of the spleen regions, performed well in training (area under the receiver operating characteristic curve (AUC) = 0.817) as well as in validation (AUC = 0.741) cohorts. There was excellent predictive performance in both the training and validation cohorts for the clinical-radiomics model (AUC = 0.925 and 0.912, respectively). Compared with the existing noninvasive models such as ratio of aspartate aminotransferase to platelets and Fibrosis-4 scores, our combined model had better predictive accuracy with the Delong's test less than 0.05. The Nomogram had a good fit in the calibration curve (P > 0.05), and the clinical decision curve further supported its clinical utility. We designed and validated a clinical-radiomics nomogram able to noninvasively predict whether cirrhotic patients will develop EGVB, thus facilitating early diagnosis and treatment.

Using CT radiomic features based on machine learning models to subtype adrenal adenoma

BackgroundFunctioning and non-functioning adrenocortical adenoma are two subtypes of benign adrenal adenoma, and their differential diagnosis is crucial. Current diagnostic procedures use an invasive method, adrenal venous sampling, for endocrinologic assessment.MethodsThis study proposes establishing an accurate differential model for subtyping adrenal adenoma using computed tomography (CT) radiomic features and machine learning (ML) methods. Dataset 1 (289 patients with adrenal adenoma) was collected to develop the models, and Dataset 2 (54 patients) was utilized for external validation. Cuboids containing the lesion were cropped from the non-contrast, arterial, and venous phase CT images, and 1,967 features were extracted from each cuboid. Ten discriminative features were selected from each phase or the combined phases. Random forest, support vector machine, logistic regression (LR), Gradient Boosting Machine, and eXtreme Gradient Boosting were used to establish prediction models.ResultsThe highest accuracies were 72.7%, 72.7%, and 76.1% in the arterial, venous, and non-contrast phases, respectively, when using radiomic features alone with the ML classifier of LR. When features from the three CT phases were combined, the accuracy of LR reached 83.0%. After adding clinical information, the area under the receiver operating characteristic curve increased for all the machine learning methods except for LR. In Dataset 2, the accuracy of LR was the highest, reaching 77.8%.ConclusionThe radiomic features of the lesion in three-phase CT images can potentially suggest the functioning or non-functioning nature of adrenal adenoma. The resulting radiomic models can be a non-invasive, low-cost, and rapid method of minimizing unnecessary testing in asymptomatic patients with incidentally discovered adrenal adenoma.

Computed Tomography-based Radiomics Nomogram for the Preoperative Prediction of Tumor Deposits and Clinical Outcomes in Colon Cancer: a Multicenter Study

To develop and validate a computed tomography (CT)-based radiomics nomogram for the preoperative prediction of tumor deposits (TDs) and clinical outcomes in patients with colon cancer. This retrospective study included 383 consecutive patients with colon cancer from two centers. Radiomics features were extracted from portal venous phase CT images. Least absolute shrinkage and selection operator regression was applied for feature selection and radiomics signature construction. The multivariate logistic regression model was used to establish a radiomics nomogram. The performance of the nomogram was assessed by using receiver operating characteristic curves, calibration curves and decision curve analysis. Kaplan‒Meier survival analysis was used to assess the difference of the overall survival (OS) in the TDs-positive and TDs-negative groups. The radiomics signature was composed of 11 TDs status related features. The AUCs of the radiomics model in the training cohort, internal validation and external validation cohorts were 0.82, 0.78 and 0.78, respectively. The radiomics nomogram that incorporated the radiomics signature and clinical independent predictors (CT-N, CEA and CA199) showed good calibration and discrimination with AUCs of 0.88, 0.80 and 0.81 in the training cohort, internal validation and external validation cohorts, respectively. The radiomics nomogram-predicted high-risk groups had a worse OS than the low-risk groups (p < 0.001). The radiomics nomogram-predicted TDs was an independent preoperative predictor of OS. The radiomics nomogram based on CT radiomics features and clinical independent predictors could effectively predict the preoperative TDs status and OS of colon cancer. CT-based radiomics nomogram may be applied in the individual preoperative prediction of TDs status in colon cancer. Additionally, there was a significant difference in OS between the high-risk and low-risk groups defined by the radiomics nomogram, in which patients with high-risk TDs had a significantly worse OS, compared with those with low-risk TDs.

Deep learning model for diagnosing early gastric cancer using preoperative computed tomography images.

Early gastric cancer (EGC) is defined as a lesion restricted to the mucosa or submucosa, independent of size or evidence of regional lymph node metastases. Although computed tomography (CT) is the main technique for determining the stage of gastric cancer (GC), the accuracy of CT for determining tumor invasion of EGC was still unsatisfactory by radiologists. In this research, we attempted to construct an AI model to discriminate EGC in portal venous phase CT images. We retrospectively collected 658 GC patients from the first affiliated hospital of Nanchang university, and divided them into training and internal validation cohorts with a ratio of 8:2. As the external validation cohort, 93 GC patients were recruited from the second affiliated hospital of Soochow university. We developed several prediction models based on various convolutional neural networks, and compared their predictive performance. The deep learning model based on the ResNet101 neural network represented sufficient discrimination of EGC. In two validation cohorts, the areas under the curves (AUCs) for the receiver operating characteristic (ROC) curves were 0.993 (95% CI: 0.984-1.000) and 0.968 (95% CI: 0.935-1.000), respectively, and the accuracy was 0.946 and 0.914. Additionally, the deep learning model can also differentiate between mucosa and submucosa tumors of EGC. These results suggested that deep learning classifiers have the potential to be used as a screening tool for EGC, which is crucial in the individualized treatment of EGC patients.

A radiomics nomogram analysis based on CT images and clinical features for preoperative Lauren classification in gastric cancer.

To develop a combined radiomics nomogram based on computed tomography (CT) images and clinical features to preoperatively distinguish Lauren's diffuse-type gastric cancer (GC) from intestinal-type GC. Ninety-five patients with Lauren's intestinal or diffuse-type GC confirmed by postoperative pathology had their preoperative clinical information and dynamic contrast CT images retrospectively analyzed and were subdivided into training and test groups in a 7:3 ratio. To select the optimal features and construct the radiomic signatures, we extracted, filtered, and minimized the radiomic features from arterial phase (AP) and venous phase (VP) CT images. We constructed four models (clinical model, AP radiomics model, VP radiomics model, and radiomics-clinical model) to assess and compare their predictive performance between the intestinal- and diffuse-type GC. Receiver-operating characteristic (ROC) curve, area under the ROC curve (AUC), and the DeLong test were used for assessment and comparison. In this study, radiomic nomograms integrating combined radiomic signatures and clinical characteristics were developed. Compared to the AP radiomics model, the VP radiomics model had better performance, with an AUC of 0.832 (95% confidence interval [CI], 0.735, 0.929) in the training cohort and 0.760 (95% CI 0.580, 0.940) in the test cohort. Among the combined models that assessed Lauren's type GC, the model including age and VP radiomics showed the best performance, with an AUC of 0.849 (95% CI 0.758, 0.940) in the training cohort and 0.793 (95% CI 0.629, 0.957) in the test cohort. Nomogram incorporating radiomic signatures and clinical features effectively differentiated Lauren's diffuse-type from intestinal-type GC.

Application of preoperative CT texture analysis in papillary gastric adenocarcinoma

BackgroundThis study aimed to analyze the ability of computed tomography (CT) texture analysis to discriminate papillary gastric adenocarcinoma (PGC) and to explore the diagnostic efficacy of multivariate models integrating clinical information and CT texture parameters for discriminating PGCs.MethodsThis retrospective study included 20 patients with PGC and 80 patients with tubular adenocarcinoma (TAC). The clinical data and CT texture parameters based on the arterial phase (AP) and venous phase (VP) of all patients were collected and analyzed. Two CT signatures based on the AP and VP were built with the optimum features selected by the least absolute shrinkage and selection operator method. The performance of CT signatures was tested by regression analysis. Multivariate models based on regression analysis and the support vector machine (SVM) algorithm were established. The diagnostic performance of the established nomogram based on regression analysis was evaluated by receiver operating characteristic curve analysis.ResultsThirty-two and fifteen CT texture parameters extracted from AP and VP CT images, respectively, differed significantly between PGCs and TACs (all p < 0.05). The diagnostic performance of CT signatures based on the AP and VP achieved AUCs of 0.873 and 0.859 in distinguishing PGCs. Multivariate models that integrated two CT signatures and age based on regression analysis and the SVM algorithm showed favorable performance in preoperatively predicting PGCs (AUC = 0.922 and 0.914, respectively).ConclusionCT texture analysis based multivariate models could preoperatively predict PGCs with satisfactory diagnostic efficacy.

Interobserver Variability and Accuracy of Preoperative CT and MRI in Pancreatic Ductal Adenocarcinoma Size Estimation: A Retrospective Cohort Study.

Purpose: To assess interobserver variability and accuracy of preoperative computed tomography (CT) and magnetic resonance imaging (MRI) in pancreatic ductal adenocarcinoma (PDAC) size estimation using surgical specimens as standard of reference. Methods: Patients with PDAC who underwent preoperative CT and MRI examinations before surgery were included. PDAC largest axial dimension was measured by 2 readers on 8 MRI sequence and 2 CT imaging phases (pancreatic parenchymal and portal venous). Measurements were compared to actual tumour size at pathologic examination. Interobserver variability was assessed using intraclass correlation coefficients (ICC) and Bland-Altman plots. Differences in tumour size (Δdiameter) between imaging and actual tumour size were searched using Wilcoxon rank sum test. Results: Twenty-nine patients (16 men; median age, 70years) with surgically resected PDAC were included. Interobserver reproducibility was good to excellent for all MRI sequences and the 2 CT imaging phases with ICCs between .862 (95%CI: .692-.942) for fat-saturated in-phase T1-weighted sequence and .955 (95%CI: .898-.980) for portal venous phase CT images. Best accuracy in PDAC size measurement was obtained with pancreatic parenchymal phase CT images with median Δdiameters of -2mm for both readers, mean relative differences of -9% and -6% and no significant differences with dimensions at histopathological analysis (P = .051). All MRI sequences led to significant underestimation of PDAC size (median Δdiameters, -6 to -1mm; mean relative differences, -21% to -11%). Conclusions: Most accurate measurement of PDAC size is obtained with CT images obtained during the pancreatic parenchymal phase. MRI results in significant underestimation of PDAC size.

Prediction of Central Lymph Node Metastasis in cN0 Papillary Thyroid Carcinoma by CT Radiomics

To explore the feasibility of the preoperative prediction of pathological central lymph node metastasis (CLNM) status in patients with negative clinical lymph node (cN0) papillary thyroid carcinoma (PTC) using a computed tomography (CT) radiomics signature. A total of 97 PTC cN0 nodules with CLNM pathology data (pN0, with CLNM, n=59; pN1, without CLNM, n=38) in 85 patients were divided into a training set (n=69) and a validation set (n=28). For each lesion, 321 radiomic features were extracted from nonenhanced, arterial and venous phase CT images. Minimum redundancy and maximum relevance and the least absolute shrinkage and selection operator were used to find the most important features with which to develop a radiomics signature in the training set. The performance of the radiomics signature was evaluated by receiver operating characteristic curves, calibration curves and decision curve analysis . Three nonzero the least absolute shrinkage and selection operator coefficient features were selected for radiomics signature construction. The radiomics signature for distinguishing the pN0 and pN1 groups achieved areas under the curve of 0.79 (95% CI 0.67, 0.91) in the training set and 0.77 (95% CI 0.55, 0.99) in the validation set. The calibration curves demonstrated good agreement between the radiomics score-predicted probability and the pathological results in the two sets (p= 0.399, p=0.191). The decision curve analysis curves showed that the model was clinically useful. This radiomic signature could be helpful to predict CLNM status in cN0 PTC patients.

Radiomics in Addition to Computed Tomography-Based Body Composition Nomogram May Improve the Prediction of Postoperative Complications in Gastric Cancer Patients

Objectives: The study aimed to determine the impact of computed tomography (CT)-based body composition and radiomics nomogram on the prediction of postoperative complications in gastric cancer. Methods: The clinical data of 457 individuals with surgically confirmed gastric cancer, 320 patients in the training cohort (TC) and 137 patients in the validation cohort (VC), were retrospectively analyzed. Body composition data were measured using CT. Postoperative complications were graded using the Clavien-Dindo system. Dedicated radiomics prototype software was used to segment lesions and extract characteristics from preoperative portal venous-phase CT images. Clinical, radiomics, and combined models were developed using logistic regression analysis. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristic curve, and the prediction ability of the optimal model was evaluated using calibration curves and decision curve analysis (DCA). Results: Nutritional Risk Screening 2002 (NRS2002) score, sarcopenia, and blood loss were independent predictors of postoperative complications in gastric cancer. A radiomics signature was created using 19 conserved radiomics features. The nomogram based on both the clinical model and radiomics signature showed the greatest predictive performance, with AUCs of 0.763 (95% confidence interval [CI], 0.708–0.817) and 0.748 (95% CI: 0.667–0.818) in the TC and VC, respectively. The calibration curve and DCA revealed that the nomogram was beneficial in clinical practice for the preoperative prediction of postoperative complications. Conclusions: The combined model consisting of NRS2002 score, sarcopenia, blood loss, and a radiomics signature holds potential application value for the individualized prediction of postoperative complications in gastric cancer patients.

Association of CT-Based Delta Radiomics Biomarker With Progression-Free Survival in Patients With Colorectal Liver Metastases Undergo Chemotherapy.

Predicting the prognosis of patients in advance is conducive to providing personalized treatment for patients. Our aim was to predict the therapeutic efficacy and progression free survival (PFS) of patients with liver metastasis of colorectal cancer according to the changes of computed tomography (CT) radiomics before and after chemotherapy.MethodsThis retrospective study included 139 patients (397 lesions) with colorectal liver metastases who underwent neoadjuvant chemotherapy from April 2015 to April 2020. We divided the lesions into training cohort and testing cohort with a ratio of 7:3. Two - dimensional region of interest (ROI) was obtained by manually delineating the largest layers of each metastasis lesion. The expanded ROI (3 mm and 5 mm) were also included in the study to characterize microenvironment around tumor. For each of the ROI, 1,316 radiomics features were extracted from delineated plain scan, arterial, and venous phase CT images before and after neoadjuvant chemotherapy. Delta radiomics features were constructed by subtracting the radiomics features after treatment from the radiomics features before treatment. Univariate Cox regression and the Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression were applied in the training cohort to select the valuable features. Based on clinical characteristics and radiomics features, 7 Cox proportional-hazards model were constructed to predict the PFS of patients. C-index value and Kaplan Meier (KM) analysis were used to evaluate the efficacy of predicting PFS of these models. Moreover, the prediction performance of one-year PFS was also evaluated by area under the curve (AUC).ResultsCompared with the PreRad (Radiomics form pre-treatment CT images; C-index [95% confidence interval (CI)] in testing cohort: 0.614(0.552-0.675) and PostRad models (Radiomics form post-treatment CT images; 0.642(0.578-0.707), the delta model has better PFS prediction performance (Delta radiomics; 0.688(0.627-0.749). By incorporating clinical characteristics, CombDeltaRad obtains the best performance in both training cohort [C-index (95% CI): 0.802(0.772-0.832)] and the testing cohort (0.744(0.686-0.803). For 1-year PFS prediction, CombDeltaRad model obtained the best performance with AUC (95% CI) of 0.871(0.828-0.914) and 0.745 (0.651-0.838) in training cohort and testing cohort, respectively.ConclusionCT radiomics features have the potential to predict PFS in patients with colorectal cancer and liver metastasis who undergo neoadjuvant chemotherapy. By combining pre-treatment radiomics features, post-treatment radiomics features, and clinical characteristics better prediction results can be achieved.

Radiomics utilization to differentiate nonfunctional adenoma in essential hypertension and functional adenoma in primary aldosteronism

We performed the present study to investigate the role of computed tomography (CT) radiomics in differentiating nonfunctional adenoma and aldosterone-producing adenoma (APA) and outcome prediction in patients with clinically suspected primary aldosteronism (PA). This study included 60 patients diagnosed with essential hypertension (EH) with nonfunctional adenoma on CT and 91 patients with unilateral surgically proven APA. Each whole nodule on unenhanced and venous phase CT images was segmented manually and randomly split into training and test sets at a ratio of 8:2. Radiomic models for nodule discrimination and outcome prediction of APA after adrenalectomy were established separately using the training set by least absolute shrinkage and selection operator (LASSO) logistic regression, and the performance was evaluated on test sets. The model can differentiate adrenal nodules in EH and PA with a sensitivity, specificity, and accuracy of 83.3%, 78.9% and 80.6% (AUC = 0.91 [0.72, 0.97]) in unenhanced CT and 81.2%, 100% and 87.5% (AUC = 0.98 [0.77, 1.00]) in venous phase CT, respectively. In the outcome after adrenalectomy, the models showed a favorable ability to predict biochemical success (Unenhanced/venous CT: AUC = 0.67 [0.52, 0.79]/0.62 [0.46, 0.76]) and clinical success (Unenhanced/venous CT: AUC = 0.59 [0.47, 0.70]/0.64 [0.51, 0.74]). The results showed that CT-based radiomic models hold promise to discriminate APA and nonfunctional adenoma when an adrenal incidentaloma was detected on CT images of hypertensive patients in clinical practice, while the role of radiomic analysis in outcome prediction after adrenalectomy needs further investigation.