Multiphase Contrast-enhanced CT Research Articles

Extracellular volume-based scoring system for tracking tumor progression in pancreatic cancer patients receiving intraoperative radiotherapy

ObjectivesTo investigate the value of extracellular volume (ECV) derived from portal-venous phase (PVP) in predicting prognosis in locally advanced pancreatic cancer (LAPC) patients receiving intraoperative radiotherapy (IORT) with initial stable disease (SD) and to construct a risk-scoring system based on ECV and clinical-radiological features.Materials and methodsOne hundred and three patients with LAPC who received IORT demonstrating SD were enrolled and underwent multiphasic contrast-enhanced CT (CECT) before and after IORT. ECV maps were generated from unenhanced and PVP CT images. Clinical and CT imaging features were analyzed. The independent predictors of progression-free survival (PFS) determined by multivariate Cox regression model were used to construct the risk-scoring system. Time-dependent receiver operating characteristic (ROC) curve analysis and the Kaplan–Meier method were used to evaluate the predictive performance of the scoring system.ResultsMultivariable analysis revealed that ECV, rim-enhancement, peripancreatic fat infiltration, and carbohydrate antigen 19-9 (CA19-9) response were significant predictors of PFS (all p < 0.05). Time-dependent ROC of the risk-scoring system showed a satisfactory predictive performance for disease progression with area under the curve (AUC) all above 0.70. High-risk patients (risk score ≥ 2) progress significantly faster than low-risk patients (risk score < 2) (p < 0.001).ConclusionECV derived from PVP of conventional CECT was an independent predictor for progression in LAPC patients assessed as SD after IORT. The scoring system integrating ECV, radiological features, and CA19-9 response can be used as a practical tool for stratifying prognosis in these patients, assisting clinicians in developing an appropriate treatment approach.Critical relevance statementThe scoring system integrating ECV fraction, radiological features, and CA19-9 response can track tumor progression in patients with LAPC receiving IORT, aiding clinicians in choosing individual treatment strategies and improving their prognosis.Key PointsPredicting the progression of LAPC in patients receiving IORT is important.Our ECV-based scoring system can risk stratifying patients with initial SD.Appropriate prognostication can assist clinicians in developing appropriate treatment approaches.Graphical

Deep Learning Assessment of Small Renal Masses at Contrast-enhanced Multiphase CT.

Background Accurate characterization of suspicious small renal masses is crucial for optimized management. Deep learning (DL) algorithms may assist with this effort. Purpose To develop and validate a DL algorithm for identifying benign small renal masses at contrast-enhanced multiphase CT. Materials and Methods Surgically resected renal masses measuring 3 cm or less in diameter at contrast-enhanced CT were included. The DL algorithm was developed by using retrospective data from one hospital between 2009 and 2021, with patients randomly allocated in a training and internal test set ratio of 8:2. Between 2013 and 2021, external testing was performed on data from five independent hospitals. A prospective test set was obtained between 2021 and 2022 from one hospital. Algorithm performance was evaluated by using the area under the receiver operating characteristic curve (AUC) and compared with the results of seven clinicians using the DeLong test. Results A total of 1703 patients (mean age, 56 years ± 12 [SD]; 619 female) with a single renal mass per patient were evaluated. The retrospective data set included 1063 lesions (874 in training set, 189 internal test set); the multicenter external test set included 537 lesions (12.3%, 66 benign) with 89 subcentimeter (≤1 cm) lesions (16.6%); and the prospective test set included 103 lesions (13.6%, 14 benign) with 20 (19.4%) subcentimeter lesions. The DL algorithm performance was comparable with that of urological radiologists: for the external test set, AUC was 0.80 (95% CI: 0.75, 0.85) versus 0.84 (95% CI: 0.78, 0.88) (P = .61); for the prospective test set, AUC was 0.87 (95% CI: 0.79, 0.93) versus 0.92 (95% CI: 0.86, 0.96) (P = .70). For subcentimeter lesions in the external test set, the algorithm and urological radiologists had similar AUC of 0.74 (95% CI: 0.63, 0.83) and 0.81 (95% CI: 0.68, 0.92) (P = .78), respectively. Conclusion The multiphase CT-based DL algorithm showed comparable performance with that of radiologists for identifying benign small renal masses, including lesions of 1 cm or less. Published under a CC BY 4.0 license. Supplemental material is available for this article.

Trustworthy multi-phase liver tumor segmentation via evidence-based uncertainty

Multi-phase liver contrast-enhanced computed tomography (CECT) images convey the complementary multi-phase information for liver tumor segmentation (LiTS), which are crucial to assist the diagnosis of liver cancer clinically. However, the performances of existing multi-phase liver tumor segmentation (MPLiTS)-based methods suffer from redundancy and weak interpretability, resulting in the implicit unreliability of clinical applications. In this paper, we propose a novel trustworthy multi-phase liver tumor segmentation (TMPLiTS), which is a unified framework jointly conducting segmentation and uncertainty estimation. The trustworthy results could assist the clinicians to make a reliable diagnosis. Specifically, Dempster–Shafer Evidence Theory (DST) is introduced to parameterize the segmentation and uncertainty with evidence following Dirichlet distribution. The reliability of segmentation results among multi-phase CECT images is quantified explicitly. Meanwhile, a multi-expert mixture scheme (MEMS) is proposed to fuse the multi-phase evidences, which can guarantee the effect of fusion procedure based on theoretical analysis. Experimental results demonstrate the superiority of TMPLiTS compared with the state-of-the-art methods. Meanwhile, the robustness of TMPLiTS is verified, where the reliable performance can be guaranteed against the perturbations.

Improving the detection of hypo-vascular liver metastases in multiphase contrast-enhanced CT with slice thickness less than 5 mm using DenseNet

IntroductionThinner slices are more susceptible in detecting small lesions but suffer from higher statistical fluctuation. This work aimed to reduce image noise in multiphase contrast-enhanced CT reconstructed with slice thickness thinner than the clinical setting (i.e., 5 mm) using convolutional neural network (CNN) for enabling better detection of hypo-vascular liver metastasis. MethodsA DenseNet model was used to generate noise map for multiphase CT reconstructed with slice thickness of 2.5 mm and 1.25 mm. Image denoising was conducted by subtracting the CNN-generated noise map from CT images with reduced photon flux due to thinner slice thickness. The performance of DenseNet was evaluated on CT scans of electron density phantoms and patients with hypovascular liver metastases less than 1.5 cm in terms of Hounsfield Unit (HU) variation, statistical fluctuation, and contrast-to-noise ratio (CNR). ResultsThe phantom study demonstrated that the CNN-based denoising method was able to reduce statistical fluctuation in CT images reconstructed with slice thickness of 2.5 mm and 1.25 mm without causing significant edge blurring or variation in HU values. With regards to patient study, it was found that the denoised 2.5-mm and 1.25-mm slices had higher CNR than the conventional 5-mm slices for hypo-vascular liver metastases in all 4 phases of multiphase CT. ConclusionOur results demonstrated that the detection of hypo-vascular liver metastases in multiphase contrast-enhanced CT with slice thickness less than 5 mm could be improved by using the CNN-based denoising method. Implications for practiceReconstruction slice thickness has a strong influence on the image quality of CT imaging. A CNN-based denoising method was used in this work to reduce the image noise in multiphase contrast-enhanced CT reconstructed with slice thickness less than 5 mm.

Opportunistic screening with multiphase contrast-enhanced dual-layer spectral CT for osteoblastic lesions in prostate cancer compared with bone scintigraphy

Our study aimed to compare bone scintigraphy and dual-layer detector spectral CT (DLCT) with multiphase contrast enhancement for the diagnosis of osteoblastic bone lesions in patients with prostate cancer. The patients with prostate cancer and osteoblastic bone lesions detected on DLCT were divided into positive bone scintigraphy group (pBS) and negative bone scintigraphy group (nBS) based on bone scintigraphy. A total of 106 patients (57 nBS and 49 pBS) was included. The parameters of each lesion were measured from DLCT including Hounsfield unit (HU), 40–140 keV monochromatic HU, effective nuclear numbers (Zeff), and Iodine no water (InW) value in non-contrast phase (N), the arterial phase (A), and venous phase (V). The slope of the spectral curve at 40 and 100 keV, the different values of the parameters between A and N phase (A-N), V and N phase (V-N), and hybrid prediction model with multiparameters were used to differentiate pBS from nBS. Receiver operating characteristic analysis was performed to compare the area under the curve (AUC) for differentiating the pBS group from the nBS group. The value of conventional HU values, slope, and InW in A-N and V-N, and hybrid model were significantly higher in the pBS group than in the nBS group. The hybrid model of all significant parameters had the highest AUC of 0.988, with 95.5% sensitivity and 94.6% specificity. DLCT with arterial contrast enhancement phase has the potential to serve as an opportunistic screening tool for detecting positive osteoblastic bone lesions, corresponding to those identified in bone scintigraphy.

An interpretable machine learning model based on contrast-enhanced CT parameters for predicting treatment response to conventional transarterial chemoembolization in patients with hepatocellular carcinoma.

To explore the potential of pre-therapy computed tomography (CT) parameters in predicting the treatment response to initial conventional TACE (cTACE) in intermediate-stage hepatocellular carcinoma (HCC) and develop an interpretable machine learning model. This retrospective study included 367 patients with intermediate-stage HCC who received cTACE as first-line therapy from three centers. We measured the mean attenuation values of target lesions on multi-phase contrast-enhanced CT and further calculated three CT parameters, including arterial (AER), portal venous (PER), and arterial portal venous (APR) enhancement ratios. We used logistic regression analysis to select discriminative features and trained three machine learning models via 5-fold cross-validation. The performance in predicting treatment response was evaluated in terms of discrimination, calibration, and clinical utility. Afterward, a Shapley additive explanation (SHAP) algorithm was leveraged to interpret the outputs of the best-performing model. The mean diameter, ECOG performance status, and cirrhosis were the important clinical predictors of cTACE treatment response, by multiple logistic regression. Adding the CT parameters to clinical variables showed significant improvement in performance (net reclassification index, 0.318, P < 0.001). The Random Forest model (hereafter, RF-combined model) integrating CT parameters and clinical variables demonstrated the highest performance on external validation dataset (AUC of 0.800). The decision curve analysis illustrated the optimal clinical benefits of RF-combined model. This model could successfully stratify patients into responders and non-responders with distinct survival (P = 0.001). The RF-combined model can serve as a robust and interpretable tool to identify the appropriate crowd for cTACE sessions, sparing patients from receiving ineffective and unnecessary treatments.

Multi-phase features interaction transformer network for liver tumor segmentation and microvascular invasion assessment in contrast-enhanced CT

&lt;abstract&gt; &lt;p&gt;Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.&lt;/p&gt; &lt;/abstract&gt;

Serial assessment of computed tomography angiography for pulmonary and systemic arteries using a reduced contrast agent dose for the diagnosis of systemic artery-to-pulmonary artery shunts

PurposeTo evaluate the diagnostic performance and feasibility of a modified computed tomography (CT) scan protocol, we performed a serial assessment of the computed tomography angiography for pulmonary artery (CTA-P) and systemic artery (CTA-S) (CTA-PS) using a reduced contrast agent dose to diagnose systemic artery-to-pulmonary artery shunts (SPSs).Materials and methodsTwenty-five patients who underwent multiphase contrast-enhanced chest CT and conventional chest angiography were included. Three image sets (CTA-P, CTA-S, and CTA-PS) were evaluated by two board-certified radiologists. The visualization of the CT image findings associated with SPSs, such as filling defects and enhancement in the pulmonary arteries, was evaluated using a 5-point scale.ResultsThe diagnostic performance (sensitivity, specificity, and accuracy) of CT imaging findings associated with SPSs in CTA-P and CTA-PS were as follows: CTA-P, 57.1%, 87.5%, and 62.0%; CTA-PS, 81.0%, 100.0%, and 84.0%. CT findings associated with SPSs in CTA-P were significantly sensitive to the CTA-PS protocol. There were no significant differences between the CTA-S and CTA-PS protocols. The area under the curve (AUC) of the CT imaging findings associated with SPSs in the CTA-P and CTA-PS groups was 0.835 and 0.911, respectively (P = 0.191). The AUC of the CT imaging findings associated with SPSs in CTA-S and CTA-PS were 0.891 and 0.926, respectively (P = 0.373).ConclusionCTA-PS using a reduced contrast agent dose protocol could improve the overall diagnostic confidence of SPSs, owing to better visualization of CT imaging findings associated with SPSs compared to individual assessments of CTA-P or CTA-S. Therefore, CTA-PS can be used as an alternative preembolization evaluation modality to conventional angiography in patients with hemoptysis suspected of having SPSs.

Imaging-Derived Biomarkers Integrated with Clinical and Laboratory Values Predict Recurrence of Hepatocellular Carcinoma After Liver Transplantation.

To investigate the prognostic value of computed tomography (CT) derived imaging biomarkers in hepatocellular carcinoma (HCC) recurrence after liver transplantation (LT) and develop a predictive nomogram model. This retrospective study included 178 patients with histopathologically confirmed HCC who underwent liver transplantation between 2007 and 2021 at the two academic liver centers. We evaluated dedicated imaging features from baseline multiphase contrast-enhanced CT supplemented by several clinical findings and laboratory parameters. Time-to-recurrence was estimated by Kaplan-Meier analysis. Univariable Cox proportional hazard regression and multivariable Least Absolute Shrinkage and Selection Operator (LASSO) regression were used to assess independent prognostic factors for recurrence. A nomogram model was then built based on the independent factors selected through LASSO regression, to predict the probabilities of HCC recurrence at one, three, and five years. The rate of HCC recurrence after LT was 17.4% (31 of 178). The LASSO analysis revealed six independent predictors associated with an elevated risk of tumor recurrence. These predictors included the presence of peritumoral enhancement, the presence of over three tumor lesions, the largest tumor diameter greater than 3 cm, serum alpha-fetoprotein (AFP) levels exceeding 400 ng/mL, and the presence of a tumor capsule. Conversely, a history of bridging therapies was found to be correlated with a reduced risk of HCC recurrence. In addition, Kaplan-Meier curves showed patients with irregular margin, satellite nodules, or small lesions displayed shorter time-to-recurrence. Our nomogram demonstrated good performance, yielding a C-index of 0.835 and AUC values of 0.86, 0.88, and 0.85 for the predictions of 1-year, 3-year, and 5-year TTR, respectively. Imaging parameters derived from baseline contrast-enhanced CT showing malignant behavior and aggressive growth patterns, along with serum AFP and history of bridging therapies, show potential as biomarkers for predicting HCC recurrence after transplantation.

Machine learning for differentiation of lipid-poor adrenal adenoma and subclinical pheochromocytoma based on multiphase CT imaging radiomics

BackgroundThere is a paucity of research investigating the application of machine learning techniques for distinguishing between lipid-poor adrenal adenoma (LPA) and subclinical pheochromocytoma (sPHEO) based on radiomic features extracted from non-contrast and dynamic contrast-enhanced computed tomography (CT) scans of the abdomen.MethodsWe conducted a retrospective analysis of multiphase spiral CT scans, including non-contrast, arterial, venous, and delayed phases, as well as thin- and thick-thickness images from 134 patients with surgically and pathologically confirmed. A total of 52 patients with LPA and 44 patients with sPHEO were randomly assigned to training/testing sets in a 7:3 ratio. Additionally, a validation set was comprised of 22 LPA cases and 16 sPHEO cases from two other hospitals. We used 3D Slicer and PyRadiomics to segment tumors and extract radiomic features, respectively. We then applied T-test and least absolute shrinkage and selection operator (LASSO) to select features. Six binary classifiers, including K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP), were employed to differentiate LPA from sPHEO. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were compared using DeLong’s method.ResultsAll six classifiers showed good diagnostic performance for each phase and slice thickness, as well as for the entire CT data, with AUC values ranging from 0.706 to 1. Non-contrast CT densities of LPA were significantly lower than those of sPHEO (P < 0.001). However, using the optimal threshold for non-contrast CT density, sensitivity was only 0.743, specificity 0.744, and AUC 0.828. Delayed phase CT density yielded a sensitivity of 0.971, specificity of 0.641, and AUC of 0.814. In radiomics, AUC values for the testing set using non-contrast CT images were: KNN 0.919, LR 0.979, DT 0.835, RF 0.967, SVM 0.979, and MLP 0.981. In the validation set, AUC values were: KNN 0.891, LR 0.974, DT 0.891, RF 0.964, SVM 0.949, and MLP 0.979.ConclusionsThe machine learning model based on CT radiomics can accurately differentiate LPA from sPHEO, even using non-contrast CT data alone, making contrast-enhanced CT unnecessary for diagnosing LPA and sPHEO.

Beyond radiologist-level liver lesion detection on multi-phase contrast-enhanced CT images by deep learning

Accurate detection of liver lesions from multi-phase contrast-enhanced CT (CECT) scans is a fundamental step for precise liver diagnosis and treatment. However, the analysis of multi-phase contexts is heavily challenged by the misalignment caused by respiration coupled with the movement of organs. Here, we proposed an AI system for multi-phase liver lesion segmentation (named MULLET) for precise and fully automatic segmentation of real-patient CECT images. MULLET enables effectively embedding the important ROIs of CECT images and exploring multi-phase contexts by introducing a transformer-based attention mechanism. Evaluated on 1,229 CECT scans from 1,197 patients, MULLET demonstrated significant performance gains in terms of Dice, Recall, and F2 score, which are 5.80%, 6.57%, and 5.87% higher than state of the arts, respectively. MULLET has been successfully deployed in real-world settings. The deployed AI web server provides a powerful system to boost clinical workflows of liver lesion diagnosis and could be straightforwardly extended to general CECT analyses.

CT-derived extracellular volume and liver volumetry can predict posthepatectomy liver failure in hepatocellular carcinoma

ObjectivesPosthepatectomy liver failure (PHLF) is a severe complication of liver resection. We aimed to develop and validate a model based on extracellular volume (ECV) and liver volumetry derived from computed tomography (CT) for preoperative predicting PHLF in resectable hepatocellular carcinoma (HCC) patients.MethodsA total of 393 resectable HCC patients from two hospitals were enrolled and underwent multiphasic contrast-enhanced CT before surgery. A total of 281 patients from our hospital were randomly divided into a training cohort (n = 181) and an internal validation cohort (n = 100), and 112 patients from another hospital formed the external validation cohort. CT-derived ECV was measured on nonenhanced and equilibrium phase images, and liver volumetry was measured on portal phase images. The model is composed of independent predictors of PHLF. The under the receiver operator characteristic curve (AUC) and calibration curve were used to reflect the predictive performance and calibration of the model. Comparison of AUCs used the DeLong test.ResultsCT-derived ECV, measured future liver remnant (mFLR) ratio, and serum albumin were independent predictors for PHLF in resectable HCC patients. The AUC of the model was significantly higher than that of the ALBI score in the training cohort, internal validation cohort, and external validation cohort (all p < 0.001). The calibration curve of the model showed good consistency in the training cohort and the internal and external validation cohorts.ConclusionsThe novel model contributes to the preoperative prediction of PHLF in resectable HCC patients.Critical relevance statementThe novel model combined CT–derived extracellular volume, measured future liver remnant ratio, and serum albumin outperforms the albumin–bilirubin score for predicting posthepatectomy liver failure in patients with resectable hepatocellular carcinoma.Key points• CT-derived ECV correlated well with the fibrosis stage of the background liver.• CT-derived ECV and mFLR ratio were independent predictors for PHLF in HCC.• The AUC of the model was higher than the CT-derived ECV and mFLR ratio.• The model showed a superior predictive performance than that of the ALBI score.Graphical

Dual-Source Contrast-Enhanced Multiphasic CT of the Liver Using Low Voltage (70 kVp): Feasibility of a Reduced Radiation Dose and a 50% of Contrast Dose.

This study investigated the feasibility of both a reduced radiation dose and a 50% of contrast dose in multiphasic CT of the liver with a 70 kVp protocol compared with a standard-tube-voltage protocol derived from dual-energy (DE) CT (blended DE protocol) with a full-dose contrast-agents in the same patient group. This study included 46 patients who underwent multiphasic contrast-enhanced dynamic CT of the liver with both a 70 kVp and a blended DE protocols. For quantitative analysis, median CT values for the liver, aorta, and portal vein, as well as signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), were measured and calculated. In addition, as a qualitative analysis, the contrast effect and overall image quality of the abdominal organs were evaluated on a five-point scale. CNR and SNR of the hepatic parenchyma were not significantly different between the 70kV protocol and the Blended DE protocol in all phases. The 70 kVp protocol showed significantly better image quality compared with the blended DE protocol in the arterial phase (p = 0.035) and the equilibrium layer phase (p = 0.016). A 70 kVp CT protocol in combination with a reduced radiation dose and half-dose iodine load is feasible for multiphasic dynamic CT of the liver by maintaining the contrast enhancement effects and image quality in comparison with the blended DE CT protocol.

A CT-Based Clinical, Radiological and Radiomic Machine Learning Model for Predicting Malignancy of Solid Renal Tumors (UroCCR-75).

Differentiating benign from malignant renal tumors is important for patient management, and it may be improved by quantitative CT features analysis including radiomic. This study aimed to compare performances of machine learning models using bio-clinical, conventional radiologic and 3D-radiomic features for the differentiation of benign and malignant solid renal tumors using pre-operative multiphasic contrast-enhanced CT examinations. A unicentric retrospective analysis of prospectively acquired data from a national kidney cancer database was conducted between January 2016 and December 2020. Histologic findings were obtained by robotic-assisted partial nephrectomy. Lesion images were semi-automatically segmented, allowing for a 3D-radiomic features extraction in the nephrographic phase. Conventional radiologic parameters such as shape, content and enhancement were combined in the analysis. Biological and clinical features were obtained from the national database. Eight machine learning (ML) models were trained and validated using a ten-fold cross-validation. Predictive performances were evaluated comparing sensitivity, specificity, accuracy and AUC. A total of 122 patients with 132 renal lesions, including 111 renal cell carcinomas (RCCs) (111/132, 84%) and 21 benign tumors (21/132, 16%), were evaluated (58 +/- 14 years, men 74%). Unilaterality (100/111, 90% vs. 13/21, 62%; p = 0.02), necrosis (81/111, 73% vs. 8/21, 38%; p = 0.02), lower values of tumor/cortex ratio at portal time (0.61 vs. 0.74, p = 0.01) and higher variation of tumor/cortex ratio between arterial and portal times (0.22 vs. 0.05, p = 0.008) were associated with malignancy. A total of 35 radiomics features were selected, and "intensity mean value" was associated with RCCs in multivariate analysis (OR = 0.99). After ten-fold cross-validation, a C5.0Tree model was retained for its predictive performances, yielding a sensitivity of 95%, specificity of 42%, accuracy of 87% and AUC of 0.74. Our machine learning-based model combining clinical, radiologic and radiomics features from multiphasic contrast-enhanced CT scans may help differentiate benign from malignant solid renal tumors.

Enhancement pattern of the pancreatic parenchyma predicts postpancreatectomy acute pancreatitis after pancreaticoduodenectomy.

To assess the association between the enhancement pattern of the pancreatic parenchyma on preoperative multiphasic contrast-enhanced computed tomography (CECT) and the occurrence of postpancreatectomy acute pancreatitis (PPAP) after pancreaticoduodenectomy (PD). A total of 513 patients who underwent PD were retrospective enrolled. The CT attenuation values of the nonenhanced (N), arterial (A), portal venous (P), and late (L) phases in the pancreatic parenchyma were measured on preoperative multiphasic CECT. The enhancement pattern was quantized by the CT attenuation value ratios in each phase. Receiver operating characteristic (ROC) curve analyses were computed to evaluate predictive performance. Regression analyses were used to identify independent risk factors for PPAP. PPAP developed in 102 patients (19.9%) and was associated with increased morbidity and a worse postoperative course. The A/P ratio, P/L ratio, and A/L ratio were significantly higher in the PPAP group. On the ROC analysis, the A/L ratio and A/P ratio both performed well in predicting PPAP (A/L: AUC = 0.7579; A/P: AUC = 0.7497). On multivariate analyses, the A/L ratio > 1.29 (OR 4.30 95% CI: 2.62-7.06, p < 0.001) and A/P ratio > 1.13 (OR 5.02 95% CI: 2.98-8.45, p < 0.001) were both independent risk factors of PPAP in each model. The enhancement pattern of the pancreatic parenchyma on multiphasic preoperative CECT is a good predictor of the occurrence of PPAP after PD, which could help clinicians identify high-risk patients or enable selective enhance recovery protocols. Preoperative identification of patients at high risk for postpancreatectomy acute pancreatitis by enhancement patterns of the pancreatic parenchyma allows surgeons to tailor their perioperative management and take precautions. PPAP is associated with increased risk of postoperative complications and a worse postoperative course. A rapid-decrease enhancement pattern of the pancreatic parenchyma is related to the occurrence of PPAP. The A/L and A/P ratios were both independent risk factors of PPAP in each multivariate model.

Small arteriole sign: an imaging feature for staging T4a colon cancer.

By analyzing the distribution of existing and newly proposed staging imaging features in pT1-3 and pT4a tumors, we searched for a salient feature and validated its diagnostic performance. Preoperative multiphase contrast-enhanced CT images of the training cohort were retrospectively collected at three centers from January 2016 to December 2017. We used the chi-square test to analyze the distribution of several stage-related imaging features in pT1-3 and pT4a tumors, including small arteriole sign (SAS), outer edge of the intestine, tumor invasion range, and peritumoral adipose tissue. Preoperative multiphase contrast-enhanced CT images of the validation cohort were retrospectively collected at Beijing Cancer Hospital from January 2018 to December 2018. The diagnostic performance of the selected imaging feature, including accuracy, sensitivity, and specificity, was validated and compared with the conventional clinical tumor stage (cT) by the McNemar test. In the training cohort, a total of 268 patients were enrolled, and only SAS was significantly different between pT1-3 and pT4a tumors. The accuracy, sensitivity, and specificity of the SAS and conventional cT in differentiating T1-3 and T4a tumors were 94.4%, 81.6%, and 97.3% and 53.7%, 32.7%, and 58.4%, respectively (all p < 0.001). In the validation cohort, a total of 135 patients were collected. The accuracy, sensitivity, and specificity of the SAS and the conventional cT were 93.3%, 76.2%, and 96.5% and 62.2%, 38.1%, and 66.7%, respectively (p < 0.001, p = 0.021, p < 0.001). Small arteriole sign positivity, an indirect imaging feature of serosa invasion, may improve the accuracy of identifying T4a colon cancer. Small arteriole sign helps to distinguish T1-3 and T4a colon cancer and further improves the accuracy of preoperative CT staging of colon cancer. • The accuracy of preoperative CT staging of colon cancer is not ideal, especially for T4a tumors. • Small arteriole sign (SAS) is a newly defined imaging feature that shows the appearance of tumor-supplying arterioles at the site where they penetrate the intestine wall. • SAS is an indirect imaging marker of tumor invasion into the serosa with a great value in distinguishing between T1-3 and T4a colon cancer.

Automated CT LI-RADS v2018 scoring of liver observations using machine learning: A multivendor, multicentre retrospective study

Assessment of computed tomography (CT)/magnetic resonance imaging Liver Imaging Reporting and Data System (LI-RADS) v2018 major features leads to substantial inter-reader variability and potential decrease in hepatocellular carcinoma diagnostic accuracy. We assessed the performance and added-value of a machine learning (ML)-based algorithm in assessing CT LI-RADS major features and categorisation of liver observations compared with qualitative assessment performed by a panel of radiologists. High-risk patients as per LI-RADS v2018 with pathologically proven liver lesions who underwent multiphase contrast-enhanced CT at diagnosis between January 2015 and March 2019 in seven centres in five countries were retrospectively included and randomly divided into a training set (n= 84 lesions) and a test set (n= 345 lesions). An ML algorithm was trained to classify non-rim arterial phase hyperenhancement, washout, and enhancing capsule as present, absent, or of uncertain presence. LI-RADS major features and categories were compared with qualitative assessment of two independent readers. The performance of a sequential use of the ML algorithm and independent readers were also evaluated in a triage and an add-on scenario in LR-3/4 lesions. The combined evaluation of three other senior readers was used as reference standard. A total of 318 patients bearing 429 lesions were included. Sensitivity and specificity for LR-5 in the test set were 0.67 (95% CI, 0.62-0.72) and 0.91 (95% CI, 0.87-0.96) respectively, with 242 (70.1%) lesions accurately categorised. Using the ML algorithm in a triage scenario improved the overall performance for LR-5. (0.86 and 0.93 sensitivity, 0.82 and 0.76 specificity, 78% and 82.3% accuracy for the two independent readers). Quantitative assessment of CT LI-RADS v2018 major features is feasible and diagnoses LR-5 observations with high performance especially in combination with the radiologist's visual analysis in patients at high-risk for HCC. Assessment of CT/MRI LI-RADS v2018 major features leads to substantial inter-reader variability and potential decrease in hepatocellular carcinoma diagnostic accuracy. Rather than replacing radiologists, our results highlight the potential benefit from the radiologist-artificial intelligence interaction in improving focal liver lesions characterisation by using the developed algorithm as a triage tool to the radiologist's visual analysis. Such an AI-enriched diagnostic pathway may help standardise and improve the quality of analysis of liver lesions in patients at high risk for HCC, especially in non-expert centres in liver imaging. It may also impact the clinical decision-making and guide the clinician in identifying the lesions to be biopsied, for instance in patients with multiple liver focal lesions.

Quantitative analysis with multiphase contrast-enhanced computed tomography to evaluate residual tumor activity of hepatocellular carcinoma after DEB-TACE.

Most hepatocellular carcinomas (HCC) treated by transcatheter arterial chemoembolization with drug-eluting beads (DEB-TACE) are characterized by coagulation necrosis; therefore, it is often difficult to distinguish enhancement in the arterial phase that would lead to false negative evaluation. This study aimed to evaluate the specificity and sensitivity of the difference value of multiphase contrast-enhanced computed tomography (CECT) in predicting residual tumor activity in HCC lesions after DEB-TACE. This retrospective diagnostic study analyzed CECT images of 73 HCC lesions in 57 patients 20 to 40 days (average 28 days) after DEB-TACE treatment at our Hospital from January to December 2019. Postoperative pathology or digital subtraction angiography images were used as references. Residual tumor activity after the first intervention was determined based on the presence of tumor staining in digital subtraction angiography or the postoperative pathological discovery of HCC tumor cells. A significant difference was observed between the active and inactive residual groups in ∆ HU difference between CT values of arterial phase and non-contrast scans (AN, P = .000), difference between CT values of venous phase and non-contrast scans (VN, P = .000), difference between CT values of delay phase and non-contrast scans (DN, P = .000), (difference between CT values of venous and arterial phase scans, P = .001), and (difference between CT values of delay and arterial phase scans, P = .005). No statistically significant difference was observed between the delayed and venous phases (difference between CT values of delay and venous phase scans, P = .361). The area under the curve (AUC) of the ROC curve showed that the diagnostic efficacies in difference in CT value of AN (AUC = 0.976), VN (AUC = 0.927), and DN (AUC = 0.924) were higher, and their cutoff values were 4.86, 12.065, 20.19 HU with their sensitivities of 93.3%, 84.4%, 77.8% and specificities of 100%, 96.4%, and 100%, respectively. difference in CT value values of AN, VN, DN, difference between CT values of venous and arterial phase scans and difference between CT values of delay and arterial phase scans can sensitively detect residual tumor activity 20-40 days after DEB-TACE. Thus, more sensitive active residual foci were detected using all 3 enhanced phases rather than only the arterial phase. Quantitative analysis of multiphase CECT can detect residual tumor activity in an early and noninvasive manner, which can provide time for patients to receive early follow-up treatment.

Prediction of Ki-67 expression in gastrointestinal stromal tumors using radiomics of plain and multiphase contrast-enhanced CT.

To study the value of radiomics models based on plain and multiphase contrast-enhanced CT to predict Ki-67 expression in gastrointestinal stromal tumors (GISTs). A total of 215 patients with GISTs were retrospectively analyzed, including 150 patients in one hospital as the training set and 65 patients in another hospital as the external verification set. The tumor at the largest level of CT images was delineated as the region of interest (ROI). The maximum diameter of the ROI was defined as the tumor size. A total of 851 radiomics features were extracted from each ROI by 3D Slicer Radiomics. After dimensionality reduction, three machine learning classification algorithms including logistic regression (LR), random forest (RF), and support vector machine (SVM) were used for Ki-67 expression prediction. Using a multivariable logistic model, a nomogram was established to predict the expression of Ki-67 individually. Delong tests showed that the SVM models had the highest accuracy in the arterial phase (Z value 0.217-1.139) and venous phase (Z value 0.022-1.396). For the plain phase, LR and SVM models had the highest accuracy (Z value 0.874-1.824, 1.139-1.763). For the delayed phase, LR models had the highest accuracy (Z value 0.056-1.824). For the combined phase, RF models had the highest accuracy (Z value 0.232-1.978). There was no significant difference among the above models for KI-67 expression prediction (Z value 0.022-1.978). A nomogram was developed with a C-index of 0.913 (95% CI, 0.878 to 0.956). Radiomics of both plain and enhanced CT images could accurately predict the expression of Ki-67 in GIST. For patients who were not suitable to use contrast agents, plain scan could be used as an alternative. CT radiomics could accurately predict the expression of Ki-67 in GIST, which has a great clinical value in reflecting the proliferative activity of tumor cells and helping determine whether a patient is suitable for adjuvant therapy with imatinib. • Radiomics of both plain and enhanced CT images could accurately predict the expression of Ki-67 in GIST. • For patients who were not suitable to use contrast agents, plain scan could be used as an alternative. • A radiomics nomogram was developed to allow personalized preoperative evaluation with high accuracy.

Radiogenomic Associations Clear Cell Renal Cell Carcinoma: An Exploratory Study

Introduction: This study investigates how quantitative texture analysis can be used to non-invasively identify novel radiogenomic correlations with clear cell renal cell carcinoma (ccRCC) biomarkers. Methods: The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma open-source database was used to identify 190 sets of patient genomic data that had corresponding multiphase contrast-enhanced CT images in The Cancer Imaging Archive. 2,824 radiomic features spanning fifteen texture families were extracted from CT images using a custom-built MATLAB software package. Robust radiomic features with strong inter-scanner reproducibility were selected. Random forest, AdaBoost, and elastic net machine learning (ML) algorithms evaluated the ability of the selected radiomic features to predict the presence of 12 clinically relevant molecular biomarkers identified from the literature. ML analysis was repeated with cases stratified by stage (I/II vs. III/IV) and grade (1/2 vs. 3/4). 10-fold cross validation was used to evaluate model performance. Results: Before stratification by tumor grade and stage, radiomics predicted the presence of several biomarkers with weak discrimination (AUC 0.60–0.68). Once stratified, radiomics predicted KDM5C, SETD2, PBRM1, and mTOR mutation status with acceptable to excellent predictive discrimination (AUC ranges from 0.70 to 0.86). Conclusions: Radiomic texture analysis can potentially identify a variety of clinically relevant biomarkers in patients with ccRCC and may have a prognostic implication.