A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma.

PURPOSE: This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC). METHODS: 320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis. RESULTS: Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05). CONCLUSIONS: A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

Deep Learning Radiomics Model of Dynamic Contrast-Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma.

BACKGROUND: Vessels encapsulating tumor cluster (VETC) is a critical prognostic factor and therapeutic predictor of hepatocellular carcinoma (HCC). However, noninvasive evaluation of VETC remains challenging. PURPOSE: To develop and validate a deep learning radiomic (DLR) model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of VETC and prognosis of HCC. STUDY TYPE: Retrospective. POPULATION: A total of 221 patients with histologically confirmed HCC and stratified this cohort into training set (n = 154) and time-independent validation set (n = 67). FIELD STRENGTH/SEQUENCE: A 1.5 T and 3.0 T; DCE imaging with T1-weighted three-dimensional fast spoiled gradient echo. ASSESSMENT: Histological specimens were used to evaluate VETC status. VETC+ cases had a visible pattern (≥5% tumor area), while cases without any pattern were VETC-. The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI and reproducibility of segmentation was evaluated. Deep neural network and machine learning (ML) classifiers (logistic regression, decision tree, random forest, SVM, KNN, and Bayes) were used to develop nine DLR, 54 ML and clinical-radiological (CR) models based on AP, PP, and DP of DCE-MRI for evaluating VETC status and association with recurrence. STATISTICAL TESTS: The Fleiss kappa, intraclass correlation coefficient, receiver operating characteristic curve, area under the curve (AUC), Delong test and Kaplan-Meier survival analysis. P value <0.05 was considered as statistical significance. RESULTS: Pathological VETC+ were confirmed in 68 patients (training set: 46, validation set: 22). In the validation set, DLR model based on peritumor PP (peri-PP) phase had the best performance (AUC: 0.844) in comparison to CR (AUC: 0.591) and ML (AUC: 0.672) models. Significant differences in recurrence rates between peri-PP DLR model-predicted VETC+ and VETC- status were found. DATA CONCLUSIONS: The DLR model provides a noninvasive method to discriminate VETC status and prognosis of HCC patients preoperatively. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 2.

A Comprehensive Model Based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging Can Better Predict the Preoperative Histological Grade of Breast Cancer Than a Radiomics Model.

Background: Histological grade is an important prognostic factor for patients with breast cancer and can affect clinical decision-making. From a clinical perspective, developing an efficient and non-invasive method for evaluating histological grading is desirable, facilitating improved clinical decision-making by physicians. This study aimed to develop an integrated model based on radiomics and clinical imaging features for preoperative prediction of histological grade invasive breast cancer. Methods: In this retrospective study, we recruited 211 patients with invasive breast cancer and randomly assigned them to either a training group (n=147) or a validation group (n=64) with a 7:3 ratio. Patients were classified as having low-grade tumors, which included grade I and II tumors, or high-grade tumors, which included grade III tumors. Three models were constructed based on basic clinical features, radiomics features, and the sum of the two. To assess diagnostic performance of the radiomics models, we employed measures such as receiver operating characteristic (ROC) curve, decision curve analysis (DCA), accuracy, sensitivity, and specificity, and the predictive performance of the three models was compared using the DeLong test and net reclassification improvement (NRI). Results: The area under the curve (AUC) of the clinical model, radiomics model, and comprehensive model was 0.682, 0.833, and 0.882 in the training set and 0.741, 0.751, and 0.836 in the validation set, respectively. NRI analysis confirmed that the combined model was better than the other two models in predicting the histological grade of breast cancer (NRI=21.4% in the testing cohort). Conclusion: Compared with the other models, the comprehensive model based on the combination of basic clinical features and radiomics features exhibits more significant potential for predicting histological grade and can better assist clinicians in optimal decision-making.

18F-FDG PET/CT radiomics signature and clinical parameters predict progression-free survival in breast cancer patients: A preliminary study.

Introduction: This study aimed to investigate the feasibility of predicting progression-free survival (PFS) in breast cancer patients using pretreatment 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) radiomics signature and clinical parameters. Methods: Breast cancer patients who underwent 18F-FDG PET/CT imaging before treatment from January 2012 to December 2020 were eligible for study inclusion. Eighty-seven patients were randomly divided into training (n = 61) and internal test sets (n = 26) and an additional 25 patients were used as the external validation set. Clinical parameters, including age, tumor size, molecular subtype, clinical TNM stage, and laboratory findings were collected. Radiomics features were extracted from preoperative PET/CT images. Least absolute shrinkage and selection operators were applied to shrink feature size and build a predictive radiomics signature. Univariate and multivariate Cox proportional hazards models and Kaplan-Meier analysis were used to assess the association of rad-score and clinical parameter with PFS. Nomograms were constructed to visualize survival prediction. C-index and calibration curve were used to evaluate nomogram performance. Results: Eleven radiomics features were selected to generate rad-score. The clinical model comprised three parameters: clinical M stage, CA125, and pathological N stage. Rad-score and clinical-model were significantly associated with PFS in the training set (P< 0.01) but not the test set. The integrated clinical-radiomics (ICR) model was significantly associated with PFS in both the training and test sets (P< 0.01). The ICR model nomogram had a significantly higher C-index than the clinical model and rad-score in the training and test sets. The C-index of the ICR model in the external validation set was 0.754 (95% confidence interval, 0.726-0.812). PFS significantly differed between the low- and high-risk groups stratified by the nomogram (P = 0.009). The calibration curve indicated the ICR model provided the greatest clinical benefit. Conclusion: The ICR model, which combined clinical parameters and preoperative 18F-FDG PET/CT imaging, was able to independently predict PFS in breast cancer patients and was superior to the clinical model alone and rad-score alone.

Preoperative MRI features for characterization of vessels encapsulating tumor clusters and microvascular invasion in hepatocellular carcinoma.

PURPOSE: This study aimed to analyze imaging features based on preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for the identification of vessels encapsulating tumor clusters (VETC)-microvascular invasion (MVI) in hepatocellular carcinoma (HCC), VM-HCC pattern. METHODS: Patients who underwent hepatectomy and preoperative DCE-MRI between January 2015 and March 2021 were retrospectively analyzed. Clinical and imaging features related to VM-HCC (VETC + /MVI-, VETC-/MVI +, VETC + /MVI +) and Non-VM-HCC (VETC-/MVI-) were determined by multivariable logistic regression analyses. Early and overall recurrence were determined using the Kaplan-Meier survival curve. Indicators of early and overall recurrence were identified using the Cox proportional hazard regression model. RESULTS: In total, 221 patients (177 men, 44 women; median age, 60 years; interquartile range, 52-66 years) were evaluated. The multivariable logistic regression analyses revealed fetoprotein > 400 ng/mL (odds ratio [OR] = 2.17, 95% confidence interval [CI] 1.07, 4.41, p = 0.033), intratumor vascularity (OR 2.15, 95% CI 1.07, 4.31, p = 0.031), and enhancement pattern (OR 2.71, 95% CI 1.17, 6.03, p = 0.019) as independent predictors of VM-HCC. In Kaplan-Meier survival analysis, intratumor vascularity was associated with early and overall recurrence (p < 0.05). CONCLUSION: Based on DCE-MRI, intratumor vascularity can be used to characterize VM-HCC and is of prognostic significance for recurrence in patients with HCC.

Venous gas caused by emphysematous pyelonephritis: a case report and review of literature.

BACKGROUND: Emphysematous pyelonephritis (EPN) is a potentially life-threatening disease caused by a gas-producing necrotizing bacterial infection that involves the renal parenchyma, collecting system, and/or perinephric tissue. EPN is often complicated by a previous diagnosis of diabetes mellitus, and venous air bubbles are an uncommon complication of it. We describe a 52-year-old woman who was admitted in coma, with a history of vomiting, and was found to have EPN with air bubbles in the uterine veins. We discuss the presentation, diagnosis, and pathogenesis of this uncommon but clinically significant event, and briefly review other case reports of venous gas or thrombosis caused by EPN. CASE PRESENTATION: We report the case of a 52-year-old woman with past history of type 2 diabetes mellitus, presenting with loss of consciousness after vomiting for half a day. Abdominal computed tomography scan revealed unilateral EPN with air bubbles in the uterine veins. The blood, pus, and urine cultures were positive for extended-spectrum beta-lactamase-producing Escherichia coli. The patient's condition improved well after conservative management comprising supportive measures, broad-spectrum antibiotics, percutaneous drainage therapy, and an open operation. CONCLUSIONS: Venous air bubbles are rare but fatal complication of EPN. Early diagnosis and treatment are critical to ensure good results.

Development and Validation of a Clinical-Image Model for Quantitatively Distinguishing Uncertain Lipid-Poor Adrenal Adenomas From Nonadenomas.

Background: There remains a demand for a practical method of identifying lipid-poor adrenal lesions. Purpose: To explore the predictive value of computed tomography (CT) features combined with demographic characteristics for lipid-poor adrenal adenomas and nonadenomas. Materials and Methods: We retrospectively recruited patients with lipid-poor adrenal lesions between January 2015 and August 2021 from two independent institutions as follows: Institution 1 for the training set and the internal validation set and Institution 2 for the external validation set. Two radiologists reviewed CT images for the three sets. We performed a least absolute shrinkage and selection operator (LASSO) algorithm to select variables; subsequently, multivariate analysis was used to develop a generalized linear model. The probability threshold of the model was set to 0.5 in the external validation set. We calculated the sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) for the model and radiologists. The model was validated and tested in the internal validation and external validation sets; moreover, the accuracy between the model and both radiologists were compared using the McNemar test in the external validation set. Results: In total, 253 patients (median age, 55 years [interquartile range, 47-64 years]; 135 men) with 121 lipid-poor adrenal adenomas and 132 nonadenomas were included in Institution 1, whereas another 55 patients were included in Institution 2. The multivariable analysis showed that age, male, lesion size, necrosis, unenhanced attenuation, and portal venous phase attenuation were independently associated with adrenal adenomas. The clinical-image model showed AUCs of 0.96 (95% confidence interval [CI]: 0.91, 0.98), 0.93 (95% CI: 0.84, 0.97), and 0.86 (95% CI: 0.74, 0.94) in the training set, internal validation set, and external validation set, respectively. In the external validation set, the model showed a significantly and non-significantly higher accuracy than reader 1 (84% vs. 65%, P = 0.031) and reader 2 (84% vs. 69%, P = 0.057), respectively. Conclusions: Our clinical-image model displayed good utility in differentiating lipid-poor adrenal adenomas. Further, it showed better diagnostic ability than experienced radiologists in the external validation set.

Diagnostic value of the relative enhancement ratio of the portal venous phase to unenhanced CT in the identification of lipid-poor adrenal tumors.

PURPOSE: Adrenal incidentalomas are common lesions found on abdominal imaging, most of which are lipid-rich adrenal adenomas. Imaging diagnoses differentiating lipid-poor adrenal adenomas (LPA) from non-adenomas (NA) are presently challenging to perform. The aim of the study was to investigate the diagnostic performance of the relative enhancement ratio parameter in identifying LPA from NA. METHODS: We retrospectively evaluated consecutively presenting patients with lipid-poor adrenal lesions (January 2015 to August 2021). Lesions were divided into LPA and NA (including hyperenhancing and hypoenhancing NA). Kruskal-Wallis and Bonferroni tests were used to determine the differences in feature parameters between these three groups. Receiver operating characteristic curve analysis was performed to determine the sensitivity for diagnosing LPA and NA at 95% specificity; the parameters were compared using the McNemar test. RESULTS: A total of 253 patients (mean age, 55 ± 12 years; 135 men), 121 with LPA and 132 with NA, were analyzed herein. The sensitivity (achieved at 95% specificity) of the relative enhancement ratio was higher than that of unenhanced attenuation in differentiating LPA from NA (60% vs. 52%, p = 0.064). The relative enhancement ratio yielded a higher sensitivity than unenhanced attenuation (79% vs. 59%, p < 0.001) in differentiating LPA from hypoenhancing NA, and a lower sensitivity (26% vs. 69%, p < 0.001) in differentiating LPA from hyperenhancing NA. CONCLUSION: The relative enhancement ratio showed better diagnostic performance than unenhanced attenuation in differentiating LPA from hypoenhancing NA, while simultaneously showing poor diagnostic performance in identifying LPA from all NA.

Can Radiomics Provide Additional Diagnostic Value for Identifying Adrenal Lipid-Poor Adenomas From Non-Adenomas on Unenhanced CT?

Background: It is difficult for radiologists to differentiate adrenal lipid-poor adenomas from non-adenomas; nevertheless, this differentiation is important as the clinical interventions required are different for adrenal lipid-poor adenomas and non-adenomas. Purpose: To develop an unenhanced computed tomography (CT)-based radiomics model for identifying adrenal lipid-poor adenomas to assist in clinical decision-making. Materials and methods: Patients with adrenal lesions who underwent CT between January 2015 and August 2021 were retrospectively recruited from two independent institutions. Patients from institution 1 were randomly divided into training and test sets, while those from institution 2 were used as the external validation set. The unenhanced attenuation and tumor diameter were measured to build a conventional model. Radiomics features were extracted from unenhanced CT images, and selected features were used to build a radiomics model. A nomogram model combining the conventional and radiomic features was also constructed. All the models were developed in the training set and validated in the test and external validation sets. The diagnostic performance of the models for identifying adrenal lipid-poor adenomas was compared. Results: A total of 292 patients with 141 adrenal lipid-poor adenomas and 151 non-adenomas were analyzed. Patients with adrenal lipid-poor adenomas tend to have lower unenhanced attenuation and smoother image textures. In the training set, the areas under the curve of the conventional, radiomic, and nomogram models were 0.94, 0.93, and 0.96, respectively. There was no difference in diagnostic performance between the conventional and nomogram models in all datasets (all p < 0.05). Conclusions: Our unenhanced CT-based nomogram model could effectively distinguish adrenal lipid-poor adenomas. The diagnostic power of conventional unenhanced CT imaging features may be underestimated, and further exploration is worthy.

No staghorn calculi and none/mild hydronephrosis may be risk factors for severe bleeding complications after percutaneous nephrolithotomy.

BACKGROUND: To explore the risk factors for severe bleeding complications after percutaneous nephrolithotomy (PCNL) according to the modified Clavien scoring system. METHODS: We retrospectively analysed 2981 patients who received percutaneous nephrolithotomies from January 2014 to December 2020. Study inclusion criteria were PCNL and postoperative mild or severe renal haemorrhage in accordance with the modified Clavien scoring system. Mild bleeding complications included Clavien 2, while severe bleeding complications were greater than Clavien 3a. It has a good prognosis and is more likely to be underestimated and ignored in retrospective studies in bleeding complications classified by Clavien 1, so no analysis about these was conducted in this study. Clinical features, medical comorbidities and perioperative characteristics were analysed. Chi-square, independent t tests, Pearson's correlation, Fisher exact tests, Mann-Whitney and multivariate logistic regression were used as appropriate. RESULTS: Of the 2981 patients 70 (2.3%), met study inclusion criteria, consisting of 51 men and 19 women, 48 patients had severe bleeding complications. The remaining 22 patients had mild bleeding. Patients with postoperative severe bleeding complications were more likely to have no or slight degree of hydronephrosis and have no staghorn calculi on univariate analysis (p < 0.05). Staghorn calculi (OR, 95% CI, p value 0.218, 0.068-0.700, 0.010) and hydronephrosis (OR, 95% CI, p value 0.271, 0.083-0.887, 0.031) were independent predictors for severe bleeding via multivariate logistic regression analysis. Other factors, such as history of PCNL, multiple kidney stones, site of puncture calyx and mean corrected intraoperative haemoglobin drop were not related to postoperative severe bleedings. CONCLUSIONS: The absence of staghorn calculi and a no or mild hydronephrosis were related to an increased risk of post-percutaneous nephrolithotomy severe bleeding complications.

Quantitative and semi-quantitative CT assessments of lung lesion burden in COVID-19 pneumonia.

This study aimed to clarify and provide clinical evidence for which computed tomography (CT) assessment method can more appropriately reflect lung lesion burden of the COVID-19 pneumonia. A total of 244 COVID-19 patients were recruited from three local hospitals. All the patients were assigned to mild, common and severe types. Semi-quantitative assessment methods, e.g., lobar-, segmental-based CT scores and opacity-weighted score, and quantitative assessment method, i.e., lesion volume quantification, were applied to quantify the lung lesions. All four assessment methods had high inter-rater agreements. At the group level, the lesion load in severe type patients was consistently observed to be significantly higher than that in common type in the applications of four assessment methods (all the p < 0.001). In discriminating severe from common patients at the individual level, results for lobe-based, segment-based and opacity-weighted assessments had high true positives while the quantitative lesion volume had high true negatives. In conclusion, both semi-quantitative and quantitative methods have excellent repeatability in measuring inflammatory lesions, and can well distinguish between common type and severe type patients. Lobe-based CT score is fast, readily clinically available, and has a high sensitivity in identifying severe type patients. It is suggested to be a prioritized method for assessing the burden of lung lesions in COVID-19 patients.

Preoperative Contrast-Enhanced MRI in Differentiating Glioblastoma From Low-Grade Gliomas in The Cancer Imaging Archive Database: A Proof-of-Concept Study.

PURPOSE: This study aimed to develop a repeatable MRI-based machine learning model to differentiate between low-grade gliomas (LGGs) and glioblastoma (GBM) and provide more clinical information to improve treatment decision-making. METHODS: Preoperative MRIs of gliomas from The Cancer Imaging Archive (TCIA)-GBM/LGG database were selected. The tumor on contrast-enhanced MRI was segmented. Quantitative image features were extracted from the segmentations. A random forest classification algorithm was used to establish a model in the training set. In the test phase, a random forest model was tested using an external test set. Three radiologists reviewed the images for the external test set. The area under the receiver operating characteristic curve (AUC) was calculated. The AUCs of the radiomics model and radiologists were compared. RESULTS: The random forest model was fitted using a training set consisting of 142 patients [mean age, 52 years ± 16 (standard deviation); 78 men] comprising 88 cases of GBM. The external test set included 25 patients (14 with GBM). Random forest analysis yielded an AUC of 1.00 [95% confidence interval (CI): 0.86-1.00]. The AUCs for the three readers were 0.92 (95% CI 0.74-0.99), 0.70 (95% CI 0.49-0.87), and 0.59 (95% CI 0.38-0.78). Statistical differences were only found between AUC and Reader 1 (1.00 vs. 0.92, respectively; p = 0.16). CONCLUSION: An MRI radiomics-based random forest model was proven useful in differentiating GBM from LGG and showed better diagnostic performance than that of two inexperienced radiologists.