Automatic Urinary Stone Detection System for Abdominal Non-Enhanced CT Images Reduces the Burden on Radiologists.

To develop a fully automatic urinary stone detection system (kidney, ureter, and bladder) and to test it in a real clinical environment. The local institutional review board approved this retrospective single-center study that used non-enhanced abdominopelvic CT scans from patients admitted urology (uPatients) and emergency (ePatients). The uPatients were randomly divided into training and validation sets in a ratio of 3:1. We designed a cascade urinary stone map location-feature pyramid networks (USm-FPNs) and innovatively proposed a ureter distance heatmap method to estimate the ureter position on non-enhanced CT to further reduce the false positives. The performances of the system were compared using the free-response receiver operating characteristic curve and the precision-recall curve. This study included 811 uPatients and 356 ePatients. At stone level, the cascade detector USm-FPNs has the mean of false positives per scan (mFP) 1.88 with the sensitivity 0.977 in validation set, and mFP was further reduced to 1.18 with the sensitivity 0.977 after combining the ureter distance heatmap. At patient level, the sensitivity and precision were as high as 0.995 and 0.990 in validation set, respectively. In a real clinical set of ePatients (27.5% of patients contain stones), the mFP was 1.31 with as high as sensitivity 0.977, and the diagnostic time reduced by > 20% with the system help. A fully automatic detection system for entire urinary stones on non-enhanced CT scans was proposed and reduces obviously the burden on junior radiologists without compromising sensitivity in real emergency data.

CT-based radiomics with various classifiers for histological differentiation of parotid gland tumors.

Objective: This study assessed whether radiomics features could stratify parotid gland tumours accurately based on only noncontrast CT images and validated the best classifier of different radiomics models. Methods: In this single-centre study, we retrospectively recruited 249 patients with a diagnosis of pleomorphic adenoma (PA), Warthin tumour (WT), basal cell adenoma (BCA) or malignant parotid gland tumours (MPGTs) from June 2020 to August 2022. Each patient was randomly classified into training and testing cohorts at a ratio of 7:3, and then, pairwise comparisons in different parotid tumour groups were performed. CT images were transferred to 3D-Slicer software and the region of interest was manually drawn for feature extraction. Feature selection methods were performed using the intraclass correlation coefficient, t test and least absolute shrinkage and selection operator. Five common classifiers, namely, random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbours (KNN) and general Bayesian network (Gnb), were selected to build different radiomics models. The receiver operating characteristic curve, area under the curve (AUC), accuracy, sensitivity, specificity and F-1 score were used to assess the prediction performances of these models. The calibration of the model was calculated by the Hosmer-Lemeshow test. DeLong's test was utilized for comparing the AUCs. Results: The radiomics model based on the RF, SVM, Gnb, LR, LR and RF classifiers obtained the highest AUC in differentiating PA from MPGTs, WT from MPGTs, BCA from MPGTs, PA from WT, PA from BCA, and WT from BCA, respectively. Accordingly, the AUC and the accuracy of the model for each classifier were 0.834 and 0.71, 0.893 and 0.79, 0.844 and 0.79, 0.902 and 0.88, 0.602 and 0.68, and 0.861 and 0.94, respectively. Conclusion: Our study demonstrated that noncontrast CT-based radiomics could stratify refined pathological types of parotid tumours well but could not sufficiently differentiate PA from BCA. Different classifiers had the best diagnostic performance for different parotid tumours. Our study findings add to the current knowledge on the differential diagnosis of parotid tumours.

Assessment of myocardial bridging and the pericoronary fat attenuation index on coronary computed tomography angiography: predicting coronary artery disease risk.

BACKGROUND: The fat attenuation index (FAI) is a radiological parameter that represents pericoronary adipose tissue (PCAT) inflammation, along with myocardial bridging (MB), which leads to pathological shear stress in the coronary vessels; both are associated with coronary atherosclerosis. In the present study, we assessed the predictive value of FAI values and MB parameters through coronary computed tomography angiography (CCTA) for predicting the risk of coronary atherosclerosis and vulnerable plaque in patients with MB. METHODS: We included 428 patients who underwent CCTA and were diagnosed with MB. FAI values, MB parameters, and high-risk coronary plaque (HRP) characteristics were recorded. The subjects were classified into two groups (A and B) according to the absence or presence of coronary plaque in the segment proximal to the MB. Group B was further divided into Groups B1 (HRP-positive) and B2 (HRP-negative) according to the HRP characteristic classification method. The differences among the groups were analysed. Multiple logistic regression analysis was performed to determine the independent correlation between FAI values and MB parameters and coronary atherosclerosis and vulnerable plaque risk. RESULTS: Compared to the subjects in Group A, those in Group B presented greater MB lengths, MB depths and muscle index values, more severe MB systolic stenosis and higher FAIlesion values (all P < 0.05). In multivariate logistic analysis, age (OR 1.076, P < 0.001), MB systolic stenosis (OR 1.102, P < 0.001) and FAIlesion values (OR 1.502, P < 0.001) were independent risk factors for the occurrence of coronary atherosclerosis. Compared to subjects in Group B2, those in Group B1 presented greater MB lengths and higher FAI values (both P < 0.05). However, only the FAIlesion value was an independent factor for predicting HRP (OR 1.641, P < 0.001). CONCLUSION: In patients with MB, MB systolic stenosis was associated with coronary plaque occurrence in the segment proximal to the MB. The FAI value was not only closely related to coronary atherosclerosis occurrence but also associated with plaque vulnerability. FAI values may provide more significant value in the prediction of coronary atherosclerosis than MB parameters in CCTA.

A nomogram model integrating LI-RADS features and radiomics based on contrast-enhanced magnetic resonance imaging for predicting microvascular invasion in hepatocellular carcinoma falling the Milan criteria.

PURPOSE: To establish and validate a nomogram model incorporating both liver imaging reporting and data system (LI-RADS) features and contrast enhanced magnetic resonance imaging (CEMRI)-based radiomics for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) falling the Milan criteria. METHODS: In total, 161 patients with 165 HCCs diagnosed with MVI (n = 99) or without MVI (n = 66) were assigned to a training and a test group. MRI LI-RADS characteristics and radiomics features selected by the LASSO algorithm were used to establish the MRI and Rad-score models, respectively, and the independent features were integrated to develop the nomogram model. The predictive ability of the nomogram was evaluated with receiver operating characteristic (ROC) curves. RESULTS: The risk factors associated with MVI (P<0.05) were related to larger tumor size, nonsmooth margin, mosaic architecture, corona enhancement and higher Rad-score. The areas under the ROC curve (AUCs) of the MRI feature model for predicting MVI were 0.85 (95% CI: 0.78-0.92) and 0.85 (95% CI: 0.74-0.95), and those for the Rad-score were 0.82 (95% CI: 0.73-0.90) and 0.80 (95% CI: 0.67-0.93) in the training and test groups, respectively. The nomogram presented improved AUC values of 0.87 (95% CI: 0.81-0.94) in the training group and 0.89 (95% CI: 0.81-0.98) in the test group (P<0.05) for predicting MVI. The calibration curve and decision curve analysis demonstrated that the nomogram model had high goodness-of-fit and clinical benefits. CONCLUSIONS: The nomogram model can effectively predict MVI in patients with HCC falling within the Milan criteria and serves as a valuable imaging biomarker for facilitating individualized decision-making.

Feasibility of T1 mapping with histogram analysis for the diagnosis and staging of liver fibrosis: Preclinical results.

PURPOSE: To compare the diagnostic accuracy of parameters derived from the histogram analysis of precontrast, 10-min hepatobiliary phase (HBP) and 20-min HBP T1 maps for staging liver fibrosis (LF). METHODS: LF was induced in New Zealand white rabbits by subcutaneous injections of carbon tetrachloride for 4-16 weeks (n = 120), and 20 rabbits injected with saline served as controls. Precontrast, 10-min and 20-min HBP modified Look-Locker inversion recovery (MOLLI) T1 mapping was performed. Histogram analysis of T1 maps was performed, and the mean, median, skewness, kurtosis, entropy, inhomogeneity and 10th/25th/75th/90th percentiles of T1native, T110min and T120min were derived. Quantitative histogram parameters were compared. For significant parameters, further receiver operating characteristic (ROC) analyses were performed to evaluate the potential diagnostic performance in differentiating LF stages. RESULTS: Finally, 17, 20, 21, 21 and 20 rabbits were included for the F0, F1, F2, F3, and F4 pathological grades of fibrosis, respectively. The mean/75th of T1native, entropy of T110min and entropy/mean/median/10th of T120min demonstrated a significant good correlation with the LF stage (|r| = 0.543-0.866, all P < 0.05). The 75th of T1native, entropy10min, and entropy20min were the three most reliable imaging markers in reflecting the stage of LF. The area under the ROC curve of entropy20min was larger than that of entropy10min (P < 0.05 for LF ≥ F2, ≥F3, and ≥ F4) and the 75th of T1native (P < 0.05 for LF ≥ F2 and ≥ F3) for staging LF. CONCLUSION: Magnetic resonance histogram analysis of T1 maps, particularly the entropy derived from 20-min HBP T1 mapping, is promising for predicting the LF stage.

Dynamic contrast-enhanced MRI with Gd-EOB-DTPA for the quantitative assessment of early-stage liver fibrosis induced by carbon tetrachloride in rabbits.

PURPOSE: To explore quantitative parameters obtained by dynamic contrast-enhanced magnetic resonance imaging (DCE MRI) with Gd-EOB-DTPA in discriminating early-stage liver fibrosis (LF) in a rabbit model. MATERIALS AND METHODS: LF was established in 60 rabbits by the injection of 50% CCl4 oil solution, whereas 30 rabbits served as the control group. All rabbits underwent pathological examination to determine the LF stage using the METAVIR classification system. DCE MRI was performed, and quantitative parameters, including Ktrans, Kep, Ve, Vp and Re were measured and evaluated among the different LF stages using spearman correlation coefficients and receiver operating characteristic curve. RESULTS: In all, 24, 25, and 22 rabbits had stage F0, stage F1, and stage F2 LF, respectively. Ktrans (r = 0.803) increased, and Kep (r = -0.495) and Re (r = -0.701) decreased with LF stage progression (P < 0.001), while no significant correlation was found for Ve or Vp. Ktrans and Re were significantly different between all LF stage pairs compared (F0 vs. F1, F0 vs. F2, F1 vs. F2, F0 vs. F1-F2, P < 0.05). With the exception of F0 vs. F1, Kep differed significantly between stages (P < 0.05). The AUC of Ktrans was higher than that of other quantitative parameters, with an AUC of 0.92, 0.99, 0.94 and 0.92 for staging F0 vs. F1, F0 vs. F2, F1 vs. F2, and F0 vs. F1-F2, respectively. CONCLUSION: Among quantitative parameters of Gd-EOB-DTPA DCE MRI, Ktrans was the best predictor for quantitatively differentiating early-stage LF.