Nephrographic Phase Research Articles

Predicting the ISUP grade of clear cell renal cell carcinoma with multiparametric MR and multiphase CT radiomics.

To investigate externally validated magnetic resonance (MR)-based and computed tomography (CT)-based machine learning (ML) models for grading clear cell renal cell carcinoma (ccRCC). Patients with pathologically proven ccRCC in 2009-2018 were retrospectively included for model development and internal validation; patients from another independent institution and The Cancer Imaging Archive dataset were included for external validation. Features were extracted from T1-weighted, T2-weighted, corticomedullary-phase (CMP), and nephrographic-phase (NP) MR as well as precontrast-phase (PCP), CMP, and NP CT. CatBoost was used for ML-model investigation. The reproducibility of texture features was assessed using intraclass correlation coefficient (ICC). Accuracy (ACC) was used for ML-model performance evaluation. Twenty external and 440 internal cases were included. Among 368 and 276 texture features from MR and CT, 322 and 250 features with good to excellent reproducibility (ICC ≥ 0.75) were included for ML-model development. The best MR- and CT-based ML models satisfactorily distinguished high- from low-grade ccRCCs in internal (MR-ACC = 73% and CT-ACC = 79%) and external (MR-ACC = 74% and CT-ACC = 69%) validation. Compared to single-sequence or single-phase images, the classifiers based on all-sequence MR (71% to 73% in internal and 64% to 74% in external validation) and all-phase CT (77% to 79% in internal and 61% to 69% in external validation) images had significant increases in ACC. MR- and CT-based ML models are valuable noninvasive techniques for discriminating high- from low-grade ccRCCs, and multiparameter MR- and multiphase CT-based classifiers are potentially superior to those based on single-sequence or single-phase imaging. • Both the MR- and CT-based machine learning models are reliable predictors for differentiating high- from low-grade ccRCCs. • ML models based on multiparameter MR sequences and multiphase CT images potentially outperform those based on single-sequence or single-phase images in ccRCC grading.

Can whole-tumor radiomics-based CT analysis better differentiate fat-poor angiomyolipoma from clear cell renal cell caricinoma: compared with conventional CT analysis?

This study aimed to discriminate fat-poor angiomyolipoma (fp-AML) from clear cell renal cell carcinoma (ccRCC) by constructing radiomics-based logistic classifiers in comparison with conventional computed tomography (CT) analysis at three CT phases. Twenty-two fp-AML patients and 62 ccRCC patients who were pathologically identified were enrolled in this study, and underwent three-phase (unenhanced phase, UP; corticomedullary phase, CMP; nephrographic phase, NP) CT examinations. Whole-tumor regions of interest (ROIs) were contoured in ITK software by two radiologists. Radiomic features were dimensionally reduced by means of ANOVA + MW, correlation analysis, and LASSO. Four radiomics logistic classifiers including the UP group, CMP group, NP group, and sum group were built, and the radiomic scores (rad-scores) were calculated. After collecting the qualitative and quantitative conventional CT characteristics, the conventional CT analysis logistic classifier and the radiomics-based logistic classifier were constructed. The receiver operating characteristic curve (ROC) was constructed to evaluate the validity of each classifier. The area under curve (AUC) of the conventional CT analysis logistic classifier including angular interface, cyst degeneration, and pseudocapsule was 0.935 (95% CI 0.860-0.977). Regarding logistic classifiers for radiomics analysis, the AUCs of the UP group were 0.950 (95% CI 0.895-1.000) and 0.917 (95% CI 0.801-1.000) in the training set and testing set, respectively, which were higher than those of the CMP and NP groups. The AUCs of the sum group were observed to be the highest. The top three selected features for the UP and sum groups belonged to GLCM parameters and histogram parameters. The radiomics-based logistic classifier encompassed cyst degeneration, pseudocapsule, and sum rad-score, and the AUC of the model was 0.988 (95% CI 0.935-1.000). Whole-tumor radiomics-based CT analysis is superior to conventional CT analysis in the differentiation of fp-AML from ccRCC. Cyst degeneration, pseudocapsule, and sum rad-score are the most significant factors. The radiomics analysis of the UP group shows a higher AUC than that of the CMP and NP groups.

Cost-effectiveness of dual-energy CT versus multiphasic single-energy CT and MRI for characterization of incidental indeterminate renal lesions

To evaluate the cost-effectiveness of DECT versus multiphasic CT and MRI for characterizing small incidentally detected indeterminate renal lesions using a Markov Monte Carlo decision-analytic model. Incidental renal lesions are commonly encountered due to the increasing utilization of medical imaging and the increasing prevalence of renal lesions with age. Currently recommended imaging modalities to further characterize incidental indeterminate renal lesions have some inherent drawbacks. Single-phase DECT may overcome these limitations, but its cost-effectiveness remains uncertain. A decision-analytic (Markov) model was constructed to estimate life expectancy and lifetime costs for otherwise healthy 64-year-old patients with small (≤ 4cm) incidentally detected, indeterminate renal lesions on routine imaging (e.g., ultrasound or single-phase CT). Three strategies for evaluating renal lesions for enhancement were compared: multiphase SECT (e.g., true unenhanced and nephrographic phase), multiphasic MRI, and single-phase DECT (nephrographic phase in dual-energy mode). The model incorporated modality-specific diagnostic test performance, incidence, and prevalence of incidental renal cell carcinomas (RCCs), effectiveness, costs, and health outcomes. An incremental cost-effectiveness analysis was performed to identify strategy preference at willingness-to-pay (WTP) thresholds of $50,000 and $100,000 per quality-adjusted life-year (QALY) gained. Deterministic and probabilistic sensitivity analysis were performed. In the base case analysis, expected mean costs per patient undergoing characterization of incidental renal lesions were $2567 for single-phase DECT, $3290 for multiphasic CT, and $3751 for multiphasic MRI. Associated quality-adjusted life-years were the highest for single-phase DECT at 0.962, for multiphasic MRI it was 0.940, and was the lowest for multiphasic CT at 0.925. Because of lower associated costs and higher effectiveness, the single-phase DECT strategy dominated the other two strategies. Single-phase DECT is potentially more cost-effective than multiphasic SECT and MRI for evaluating small incidentally detected indeterminate renal lesions.

Comparative evaluation of the role of CT urography in diagnosis of urinary tract in patients with hematuria

Background and Aim: CT urography is a single comprehensive modality for the diagnosis of patients suspected with hematuria. Hence, the present study was designed to evaluate the efficacy of the diagnostic role of CTU in comparison with other diagnostic modalities. Material and Methods: A total of 83 patients suspected with hematuria between 18-75 years of age presented at the Department of Radio-diagnosis, Kasturba Medical College (KMC), Manipal University, and Mangalore were selected. The patients were subjected to 3 phase CT examination after obtaining informed consent—first was an initial non-contrast phase followed by a nephrographic phase and then pyelographic phase. Patients' demographic details viz. age, gender, and clinical manifestations were recorded. Assessment parameters like sensitivity, specificity, positive predictive value, and negative predictive value were analyzed. Results: The majority of study subjects with hematuria i.e. 28.92% belonged to the age group of 60-70 years followed by 25.30% in 50-60 years and 20.48% fallen in the age group of 40-50 years with male predominance. Ureteroscopy was done for 17 cases, nephroscopy for 4 cases. 6 were radiodense calculi and 2 were radiolucent calculi. USG showed renal, PUJ and one VUJ calculus and hydronephrosis but it was only after CTU ureteric calculi were detected. 9 patients had both renal and ureteric calculi. Cystoscopy was done for 25 cases, out of which 17 cases showed bladder transitional cell carcinoma (TCC). In 14 cases, 11 out of 14 cases showed masses confined to the kidney (

Distinguishing Infiltrative Transitional Cell Carcinoma From Other Infiltrative Lesions of the Kidneys on Multidetector Computed Tomography

Background: The infiltrative renal growth pattern is either characteristic of certain prototype transitional cell carcinomas (TCCs) or other mimickers. Specific computed tomography (CT) features may be used to differentiate TCCs from other overlap findings. Accurate early diagnosis is important to improve treatment outcome and prevent morbidity and mortality from delayed specific treatment.
 Objective: To determine the multidetector computed tomography (MDCT) features that discriminate infiltrative TCCs from other infiltrative renal lesions.
 Methods: A retrospective review was performed on patients with infiltrative, proven renal lesions on CT from January 2008 to July 2014. Individual CT sequences were analyzed for lesion number, location, size, and density on unenhanced and nephrographic phase scans. Final diagnoses were confirmed by histopathology or clinical or imaging follow-up after treatment. The CT findings of intrarenal TCCs and mimics were compared by using logistic regression analysis.
 Results: In 73 patients, there were 18 (24.6%) TCCs, 2 (2.7%) renal cell carcinomas (RCCs), 11 (15.1%) lymphomas, 15 (20.5%) renal parenchymal metastases, 17 (23.3%) infections, and 10 (13.7%) other diagnosis. Compared to non-TCCs, intrarenal TCCs were more likely to be solitary lesion, lack intralesional calcification, less avidly enhance in nephrographic phase and infiltrate pelvicalyceal and perinephric tissue (P < .05).
 Conclusions: Five MDCT features including solitary lesion, absence of calcification and poor absolute, relative enhancement, pelvicalyceal system involvement, and perinephric tissue invasion were significantly associated with intrarenal and infiltrative TCCs.

Differentiation of Upper Urinary Tract Lesions Using MDCT: Benign Vs Malignant

To evaluate the accuracy of multiple detector computed tomography (MDCT) in differentiating benign and malignant lesions of upper urinary tract (UUT). Fifty-four patients with 55 suspected UUT lesions were included in the study. All patients underwent MDCT scan with nephrographic and excretory phases. The unenhanced phase was also performed in 38 cases. The final diagnosis was made by histology in 48 lesions: 43-after surgery, 5-after biopsy and by MDCT follow-up over at least 15 months in the remaining 7 lesions. The following CT features were evaluated: number of lesions, lesion appearance (mass or wall thickening), presence of calcifications, internal border appearance (smooth or irregular), and size and enhancement (presence or absence). The relationship between imaging characteristics and pathology (benign vs malignant) was assessed with logistic regression, univariable diagnostic accuracy, and with classification and regression tree analysis. Patients with mass morphology had a significantly higher probability of malignancy (odds ratio [OR]: 3.73, 95%CI: 1.02-13.72, p = 0.047) compared to patients with thickened wall morphology. The presence of an irregular internal border was also significantly associated with malignancy (OR: 12.14, 95%CI: 2.95-50.06, p < 0.001). No significant associations were found between malignancy and lesion size (p = 0.29), calcifications (p = 0.93) or enhancement (p = 0.68). Mass morphology and irregular internal border are reliable signs to suggest malignancy in UUT lesions.

Imaging of Renal Cancer

Renal masses are common incidental findings on cross-sectional imaging. Accurate characterization of renal masses is essential to guide management. Renal mass CT protocol comprises of a good quality noncontrast, corticomedullary and nephrographic phases, with each phase providing complementary information for diagnosis. Attenuation measurements in different phases are central to the 'golden-rules' in renal mass imaging in the characterization of renal masses. Newer modalities like dual energy CT scan obviate need for repeat imaging by generation of iodine-overlay image and also help in eliminating artifactual pseudoenhancement which can be problematic, especially in small endophytic cysts. Contrast- enhanced ultrasound (CEUS) is extremely sensitive in identification of enhancing components in indeterminate masses, especially in the setting of renal failure as the microbubbles are not excreted via the renal route. The Bosniak classification for renal cystic masses has been revised in 2019 to standardize terminology and further improve upon the original version. The current version includes CT and MRI, although CEUS is yet to be included. Image- guided biopsy of renal mass helps confirm the diagnosis and also gives information regarding the subtype and grading and is useful in avoiding overtreatment of benign entities, and in active surveillance. Multiparametric MRI can potentially help avoid needle biopsy in a subset of patients by accurate characterization through a previously validated algorithm.

Texture analysis and machine learning algorithms accurately predict histologic grade in small (&lt; 4 cm) clear cell renal cell carcinomas: a pilot study

To predict the histologic grade of small clear cell renal cell carcinomas (ccRCCs) using texture analysis and machine learning algorithms. Fifty-two noncontrast (NC), 26 corticomedullary (CM) phase, and 35 nephrographic (NG) phase CTs of small (< 4cm) surgically resected ccRCCs were retrospectively identified. Surgical pathology classified the tumors as low- or high-Fuhrman histologic grade. The axial image with the largest cross-sectional tumor area was exported and segmented. Six histogram and 31 texture (gray-level co-occurrences (GLC) and gray-level run-lengths (GLRL)) features were calculated for each tumor in each phase. T testing compared feature values in low- and high-grade ccRCCs, with a (Benjamini-Hochberg) false discovery rate of 10%. Area under the receiver operating curve (AUC) was calculated for each feature to assess prediction of low- and high-grade ccRCCs in each phase. Histogram, texture, and combined histogram and texture data sets were used to train and test four algorithms (k-nearest neighbor (KNN), support vector machine (SVM), random forests, and decision tree) with tenfold cross-validation; AUCs were calculated for each algorithm in each phase to assess prediction of low- and high-grade ccRCCs. Zero, 23, and 0 features in the NC, CM, and NG phases had statistically significant differences between low and high-grade ccRCCs. CM histogram skewness and GLRL short run emphasis had the highest AUCs (0.82) in predicting histologic grade. All four algorithms had the highest AUCs (0.97) predicting histologic grade using CM histogram features. The algorithms' AUCs decreased using histogram or texture features from NC or NG phases. The histologic grade of small ccRCCs can be accurately predicted with machine learning algorithms using CM histogram features, which outperform NC and NG phase image data.

Contrast-enhanced computed tomography findings of canine primary renal tumors including renal cell carcinoma, lymphoma, and hemangiosarcoma.

In veterinary medicine, abdominal ultrasonography is used to rank the differential diagnosis of renal lesions. However, a conventional sonographic examination may show nonspecific findings. The purpose of this study was to assess the computed tomography (CT) findings of canine renal tumors, including renal cell carcinoma (RCC), lymphoma, and hemangiosarcoma (HSA). In this retrospective study, the following CT parameters were recorded for each dog: 1) extent of renal involvement of tumors, 2) enhancement pattern, 3) number of renal tumors, 4) renal tumor vessel enhancement in the corticomedullary phase, 5) presence of lymphadenopathy and lung metastasis, and 6) attenuation values of the renal tumors on the pre- and post-contrast corticomedullary, nephrographic, and excretory phase images. Fifteen dogs met the inclusion criteria, of which nine had RCCs, four had lymphomas, and two had HSAs. RCCs tended to show heterogeneous enhancement and unilateral renal involvement, and vessel enhancement was detected in the corticomedullary phase in dogs with RCC. Conversely, renal lymphomas showed homogeneous enhancement, bilateral renal involvement, and multiple masses; in these dogs, no vessel enhancement was detected in the corticomedullary phase, and the incidence of lymphadenopathy was low. However, in dogs with lymphadenopathy, the renal lymphoma was associated with regionally severe lymphadenopathy. Finally, renal HSAs tended to show heterogeneous enhancement with a non-enhanced area and unilateral renal involvement; in these dogs, vessel enhancement was detected in the nephrographic phase, with the enhancement expanding around the vessel. These findings had no significant differences. Further studies with a larger sample size are required to examine the association between CT and histopathological findings.

Examining the upper urinary tract in patients with hematuria-time to revise the CT urography protocol?

Three-phase CT urography (CTU) is the gold standard for evaluating the upper urinary tract in patients with hematuria. We aimed to evaluate the accuracy of CTU for detecting upper urothelial cell carcinomas (UCC) in patients with hematuria and negative cystoscopy. Secondly, we aimed to determine the tumor visibility on each CTU phase. This retrospective study included all patients with hematuria referred to CTU after a negative cystoscopy during 2016 and 2017. The original CTU reports were dichotomized as negative or positive. All patient charts were reviewed after a minimum of 18-month follow-up in order to register missed cancers. The results of biopsies and clinical follow-up were used as the reference standard. Two reviewers retrospectively evaluated the tumor visibility of each CT sequence in all true-positive CTUs. We included 376 patients with hematuria who underwent CTU after a negative cystoscopy. Macroscopic and microscopic hematuria occurred in 87% (327) and 13% (49), respectively. The incidence of upper urothelial cell carcinoma was 1.9% (7), and the sensitivity of CTU was 100% (95% CI, 59-100), specificity was 99% (95% CI, 98-100), positive predictive value was 88% (95% CI, 47-99), and negative predictive value was 100% (95% CI, 99-100). The accuracy was 99% (95% CI, 90-100). All UCCs were visible on the nephrographic phase for both reviewers. CTU is highly accurate for detecting upper UCCs. All cases were seen on the nephrographic phase. This suggests that the CTU protocol can be simplified. • CT urography is highly accurate for detecting upper urothelial cell carcinomas. • All cancers were seen on the nephrographic phase. • All cancers were detected in patients with macroscopic hematuria.

Clear cell renal cell carcinoma: Machine learning-based computed tomography radiomics analysis for the prediction of WHO/ISUP grade

PurposeTo evaluate the performance of machine learning (ML)-based computed tomography (CT) radiomics analysis for discriminating between low grade (WHO/ISUP I-II) and high grade (WHO/ISUP III-IV) clear cell renal cell carcinomas (ccRCCs). MethodsA total of 164 low grade and 107 high grade ccRCCs were retrospectively analyzed in this study. Radiomic features were extracted from corticomedullary phase (CMP) and nephrographic phase (NP) CT images. Intraclass correlation coefficient (ICC) was calculated to quantify the feature’s reproducibility. The training and validation cohort consisted of 163 and 108 cases. Least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were k-NearestNeighbor (KNN), Logistic Regression (LR), multilayer perceptron (MLP), Random Forest (RF), and support vector machine (SVM). The performance of classifiers was mainly evaluated and compared by certain metrics. ResultsSeven CMP features (ICC range, 0.990-0.999) and seven NP features (ICC range, 0.931-0.999) were selected. The accuracy of CMP, NP and the combination of CMP and NP ranged from 82.2%–85.9 %, 82.8%–94.5 % and 86.5%–90.8 % in the training cohort, and 90.7%–95.4%, 77.8%–79.6 % and 91.7%–93.5 % in the validation cohort. The AUC of CMP, NP and the combination of CMP and NP ranged from 0.901 to 0.938, 0.912 to 0.976, 0.948 to 0.968 in the training cohort, and 0.957 to 0.974, 0.856 to 0.875, 0.960 to 0.978 in the validation cohort. ConclusionsML-based CT radiomics analysis can be used to predict the WHO/ISUP grade of ccRCCs preoperatively.

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

PurposeTo explore the value of CT-enhanced quantitative features combined with machine learning for differential diagnosis of renal chromophobe cell carcinoma (chRCC) and renal oncocytoma (RO).MethodsSixty-one cases of renal tumors (chRCC = 44; RO = 17) that were pathologically confirmed at our hospital between 2008 and 2018 were retrospectively analyzed. All patients had undergone preoperative enhanced CT scans including the corticomedullary (CMP), nephrographic (NP), and excretory phases (EP) of contrast enhancement. Volumes of interest (VOIs), including lesions on the images, were manually delineated using the RadCloud platform. A LASSO regression algorithm was used to screen the image features extracted from all VOIs. Five machine learning classifications were trained to distinguish chRCC from RO by using a fivefold cross-validation strategy. The performance of the classifier was mainly evaluated by areas under the receiver operating characteristic (ROC) curve and accuracy.ResultsIn total, 1029 features were extracted from CMP, NP, and EP. The LASSO regression algorithm was used to screen out the four, four, and six best features, respectively, and eight features were selected when CMP and NP were combined. All five classifiers had good diagnostic performance, with area under the curve (AUC) values greater than 0.850, and support vector machine (SVM) classifier showed a diagnostic accuracy of 0.945 (AUC 0.964 ± 0.054; sensitivity 0.999; specificity 0.800), showing the best performance.ConclusionsAccurate preoperative differential diagnosis of chRCC and RO can be facilitated by a combination of CT-enhanced quantitative features and machine learning.

Association of tumor grade, enhancement on multiphasic CT and microvessel density in patients with clear cell renal cell carcinoma.

Clear cell renal cell carcinoma (ccRCC) comprises nearly 90% of all diagnosed RCC subtypes and has the worst prognosis and highest metastatic potential. The strongest prognostic factors for patients with ccRCC include histological subtype and Fuhrman grade, which are incorporated into prognostic models. Since ccRCC is a highly vascularized tumor, there may be differences in enhancement patterns on multidetector CT (MDCT) due to the hemodynamics and microvessel density (MVD) of the lesions. This may provide a noninvasive method to characterize incidentally detected low- and high-grade ccRCCs on MDCT. The purpose of our study was to determine the correlation between MDCT enhancement parameters, ccRCC MVD, and Fuhrman grade to determine its utility and value in assessing tumor vascularity and grade in vivo. In this retrospective, HIPAA-compliant, institutional review board-approved study with waiver of informed consent, 127 consecutive patients with 89 low-grade (LG), and 43 high-grade (HG) ccRCCs underwent preoperative four-phase MDCT. A 3D volume of interest (VOI) was obtained for every tumor and absolute enhancement and the wash-in/wash-out of enhancement for each phase was assessed. Immunohistochemistry on resected specimens was used to quantify MVD. Linear regression and Pearson correlation were used to investigate the strength of the association between3D VOI enhancement and MVD. Stepwise logistic regression analysis determined independent predictors of HG ccRCC. Cut-off values and odds Ratio (OR) with 95% CIs were reported. The clinical, radiomic, and pathologic features with the highest performance in the stepwiselogistic regression analysis were evaluated using receiver operator characteristics (ROC) and area under the curve (AUC). Absolute enhancement in the nephrographic phase < 52.1 Hounsfield Units (HU) (HR 0.979, 95% CI 0.964-0.994, p value = 0.006), lesion size > 4.3cm (HR 1.450, 95% CI 1.211-1.738, p value < 0.001), and an intratumoral MVD < 15% (HR 0.932, 95% CI 0.867-1.002, p value = 0.058) were independent predictors of HG ccRCC with an AUC of 0.818 (95% CI 0.725-0.911). HG ccRCCs had a significant association between3D VOI enhancement and MVD in each post-contrast phase (r2 = 0.238 to 0.455, p < 0.05). Absolute enhancement of the entire lesion obtained from a 3DVOI in the nephrographic phase on preoperative MDCT can provide quantitative data that are a significant, independent predictor of a high-grade clear cell RCC and can be used to assess tumor vascularity and grade in vivo.

A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma.

To develop and validate a radiomics nomogram for preoperative differentiating renal angiomyolipoma without visible fat (AML.wovf) from homogeneous clear cell renal cell carcinoma (hm-ccRCC). Ninety-nine patients with AML.wovf (n = 36) and hm-ccRCC (n = 63) were divided into a training set (n = 80) and a validation set (n = 19). Radiomics features were extracted from corticomedullary phase and nephrographic phase CT images. A radiomics signature was constructed and a radiomics score (Rad-score) was calculated. Demographics and CT findings were assessed to build a clinical factors model. Combined with the Rad-score and independent clinical factors, a radiomics nomogram was constructed. Nomogram performance was assessed with respect to calibration, discrimination, and clinical usefulness. Fourteen features were used to build the radiomics signature. The radiomics signature showed good discrimination in the training set (AUC [area under the curve], 0.879; 95%; confidence interval [CI], 0.793-0.966) and the validation set (AUC, 0.846; 95% CI, 0.643-1.000). The radiomics nomogram showed good calibration and discrimination in the training set (AUC, 0.896; 95% CI, 0.810-0.983) and the validation set (AUC, 0.949; 95% CI, 0.856-1.000) and showed better discrimination capability (p < 0.05) compared with the clinical factor model (AUC, 0.788; 95% CI, 0.683-0.893) in the training set. Decision curve analysis demonstrated the nomogram outperformed the clinical factors model and radiomics signature in terms of clinical usefulness. The CT-based radiomics nomogram, a noninvasive preoperative prediction tool that incorporates the Rad-score and clinical factors, shows favorable predictive efficacy for differentiating AML.wovf from hm-ccRCC, which might assist clinicians in tailoring precise therapy. • Differential diagnosis between AML.wovf and hm-ccRCC is rather difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, demographics, and CT findings facilitates differentiation of AML.wovf from hm-ccRCC with improved diagnostic efficacy. • The CT-based radiomics nomogram might spare unnecessary surgery for AML.wovf.

Radiomics of small renal masses on multiphasic CT: accuracy of machine learning–based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat

To investigate the discriminative capabilities of different machine learning-based classification models on the differentiation of small (< 4cm) renal angiomyolipoma without visible fat (AMLwvf) and renal cell carcinoma (RCC). This study retrospectively collected 163 patients with pathologically proven small renal mass, including 118 RCC and 45 AMLwvf patients. Target region of interest (ROI) delineation, followed by texture feature extraction, was performed on a representative slice with the largest lesion area on each phase of the four-phase CT images. Fifteen concatenations of the four-phasic features were fed into 224 classification models (built with 8 classifiers and 28 feature selection methods), classification performances of the 3360 resultant discriminative models were compared, and the top-ranked features were analyzed. Image features extracted from the unenhanced phase (UP) CT image demonstrated dominant classification performances over features from other three phases. The two discriminative models "SVM + t_score" and "SVM + relief" achieved the highest classification AUC of 0.90. The 10 top-ranked features from UP included 1 shape feature, 5 first-order statistics features, and 4 texture features, where the shape feature and the first-order statistics features showed superior discriminative capabilities in differentiating RCC vs. AMLwvf through the t-SNE visualization. Image features extracted from UP are sufficient to generate accurate differentiation between AMLwvf and RCC using machine learning-based classification model. • Radiomics extracted from unenhanced CT are sufficient to accurately differentiate angiomyolipoma without visible fat and renal cell carcinoma using machine learning-based classification model. • The highest discriminative models achieved an AUC of 0.90 and were based on the analysis of unenhanced CT, alone or in association with images obtained at the nephrographic phase. • Features related to shape and to histogram analysis (first-order statistics) showed superior discrimination compared with gray-level distribution of the image (second-order statistics, commonly called texture features).

Image quality and pathology assessment in CT Urography: when is the low-dose series sufficient?

BackgroundOur aim was to compare CT images from native, nephrographic and excretory phases using image quality criteria as well as the detection of positive pathological findings in CT Urography, to explore if the radiation burden to the younger group of patients or patients with negative outcomes can be reduced.MethodsThis is a retrospective study of 40 patients who underwent a CT Urography examination on a 192-slice dual source scanner. Image quality was assessed for four specific renal image criteria from the European guidelines, together with pathological assessment in three categories: renal, other abdominal, and incidental findings without clinical significance. Each phase was assessed individually by three radiologists with varying experience using a graded scale. Certainty scores were derived based on the graded assessments. Statistical analysis was performed using visual grading regression (VGR). The limit for significance was set at p = 0.05.ResultsFor visual reproduction of the renal parenchyma and renal arteries, the image quality was judged better for the nephrogram phase (p < 0.001), whereas renal pelvis/calyces and proximal ureters were better reproduced in the excretory phase compared to the native phase (p < 0.001). Similarly, significantly higher certainty scores were obtained in the nephrogram phase for renal parenchyma and renal arteries, but in the excretory phase for renal pelvis/calyxes and proximal ureters. Assessment of pathology in the three categories showed no statistically significant differences between the three phases. Certainty scores for assessment of pathology, however, showed a significantly higher certainty for renal pathology when comparing the native phase to nephrogram and excretory phase and a significantly higher score for nephrographic phase but only for incidental findings.ConclusionVisualisation of renal anatomy was as expected with each post-contrast phase showing favourable scores compared to the native phase. No statistically significant differences in the assessment of pathology were found between the three phases. The low-dose CT (LDCT) seems to be sufficient in differentiating between normal and pathological examinations. To reduce the radiation burden in certain patient groups, the LDCT could be considered a suitable alternative as a first line imaging method. However, radiologists should be aware of its limitations.

Role of MR texture analysis in histological subtyping and grading of renal cell carcinoma: a preliminary study

The study evaluated the usefulness of magnetic resonance imaging (MRI) texture parameters in differentiating clear cell renal carcinoma (CC-RCC) from non-clear cell carcinoma (NC-RCC) and in the histological grading of CC-RCC. After institutional ethical approval, this retrospective study analyzed 33 patients with 34 RCC masses (29 CC-RCC and five NC-RCC; 19 low-grade and 10 high-grade CC-RCC), who underwent MRI between January 2011 and December 2012 on a 1.5-T scanner (Avanto, Siemens, Erlangen, Germany). The MRI protocol included T2-weighted imaging (T2WI), diffusion-weighted imaging [DWI; at b 0, 500 and 1000s/mm2 with apparent diffusion coefficient (ADC) maps] and T1-weighted pre and postcontrast [corticomedullary (CM) and nephrographic (NG) phase] acquisition. MR texture analysis (MRTA) was performed using the TexRAD research software (Feedback Medical Ltd., Cambridge, UK) by a single reader who placed free-hand polygonal region of interest (ROI) on the slice showing the maximum viable tumor. Filtration histogram-based texture analysis was used to generate six first-order statistical parameters [mean intensity, standard deviation (SD), mean of positive pixels (MPP), entropy, skewness and kurtosis] at five spatial scaling factors (SSF) as well as on the unfiltered image. Mann-Whitney test was used to compare the texture parameters of CC-RCC versus NC-RCC, and high-grade versus low-grade CC-RCC. P value < 0.05 was considered significant. A 3-step feature selection was used to obtain the best texture metrics for each MRI sequence and included the receiver-operating characteristic (ROC) curve analysis and Pearson's correlation test. The best performing texture parameters in differentiating CC-RCC from NC-RCC for each sequence included (area under the curve in parentheses): entropy at SSF 4 (0.807) on T2WI, SD at SSF 4 (0.814) on DWI b500, SD at SSF 6 (0.879) on DWI b1000, mean at SSF 0 (0.848) on ADC, skewness at SSF 2 (0.854) on T1WI and skewness at SSF 3 (0.908) on CM phase. In differentiating high from low-grade CC-RCC, the best parameters were: entropy at SSF 6 (0.823) on DWI b1000, mean at SSF 3 (0.889) on CM phase and MPP at SSF 5 (0.870) on NG phase. Several MR texture parameters showed excellent diagnostic performance (AUC > 0.8) in differentiating CC-RCC from NC-RCC, and high-grade from low-grade CC-RCC. MRTA could serve as a useful non-invasive tool for this purpose.

Role of CT urography in patients with suspected urinary tract calculi

An observational study carried out in a period of two years, in the Department of Radio-Diagnosis, Dr. D. Y. Patil Medical College, Hospital and Research centre, Pimpri, Pune. 50 patients with suspected or known cases of urinary tract calculi who came with renal colic or hematuria were subjected to CT urography. The study comprised of 23 females (46%) and 27 males (54%), thus showing male preponderance. The majority of the patients were from the age group of 12-30 years, with mean age of 38.96 years. 35 patients had urolithiasis. 22 patients (44%) had renal calculi, 7 patients (14%) had calculi at other sites and 6 patients (12%) had calculi at multiple sites. At other sites, calculi were most commonly seen in ureters, followed by PU junction, VU junction and urinary bladder. Right kidney was more commonly affected than left kidney. Obstructive changes were commonly due to calculi in ureters. Nephrographic phase was delayed in 1 patient (2%) and absent in 1 patient (2%), while excretory phase was delayed in 5 patients (10%) and absent in 2 patients (4%). Other pathological findings were identified in the study included renal cysts, reflux nephropathy, lymphocele, abscess, pyelonephritis, PUJ block, polycystic kidneys and neoplasm. The anatomical variants seen in the study included supernumerary kidneys, duplex collecting system, trifid pelvis, ectopic kidney, horse shoe kidney and retrocaval ureter.

What a difference a delay makes! CT urogram: a pictorial essay.

The aim of this pictorial essay is to demonstrate several cases where the diagnosis would have been difficult or impossible without the excretory phase image of CT urography. A brief discussion of CT urography technique and dose reduction is followed by several cases illustrating the utility of CT urography. CT urography has become the primary imaging modality for evaluation of hematuria, as well as in the staging and surveillance of urinary tract malignancies. CT urography includes a non-contrast phase and contrast-enhanced nephrographic and excretory (delayed) phases. While the three phases add to the diagnostic ability of CT urography, it also adds potential patient radiation dose. Several techniques including automatic exposure control, iterative reconstruction algorithms, higher noise tolerance, and split-bolus have been successfully used to mitigate dose. The excretory phase is timed such that the excreted contrast opacifies the urinary collecting system and allows for greater detection of filling defects or other abnormalities. Sixteen cases illustrating the utility of excretory phase imaging are reviewed. Excretory phase imaging of CT urography can be an essential tool for detecting and appropriately characterizing urinary tract malignancies, renal papillary and medullary abnormalities, CT radiolucent stones, congenital abnormalities, certain chronic inflammatory conditions, and perinephric collections.

Diagnostic Accuracy of Attenuation Difference and Iodine Concentration Thresholds at Rapid-Kilovoltage-Switching Dual-Energy CT for Detection of Enhancement in Renal Masses.

OBJECTIVE. The objective of our study was to evaluate iodine concentration and attenuation change in Hounsfield unit (ΔHU) thresholds to diagnose enhancement in renal masses at rapid-kilovoltage-switching dual-energy CT (DECT). MATERIALS AND METHODS. We evaluated 30 consecutive histologically confirmed solid renal masses (including nine papillary renal cell carcinomas [RCCs]) and 27 benign cysts (17 simple and 10 hemorrhagic or proteinaceous cysts) with DECT December 2016 and May 2018. A blinded radiologist measured iodine concentration (in milligrams per milliliter) and ΔHU (attenuation on enhanced CT - attenuation on unenhanced CT) using 70-keV corticomedullary (CM) phase virtual monochromatic and 120-kVp nephrographic (NG) phase images. The accuracies of previously described enhancement thresholds were compared by ROC curve analysis. RESULTS. An iodine concentration of ≥ 2.0 mg/mL and an iodine concentration of ≥ 1.2 mg/mL achieved sensitivity, specificity, and the area under the ROC curve (AUC) of 73.3%, 100.0%, and 0.87 and 86.7%, 100.0%, and 0.93, respectively. On 70-keV CM phase images, ΔHU ≥ 20 HU and ΔHU ≥ 15 HU yielded sensitivity, specificity, and AUC of 80.0%, 100.0%, and 0.90 and 90.0%, 100.0%, and 0.95, respectively. The numbers of incorrectly classified papillary RCCs were as follows: iodine concentration of ≥ 2.0 mg/mL, 77.8% (7/9; range, 0.7-1.6 mg/mL); iodine concentration of ≥ 1.2 mg/mL, 44.4% (4/9; range, 0.7-0.9 mg/mL); ΔHU ≥ 20 HU on 70-keV CM phase images, 66.7% (6/9; range, 4-17 HU); and ΔHU ≥ 15 HU on 70-keV DECT images, 33.3% (3/9; 4-12 HU). No cyst pseudoenhancement occurred on DECT. For 120-kVp NG phase DECT, ΔHU ≥ 20 HU and ΔHU ≥ 15 HU yielded sensitivity, specificity, and AUC of 93.3%, 96.3%, and 0.95 and 100.0%, 88.9%, and 0.94, respectively. With ΔHU ≥ 20 HU, 22.2% (2/9) (range, 15-18 HU) of papillary RCCs were misclassified and there was one pseudoenhancing cyst. With ΔHU ≥ 15 HU, no papillary RCCs were misclassified but 11.1% (3/27) of cysts showed pseudoenhancement. Only an iodine concentration of ≥ 2.0 mg/mL showed significantly lower accuracy than other measures (p = 0.031-0.045). CONCLUSION. DECT applied in the CM phase performed best using an iodine concentration of ≥ 1.2 mg/mL or a 70-keV ΔHU ≥ 15 HU; these parameters improved sensitivity for the detection of enhancement in renal masses without instances of cyst pseudoenhancement.