Clinical and Contrast-enhanced Ultrasound Characteristics of Epithelioid and Classic Hepatic Angiomyolipoma: Comparison With Alpha-fetoprotein-negative Hepatocellular Carcinoma

Hepatic angiomyolipoma (HAML) comprises epithelioid angiomyolipoma (EAML) and classic hepatic angiomyolipoma (CAML). The imaging appearance of HAML varies widely, and EAML is more easily misdiagnosed as hepatocellular carcinoma (HCC) than as CAML. The clinical and contrast-enhanced ultrasound (CEUS) features of CAML, EAML and HCC with negative alpha-fetoprotein protein expression (HCC[AFP-]) were retrospectively reviewed. The hyper-vascular type was more commonly found in CAML and EAML lesions than in HCC lesions. Most lesions were hyper-enhanced in the arterial phase. CAMLs showed prolonged hyper-enhancement or iso-enhancement during the portal and late phases on CEUS, making them easily distinguishable from HCC(AFP-). Some EAML lesions (41.7%) were hypo-echoic, similar to HCC(AFP-). However, the hypo-enhancement of EAML lesions occurred later than that of HCC(AFP-) lesions. Thus, our findings may be useful in distinguishing among these lesions to improve diagnostic accuracy.

Early dark cortical band sign on CT for differentiating clear cell renal cell carcinoma from fat poor angiomyolipoma and detecting peritumoral pseudocapsule

OBJECTIVES

To retrospectively evaluate whether the early dark cortical band (EDCB) on CT can be a predictor to differentiate clear cell renal cell carcinoma (ccRCC) from fat poor angiomyolipoma (Fp-AML) and to detect peritumoral pseudocapsules in ccRCC.

METHODS

The EDCBs, which are comprised of unenhanced thin lines at the tumor-renal cortex border in the corticomedullary phase, on the CT images of 342 patients who underwent partial nephrectomy were evaluated. Independent predictors among the clinical and CT findings for differentiating ccRCC from Fp-AML were identified using multivariate analyses. The diagnostic performance of the EDCB for diagnosing peritumoral pseudocapsule in ccRCC and differentiating ccRCC from Fp-AML was calculated.

RESULTS

The EDCB was observed in 157 of 254 (61.8%) ccRCCs, 4 of 31 (12.9%) chromophobe RCCs, 1 of 21 (4.8%) papillary RCCs, 3 of 11 (27.3%) clear cell papillary RCCs, 3 of 8 (37.5%) oncocytomas, and 0 of 17 (0%) Fp-AMLs. There was substantial interobserver agreement for the EDCB (k = 0.719). The EDCB was a significant predictor for differentiating ccRCC from Fp-AML (p < 0.001). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value of the EDCB for differentiating ccRCC from Fp-AML were 61.8%, 100%, 100%, and 14.9%, respectively, and those for detecting pseudocapsule in 236 ccRCCs were 62.3%, 68.8%, 96.5%, and 11.7%, respectively.

CONCLUSION

Although diagnostic accuracy of the EDCB for detecting peritumoral pseudocapsule in RCC is inadequate, it can be a predictor for differentiating ccRCC from Fp-AML with high specificity and PPV.

KEY POINTS

• The early dark cortical band (EDCB) sign is observed in nearly two-thirds of clear cell renal cell carcinoma (ccRCC) that are treated by partial nephrectomy and have substantial interobserver agreement. • The EDCB is a significant predictor for differentiating ccRCCs from fat poor angiomyolipomas, with a high specificity and positive predictive value. • Diagnostic accuracy of the EDCB for detecting peritumoral pseudocapsule in ccRCC is inadequate, though better than those in the nephrographic and excretory-phase images.

Imaging Characterization of Renal Masses

The detection of a renal mass is a relatively frequent occurrence in the daily practice of any Radiology Department. The diagnostic approaches depend on whether the lesion is cystic or solid. Cystic lesions can be managed using the Bosniak classification, while management of solid lesions depends on whether the lesion is well-defined or infiltrative. The approach to well-defined lesions focuses mainly on the differentiation between renal cancer and benign tumors such as angiomyolipoma (AML) and oncocytoma. Differential diagnosis of infiltrative lesions is wider, including primary and secondary malignancies and inflammatory disease, and knowledge of the patient history is essential. Radiologists may establish a possible differential diagnosis based on the imaging features of the renal masses and the clinical history. The aim of this review is to present the contribution of the different imaging techniques and image guided biopsies in the diagnostic management of cystic and solid renal lesions.

Review of Value of CT Texture Analysis and Machine Learning in Differentiating Fat-Poor Renal Angiomyolipoma from Renal Cell Carcinoma

The diagnosis of patients with suspected angiomyolipoma relies on the detection of abundant macroscopic intralesional fat, which is always of no use to differentiate fat-poor angiomyolipoma (fp-AML) from renal cell carcinoma and diagnosis of fp-AML excessively depends on individual experience. Texture analysis was proven to be a potentially useful biomarker for distinguishing between benign and malignant tumors because of its capability of providing objective and quantitative assessment of lesions by analyzing features that are not visible to the human eye. This review aimed to summarize the literature on the use of texture analysis to diagnose patients with fat-poor angiomyolipoma vs those with renal cell carcinoma and to evaluate its current application, limitations, and future challenges in order to avoid unnecessary surgical resection.

[A Resected Case of Angiomyolipoma Difficult to Be Distinguished from Hepatocellular Carcinoma]

A 42-year-old man complaining of left back pain was admitted to our hospital. The hepatis B and C surface antigens were negative. The serum levels of tumor markers were within the reference ranges. Abdominal ultrasound revealed an 8 cm-sized, primarily round and hyperechoic mass in the left lateral segment. Contrast-echo showed non-uniform enhancement in the arterial phase and uniform enhancement in the portal phase. This mass did not indicate"wash-out"on contrast- enhanced CT. It showed hypointensity in the hepatobiliary phase on MRI. The definitive diagnosis could not be obtained, and the patient was suspected with malignancy, such as hepatocellular carcinoma(HCC). Therefore, left hemi-hepatectomy was performed for the diagnostic treatment. Based on the immunochemical staining results, he was diagnosed with angiomyolipoma( AML). AML is composed of fat, blood vessels, and smooth muscles. It is regarded as a tumor of perivascular epithelioid cell tumor(PEComa). Early venous return and adipose tissues in the tumor were the distinctive features of this tumor. The preoperative diagnosis of AML without any fatty component as in this case is very difficult.

Hepatic Angiomyolipoma: Clinical Features and Imaging Findings of Quantitative Contrast-Enhanced Ultrasound Perfusion Analysis and Magnetic Resonance Imaging

OBJECTIVES

To investigate whether quantitative contrast-enhanced ultrasound (CEUS) analysis and magnetic resonance imaging (MRI) can differentiate hepatic angiomyolipoma (AML) from hepatocellular carcinoma (HCC) and hepatic epithelial angiomyolipoma (EAML) from nonepithelial AML.

METHODS

Retrospective analysis of 26 CEUS lesions pathologically confirmed as AML and 60 patients with confirmed HCC. Clinical and ultrasound (US) features of AML versus HCC and EAML versus nonepithelial AML were analyzed. Quantitative parameters, including arrival time, ascending slope, time to peak, peak intensity (PI), fall time (FT), and mean transit time (MTT), were analyzed. Diagnostic performance of MRI and CEUS was compared.

RESULTS

Angiomyolipoma was significantly different from HCC in US findings of solitary tumor (P < .001), well-defined border (P = .025), and hyperechogenicity (P < .001). Tumor types were significantly different in US findings of centripetal filling pattern (P < .001), less hypoenhancement in the CEUS delayed phase (P = .04), high PI (P = .007) and ascending slope (P = .006), and short FT (P = .001) and MTT (P < .05). The sensitivity and specificity of quantitative parameters were 61.5% to 96.2% and 55.0% to 71.7% (area under the curve, 0.642-0.773). An early draining vein and tumor vessels, intratumor fat, absence of pseudocapsules, mild signal intensity on diffusion-weighted imaging, and hypointensity in the MRI delayed phase were helpful for differentiation of AML from HCC (P < .05). The positive predictive values of CEUS and MRI were 46.3% to 100% and 42.9% to 75%, with no significant difference (P > .05). Epithelial AML was more likely to be hypoechoic with a centripetal filling pattern than nonepithelial AML (P < .05). The MTT and FT of EAML were shorter than those of nonepithelial AML (P < .05). The PI of EAML was significantly stronger than that of nonepithelial AML (P < .01). The sensitivity and specificity of quantitative parameters were 68.7% to 100.0% and 60.0% to 100.0% (area under the curve, 0.825-0.941). Less intratumor fat was helpful for differentiation of EAML from nonepithelial AML (P < .05). The positive predictive values of CEUS and MRI were 77.8% to 100% and 85.7%, with a significant difference (P < .05).

CONCLUSIONS

Quantitative CEUS findings could be valuable in differentiating EAML from HCC.

Differential diagnosis of hypervascular ultra-small renal cell carcinoma and renal angiomyolipoma with minimal fat in early stage by using thin-section multidetector computed tomography

PURPOSE

The purpose of this study was to investigate the difference between imaging features of ultra-small renal cell carcinoma (usRCC) and angiomyolipoma with minimal fat (mfAML) whose enhancement were both hypervascular by using multidetector computed tomography (MDCT).

MATERIALS AND METHODS

Confirmed by pathology, 40 cases of hypervascular usRCC and 21 cases of hypervascular mfAML both with diameter of 2 cm or less were compared and analyzed retrospectively, including traditional imaging features and thin-section computed tomography (CT) dynamic enhanced parameters. Meanwhile, receiver operating characteristic (ROC) curves were constructed to evaluate the diagnostic efficacy of each significant parameter and the information with diagnostic value was selected to construct the prediction model.

RESULTS

Comparison of traditional imaging features: the features, included age, shape, location, central location of tumor, wedge sign, renal cortex lift sign, black star sign, enhanced homogeneity in cortical phase (CP) and enhancement pattern had no significant difference between usRCC and mfAML (P > 0.05); sex, cystic degeneration or necrosis, pseudocapsule sign, and enhanced homogeneity in nephrographic phase (NP) had significant differences between usRCC and mfAML (P < 0.05). Comparison of CT dynamic enhanced parameters: the CT value, NEV and REV of usRCC were all higher than mfAML in both CP and NP (P < 0.01). Respectively, the area under the ROC curve (AUC) were 0.74, 0.75, 0.78, 0.83, 0.81 and 0.78. The sensitivity and specificity for differentiating ucRCC from mfAML were 85.0% and 76.2% respectively when NEV_NP was 73.6 HU as the critical value. Multivariate analysis showed that male, cystic degeneration or necrosis, and NEV_NP higher than 73.6 HU as an independent risk factor for usRCC (P < 0.01). The AUC value of the prediction model constructed by the combination was 0.94, the accuracy was 86.89%, the sensitivity was 82.50%, and the specificity was 95.24%.

CONCLUSION

Morphological characteristics in traditional diagnosis of small renal carcinoma (diameter of 4 cm or less) have certain significance in differentiating hypervascular usRCC and mfAML in early stage, but the diagnostic efficacy was limited. Sex, cystic degeneration or necrosis, and quantitative parameters measured after enhancement play an important role in differential diagnosis of hypervascular usRCC and mfAML, and the prediction model constructed by the combination has a good diagnostic performance.

Contrast-Enhanced Ultrasound Findings and Differential Diagnosis of Hepatic Epithelioid Angiomyolipoma Compared with Hepatocellular Carcinoma

Hepatic epithelioid angiomyolipoma (EAML) has malignant potential that can easily be misdiagnosed as hepatocellular carcinoma (HCC), but the treatment options of these conditions are different. This retrospective study investigated whether contrast-enhanced ultrasound (CEUS) can differentiate EAML from HCC. We included 24 patients with pathologically confirmed EAML and 36 patients with HCC who underwent pre-operative conventional ultrasound and CEUS. The conventional ultrasound and CEUS features of the two groups were analyzed. Time intensity curves (TICs) were analyzed for all lesions using quantitative perfusion analysis software. This study found that significant differences existed between the EAML and HCC groups in terms of clinical features such as sex, age, symptoms, alpha-fetoprotein and history of hepatitis B virus infection (p < 0.05). Tumor size, number, border and echogenicity on conventional ultrasound were significantly different between EAML and HCC (p < 0.05). Regarding CEUS, EAML was more likely to have a centripetal enhancement pattern than HCC (p < 0.05). The tumor enhancement degree in the delayed phase in CEUS was significantly different between EAML and HCC (p < 0.05). Quantitative analysis of CEUS parameters revealed that the wash-in area under the curve (AUC) was larger in EAML than in HCC (p < 0.05). Time to peak was significantly shorter in EAML than in HCC (p < 0.05). The peak intensity was significantly stronger in EAML than in HCC (p < 0.05). Regarding the diagnostic performance of CEUS parameters that showed statistical significance on univariate analysis, the sensitivity and specificity for distinguishing EAML from HCC was 66.7%-100.0% and 55.6%-91.7%, respectively. Overall, CEUS could be valuable in differentiating EAML from HCC. Specific features such as the centripetal filling and prolonged enhancement patterns on CEUS, higher peak intensity, bigger wash-in AUC and shorter time to peak on TICs may contribute to a more confirmative differential diagnosis of EAML.

Radiomics of computed tomography and magnetic resonance imaging in renal cell carcinoma-a systematic review and meta-analysis

OBJECTIVES

(1) To assess the methodological quality of radiomics studies investigating histological subtypes, therapy response, and survival in patients with renal cell carcinoma (RCC) and (2) to determine the risk of bias in these radiomics studies.

METHODS

In this systematic review, literature published since 2000 on radiomics in RCC was included and assessed for methodological quality using the Radiomics Quality Score. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies tool and a meta-analysis of radiomics studies focusing on differentiating between angiomyolipoma without visible fat and RCC was performed.

RESULTS

Fifty-seven studies investigating the use of radiomics in renal cancer were identified, including 4590 patients in total. The average Radiomics Quality Score was 3.41 (9.4% of total) with good inter-rater agreement (ICC 0.96, 95% CI 0.93-0.98). Three studies validated results with an independent dataset, one used a publically available validation dataset. None of the studies shared the code, images, or regions of interest. The meta-analysis showed moderate heterogeneity among the included studies and an odds ratio of 6.24 (95% CI 4.27-9.12; p < 0.001) for the differentiation of angiomyolipoma without visible fat from RCC.

CONCLUSIONS

Radiomics algorithms show promise for answering clinical questions where subjective interpretation is challenging or not established. However, the generalizability of findings to prospective cohorts needs to be demonstrated in future trials for progression towards clinical translation. Improved sharing of methods including code and images could facilitate independent validation of radiomics signatures.

KEY POINTS

• Studies achieved an average Radiomics Quality Score of 10.8%. Common reasons for low Radiomics Quality Scores were unvalidated results, retrospective study design, absence of open science, and insufficient control for multiple comparisons. • A previous training phase allowed reaching almost perfect inter-rater agreement in the application of the Radiomics Quality Score. • Meta-analysis of radiomics studies distinguishing angiomyolipoma without visible fat from renal cell carcinoma show moderate diagnostic odds ratios of 6.24 and moderate methodological diversity.

Contrast-enhanced sonographic appearances of two primary hepatic epithelioid angiomyolipomas

Epithelioid hepatic angiomyolipoma (Epi-HAML) is a rare hepatic tumor frequently misdiagnosed as hepatocellular carcinoma (HCC). Unlike conventional angiomyolipoma (AML), Epi-HAML contains minimal amount of adipose tissue, which is a radiological distinguishing feature between AML and HCC. Two patients were referred for management of incidentally found hepatic lesions confirmed to be Epi-HAML on post-resection tissue analysis. CT and MRI findings were suggestive of HCC. Contrast-enhanced ultrasound demonstrated intratumoral shunting, a feeding artery, and early draining hepatic vein. These findings should alert radiologists to the possibility of Epi-HAML. Furthermore, these features may be better assessed by contrast-enhanced ultrasound due to its superior dynamic temporal resolution.

Small renal masses (≤ 4 cm): differentiation of oncocytoma from renal clear cell carcinoma using ratio of lesion to cortex attenuation and aorta-lesion attenuation difference (ALAD) on contrast-enhanced CT

PURPOSE

We investigate the use of ratio of lesion to cortex (L/C) attenuation and aorta-lesion attenuation difference (ALAD) on multiphase contrast-enhanced CT to help distinguish oncocytoma from clear cell RCC in small renal masses (diameter < 4 cm).

METHODS

We retrospectively identified 76 patients that undergo CT before surgery for a suspicious small renal mass between January 2014 and December 2018 with pathological diagnosis of 21 oncocytomas (ROs), 25 clear cell RCCs, 7 chromophobe RCCs, 7 papillary RCCs, 7 multilocular cystic RCCs, 7 angiomyolipomas and 2 leiomyomas. CT attenuation values were obtained for the tumor, the normal renal cortex and the aorta, placing a circular region of interest (ROI) in the same slice by two radiologists, independently.

RESULTS

In the corticomedullary phase, ROs showed isodense enhancement to the renal cortex (ratio L/C 0.92 ± 0.12), while clear cell RCCs appeared hypodense to the renal cortex (ratio L/C 0.69 ± 0.20; p < 0.01) with an accuracy of 80% for diagnosing RO. In nephrographic phase, the ratio L/C attenuation was lower than the corticomedullary phase in ROs (0.78 ± 0.11) showing an early washout pattern, while the ratio L/C was similar to the corticomedullary phase in clear cell RCCs (0.69 ± 0.13; p = 0.025, with an accuracy of 65% for diagnosing RO). The ratio L/C attenuation showed considerable overlap between ROs and clear cell RCCs in the excretory phase (p = 0.27). Mean ALAD values in the nephrographic phase were 21.95 ± 16.24 for ROs and 36.96 ± 30.53 for clear cell RCCs (p = 0.049).

CONCLUSION

The ratio L/C attenuation in corticomedullary phase may be useful to differentiate RO from clear cell RCC.

Comparison of hepatic epithelioid angiomyolipoma and non-hepatitis B, non-hepatitis C hepatocellular carcinoma on contrast-enhanced ultrasound

PURPOSE

The purpose of this study was to retrospectively compare the imaging features of hepatic epithelioid angiomyolipoma (HEAML) to those of hepatocellular carcinoma negative for hepatitis B surface antigen and hepatitis C antibody (NBNC-HCC) on contrast-enhanced ultrasound (CEUS) with sulphur hexafluoride microbubbles.

MATERIAL AND METHODS

Twenty-two patients (4 men, 18 women) with a mean age of 42.6±10.2 (SD) years (range: 22-63 years) with histopathologically confirmed HEMAL were included in the study. Forty-four patients (30 men, 14 women) with a mean age of 57.3±15.9 years (range: 19-85 years) with histopathologically confirmed NBNC-HCC were randomly selected from our institution's database as a control group. The CEUS characteristics of the two groups were compared.

RESULTS

On conventional ultrasound, significant differences in tumor diameter were found between HEAML (4.0±2.0 [SD] cm; range: 1.3-8.9cm) and NBNC-HCC (8.4±4.4 [SD] cm; range: 1.6-18cm) (P<0.001) as well as in degrees of enhancement during the portal (P=0.001) and late phases (P=0.003), contrast distribution (P<0.001) and absence of pseudocaspule (P<0.001). On CEUS, hyperenhancement during the arterial phase was observed in 21/22 (95.5%) HEAMLs and in 43/44 (97.7%) NBNC-HCCs (P>0.999). Homogeneous enhancement was more frequent in HEAMLs (20/22; 90.9%) than in NBNC-HCCs (13/44; 29.6%) (P<0.001). Pseudocapsule was observed in 0/22 HEAMLs (0.0%) and in 36/44 NBNC-HCCs (81.8%) (P=0.017). A prolonged enhancement was observed in 5/22 HEAMLs (22.7%) and in 0/44 NBNC-HCCs (0.0%) (P<0.001) during the late phase.

CONCLUSION

CEUS with sulphur hexafluoride microbubbles is helpful in discriminating between HEAML and NBNC-HCC. Homogeneous enhancement and lack of pseudocapsule are suggestive features for the diagnosis of HEAML.

Differentiation between fat-poor angiomyolipoma and clear cell renal cell carcinoma: qualitative and quantitative analysis using arterial spin labeling MR imaging

PURPOSE

To assess the diagnostic effectiveness of arterial spin labeling (ASL) MR imaging in differentiating fat-poor AML from clear cell renal cell carcinoma (ccRCC).

METHODS

In this prospective study, 29 ccRCC patients and 9 fat-poor AML patients underwent routine anatomical MRI and ASL at 3T before surgery after signing written informed consent form. For each tumor, tumor blood flow (TBF) was measured in a region of interest (ROI) which was positioned to outline the edge of the target lesions on ASL perfusion maps. Additionally, the mean TBF values were obtained by standardizing the TBF using a blood flow measurement in the reference ROI. Moreover, a cluster containing more than 10 voxels was chosen from the renal cortex and medulla area in normal contralateral kidney as a reference ROI to calculate tumor-to-cortex ratio and tumor-to-medulla ratio. Independent sample t test was used to examine the alteration among the groups of fat-poor AML and ccRCC. ASL images were together analyzed by two radiologists to assess the following characteristics of the renal mass: predominant SI in the tumor on ASL images was lower than, as same as, or higher than SI of the cortex. For qualitative variables, Fisher's exact test was employed to compare the proportions of these two groups. The sensitivity, specificity ,and accuracy required for discrimination of fat-poor AML from ccRCC were quantified using receiver operating characteristic (ROC) curve. The corresponding optimal cutoff value was obtained for each parameter as well.

RESULTS

The TBF value was significantly higher in ccRCC group than that in fat-poor AML (270.49 ± 78.88 ml/100 g/min vs. 146.68 ± 47.21 ml/100 g/min; P < 0.01). Both tumor-to-cortex and tumor-to-medulla ratios were notably higher in ccRCC group compared with those in fat-poor AML group (1.22 ± 0.26 vs. 0.74 ± 0.14, 3.13 ± 0.94 vs. 1.77 ± 0.55; P < 0.05). The values of area under the ROC curve (AUC) for TBF, tumor-to-cortex ratio, and tumor-to-medulla ratio were 0.931, 0.964, and 0.900, respectively. No significant difference in AUC values among these three measurements was observed. For qualitative variables, the SI of fat-poor AML was equal to or slightly lower than that of renal medulla and the SI of ccRCC was found to be higher than renal cortex in ASL.

CONCLUSION

ASL MRI performs well in differentiating fat-poor AML from ccRCC in both qualitative and quantitative analyses.

Benign liver angiomyolipoma: a case study

INTRODUCTION

Hepatic angiomyolipoma is a rare mesenchymal tumor. It consists of vessels, fatty tissue and muscle tissue. These can appear in various ratios. While the kidney is the most common localization of angiomyolipoma, only about 300 cases have been described in the liver so far. It is a tumor of uncertain behavior. Most of the patients suffering from the lesion is asymptomatic. It is often preoperatively misdiagnosed using various imaging methods given its similarity to other hepatic tumors.

CASE REPORT

Our 64 years old female patient was being examined for dull abdominal pains with no other symptoms. Her close relatives suffered from no malignancies. Imaging exams showed a liver lesion highly suspicious for hepatocellular carcinoma. However, the patient showed no elevation of typical oncomarkers. We performed left lateral sectionectomy. A grey solid focal lesion was found in the resected tissue. Histological and immunohistochemical evaluation determined the diagnosis of angiomyolipoma. The postoperative period was uncomplicated. The patient has been followed at an office for hepato-pancreato-biliary diseases, with no signs of recurrence until the present.

CONCLUSION

Hepatic angiomyolipoma is a rare disease. The diagnostic process can be challenging as illustrated by the presented case. Even though the working diagnosis proved false, the chosen treatment was appropriate and delivered good results. Long-term postoperative follow-up is required.

Wunderlichs syndrome in patient with sporadic bilateral angiomyolipomas - case report

We present the case report of bilateral renal angiomyolipomas in a 70-year-old patient. Spontaneous bleeding into the retroperitoneum and hemodynamic instability required an acute surgical revision with a left-sided nephrectomy. The contralateral angiomyolipoma was selectively embolized in the second period and subsequently resected.

Epithelioid angiomyolipoma with tumor thrombus

Epithelioid renal angiomyolipoma is a rare malignant variant of angiomyolipoma (AML); the latter being a well-characterized, benign kidney tumor derived from various connective tissue elements. In this case report, we describe a patient with an epithelioid AML and renal vein thrombus.

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

OBJECTIVE

To investigate the discriminative capabilities of different machine learning-based classification models on the differentiation of small (< 4 cm) renal angiomyolipoma without visible fat (AMLwvf) and renal cell carcinoma (RCC).

METHODS

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.

RESULTS

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.

CONCLUSION

Image features extracted from UP are sufficient to generate accurate differentiation between AMLwvf and RCC using machine learning-based classification model.

KEY POINTS

• 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).

Point Shear Wave Elastography Using Machine Learning to Differentiate Renal Cell Carcinoma and Angiomyolipoma

The question of whether ultrasound point shear wave elastography can differentiate renal cell carcinoma (RCC) from angiomyolipoma (AML) is controversial. This study prospectively enrolled 51 patients with 52 renal tumors (42 RCCs, 10 AMLs). We obtained 10 measurements of shear wave velocity (SWV) in the renal tumor, cortex and medulla. Median SWV was first used to classify RCC versus AML. Next, the prediction accuracy of 4 machine learning algorithms-logistic regression, naïve Bayes, quadratic discriminant analysis and support vector machines (SVMs)-was evaluated, using statistical inputs from the tumor, cortex and combined statistical inputs from tumor, cortex and medulla. After leave-one-out cross validation, models were evaluated using the area under the receiver operating characteristic (ROC) curve (AUC). Tumor median SWV performed poorly (AUC = 0.62; p = 0.23). Except logistic regression, all machine learning algorithms reached statistical significance using combined statistical inputs (AUC = 0.78-0.98; p < 7.1 × 10-3). SVMs demonstrated 94% accuracy (AUC = 0.98; p = 3.13 × 10-6) and clearly outperformed median SWV in differentiating RCC from AML (p = 2.8 × 10-4).

A Radiologic Intervention in a Tuberous Sclerosis Patient with Massive Bilateral Angiomyolipomas Causing Symptomatic Bleeding: A Case Report and Review of the Renal Manifestations and CT Imaging Features

Angiomyolipomas are commonly found in patients with tuberous sclerosis (TS), a rare genetic disorder. Angiomyolipomas are benign renal tumors composed of heterogeneously arranged blood vessels, smooth muscle tissue, and fat. Most commonly, angiomyolipomas are small and asymptomatic, but are more prone to enlargement and symptomatic bleeding in TS patients. This case report describes a rare case of massive bilateral angiomyolipomas in a TS patient who presented with spontaneous symptomatic bleeding, anorexia, and failure to thrive. Selective renal embolization was done to decrease the bleeding risk and to reduce the volume of the angiomyolipoma to reduce anorexia, and ultimately failure to thrive. Classic angiomyolipomas have characteristic imaging features including microscopic fat.

Tuberous Sclerosis

Tuberous sclerosis is a rare genetic disorder inherited in an autosomal dominant fashion. It is a multisystem disorder involving brain, eye, skin, kidney and lungs which manifest in late childhood. We present a typical case of tuberous sclerosis in a young female patient.Extensive work-up including MRI brain, MRI abdomen and CT Thorax was performed. The clinical and radiological findingswere consistent with thediagnosis of tuberous sclerosis.

Trans-Radial Embolization of Bleeding Renal Angiomyolipoma in Pregnant 30-Year-Old Female - A Case Report

Trans-radial access offers several unique advantages and is being used more frequently for interventional radiology procedures. We report the use of trans-radial arterial access to embolize a large bleeding angiomyolipoma in a 30-year-old pregnant patient presenting in the first trimester. Trans-radial approach was chosen to minimize the effects of radiation on the fetus. Subsequent postprocedural pregnancy course was uneventful with stability of the angiomyolipoma and no further hemorrhage. This case highlights the benefits of trans-radial embolotherapy in gravid patients to reduce the risk of radiation exposure to the fetus.