Cost‐effectiveness analysis of multiple imaging modalities in diagnosis and follow‐up of intermediate complex cystic renal lesions

Intra- and Interobserver Study Investigating the Adapted EFSUMB Bosniak Cyst Categorization Proposed for Contrast-Enhanced Ultrasound (CEUS) in 2020

BACKGROUND

To investigate the inter- and intraobserver variability in comparison to an expert gold standard of the new and modified renal cyst Bosniak classification proposed for contrast-enhanced ultrasound findings (CEUS) by the European Federation of Societies for Ultrasound in Medicine and Biology (EFSUMB) in 2020.

MATERIALS AND METHODS

84 CEUS examinations for the evaluation of renal cysts were evaluated retrospectively by six readers with different levels of ultrasound expertise using the modified Bosniak classification proposed for CEUS. All cases were anonymized, and each case was rated twice in randomized order. The consensus reading of two experts served as the gold standard, to which all other readers were compared. Statistical analysis was performed using Cohen's weighted kappa tests, where appropriate.

RESULTS

Intraobserver variability showed substantial to almost perfect agreement (lowest kappa κ=0.74; highest kappa κ=0.94), with expert level observers achieving the best results. Comparison to the gold standard was almost perfect for experts (highest kappa κ=0.95) and lower for beginner and intermediate level readers still achieving mostly substantial agreement (lowest kappa κ=0.59). Confidence of rating was highest for Bosniak classes I and IV and lowest for classes IIF and III.

CONCLUSION

Categorization of cystic renal lesions based on the Bosniak classification proposed by the EFSUMB in 2020 showed very good reproducibility. While even less experienced observers achieved mostly substantial agreement, training remains a major factor for better diagnostic performance.

Bosniak Classification of Cystic Renal Masses: Looking Back, Looking Forward

RATIONALE AND OBJECTIVES

According to the 2019 update of the Bosniak classification, the main imaging features that need to be evaluated to achieve a correct characterization of renal cystic masses include the thickness of walls and septa, the number of septa, the appearance of walls and septa, the attenuation/intensity on non-contrast CT/MRI and the presence of unequivocally perceived or measurable enhancement of walls and septa. Despite the improvement deriving from a quantitative evaluation of imaging features, certain limitations seem to persist and some possible scenarios that can be encountered in clinical practice are still missing.

MATERIALS AND METHODS

A deep analysis of the 2019 update of the Bosniak classification was performed.

RESULTS

The most notable potential flaws concern: (1) the quantitative measurement of the walls and septa; (2) the fact that walls and septa > 2 mm are always referred to as "enhancing", not considering the alternative scenario; (3) the description of some class II masses partially overlaps with each other and with the definition of class I masses and (4) the morphological variations of cystic masses over time is not considered.

CONCLUSION

The present paper analyzes in detail the limitations of the 2019 Bosniak classification to improve this important tool and facilitate its use in daily radiological practice.

Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions

BACKGROUND

The rising prevalence of cystic renal lesions (CRLs) detected by computed tomography necessitates better identification of the malignant cystic renal neoplasms since a significant majority of CRLs are benign renal cysts. Using arterial phase CT scans combined with pathology diagnosis results, a fusion feature-based blending ensemble machine learning model was created to identify malignant renal neoplasms from cystic renal lesions (CRLs). Histopathology results were adopted as diagnosis standard. Pretrained 3D-ResNet50 network was selected for non-handcrafted features extraction and pyradiomics toolbox was selected for handcrafted features extraction. Tenfold cross validated least absolute shrinkage and selection operator regression methods were selected to identify the most discriminative candidate features in the development cohort. Feature's reproducibility was evaluated by intra-class correlation coefficients and inter-class correlation coefficients. Pearson correlation coefficients for normal distribution and Spearman's rank correlation coefficients for non-normal distribution were utilized to remove redundant features. After that, a blending ensemble machine learning model were developed in training cohort. Area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA) were employed to evaluate the performance of the final model in testing cohort.

RESULTS

The fusion feature-based machine learning algorithm demonstrated excellent diagnostic performance in external validation dataset (AUC = 0.934, ACC = 0.905). Net benefits presented by DCA are higher than Bosniak-2019 version classification for stratifying patients with CRL to the appropriate surgery procedure.

CONCLUSIONS

Fusion feature-based classifier accurately distinguished malignant and benign CRLs which outperformed the Bosniak-2019 version classification and illustrated improved clinical decision-making utility.

Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm

Using nephrographic phase CT images combined with pathology diagnosis, we aim to develop and validate a fusion feature-based stacking ensemble machine learning model to distinguish malignant renal neoplasms from cystic renal lesions (CRLs). This retrospective research includes 166 individuals with CRLs for model training and 47 individuals with CRLs in another institution for model testing. Histopathology results are adopted as diagnosis criterion. Nephrographic phase CT scans are selected to build the fusion feature-based machine learning algorithms. The pretrained 3D-ResNet50 CNN model and radiomics methods are selected to extract deep features and radiomics features, respectively. Fivefold cross-validated least absolute shrinkage and selection operator (LASSO) regression methods are adopted to identify the most discriminative candidate features in the development cohort. Intraclass correlation coefficients and interclass correlation coefficients are employed to evaluate feature’s reproducibility. Pearson correlation coefficients for normal distribution features and Spearman’s rank correlation coefficients for non-normal distribution features are used to eliminate redundant features. After that, stacking ensemble machine learning models are developed in the training cohort. The area under the receiver operator characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) are adopted in the testing cohort to evaluate the performance of each model. The stacking ensemble machine learning algorithm reached excellent diagnostic performance in the testing dataset. The calibration plot shows good stability when using the stacking ensemble model. Net benefits presented by DCA are higher than the Bosniak 2019 version classification when employing any machine learning algorithm. The fusion feature-based machine learning algorithm accurately distinguishes malignant renal neoplasms from CRLs, which outperformed the Bosniak 2019 version classification, and proves to be more applicable for clinical decision-making.

Diagnostic value of contrast-enhanced ultrasound (CEUS) in kidney allografts - 12 years of experience in a tertiary referral center

BACKGROUND

B-Mode and Doppler ultrasound are standard diagnostic techniques for early postoperative monitoring and long-term follow-up of kidney transplants. In certain cases, contrast-enhanced ultrasound (CEUS) is used to clarify unclear Doppler findings.

OBJECTIVE

To investigate the diagnostic performance of CEUS in the workup of renal allograft pathologies.

METHODS

A systematic search for CEUS examinations of renal transplants conducted in our department between 2008 and 2020 was performed using the following inclusion criteria: i) patient age ≥18 years and ii) confirmation of diagnosis by biopsy and histopathology, imaging follow-up by CEUS, contrast-enhanced computed tomography (ceCT), contrast-enhanced magnetic resonance imaging (ceMRI), or angiography, or intraoperative findings. Exclusion criteria were: i) CEUS performed in the setting of a study and ii) CEUS for other indications than dedicated renal transplant examination. Statistical analysis was performed separately for subgroups with different indications (focal vs non-focal).

RESULTS

Overall, 78 patients were included in the statistical analysis, which revealed high sensitivity (92.2%, 95% -confidence interval [CI] 81.5-96.9%) and high specificity (88.9%, 95% -CI 71.9-96.1%) of CEUS.

CONCLUSIONS

The high diagnostic performance demonstrated here and the superficial location of kidney allografts advocate the additional use of CEUS in the follow-up of renal transplant recipients.

Contrast-enhanced ultrasound (CEUS) in characterization of inconclusive cervical lymph nodes: a meta-analysis and systematic review

Lymph node metastases are common in malignant neoplasms of head and neck. Since cervical lymph nodes (cLN) are localized superficially, ultrasound (US) represents the primary imaging modality. The aim of the study is to report the value of US and contrast-enhanced ultrasound (CEUS) and their diagnostic confidence in the characterization of inconclusive cLN. A systematic review was performed using the literature data base PubMed. Results were filtered (published in a peer-reviewed journal, full-text available, published within the last ten years, species human, English or German full-text) and inclusion criteria were clearly defined (cohort with lymphadenopathy or malignancy in head and neck ≥ 50 patients, histological confirmation of malignant imaging findings, performance of CEUS as outcome variable). The results were quantified in a meta-analysis using a random-effects model. Overall, five studies were included in qualitative and quantitative analysis. The combination of non-enhanced US and CEUS enlarges the diagnostic confidence in the characterization of lymph nodes of unclear dignity. The pooled values for sensitivity and specificity in the characterization of a malignant cervical lymph node using US are 76% (95%-CI 66-83%, I2 = 63%, p < 0.01) and 80% (95%-CI 45-95%, I2 = 92%, p < 0.01), compared to 92% (95%-CI 89-95%, I2 = 0%, p = 0.65) and 91% (95%-CI 87-94%, I2 = 0%, p = 0.40) for the combination of US and CEUS, respectively. Consistent results of the included studies show improved diagnostic performance by additional CEUS. Nevertheless, more prospective studies are needed to implement CEUS in the diagnostic pathway of cLN.

The quantitative evaluation of contrast-enhanced ultrasound in the differentiation of small renal cell carcinoma subtypes and angiomyolipoma

Background

Contrast-enhanced ultrasound (CEUS) has been widely used for renal lesion diagnosis and differential diagnosis. However, qualitative analysis of CEUS is subject to examinations with low reproducibility. This study aims to investigate the diagnostic value of CEUS quantitative parameters in differentiating small renal cell carcinoma (RCC) subtypes and angiomyolipoma (AML).

Methods

A retrospective analysis was performed on 97 cases of a small renal mass undergoing a CEUS before a radical or partial nephrectomy procedure. A region of interest (ROI) was placed in the tumor's maximum enhanced region (ROI_max) as much as possible, and adjacent renal cortex (ROI_refer) was selected from normal renal tissue around a mass of the same depth. The time-intensity curve (TIC) was used to analyze the ROI_max and the ROI_refer of the tumors quantitatively. Then the parameters of the ROI_max and the ROI_refer, including the differences between the parameters of the ROI_max and the ROI_refer, were analyzed statistically.

Results

In RCC and clear cell renal cell carcinoma (ccRCC), the peak intensity (PI), slope (SL), area under the curve (AUC), area under the wash-in curve (AWI), area under the wash-out curve (AWO), time to peak intensity (TTP) and the mean transit time (MTT) were statistically significant between ROI_max and ROI_refer (all P=0.000). The △PI (△PI = PI_max - PI_refer), △SL (△SL = SL_max - SL_refer), △AUC (△AUC = AUC_max - AUC_refer), △AWI (△AWI = AWI_max - AWI_refer) and △AWO (△AWO = AWO_max - AWO_refer) of RCC were significantly higher than in AML (P=0.007, 0.000, 0.003, 0.048, 0.009, respectively), while the TTP (△TTP = TTP_max - TTP_refer) and △MTT (△MTT = MTT_max - MTT_refer) of RCC were significantly lower (both P=0.000). In comparison with papillary renal cell carcinoma (pRCC) and chromophobe renal cell carcinoma (chRCC), the △PI, △SL, △AUC and △AWO of ccRCC were all larger (all P<0.05). The sensitivity, specificity, and AUC of the combination of parameter difference for differentiating RCC from AML were 100%, 81.2%, and 0.965, respectively, and for differentiating ccRCC from pRCC and chRCC, 85.71%, 85.92% and 0.911, respectively.

Conclusions

CEUS quantitative parameters have value in differentiating small RCC from AML and distinguishing ccRCC from pRCC and chRCC.