Long-term follow-up study of the malignant transformation potential of the simple renal cysts

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.

Relationship Between Sporadic Renal Cysts and Renal Function Detected by Isotope Renography in Type 2 Diabetes

PURPOSE

This study aimed to reveal the relationship between the volume of sporadic renal cysts and renal function in patients with type 2 diabetes (T2D).

MATERIALS AND METHODS

One hundred and seventy-one patients that underwent renal imaging and other routine examinations at the Shanghai Pudong Hospital were included in this study. The Gates' method of glomerular filtration rate (GFR) was measured by ^99mTc-DTPA renal dynamic imaging in addition to the eGFR, calculated by the Chronic Kidney Disease Epidemiology Collaboration equation (CKD-EPI).

RESULTS

Our results showed that BMI, total iGFR, and eGFR showed significant differences between patients with T2D with or without SRC (p < 0.05). Spearman correlation analysis showed that cyst volume was positively correlated with Scr and gender but not iGFR (p > 0.05). The total iGFR positively correlated with eGFR (r = 0.83, p < 0.0001) and negatively with Scr (r = -0.78, p < 0.0001), age (r = -0.43, p < 0.0001), duration of T2D (r = -0.25, p = 0.001), and BMI (r = -0.21, p = 0.006) but not gender (r = -0.03, p = 0.668). The multilinear regression model revealed that gender (β = 0.346, p < 0.001), iGFR (β = -0.705, p < 0.001), and serum uric acid (β = 0.195, p = 0.032) were independent predictors of Scr. Moreover, we observed a significant increase in Scr in males (p < 0.05). Finally, we found that the split kidney function reflected by iGFR and related parameters such as time to peak (PTT) and half time of excretion (excrete t1/2) did not mutually distinguish from each other significantly whether they are measured in patients with renal cysts or in those without renal cysts (p > 0.05).

CONCLUSION

Our preliminary results suggest that in T2D, SRCs may be a renal complication of diabetic nephropathy. Although we found that the patients with renal cysts may display reduced iGFR, the volume of simple cysts seems not to exacerbate renal insufficiency. Isotope renography is a useful tool to evaluate the split kidney functions in diabetic patients who acquire single-side cysts.

Prevalence, risk factors and clinical characteristics of renal dysfunction in Chinese outpatients with growth simple renal cysts

Background

Researchers have proved that simple renal cysts (SRCs) might be correlated with renal dysfunction, but it is still controversial. Thus, we conducted clinical research study with large sample size and long-term follow-up to clarify the relationship between SRCs and renal dysfunction.

Methods

A total of 571 SRCs patients in outpatients of nephrology department were included, we investigated the clinical characteristics of growth SRCs compared with non-growth SRCs, evaluated the incidence of renal dysfunction in SRCs and explored the risk factors of renal dysfunction in growth SRCs.

Results

The mean baseline age was 51.31 ± 14.37 years in the whole cohort, ranging from 19 to 79 years, and 57.6% of them were male. The median follow-up duration was 3 years, ranging from 1 to 10 years. In addition, the final maximum diameter increased 1 mm (2.74%) per year. Patients in growth SRCs group tented to have higher percentage of hypertension, hematuria, large cyst and multiple cysts compared with non-growth SRCs group. The prevalence of renal dysfunction was 15.6% after the follow-up, and the prevalence of renal dysfunction was about 10 times higher in growth SRCs group than non-growth SRCs group (23.3% vs. 2.4%). Renal dysfunction was significantly associated with age, female, total cholesterol, diastolic blood pressure, final maximum diameter and yearly change in maximum diameter in growth SRCs.

Conclusions

SRCs were closely related to the decline of renal function, we recommend close follow-up for growth SRCs.