Retroperitoneoscopic Partial Nephrectomy for Moderately Complex Ventral Hilar Tumors: Surgical Technique and Trifecta Outcomes from a Single Institution in China

Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma

Due to the complicated histopathological characteristics of clear-cell renal-cell carcinoma (ccRCC), non-invasive prognosis before operative treatment is crucial in selecting the appropriate treatment. A total of 126 345 computerized tomography (CT) images from four independent patient cohorts were included for analysis in this study. We propose a V Bottleneck multi-resolution and focus-organ network (VB-MrFo-Net) using a cascade framework for deep learning analysis. The VB-MrFo-Net achieved better performance than VB-Net in tumor segmentation, with a Dice score of 0.87. The nuclear-grade prediction model performed best in the logistic regression classifier, with area under curve values from 0.782 to 0.746. Survival analysis revealed that our prediction model could significantly distinguish patients with high survival risk, with a hazard ratio (HR) of 2.49 [95% confidence interval (CI): 1.13-5.45, P = 0.023] in the General cohort. Excellent performance had also been verified in the Cancer Genome Atlas cohort, the Clinical Proteomic Tumor Analysis Consortium cohort, and the Kidney Tumor Segmentation Challenge cohort, with HRs of 2.77 (95%CI: 1.58-4.84, P = 0.0019), 3.83 (95%CI: 1.22-11.96, P = 0.029), and 2.80 (95%CI: 1.05-7.47, P = 0.025), respectively. In conclusion, we propose a novel VB-MrFo-Net for the renal tumor segmentation and automatic diagnosis of ccRCC. The risk stratification model could accurately distinguish patients with high tumor grade and high survival risk based on non-invasive CT images before surgical treatments, which could provide practical advice for deciding treatment options.

Machine learning-based pathomics signature could act as a novel prognostic marker for patients with clear cell renal cell carcinoma

BACKGROUND

Traditional histopathology performed by pathologists through naked eyes is insufficient for accurate survival prediction of clear cell renal cell carcinoma (ccRCC).

METHODS

A total of 483 whole slide images (WSIs) data from three patient cohorts were retrospectively analyzed. We performed machine learning algorithm to identify optimal digital pathological features and constructed machine learning-based pathomics signature (MLPS) for ccRCC patients. Prognostic performance of the prognostic model was also verified in two independent validation cohorts.

RESULTS

MLPS could significantly distinguish ccRCC patients with high survival risk, with hazard ratio of 15.05, 4.49 and 1.65 in three independent cohorts, respectively. Cox regression analysis revealed that the MLPS could act as an independent prognostic factor for ccRCC patients. Integration nomogram based on MLPS, tumour stage system and tumour grade system improved the current survival prediction accuracy for ccRCC patients, with area under curve value of 89.5%, 90.0%, 88.5% and 85.9% for 1-, 3-, 5- and 10-year disease-free survival prediction.

DISCUSSION

The machine learning-based pathomics signature could act as a novel prognostic marker for patients with ccRCC. Nevertheless, prospective studies with multicentric patient cohorts are still needed for further verifications.

[Primary application of Gerota's fascia suspension device in retroperitoneal laparoscopic partial nephrectom]

OBJECTIVE

To evaluate the value of Gerota's fascia suspension device in retroperitoneal laparoscopic partial nephrectomy, and to share the operation experience.

METHODS

From October 2018 to December 2020, 6 cases of tumor located in the ventral side of the kidney were selected, including 3 males and 3 females, with 3 cases on the right side and 3 cases on the left side, aged 38-60 years, with an average of 52 years. The body mass index (BMI) was 18.3-30.2 kg/m², with an average of 22.9 kg/m². One patient with diabetes mellitus, three patients with renal cysts, and two patients underwent cholecystectomy before. All the patients were found by physical examinations. The course of disease was 7 days to 20 years, with a median time of 1 month. The tumor was in the ventral side of the kidney, 2 cases located in the upper pole, 1 case in the lower pole and 3 cases near the renal hilum. The tumor size was 1.2-7.8 cm, with an average of 4.5 cm. The R.E.N.A.L score was 7 in 1 case, 8 in 3 cases and 9 in 2 cases. After the preoperative examination completed, retroperitoneal laparoscopic partial nephrectomy (Gerota's fascia suspension device) was performed.

RESULTS

All the operations were successfully completed. The operation time ranged from 139 to 193 min, with an average of 172 min. The renal artery occlusion time was 7-43 min, with an average of 19 min, only one case was more than 30 min. The blood loss ranged from 10 to 500 mL, with an average of 128 mL. The postoperative hospital stay ranged from 4 to 13 days, with an average of 6.5 days. Postoperative pathology revealed 4 cases of renal angiomyolipoma and 2 cases of renal clear cell carcinoma. The patients were followed up for 2-27 months, with an average of 17 months, without recurrence.

CONCLUSION

In the operation of retroperitoneal laparoscopic partial nephrectomy, Gerota's fascia suspension device is beneficial to expose the ventral surgical field, and it is convenient for the surgeon to operate with both hands. This technique is an effective method to deal with the ventral renal tumor, which is worthy of promotion.

Computed Tomography Radiomics for Predicting Pathological Grade of Renal Cell Carcinoma

Background

Clear cell renal cell carcinoma (ccRCC) is the most common renal cancer and it has the worst prognosis among all renal cancers. However, traditional radiological characteristics on computed tomography (CT) scans of ccRCC have been insufficient to predict the pathological grade of ccRCC before surgery.

Methods

Patients with ccRCC were retrospectively enrolled into this study and were separated into two groups according to the World Health Organization (WHO)/International Society of Urological Pathology (ISUP) grading system, i.e., low-grade (Grade I and II) group and high-grade (Grade III and IV) group. Traditional CT radiological characteristics such as tumor size, pre- and post-enhancing CT densities were assessed. In addition, radiomic texture analysis based on the CT imaging of the ccRCC were also performed. A CT-based machine learning method combining the traditional radiological characteristics and radiomic features was used in the predictive modeling for differentiating the low-grade from the high-grade ccRCC. Model performance was evaluated with the receiver operating characteristic curve (ROC) analysis.

Results

A total of 264 patients with pathologically confirmed ccRCC were included in this study. In this cohort, 206 patients had the low-grade tumors and 58 had the high-grade tumors. The model built with traditional radiological characteristics achieved an area under the curve (AUC) of 0.9175 (95% CI: 0.8765–0.9585) and 0.8088 (95% CI: 0.7064–0.9113) in differentiating the low-grade from the high-grade ccRCC for the training cohort and the validation cohort respectively. The model built with the radiomic textural features yielded an AUC value of 0.8170 (95% CI: 0.7353–0.8987) and 0.8017 (95% CI: 0.6878–0.9157) for the training cohort and the validation cohort, respectively. The combined model integrating both the traditional radiological characteristics and the radiomic textural features achieved the highest efficacy, with an AUC of 0.9235 (95% CI: 0.8646–0.9824) and an AUC of 0.9099 (95% CI: 0.8324–0.9873) for the training cohort and validation cohort, respectively.

Conclusion

We developed a machine learning radiomic model achieving a satisfying performance in differentiating the low-grade from the high-grade ccRCC. Our study presented a potentially useful non-invasive imaging-focused method to predict the pathological grade of renal cancers prior to surgery.

Retroperitoneal laparoscopic partial versus radical nephrectomy for large (≥ 4 cm) and anatomically complex renal tumors: A propensity score matching study

INTRODUCTION

To assess the safety and efficiency of retroperitoneal laparoscopic partial nephrectomy (RLPN) and retroperitoneal laparoscopic radical nephrectomy (RLRN) for large (≥4 cm) renal tumors with a RENAL nephrometry score ≥7.

MATERIALS AND METHODS

We retrospectively identified and analyzed the data of 254 patients who underwent RLPN or RLRN for large (≥4 cm) and anatomically complex renal tumors between 2008 and 2017. Propensity score matching (PSM) (1:1) method was conducted to adjust for preoperative clinical characteristics. Preoperative, renal functional, and oncological outcomes were compared.

RESULTS

Finally, no significant differences in the baseline characteristics existed between the two groups after PSM. Within the well-balanced matched cohort, longer operating time (OT) and higher estimated blood loss (EBL) were found in RLPN group (p = 0.015 and p = 0.019, respectively), and RLPN trended to protect renal function better at a higher risk of low-grade complications (-10.9 vs -16.8 ml/min, p = 0.001; 23.0% vs 10.8%, p = 0.048, respectively). The patients in the RLPN group had a better overall survival (OS) than those in RLRN group, but cancer-specific survival and progression-free survival didn't differ significantly between the two groups.

CONCLUSION

For patients with large (≥4 cm) and anatomically complex renal tumors, RLPN by highly experienced hands has an evident tendency to a better protection of renal function and a longer OS without waiving oncological control in comparison with RLRN, but at the expense of longer OT, a higher EBL and a higher risk of low-grade complications.

Renal solitary fibrous tumor/hemangiopericytoma: computed tomography findings and clinicopathologic features

PURPOSE

To retrospectively characterize the clinical, pathological, and computed tomography (CT) findings of renal solitary fibrous tumor/hemangiopericytoma (rSFT/HPC).

METHODS

Twelve patients with rSFT/HPCs were enrolled. The CT findings and clinicopathological features were retrospectively reviewed.

RESULTS

This study included six male and six female patients (median age: 47; age range: 20-82 years). Eight benign (grade I) and four malignant (grade III) rSFT/HPCs were identified. Of the 12 lesions, 10 were in the renal sinus near the renal pelvis, while two replaced the whole kidney. Five lesions were well-defined, five were partially ill-defined, and two were ill-defined. Mild (5/12) and intermediate (1/12) hydronephrosis was observed. On the unenhanced CT images, ten tumors showed slightly higher density when compared to the normal renal parenchyma, and two masses were isodense to hypodense. After intravenous contrast medium injection, three enhancement patterns were observed, including "prolonged enhancement" (PE) (6/12), "gradual enhancement" (4/12), and "early washout" (2/12). A central fibrous scar was found in five patients. Compared to the grade I lesions, the grade III rSFT/HPC lesions tended to be larger (maximal diameter > 10 cm) and more heterogeneous with a higher incidence of the PE pattern.

CONCLUSIONS

We have shown that rSFT/HPCs usually arise from the renal sinus, and present as lobulated, slightly hyperdense, gradually enhancing soft tissue masses. CT findings, including large size, heterogeneity, and the PE pattern, may assist in the pre-operative identification of malignant grade III rSFT/HPCs.