ABSTRACT
BACKGROUND AND OBJECTIVE: Renal function preservation is particularly important following nonoperative treatment of localized renal cell carcinoma (RCC) since patients are often older with medical comorbidities. Our objective was to report long-term renal function outcomes after stereotactic ablative radiotherapy (SABR) including patients with a solitary kidney. METHODS: Patients with primary RCC treated with SABR with ≥2 yr of follow-up at 12 International Radiosurgery Consortium for Kidney institutions were included. Renal function was measured by estimated glomerular filtration rate (eGFR). KEY FINDINGS AND LIMITATIONS: In total, 190 patients (56 with a solitary kidney) underwent SABR and were followed for a median of 5.0 yr (interquartile range [IQR]: 3.4-6.8). In patients with a solitary kidney versus bilateral kidneys, pre-SABR eGFR (mean [standard deviation]) was 61.1 (23.2) versus 58.0 (22.3) ml/min (p = 0.32) and the median tumor size was 3.65 cm (IQR: 2.59-4.50 cm) versus 4.00 cm (IQR: 3.00-5.00 cm; p = 0.026). At 5 yr after SABR, eGFR decreased by -14.5 (7.6) and -13.3 (15.9) ml/min (p = 0.67), respectively, and there were similar rates of post-SABR dialysis (3.6% [n = 2/56] vs 3.7% [n = 5/134]). A multivariable analysis demonstrated that increasing tumor size (odds ratio [OR] per 1 cm: 1.57; 95% confidence interval [CI]: 1.14-2.16, p = 0.0055) and baseline eGFR (OR per 10 ml/min: 1.30; 95% CI: 1.02-1.66, p = 0.034) were associated with an eGFR decline of ≥15 ml/min at 1 yr. CONCLUSIONS AND CLINICAL IMPLICATIONS: With long-term follow-up after SABR, kidney function decline remains moderate, with no observed difference between patients with a solitary kidney and bilateral kidneys. Tumor size and baseline eGFR are dominant factors predictive of long-term renal function decline. PATIENT SUMMARY: With long-term follow-up, stereotactic ablative radiotherapy (SABR) yields moderate long-term renal function decline and low dialysis rates even in patients with a solitary kidney. SABR thus represents a promising noninvasive, nephron-sparing option for patients with localized renal cell carcinoma.
ABSTRACT
Background and purpose: Radiation-induced erectile dysfunction (RiED) commonly affects prostate cancer patients, prompting clinical trials across institutions to explore dose-sparing to internal-pudendal-arteries (IPA) for preserving sexual potency. IPA, challenging to segment, isn't conventionally considered an organ-at-risk (OAR). This study proposes a deep learning (DL) auto-segmentation model for IPA, using Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) or CT alone to accommodate varied clinical practices. Materials and methods: A total of 86 patients with CT and MRI images and noisy IPA labels were recruited in this study. We split the data into 42/14/30 for model training, testing, and a clinical observer study, respectively. There were three major innovations in this model: 1) we designed an architecture with squeeze-and-excite blocks and modality attention for effective feature extraction and production of accurate segmentation, 2) a novel loss function was used for training the model effectively with noisy labels, and 3) modality dropout strategy was used for making the model capable of segmentation in the absence of MRI. Results: Test dataset metrics were DSC 61.71 ± 7.7 %, ASD 2.5 ± .87 mm, and HD95 7.0 ± 2.3 mm. AI segmented contours showed dosimetric similarity to expert physician's contours. Observer study indicated higher scores for AI contours (mean = 3.7) compared to inexperienced physicians' contours (mean = 3.1). Inexperienced physicians improved scores to 3.7 when starting with AI contours. Conclusion: The proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.