Deep Learning Improves Speed and Accuracy of Prostate Gland Segmentations on Magnetic Resonance Imaging for Targeted Biopsy.

PURPOSE: Targeted biopsy improves prostate cancer diagnosis. Accurate prostate segmentation on magnetic resonance imaging (MRI) is critical for accurate biopsy. Manual gland segmentation is tedious and time-consuming. We sought to develop a deep learning model to rapidly and accurately segment the prostate on MRI and to implement it as part of routine magnetic resonance-ultrasound fusion biopsy in the clinic. MATERIALS AND METHODS: A total of 905 subjects underwent multiparametric MRI at 29 institutions, followed by magnetic resonance-ultrasound fusion biopsy at 1 institution. A urologic oncology expert segmented the prostate on axial T2-weighted MRI scans. We trained a deep learning model, ProGNet, on 805 cases. We retrospectively tested ProGNet on 100 independent internal and 56 external cases. We prospectively implemented ProGNet as part of the fusion biopsy procedure for 11 patients. We compared ProGNet performance to 2 deep learning networks (U-Net and holistically-nested edge detector) and radiology technicians. The Dice similarity coefficient (DSC) was used to measure overlap with expert segmentations. DSCs were compared using paired t-tests. RESULTS: ProGNet (DSC=0.92) outperformed U-Net (DSC=0.85, p <0.0001), holistically-nested edge detector (DSC=0.80, p <0.0001), and radiology technicians (DSC=0.89, p <0.0001) in the retrospective internal test set. In the prospective cohort, ProGNet (DSC=0.93) outperformed radiology technicians (DSC=0.90, p <0.0001). ProGNet took just 35 seconds per case (vs 10 minutes for radiology technicians) to yield a clinically utilizable segmentation file. CONCLUSIONS: This is the first study to employ a deep learning model for prostate gland segmentation for targeted biopsy in routine urological clinical practice, while reporting results and releasing the code online. Prospective and retrospective evaluations revealed increased speed and accuracy.

Contemporary Use of Partial Nephrectomy: Are Older Patients With Impaired Kidney Function Being Left Behind?

OBJECTIVE: To assess whether patient factors, such as age and preoperative kidney function, were associated with receipt of partial nephrectomy in a national integrated healthcare system. MATERIALS AND METHODS: We identified patients treated with a radical or partial nephrectomy from 2002 to 2014 in the Veterans Health Administration. We examined associations among patient age, sex, race or ethnicity, multimorbidity, baseline kidney function, tumor characteristics, and receipt of partial nephrectomy. We estimated the odds of receiving a partial nephrectomy and assessed interactions between covariates and the year of surgery to explore whether patient factors associated with partial nephrectomy changed over time. RESULTS: In our cohort of 14,186 patients, 4508 (31.2%) received a partial nephrectomy. Use of partial nephrectomy increased from 17% in 2002 to 32% in 2008 and to 38% in 2014. Patient race or ethnicity, age, tumor stage, and year of surgery were independently associated with receipt of partial nephrectomy. Black veterans had significantly increased odds of receipt of partial nephrectomy, whereas older patients had significantly reduced odds. Partial nephrectomy utilization increased for all groups over time, but older patients and patients with worse baseline kidney function showed the least increase in odds of partial nephrectomy. CONCLUSION: Although the utilization of partial nephrectomy increased for all groups, the greatest increase occurred in the youngest patients and those with the highest baseline kidney function. These trends warrant further investigation to ensure that patients at the highest risk of impaired kidney function are considered for partial nephrectomy whenever possible.

Spirituality influences health related quality of life in men with prostate cancer.

Spirituality is interdependent with the biological, psychological, and interpersonal aspects of life. Although spirituality has been studied in breast cancer survivors, little work has been done in men with prostate cancer. We sought to determine whether lower spirituality in men with early stage prostate cancer is associated with worse general health-related quality of life (HRQOL), disease-specific HRQOL, or psychosocial health. Two hundred and twenty-two subjects were drawn from a state-funded program providing free prostate cancer treatment to indigent men. Validated instruments captured spirituality, general and disease-specific HRQOL, anxiety, symptom distress, and emotional well-being. We found a consistent relationship between spirituality and the outcomes assessed. Low spirituality was associated with significantly worse physical and mental health, sexual function and more urinary bother after controlling for covariates. All of the psychosocial variables studied reflected worse adjustment in the men with low spirituality. Because the likelihood of prostate cancer survivorship is high, interventions targeting spirituality could impact the physical and psychosocial health of many men.