Browsing by Subject "Radical prostatectomy"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Predictors of Worsening Erectile Function in Men with Functional Erections Early After Radical Prostatectomy
    (Oxford, 2022-12) Salter, Carolyn A.; Tin, Amy L.; Bernie, Helen L.; Nascimento, Bruno; Katz, Darren J.; Benfante, Nicole E.; Carlsson, Sigrid V.; Mulhall, John P.; Urology, School of Medicine
    Background: Prior studies suggest that men with good erectile function shortly after radical prostatectomy (RP) can subsequently have worsened erectile function. Aim: To determine the prevalence and predictors of early erectile function recovery post-RP and of worsening erectile function after initial erectile function recovery. Methods: We retrospectively queried our institutional database. Men who underwent RP during 2008-2017 and who completed the International Index of Erectile Function erectile function domain both pre-RP and serially post-RP, constituted the population. Functional erections were defined as International Index of Erectile Function (IIEF)-6 erectile function domain scores ≥24. We analyzed factors predicting functional erections at 3 months post-RP as well as factors predicting a decrease in functional erections between 3 and 6 months, defined as ≥2-point drop in the erectile function domain. Multivariable logistic regression models were used to identify predictors of early erectile function recovery and also of subsequent decline. Outcomes: Erectile function recovery rates at 3 months post-RP and predictive factors; rates of erectile function decline between 3-6 months and associated predictors. Results: Eligible patients comprised 1,655 men with median age of 62 (IQR 57, 67) years. Bilateral nerve-sparing (NS) surgery was performed in 71% of men, unilateral NS in 19%, and no NS in 10%. Of this population, 224 men (14%; 95% CI 12%, 15%) had functional erections at 3 months post-RP. On multivariable analysis, significant predictors of early erectile function recovery included: younger age (OR 0.93, P < .001), higher baseline erectile function domain score (OR 1.14, P < .001) and bilateral NS (OR 3.81, P = .002). The presence of diabetes (OR 0.43, P = .028) and a former smoking history (OR 0.63, P = .008; reference group: never smoker) was associated with the erectile dysfunction at 3 months post-RP. Of the men with early functional erections, 41% (95% CI 33%, 48%) had a ≥ 2-point decline in erectile function between 3 and 6 months. No factors were identified as predictors for this decline. Clinical implications: Only a small proportion of men have functional erections at 3 months post-RP and a notable number of them will experience a decline in erectile function between 3 and 6 months. Strengths and limitations: Strengths: large patient population and the use of validated questionnaire. Limitations: single-center retrospective study. Conclusion: A minority of men had functional erections 3 months post-RP, about half of whom had a decline in erectile function by month 6. We recommend appropriately counseling post-RP patients on the risk of such a decline in erectile function. Salter CA, Tin AL, Bernie HL, et al. Predictors of Worsening Erectile Function in Men with Functional Erections Early After Radical Prostatectomy. J Sex Med 2022;19:1790-1796.
  • Thumbnail Image
    Item
    Stress testing deep learning models for prostate cancer detection on biopsies and surgical specimens
    (Wiley, 2025) Flannery, Brennan T.; Sandler, Howard M.; Lal, Priti; Feldman, Michael D.; Santa-Rosario, Juan C.; Pathak, Tilak; Mirtti, Tuomas; Farre, Xavier; Correa, Rohann; Chafe, Susan; Shah, Amit; Efstathiou, Jason A.; Hoffman, Karen; Hallman, Mark A.; Straza, Michael; Jordan, Richard; Pugh, Stephanie L.; Feng, Felix; Madabhushi, Anant; Pathology and Laboratory Medicine, School of Medicine
    The presence, location, and extent of prostate cancer is assessed by pathologists using H&E-stained tissue slides. Machine learning approaches can accomplish these tasks for both biopsies and radical prostatectomies. Deep learning approaches using convolutional neural networks (CNNs) have been shown to identify cancer in pathologic slides, some securing regulatory approval for clinical use. However, differences in sample processing can subtly alter the morphology between sample types, making it unclear whether deep learning algorithms will consistently work on both types of slide images. Our goal was to investigate whether morphological differences between sample types affected the performance of biopsy-trained cancer detection CNN models when applied to radical prostatectomies and vice versa using multiple cohorts (N = 1,000). Radical prostatectomies (N = 100) and biopsies (N = 50) were acquired from The University of Pennsylvania to train (80%) and validate (20%) a DenseNet CNN for biopsies (MB), radical prostatectomies (MR), and a combined dataset (MB+R). On a tile level, MB and MR achieved F1 scores greater than 0.88 when applied to their own sample type but less than 0.65 when applied across sample types. On a whole-slide level, models achieved significantly better performance on their own sample type compared to the alternative model (p < 0.05) for all metrics. This was confirmed by external validation using digitized biopsy slide images from a clinical trial [NRG Radiation Therapy Oncology Group (RTOG)] (NRG/RTOG 0521, N = 750) via both qualitative and quantitative analyses (p < 0.05). A comprehensive review of model outputs revealed morphologically driven decision making that adversely affected model performance. MB appeared to be challenged with the analysis of open gland structures, whereas MR appeared to be challenged with closed gland structures, indicating potential morphological variation between the training sets. These findings suggest that differences in morphology and heterogeneity necessitate the need for more tailored, sample-specific (i.e. biopsy and surgical) machine learning models.