Multiple mask and boundary scoring R-CNN with cGAN data augmentation for bladder tumor segmentation in WLC videos.

Automatic diagnosis systems capable of handling multiple pathologies are essential in clinical practice. This study focuses on enhancing precise lesion localization, classification and delineation in transurethral resection of bladder tumor (TURBT) to reduce cancer recurrence. Despite deep learning models success, medical applications face challenges like small and limited datasets and poor image characterization, including the absence lack of color/texture modeling. To address these issues, three solutions are proposed: (1) an improved texture-constrained version of the pix2pixHD cGAN for data augmentation, addressing the tradeoff of generating high-quality images with enough stochasticity using the Fréchet Inception Distance (FID) measure. (2) Introducing the Multiple Mask and Boundary Scoring R-CNN (MM&BS R-CNN), a new mask sub-net scheme where multiple masks are generated from the different levels of the mask sub-net pipeline, improving segmentation accuracy by including a new scoring module to refine object boundaries. (3) A novel accelerated training strategy based on the SGD optimizer with the second momentum. Experimental results show significant mAP improvements: the data generation scheme improves by more than 12 %; MM&BS R-CNN proposed architecture is responsible for an improvement of about 1.25 %, and the training algorithm based on the second-order momentum increases mAP by 2-3 %. The simultaneous use of all three proposals improved the state-of-the-art mAP by 17.44 %.

Prognostic Factor Risk Groups for Clinical Stage I Seminoma: An Individual Patient Data Analysis by the European Association of Urology Testicular Cancer Guidelines Panel and Guidelines Office.

BACKGROUND: The relapse rate in patients with clinical stage I (CSI) seminomatous germ cell tumor of the testis (SGCTT) who were undergoing surveillance after radical orchidectomy is 4-30%, depending on tumor size and rete testis invasion (RTI). However, the level of evidence supporting the use of both risk factors in clinical decision-making is low. OBJECTIVE: We aimed to identify the most important prognostic factors for relapse in CSI SGCTT patients. DESIGN, SETTING, AND PARTICIPANTS: Individual patient data for 1016 CSI SGCTT patients diagnosed between 1994 and 2019 with normal postorchidectomy serum tumor marker levels and undergoing surveillance were collected from nine institutions. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Multivariable Cox proportional hazard regression models were fit to identify the most important prognostic factors. The primary endpoint was the time to first relapse by imaging and/or markers. Relapse probabilities were estimated by the Kaplan-Meier method. RESULTS AND LIMITATIONS: After a median follow-up of 7.7 yr, 149 (14.7%) patients had relapsed. Categorical tumor size (≤2, >2-5, and >5 cm), presence of RTI, and lymphovascular invasion were used to form three risk groups: low (56.4%), intermediate (41.3%), and high (2.3%) risks with 5-yr cumulative relapse probabilities of 8%, 20%, and 44%, respectively. The model outperformed the currently used model with tumor size ≤4 versus >4 cm and presence of RTI (Harrell's C index 0.65 vs 0.61). The low- and intermediate-risk groups were validated successfully in an independent cohort of 285 patients. CONCLUSIONS: The risk of relapse after radical orchidectomy in CSI SGCTT patients under surveillance is low. We propose a new risk stratification model that outperformed the current model and identified a small subgroup with a high risk of relapse. PATIENT SUMMARY: The risk of relapse after radical orchidectomy in patients with clinical stage I seminomatous germ cell tumor of the testis is low. We propose a new risk stratification model that outperformed the current model and identified a small subgroup with a high risk of relapse.

Testis-sparing Surgery in Adult Patients with Germ Cell Tumors: Systematic Search of the Literature and Focused Review.

Testis-sparing surgery (TSS) is a guideline-recommended treatment option for men with synchronous or metachronous bilateral testicular germ-cell tumor (GCT) or GCT in a solitary testicle. The tumor volume should not exceed 50% of the total testicular volume and serum concentrations of both testosterone and luteinizing hormone should be within the normal ranges. After tumor enucleation, patients should undergo adjuvant radiation of the testicle in case of germ cell neoplasia in situ. The local relapse rate is approximately 4% if TSS is performed properly. Physiological serum testosterone concentrations are achieved in more than 85% of patients, and approximately 50% of men with intact spermatogenesis can achieve paternity. The risk of systemic metastases is not increased by TSS. PATIENT SUMMARY: Testis-sparing surgery is the treatment of choice for men with testicular cancer in both testes or in men who have just one testis. In more than 85% of patients this approach results in maintenance of normal testosterone levels.