RESUMEN
Artificial intelligence is highly regarded as the most promising future technology that will have a great impact on healthcare across all specialties. Its subsets, machine learning, deep learning, and artificial neural networks, are able to automatically learn from massive amounts of data and can improve the prediction algorithms to enhance their performance. This area is still under development, but the latest evidence shows great potential in the diagnosis, prognosis, and treatment of urological diseases, including bladder cancer, which are currently using old prediction tools and historical nomograms. This review focuses on highly significant and comprehensive literature evidence of artificial intelligence in the management of bladder cancer and investigates the near introduction in clinical practice.
RESUMEN
INTRODUCTION: Oncologic implications of variant histology (VH) have been extensively studied in bladder cancer; however, further investigation is needed in upper tract urothelial carcinoma (UTUC). Our study aims to evaluate the impact of VH on oncological outcomes in UTUC patients treated with radical nephroureterectomy (RNU). METHODS: A retrospective analysis was performed on patients who underwent a robotic or laparoscopic RNU for UTUC using the ROBUUST database, a multi-institutional collaborative including 17 centers worldwide. Logistic regression was used to assess the effect of VH on urothelial recurrence (bladder, contralateral upper tract), metastasis, and survival following RNU. RESULTS: A total of 687 patients were included in this study. Median (IQR) age was 71 (64-78) years and 470 (68%) had organ confined disease. VH was present in 70 (10.2%) patients. In a median follow-up of 16 months, the incidence of urothelial recurrence, metastasis, and mortality was 26.8%, 15.3%, and 11.8%, respectively. VH was associated with increased risk of metastasis (HR 4.3, P <.0001) and death (HR 2.0, P =.046). In multivariable analysis, VH was noted to be an independent risk factor for metastasis (HR 1.8, P =.03) but not for urothelial recurrence (HR 0.99, P =.97) or death (HR 1.4, P =.2). CONCLUSION: Variant histology can be found in 10% of patients with UTUC and is an independent risk factor for metastasis following RNU. Overall survival rates and the risk of urothelial recurrence in the bladder or contralateral kidney are not affected by the presence of VH.
Asunto(s)
Carcinoma de Células Transicionales , Neoplasias Ureterales , Neoplasias de la Vejiga Urinaria , Anciano , Humanos , Carcinoma de Células Transicionales/cirugía , Carcinoma de Células Transicionales/patología , Riñón/patología , Recurrencia Local de Neoplasia/patología , Nefroureterectomía/métodos , Estudios Retrospectivos , Neoplasias Ureterales/patología , Neoplasias de la Vejiga Urinaria/cirugíaRESUMEN
BACKGROUND: Contouring of anatomical regions is a crucial step in the medical workflow and is both time-consuming and prone to intra- and inter-observer variability. This study compares different strategies for automatic segmentation of the prostate in T2-weighted MRIs. METHODS: This study included 100 patients diagnosed with prostate adenocarcinoma who had undergone multi-parametric MRI and prostatectomy. From the T2-weighted MR images, ground truth segmentation masks were established by consensus from two expert radiologists. The prostate was then automatically contoured with six different methods: (1) a multi-atlas algorithm, (2) a proprietary algorithm in the Syngo.Via medical imaging software, and four deep learning models: (3) a V-net trained from scratch, (4) a pre-trained 2D U-net, (5) a GAN extension of the 2D U-net, and (6) a segmentation-adapted EfficientDet architecture. The resulting segmentations were compared and scored against the ground truth masks with one 70/30 and one 50/50 train/test data split. We also analyzed the association between segmentation performance and clinical variables. RESULTS: The best performing method was the adapted EfficientDet (model 6), achieving a mean Dice coefficient of 0.914, a mean absolute volume difference of 5.9%, a mean surface distance (MSD) of 1.93 pixels, and a mean 95th percentile Hausdorff distance of 3.77 pixels. The deep learning models were less prone to serious errors (0.854 minimum Dice and 4.02 maximum MSD), and no significant relationship was found between segmentation performance and clinical variables. CONCLUSIONS: Deep learning-based segmentation techniques can consistently achieve Dice coefficients of 0.9 or above with as few as 50 training patients, regardless of architectural archetype. The atlas-based and Syngo.via methods found in commercial clinical software performed significantly worse (0.855[Formula: see text]0.887 Dice).
Asunto(s)
Próstata , Neoplasias de la Próstata , Masculino , Humanos , Próstata/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Algoritmos , Neoplasias de la Próstata/diagnóstico por imagen , Imagen por Resonancia Magnética/métodosRESUMEN
Clear cell renal cell carcinoma (ccRCC) is fundamentally a metabolic disease. Given the importance of lipids in many cellular processes, in this study we delineated a lipidomic profile of human ccRCC and integrated it with transcriptomic data to connect the variations in cancer lipid metabolism with gene expression changes. Untargeted lipidomic analysis was performed on 20 ccRCC and 20 paired normal tissues, using LC-MS and GC-MS. Different lipid classes were altered in cancer compared to normal tissue. Among the long chain fatty acids (LCFAs), significant accumulations of polyunsaturated fatty acids (PUFAs) were found. Integrated lipidomic and transcriptomic analysis showed that fatty acid desaturation and elongation pathways were enriched in neoplastic tissue. Consistent with these findings, we observed increased expression of stearoyl-CoA desaturase(SCD1) and FA elongase 2 and 5 in ccRCC. Primary renal cancer cells treated with a small molecule SCD1 inhibitor (A939572) proliferated at a slower rate than untreated cancer cells. In addition, after cisplatin treatment, the death rate of tumor cells treated with A939572 was significantly greater than that of untreated cancer cells. In conclusion, our findings delineate a ccRCC lipidomic signature and showed that SCD1 inhibition significantly reduced cancer cell proliferation and increased cisplatin sensitivity, suggesting that this pathway can be involved in ccRCC chemotherapy resistance.
RESUMEN
Perineal seeding of tumor cells from prostate cancer (PCa) is very rare, and no standard treatment exists for this atypical presentation with no evidence of distant metastases. Local excision or external beam radiotherapy are used as local salvage treatments for such perineal masses, including those occurring after biopsy, surgery, or interstitial brachytherapy. We report on a patient who presented no evidence of disease and no late urinary or gastrointestinal toxicities at 58 months after receiving high-dose-rate brachytherapy (HDR-BT) for perineal recurrence of PCa after radical prostatectomy and salvage external beam radiotherapy. To the best of our knowledge, this is the first case treated with HDR-BT in this scenario.
RESUMEN
ABSTRACT Background: To date, few series on robot-assisted radical prostatectomy (RARP) in kidney transplant recipients (KTRs) have been published. Purpose: To report the experience of two referral centers adopting two different RARP approaches in KTRs. Surgical, oncological and functional results were primary outcomes evaluated in the study. Material and methods: We retrospectively analyzed data from 9 KTRs who underwent transperitoneal RARP or Retzius-sparing RARP for PCa from October 2012 to April 2016. Data were reported as median and interquartile range (IQR). Pre- and postoperative outcomes were compared by non-parametric Wilcoxon signed-rank test. Significant differences were accepted when p ≤ 0.05. Overall survival was assessed using Kaplan-Meier method. Results: Four KTRs underwent a T-RARP and 5 a RS-RARP. Patient median age was 60 (56-63) years. Charlson comorbidity index was 6 (5-6). Preoperative median PSA was 5.6 (5-15) ng / mL. Preoperative Gleason score (GS) was 6 in 5 patients, 7 (3 + 4) in 3, and 8 (4 + 4) in one. Pre- and postoperative creatinine were 1.17 (1.1; 1.4) and 1.3 (1.07; 1.57) mg / dL (p = 0.237), while eGFR was 66 (60-82) and 62 (54-81) mL / min / 1.73m2 (p = 0.553), respectively. One (11.1%) Clavien-Dindo grade II complication occurred. Two extended template lymphadenectomies were performed, both with nodal invasion. These two patients experienced a biochemical recurrence and were subjected to RT. Two patients (22.2%) had PSMs. Median follow-up was 42 months. Seven patients (77.8%) were continent, 5 (55.6%) were potent. Two (22.2%) patients died during follow-up for oncologic unrelated causes. Conclusions: Our series suggests that both RARP approaches are safe and feasible techniques in KTRs for PCa.
Asunto(s)
Humanos , Masculino , Prostatectomía/métodos , Neoplasias de la Próstata/cirugía , Trasplante de Riñón/métodos , Procedimientos Quirúrgicos Robotizados/métodos , Periodo Posoperatorio , Próstata/patología , Neoplasias de la Próstata/patología , Estudios Retrospectivos , Estudios de Seguimiento , Resultado del Tratamiento , Estimación de Kaplan-Meier , Clasificación del Tumor , Escisión del Ganglio Linfático , Persona de Mediana EdadRESUMEN
AIMS: Carboplatin plus etoposide has modest efficacy in docetaxel-pretreated castration-resistant prostate cancer patients. We hypothesized that carboplatin-etoposide could still exert some therapeutic activity after docetaxel, cabazitaxel and either abiraterone or enzalutamide. PATIENTS & METHODS: We enrolled 15 patients in the first step of a Phase II trial. The target sample size is 46 patients. The primary end point of the study was progression-free survival after 12 weeks. RESULTS: The median progression-free survival was 11 weeks (range: 8-18), while median overall survival was 18 weeks (range: 12-26). Of seven patients with measurable disease, two had a partial response, two showed stable disease and the remaining three had progressive disease as the best radiological response. Five patients were considered progression-free after 12 weeks, prompting continuation of the trial. CONCLUSION: Our preliminary findings support the hypothesis that carboplatin plus etoposide may yield some clinical benefit in a population of patients who failed all currently approved therapeutic options for prostate cancer.