RESUMEN
OBJECTIVE: Develop a pioneer surgical anonymization algorithm for reliable and accurate real-time removal of out-of-body images validated across various robotic platforms. BACKGROUND: The use of surgical video data has become a common practice in enhancing research and training. Video sharing requires complete anonymization, which, in the case of endoscopic surgery, entails the removal of all nonsurgical video frames where the endoscope can record the patient or operating room staff. To date, no openly available algorithmic solution for surgical anonymization offers reliable real-time anonymization for video streaming, which is also robotic-platform and procedure-independent. METHODS: A data set of 63 surgical videos of 6 procedures performed on four robotic systems was annotated for out-of-body sequences. The resulting 496.828 images were used to develop a deep learning algorithm that automatically detected out-of-body frames. Our solution was subsequently benchmarked against existing anonymization methods. In addition, we offer a postprocessing step to enhance the performance and test a low-cost setup for real-time anonymization during live surgery streaming. RESULTS: Framewise anonymization yielded a receiver operating characteristic area under the curve score of 99.46% on unseen procedures, increasing to 99.89% after postprocessing. Our Robotic Anonymization Network outperforms previous state-of-the-art algorithms, even on unseen procedural types, despite the fact that alternative solutions are explicitly trained using these procedures. CONCLUSIONS: Our deep learning model, Robotic Anonymization Network, offers reliable, accurate, and safe real-time anonymization during complex and lengthy surgical procedures regardless of the robotic platform. The model can be used in real time for surgical live streaming and is openly available.
Asunto(s)
Algoritmos , Procedimientos Quirúrgicos Robotizados , Humanos , Anonimización de la Información , Grabación en Video , Aprendizaje ProfundoRESUMEN
Despite being standard tools for decision-making, the European Organisation for Research and Treatment of Cancer (EORTC), European Association of Urology (EAU), and Club Urologico Espanol de Tratamiento Oncologico (CUETO) risk groups provide moderate performance in predicting recurrence-free survival (RFS) and progression-free survival (PFS) in non-muscle-invasive bladder cancer (NMIBC). In this retrospective combined-cohort data-mining study, the training group consisted of 3570 patients with de novo diagnosed NMIBC. Predictors included gender, age, T stage, histopathological grading, tumor burden and diameter, EORTC and CUETO scores, and type of intravesical treatment. The models developed were externally validated using an independent cohort of 322 patients. Models were trained using Cox proportional-hazards deep neural networks (deep learning; DeepSurv) with a proprietary grid search of hyperparameters. For patients treated with surgery and bacillus Calmette-Guérin-treated patients, the models achieved a c index of 0.650 (95% confidence interval [CI] 0.649-0.650) for RFS and 0.878 (95% CI 0.873-0.874) for PFS in the training group. In the validation group, the c index was 0.651 (95% CI 0.648-0.654) for RFS and 0.881 (95% CI 0.878-0.885) for PFS. After inclusion of patients treated with mitomycin C, the c index for RFS models was 0.6415 (95% CI 0.6412-0.6417) for the training group and 0.660 (95% CI 0.657-0.664) for the validation group. Models for PFS achieved a c index of 0.885 (95% CI 0.885-0.885) for the training set and 0.876 (95% CI 0.873-0.880) for the validation set. Our tool outperformed standard-of-care risk stratification tools and showed no evidence of overfitting. The application is open source and available at https://biostat.umed.pl/deepNMIBC/. PATIENT SUMMARY: We created and validated a new tool to predict recurrence and progression of early-stage bladder cancer. The application uses advanced artificial intelligence to combine state-of-the-art scales, outperforms these scales for prediction, and is freely available online.
Asunto(s)
Aprendizaje Profundo , Neoplasias de la Vejiga Urinaria , Inteligencia Artificial , Progresión de la Enfermedad , Femenino , Humanos , Masculino , Invasividad Neoplásica , Recurrencia Local de Neoplasia/patología , Pronóstico , Estudios Retrospectivos , Medición de Riesgo , Neoplasias de la Vejiga Urinaria/patologíaRESUMEN
Pathophysiological changes in the prostate gland-benign prostatic hyperplasia (BPH) and prostatic adenocarcinoma (PCa)-are closely related to the age of men. In the prostate gland, zinc is of particular importance for its proper functioning, especially with regard to the effects of hormonal disorders. The aim of this study was to evaluate zinc, copper and selenium concentrations in different parts of the prostate gland in relation to age and the nature of pathological changes. Zinc and copper were determined by the AAS method and selenium by the spectrofluorometric method. The concentration of zinc in the central part of the prostate increases with age, and in patients over 36 years it is twice as high as in the peripheral part, where no increase in the level of this element was observed with the age of patients. The above data confirm a possible influence of zinc on the formation of PCa (located mostly in the peripheral part of the prostate, with low levels of zinc) and BPH in the central part where the levels of this element are the highest. The results apparently confirm the disturbed homeostasis of zinc and other essential elements in the etiology of BPH and PCa.
Asunto(s)
Envejecimiento/metabolismo , Cobre/metabolismo , Próstata/metabolismo , Selenio/metabolismo , Zinc/metabolismo , Adulto , Factores de Edad , Anciano , Anciano de 80 o más Años , Humanos , Masculino , Persona de Mediana Edad , Próstata/patología , Adulto JovenRESUMEN
BRIEF DESCRIPTION: The results demonstrate that the European Organisation for Research and Treatment of Cancer (EORTC) scale provides the best recurrence and progression prediction in comparison with European Association of Urology (EAU) and Club Urologico Espanol de Tratamiento Oncologico (CUETO) risk scores among a mixed population of patients with non-muscle-invasive bladder who were treated with, or without, Bacillus Calmette-Guerin (BCG) and without any immediate postoperative chemotherapy. The study highlights the role of tumor diameter and extent in transition prediction. This retrospective cohort analysis of 322 patients with newly diagnosed non-muscle-invasive bladder cancer (NMIBC) assesses the concordance and accuracy of predicting recurrence and progression by EAU-recommended tools (EAU risk groups, EORTC, and CUETO). One-year and five-year c-indices ranged from 0.55 to 0.66 for recurrence and from 0.72 to 0.82 for progression. AUCROC of predictions ranged from 0.46 for 1-year recurrence risk based on CUETO groups, to 0.82 for 1-year progression risk based on EAU risk groups. Diameter (HR: 1.91; 95% CI: 1.39-2.61) and tumor extent (HR: 1.21; 95% CI: 1.01-1.46 for recurrence; HR: 3.1; 95% CI: 1.40-6.87 for progression) were shown to be significant predictors in multistate analysis. Lower accuracy of prediction was observed for patients treated with BCG maintenance immunotherapy. The EORTC model (overall c-index c = 0.64; 95% CI: 0.61-0.68) was superior to the EAU (P = .035; .62; 95% CI: 0.59-0.66) and CUETO (P < .001; c = 0.53; 95% CI: 0.50-0.56) models in predicting recurrence. The EORTC model (c = 0.82; 95% CI: 0.77-0.86) also performed better than CUETO (P = .008; c = 0.73; 95% CI: 0.66-0.81) but there was no sufficient evidence that it performed better than EAU (P = .572; c = 0.81; 95% CI: 0.77-0.84) for predicting progression. EORTC and CUETO gave similar predictions for progression in BCG-treated EAU high-risk patients (P = .48). We share anonymized individual patient data. In conclusion, despite moderate accuracy, EORTC provided the best recurrence and progression prediction for a mixed population of patients treated with, or without BCG, and without immediate postoperative chemotherapy.
Asunto(s)
Cistectomía/mortalidad , Recurrencia Local de Neoplasia/mortalidad , Guías de Práctica Clínica como Asunto/normas , Medición de Riesgo/métodos , Medición de Riesgo/normas , Neoplasias de la Vejiga Urinaria/mortalidad , Anciano , Progresión de la Enfermedad , Femenino , Estudios de Seguimiento , Humanos , Masculino , Recurrencia Local de Neoplasia/patología , Recurrencia Local de Neoplasia/cirugía , Pronóstico , Estudios Retrospectivos , Factores de Riesgo , Tasa de Supervivencia , Neoplasias de la Vejiga Urinaria/patología , Neoplasias de la Vejiga Urinaria/cirugíaRESUMEN
INTRODUCTION: The aim of the study is to evaluate the number of years of life lost in inhabitants of Poland due to bladder cancer (BC), identify trends of the mortality and calculate the pace of change which has happened over the period of the first fifteen years of the 21st century. MATERIAL AND METHODS: The study material was a database including 44,283 death certificates of Polish inhabitants who died due to bladder cancer in the period 2000-2014. The number of years of life lost were calculated using the SEYLL indices: SEYLLp (Standard Expected Years of Life Lost per living person) and SEYLLd (Standard Expected Years of Life Lost per death). RESULTS: The crude death rates (CDR) index increased from 10.79 per 100,000 males in 2000 to 14.30 in 2014 (Annual Percentage Change [APC] = 2.1%, p <0.05). In women, the group value of the CDR index increased from 2.50 in 2000 to 3.83 in 2014 (APC = 2.9%, p <0.05). The standardized death rates (SDR) index fell from 23.27 in 2000 to 22.48 in 2014 (APC = -0.1%, p >0.05) in men, but rose from 3.54 in 2000 to 3.83 in 2014 (APC = 0.4%, p <0.05) in women.The SEYLLp index (per 100,000 population) due to bladder cancer in Poland increased from 202.9 in 2000 to 243.4 in 2014 (APC = 1.3%, p <0.05) in men, and from 40.4 in 2000 to 60.1 in 2014 (APC = 2.7%, p <0.05) in women. CONCLUSIONS: Despite the prolongation of patient life, as shown by the SEYLLd factor, Polish patients still lose too many years of life due to BC than compared to United States patients.