A novel model of artificial intelligence based automated image analysis of CT urography to identify bladder cancer in patients investigated for macroscopic hematuria.

OBJECTIVE: To evaluate whether artificial intelligence (AI) based automatic image analysis utilising convolutional neural networks (CNNs) can be used to evaluate computed tomography urography (CTU) for the presence of urinary bladder cancer (UBC) in patients with macroscopic hematuria. METHODS: Our study included patients who had undergone evaluation for macroscopic hematuria. A CNN-based AI model was trained and validated on the CTUs included in the study on a dedicated research platform (Recomia.org). Sensitivity and specificity were calculated to assess the performance of the AI model. Cystoscopy findings were used as the reference method. RESULTS: The training cohort comprised a total of 530 patients. Following the optimisation process, we developed the last version of our AI model. Subsequently, we utilised the model in the validation cohort which included an additional 400 patients (including 239 patients with UBC). The AI model had a sensitivity of 0.83 (95% confidence intervals [CI], 0.76-0.89), specificity of 0.76 (95% CI 0.67-0.84), and a negative predictive value (NPV) of 0.97 (95% CI 0.95-0.98). The majority of tumours in the false negative group (n = 24) were solitary (67%) and smaller than 1 cm (50%), with the majority of patients having cTaG1-2 (71%). CONCLUSIONS: We developed and tested an AI model for automatic image analysis of CTUs to detect UBC in patients with macroscopic hematuria. This model showed promising results with a high detection rate and excessive NPV. Further developments could lead to a decreased need for invasive investigations and prioritising patients with serious tumours.

Artificial Intelligence-Based Organ Delineation for Radiation Treatment Planning of Prostate Cancer on Computed Tomography.

Purpose: Meticulous manual delineations of the prostate and the surrounding organs at risk are necessary for prostate cancer radiation therapy to avoid side effects to the latter. This process is time consuming and hampered by inter- and intraobserver variability, all of which could be alleviated by artificial intelligence (AI). This study aimed to evaluate the performance of AI compared with manual organ delineations on computed tomography (CT) scans for radiation treatment planning. Methods and Materials: Manual delineations of the prostate, urinary bladder, and rectum of 1530 patients with prostate cancer who received curative radiation therapy from 2006 to 2018 were included. Approximately 50% of those CT scans were used as a training set, 25% as a validation set, and 25% as a test set. Patients with hip prostheses were excluded because of metal artifacts. After training and fine-tuning with the validation set, automated delineations of the prostate and organs at risk were obtained for the test set. Sørensen-Dice similarity coefficient, mean surface distance, and Hausdorff distance were used to evaluate the agreement between the manual and automated delineations. Results: The median Sørensen-Dice similarity coefficient between the manual and AI delineations was 0.82, 0.95, and 0.88 for the prostate, urinary bladder, and rectum, respectively. The median mean surface distance and Hausdorff distance were 1.7 and 9.2 mm for the prostate, 0.7 and 6.7 mm for the urinary bladder, and 1.1 and 13.5 mm for the rectum, respectively. Conclusions: Automated CT-based organ delineation for prostate cancer radiation treatment planning is feasible and shows good agreement with manually performed contouring.

Shortened time to diagnosis for patients suspected of urinary bladder cancer managed in a standardized care pathway was associated with an improvement in tumour characteristics.

Objectives: To evaluate whether the implementation of standardized care pathway (SCP) for patients with suspected urinary bladder cancer (UBC) was associated with changes in tumour characteristics. Additionally, the study aims to explore whether there was a shift in the selection of patients prioritized for immediate evaluation regarding suspicion of UBC. Materials and Methods: The study included all patients diagnosed with UBC in the NU Hospital Group between 2010 and 2019. To evaluate changes associated with SCP, patients were divided into two diagnostic time periods, either before (2010-2015) or during (2016-2019) the implementation of the SCP. To evaluate which patients were prioritized for prompt evaluation within 13 days, logistic regression analysis was performed on all patients before and during SCP. Results: Median time to transurethral resection of the tumour in urinary bladder (TURBT) decreased from 29 days (interquartile range [IQR] 16-48) before SCP to 12 days (IQR 8-19) during SCP (p < 0.001) with a clear break from 2016. The proportion of cT2 + tumours decreased during SCP from 26% to 20% (p = 0.035). In addition, tumours detected during SCP were smaller (p = 0.023), but with more multiple lesions (p = 0.055) and G3 tumours (p = 0.007). During SCP, there was no statistically significant difference between the groups of patients with TURBT within or after 13 days. In contrast, before SCP, a majority of the patients treated within 13 days had advanced tumours and were admitted from the emergency ward. Conclusions: The implementation of an SCP for suspected UBC was associated with improved tumour characteristics. Interestingly, during SCP, there were no substantial differences in patients' or tumours' characteristics among those who underwent TURBT within or after 13 days. This indicates that the 13-day timeframe for TURBT might be prolonged, especially in less urgent cases in order to facilitate a prioritization of more severe cases with treatable disease.

Diagnostic value of repeated comprehensive investigation with CT urography and cystoscopy for recurrent macroscopic haematuria.

Objectives: To perform a descriptive analysis of a series of patients with recurrent macroscopic haematuria after a primary standard evaluation including computed tomography urography (CTU) and cystoscopy negative for urinary bladder cancer (UBC) and upper tract urothelial cancer (UTUC) and to identify potential factors associated with occurrence of recurrent macroscopic haematuria. Methods: All patients older than 50 years who underwent urological investigation for macroscopic haematuria with both cystoscopy and CTU 2015-2017 were retrospectively reviewed. A descriptive analysis of the primary and later investigations for recurrent macroscopic haematuria was performed. To investigate the association between explanatory variables and the occurrence of recurrent macroscopic haematuria, a Poisson regression analysis was performed. Results: A total of 1395 eligible individuals with primary standard investigation negative for UBC and UTUC were included. During a median follow-up of 6.2 (IQR 5.3-7) years, 248 (18%) patients had recurrent macroscopic haematuria, of whom six patients were diagnosed with UBC, two with prostate cancer, one with renal cell carcinoma and one had a suspected UTUC at the repeated investigation. Within 3 years, 148 patients (11%) experienced recurrent macroscopic haematuria, of whom two patients were diagnosed with low-grade UBC (TaG1-2), one with T2G3 UBC and one with low-risk prostate cancer. The presence of an indwelling catheter, use of antithrombotic medication, pathological findings at CTU or cystoscopy or history of pelvic radiotherapy were all statistically significant independent predictors for increased risk for recurrent macroscopic haematuria. Conclusion: In the case of recurrent macroscopic haematuria within 3 years of primary standard evaluation for urinary tract cancer, there was a low risk of later urological malignancies in patients initially negative for UBC and UTUC. Therefore, waiting 3 years before conducting another complete investigation in cases of recurrent macroscopic haematuria might be appropriate.

A randomised study of TURP after intraprostatic injection of mepicacaine/adrenaline versus regular TURP in patients with LUTS/BPO.

INTRODUCTION: During transurethral resection of the prostate (TURP), the most established surgical treatment of lower urinary tract symptoms (LUTS) due to benign prostatic obstruction (BPO), the prostate can bleed profusely, bringing about anaemia and compromised oxygen delivery to the entire body. OBJECTIVE: The primary objective of this study was to assess the efficacy of mepivacaine and adrenaline (MA) injected into the prostate on bleeding. The primary endpoint was to measure blood loss per resected weight of prostate tissue. MATERIAL AND METHODS: This randomised controlled trial evaluated 81 patients with LUTS/BPO. Patients were randomly allocated to regular TURP or TURP with intraprostatic injections of MA. RESULTS: On univariable analyses there was a significant difference in resection weight in favour of the experimental group, not reflected by a statistically significant difference in the other studied outcome parameters. Nevertheless, in multivariable analyses, blood loss per resection weight, which was the primary outcome, showed a significant decrease in favour of the experimental group. Clavien-Dindo complication classification showed three men with a grade I complication and two men with grade II. CONCLUSIONS: The results obtained in this study showed that it is beneficial to apply intraprostatic injections of MA in immediate conjunction with TURP, in terms of blood loss per resected gram. The study is, however, small and corroboration of our results in more extensive prospective studies may therefore be warranted before embarking upon this technique.

Clinical Value of a Routine Urine Culture Prior to Transrectal Prostate Biopsy.

Background: Infectious complications after a transrectal prostate biopsy may be severe. In Sweden, a routine culture prior to all prostate biopsies was introduced to enable targeted antimicrobial prophylaxis and reduce postbiopsy infections. Objective: To investigate whether a clinical routine with a urine culture prior to a prostate biopsy and targeted prophylactic antibiotic therapy reduces postbiopsy infections. Design setting and participants: In 2015, a site-specific antimicrobial stewardship programme with a urine culture prior to a prostate biopsy was initiated in Region Kronoberg. To evaluate this routine, we designed a population-based register study including all men who had an outpatient prostate biopsy in 2015-2019 and a control period including all men who had a biopsy in 2010-2014, when a urinary culture was obtained only on clinical suspicion. Outcome measurements and statistical analysis: The primary outcome was infectious complications within 10 d and the secondary outcome was a change in antibiotic prophylactic treatment. An infectious complication was defined as prescription of antibiotics for urinary tract infections or admission to hospital for urinary tract infections or sepsis after a biopsy. Results and limitations: The urine culture period included 2971 prostate biopsy procedures, of which 2684 (90%) were preceded by a urine culture. The control period included 2818 procedures, of which 135 (4.8%) were preceded by a urine culture. Infectious complications were slightly more common during the urine culture period (5.0%) than during the control period (4.3%, p = 0.17), as was inpatient care for infections (3.5% vs 2.2%, p = 0.002). The routine identified 5.4% men with asymptomatic bacteriuria. Despite targeted antibiotic treatment (1.5% received a nonfluoroquinolone treatment), the rate of infectious complications (6.3%) was similar to that in the control period. Conclusions: Prebiopsy urine culture did not lead to fewer postbiopsy infections. Other measures are needed to reduce infectious complications after a prostate biopsy. Patient summary: In this report, we evaluated a routine with urine culture prior to a transrectal prostate biopsy and found that it did not lead to fewer infectious complications.

Noninvasive detection of any-stage cancer using free glycosaminoglycans.

Cancer mortality is exacerbated by late-stage diagnosis. Liquid biopsies based on genomic biomarkers can noninvasively diagnose cancers. However, validation studies have reported ~10% sensitivity to detect stage I cancer in a screening population and specific types, such as brain or genitourinary tumors, remain undetectable. We investigated urine and plasma free glycosaminoglycan profiles (GAGomes) as tumor metabolism biomarkers for multi-cancer early detection (MCED) of 14 cancer types using 2,064 samples from 1,260 cancer or healthy subjects. We observed widespread cancer-specific changes in biofluidic GAGomes recapitulated in an in vivo cancer progression model. We developed three machine learning models based on urine (Nurine = 220 cancer vs. 360 healthy) and plasma (Nplasma = 517 vs. 425) GAGomes that can detect any cancer with an area under the receiver operating characteristic curve of 0.83-0.93 with up to 62% sensitivity to stage I disease at 95% specificity. Undetected patients had a 39 to 50% lower risk of death. GAGomes predicted the putative cancer location with 89% accuracy. In a validation study on a screening-like population requiring ≥ 99% specificity, combined GAGomes predicted any cancer type with poor prognosis within 18 months with 43% sensitivity (21% in stage I; N = 121 and 49 cases). Overall, GAGomes appeared to be powerful MCED metabolic biomarkers, potentially doubling the number of stage I cancers detectable using genomic biomarkers.

The transferability of laparoscopic and open surgical skills to robotic surgery.

BACKGROUND: Within the last decades, robotic surgery has gained popularity. Most robotic surgeons have changed their main surgical activity from open or laparoscopic without prior formal robotic training. With the current practice, it is of great interest to know whether there is a transfer of surgical skills. In visualization, motion scaling, and freedom of motion, robotic surgery resembles open surgery far more than laparoscopic surgery. Therefore, our hypothesis is that open-trained surgeons have more transfer of surgical skills to robotic surgery, compared to surgeons trained in laparoscopy. METHODS: Thirty-six surgically inexperienced medical students were randomized into three groups for intensive simulation training in an assigned modality: open surgery, laparoscopy, or robot-assisted laparoscopy. The training period was, for all study subjects, followed by performing a robot-assisted bowel anastomosis in a pig model. As surrogate markers of surgical quality, the anastomoses were tested for resistance to pressure, and video recordings of the procedure were evaluated by two blinded expert robotic surgeons, using a global rating scale of robotic operative performance (Global Evaluative Assessment of Robotic Skills (GEARS)). RESULTS: The mean leak pressure of bowel anastomosis was 36.25 (7.62-64.89) mmHg in the laparoscopic training group and 69.01 (28.02-109.99) mmHg in the open surgery group, and the mean leak pressure for the robotic training group was 108.45 (74.96-141.94) mmHg. The same pattern was found with GEARS as surrogate markers of surgical quality. GEARS score was 15.71 (12.37-19.04) in the laparoscopic training group, 18.14 (14.70-21.58) in the open surgery group, and 22.04 (19.29-24.79) in the robotic training group. In comparison with the laparoscopic training group, the robotic training group had a statistically higher leak pressure (p = 0.0015) and GEARS score (p = 0.0023). No significant difference, for neither leak pressure nor GEARS, between the open and the robotic training group. CONCLUSION: In our study, training in open surgery was superior to training in laparoscopy when transitioning to robotic surgery in a simulation setting performed by surgically naive study subjects.

Treatment with CoreTherm in 570 patients with prostate volumes of 80-366 ml: an evaluation of short- and long-term retreatment risk.

INTRODUCTION: CoreTherm (ProstaLund AB, Lund, Sweden) is an outpatient treatment option in men with lower urinary tract symptoms and catheter-dependent men with chronic urinary retention caused by benign prostatic obstruction (BPO). CoreTherm is high-energy transurethral microwave thermotherapy with feedback technique. Modern treatment with CoreTherm includes transurethral intraprostatic injections of mepivacaine and adrenaline via the Schelin Catheter (ProstaLund AB, Lund, Sweden) and is often referred to as the CoreTherm Concept. OBJECTIVES: The aim of this study was to evaluate the short- and long-term retreatment risk in men with large prostates and BPO or chronic urinary retention, all primarily treated with CoreTherm. MATERIAL AND METHODS: All men from the same geographical area with prostate volumes ≥ 80 ml treated 1999-2015 with CoreTherm and having BPO or were catheter-dependent due to chronic urinary retention, were included. End of study period was defined as December 31, 2019. RESULTS: We identified and evaluated 570 men treated with CoreTherm, where 12% (71 patients) were surgically retreated during the follow-up. Mean follow-up was 11 years, and maximum follow-up was 20 years. The long-term retreatment rate in our study was 23%. A majority of these could be retreated with CoreTherm or TURP, with only 3% requiring open surgery. CONCLUSION: We conclude that CoreTherm is a suitable outpatient treatment option in patients with profoundly enlarged prostates, regardless of age, prostate size, and reason for treatment.

Detection of lymph node metastases in patients with prostate cancer: Comparing conventional and digital [18 F]-fluorocholine PET-CT using histopathology as a reference.

BACKGROUND: Positron emission tomography-computed tomography (PET-CT) with [18 F]-fluorocholine (FCH) is used to detect and stage metastatic lymph nodes in patients with prostate cancer. Improvements to hardware and software have recently been made. We compared the capability of detecting regional lymph node metastases using conventional and digital silicon photomultiplier (SiPM)-based PET-CT technology for FCH. Extended pelvic lymph node dissection (ePLND) histopathology was used as a reference method. METHODS: The study retrospectively examined 177 patients with intermediate or high-risk prostate cancer who had undergone staging with FCH PET-CT before ePLND. Images were obtained with either the conventional Philips Gemini PET-CT (n = 93) or the digital SiPM-based GE Discovery MI PET-CT (n = 84) and compared. RESULTS: Images that were obtained using the Philips Gemini PET-CT system showed 19 patients (20%) with suspected lymph node metastases, whereas the GE Discovery MI PET-CT revealed 36 such patients (43%). The sensitivity, specificity, and positive and negative predictive values were 0.3, 0.84, 0.47, and 0.72 for the Philips Gemini, while they were 0.58, 0.62, 0.31, and 0.83 for the GE Discovery MI, respectively. The areas under the curves in a receiver operating characteristic curve analysis were similar between the two PET-CT systems (0.57 for Philips Gemini and 0.58 for GE Discovery MI, p = 0.89). CONCLUSIONS: Marked differences in sensitivity and specificity were found for the different PET-CT systems, although the overall diagnostic performance was similar. These differences are probably due to differences in both hardware and software, including reconstruction algorithms, and should be considered when new technology is introduced.

Computed tomography urography with corticomedullary phase can exclude urinary bladder cancer with high accuracy.

BACKGROUND: To evaluate the diagnostic accuracy of computed tomography-urography (CTU) to rule out urinary bladder cancer (UBC) and whether patients thereby could omit cystoscopy. METHODS: All patients evaluated for macroscopic hematuria with CTU with cortico-medullary phase (CMP) and cystoscopy at our institute between 1st November 2016 and 31st December 2019 were included. From this study cohort a study group consisting of all UBC patients and a control group of 113 patients randomly selected from all patients in the study cohort without UBC. Two radiologists blinded to all clinical data reviewed the CTUs independently. CTUs were categorized as positive, negative or indeterminate. Diagnostic accuracy and proportion of potential omittable cystoscopies were calculated for the study cohort by generalizing the results from the study group. RESULTS: The study cohort consisted of 2195 patients, 297 of which were in the study group (UBC group, n = 207 and control group, n = 90). Inter-rater reliability was high (κ 0.84). Evaluation of CTUs showed that 174 patients were assesessed as positive (showing UBC), 46 patients as indeterminate (not showing UBC but with limited quality of CTU), and 77 patients as negative (not showing UBC with good quality of CTU). False negative rate was 0.07 (95%, CI 0.04-0.12), false positive rate was 0.01 (95% CI 0.0-0.07) and negative predictive value was 0.99 (95% CI 0.92-1.0). The area under the curve was 0.93 (95% CI 0.90-0.96). Only 2.9% (3/102) with high-risk tumors and 11% (12/105) with low- or intermediate-risk tumors had a false negative CTU. Cystoscopy could potentially have been omitted in 57% (1260/2195) of all evaluations. CONCLUSIONS: CTU with CMP can exclude UBC with high accuracy. In case of negative CTU, it might be reasonable to omit cystoscopy, but future confirmative studies with possibly refined technique are needed.

Standardized care pathways for patients with suspected urinary bladder cancer: the Swedish experience.

OBJECTIVES: To compare time intervals to diagnosis and treatment, tumor characteristics, and management in patients with primary urinary bladder cancer, diagnosed before and after the implementation of a standardized care pathway (SCP) in Sweden. MATERIALS AND METHODS: Data from the Swedish National Register of Urinary Bladder Cancer was studied before (2011-2015) and after (2016-2019) SCP. Data about time from referral to transurethral resection of bladder tumor (TURBT), patients and tumor characteristics, and management were analyzed. Subgroup analyses were performed for cT1 and cT2-4 tumors. RESULTS: Out of 26,795 patients, median time to TURBT decreased from 37 to 27 days after the implementation of SCP. While the proportion of cT2-T4 tumors decreased slightly (22-21%, p < 0.001), this change was not stable over time and the proportions cN + and cM1 remained unchanged. In the subgroups with cT1 and cT2-4 tumors, the median time to TURBT decreased and the proportions of patients discussed at a multidisciplinary team conference (MDTC) increased after SCP. In neither of these subgroups was a change in the proportions of cN + and cM1 observed, while treatment according to guidelines increased after SCP in the cT1 group. CONCLUSION: After the implementation of SCP, time from referral to TURBT decreased and the proportion of patients discussed at MDTC increased, although not at the levels recommended by guidelines. Thus, our findings point to the need for measures to increase adherence to SCP recommendations and to guidelines.

The transferability of the minimal invasive surgeon's skills to open surgery.

BACKGROUND: Robot-assisted laparoscopic surgery has gained popularity, which has contributed to a decrease in the number of open procedures. Hence a growing concern regarding the ability of laparoscopically trained surgeons to perform open surgery (e.g. due to bleeding complications) has been raised. The aim of the study was to investigate the ability of conversion to open surgery following exclusively robotic or laparoscopic training. METHODS: Thirty-six medical students were randomized into three groups: Open surgery, laparoscopy, and robot-assisted laparoscopy. All underwent intensive simulation training in the allocated surgical modality. Subsequently, all study subjects performed an open bowel anastomosis in a pig model where anastomoses were tested for resistance to pressure and leak as a surrogate marker of surgical quality. RESULTS: The primary endpoint was the surgical quality of an open surgery model assessed as, leak pressure, which was 80.01 ± 36.16 mmHg in the laparoscopic training group, 106.57 ± 23.03 mmHg in the robotic training group, and 133.65 ± 18.32 mmHg in the open surgery training group (mean, SD). We found that there were no significant differences between the open surgery training group and the robotic training group whereas a significant difference was found when comparing laparoscopic and open surgery training groups in favor of open procedure training (p < 0.001). CONCLUSION: In a surrogate open surgery model based on bowel anastomosis, we found that skills acquired through practice on robotic simulation platforms were not significantly worse when compared to skills acquired through training in open surgery, whereas skills acquired from laparoscopic training were significantly poorer when compared to open surgery practice.

Automated artificial intelligence-based analysis of skeletal muscle volume predicts overall survival after cystectomy for urinary bladder cancer.

BACKGROUND: Radical cystectomy for urinary bladder cancer is a procedure associated with a high risk of complications, and poor overall survival (OS) due to both patient and tumour factors. Sarcopenia is one such patient factor. We have developed a fully automated artificial intelligence (AI)-based image analysis tool for segmenting skeletal muscle of the torso and calculating the muscle volume. METHODS: All patients who have undergone radical cystectomy for urinary bladder cancer 2011-2019 at Sahlgrenska University Hospital, and who had a pre-operative computed tomography of the abdomen within 90 days of surgery were included in the study. All patients CT studies were analysed with the automated AI-based image analysis tool. Clinical data for the patients were retrieved from the Swedish National Register for Urinary Bladder Cancer. Muscle volumes dichotomised by the median for each sex were analysed with Cox regression for OS and logistic regression for 90-day high-grade complications. The study was approved by the Swedish Ethical Review Authority (2020-03985). RESULTS: Out of 445 patients who underwent surgery, 299 (67%) had CT studies available for analysis. The automated AI-based tool failed to segment the muscle volume in seven (2%) patients. Cox regression analysis showed an independent significant association with OS (HR 1.62; 95% CI 1.07-2.44; p = 0.022). Logistic regression did not show any association with high-grade complications. CONCLUSION: The fully automated AI-based CT image analysis provides a low-cost and meaningful clinical measure that is an independent biomarker for OS following radical cystectomy.

Artificial intelligence-based measurements of PET/CT imaging biomarkers are associated with disease-specific survival of high-risk prostate cancer patients.

OBJECTIVE: Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUVmax, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements. METHODS: An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The algorithm was then tested retrospectively on 285 high-risk patients, who were examined using 18F-choline PET/CT for primary staging between April 2008 and July 2015. Prostate tumour volume, tumour fraction of the prostate gland, lesion uptake of the entire tumour, and SUVmax were obtained automatically. Associations between these measurements, age, PSA, Gleason score and prostate cancer-specific survival were studied, using a Cox proportional-hazards regression model. RESULTS: Twenty-three patients died of prostate cancer during follow-up (median survival 3.8 years). Total tumour volume of the prostate (p = 0.008), tumour fraction of the gland (p = 0.005), total lesion uptake of the prostate (p = 0.02), and age (p = 0.01) were significantly associated with disease-specific survival, whereas SUVmax (p = 0.2), PSA (p = 0.2), and Gleason score (p = 0.8) were not. CONCLUSION: AI-based assessments of total tumour volume and lesion uptake were significantly associated with disease-specific survival in this patient cohort, whereas SUVmax and Gleason scores were not. The AI-based approach appears well-suited for clinically relevant patient stratification and monitoring of individual therapy.

Cumulative incidence of ureteroenteric strictures after radical cystectomy in a population-based Swedish cohort.

OBJECTIVE: The incidence of benign ureteroenteric strictures following radical cystectomy (RC) for urinary bladder cancer (UBC) is investigated mainly in single-centre studies from high-volume centres. The aim of this study was to evaluate the cumulative incidence of strictures and risk factors in a population-based cohort. PATIENTS AND METHODS: Data was collected from Bladder Cancer Data Base Sweden (BladderBaSe). The primary endpoint was stricture with intervention. Secondary endpoint included hydronephrosis both with/without intervention. RESULTS: In total, 5,816 patients were registered as having had RC due to UBC between 1997 and 2014. After a median follow-up of 23.5 months (IQR = 9.0-63.1 months; range = 0.0-214.0 months), we found that 515 (8.9%) patients underwent intervention for stricture. Seven hundred and sixty-one (13.1%) patients were diagnosed with hydronephrosis without intervention. The cumulative incidence of strictures with intervention was 19.7% (95% CI = 16.7-23.1%) during the 17 years of follow-up. In the first year, the cumulative incidence of strictures was 5.6% (95% CI = 5.0-6.2%), and in the first 2 years 8.4% (95% CI = 7.6-9.3%). For the secondary endpoint, the cumulative incidence was 30.4% (95% CI = 26.7-33.1%) after 17 years. Only the year of RC was associated with stricture incidence in Cox regression analysis, whereas hospital cystectomy volume, patient age and patient sex were not. CONCLUSION: Ureteroenteric strictures requiring intervention may be more common than previously reported, affecting nearly one fifth of patients who have undergone RC for UBC. The annual incidence was highest in the first 2 years after surgery but the cumulative incidence increased continuously during 17 years of follow-up.

A retrospective study assessing the accuracy of [18F]-fluorocholine PET/CT for primary staging of lymph node metastases in intermediate and high-risk prostate cancer patients undergoing robotic-assisted laparoscopic prostatectomy with extended lymph node dissection.

BACKGROUND: Previous studies have investigated [18F]-fluorocholine (FCH) positron emission tomography with computed tomography (PET/CT) in primary staging of men with intermediate or high-risk prostate cancer and have generally shown high specificity and poor sensitivity. FCH PET/CT is not recommended for the primary staging of metastases in the European guidelines for prostate cancer. However, it has been an option in the Swedish recommendations. Our aim was to assess PET/CT for primary staging of lymph node metastases before robotic-assisted laparoscopic prostatectomy (RALP) with extended pelvic lymph node dissection (ePLND) in patients with intermediate or high-risk prostate cancer. METHOD: We identified all men with prostate cancer undergoing FCH PET/CT for initial staging followed by RALP and ePLND at Skåne University Hospital between 2015 and 2018. The result from PET/CT scan was compared with pathology report as the reference method for calculation of sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). RESULTS: In total, 252 patients were included in the final analysis. Among 85 patients with a suspicion of regional lymph node metastases on FCH PET/CT only 31 had pathology-proven metastases. The sensitivity was 43% (95% CI 0.32-0.55) and the specificity 70% (95% CI 0.63-0.76) for PET/CT to predict lymph node metastases. PPV was 36% and NPV was 75%. Risk group analyses showed similar results. CONCLUSION: Our study emphasizes the poor performance of FCH PET/CT to predict lymph node metastasis in intermediate and high-risk prostate cancer. The method should be replaced with newer radiopharmaceuticals, such as prostate-specific membrane antigen ligands.

Artificial intelligence-aided CT segmentation for body composition analysis: a validation study.

BACKGROUND: Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images. METHODS: Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3 days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations. RESULTS: The accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p < 0.001) for SAT and 1.9% versus 3.9% (p < 0.001) for muscle. The 95% confidence intervals for predicted volumes in an individual subject from the corresponding single CT slice areas were in the order of ± 20%. CONCLUSIONS: The AI-based tool for quantification of SAT and muscle volumes showed high accuracy and reproducibility and provided a body composition analysis that is more relevant than manual analysis of a single CT slice.

Artificial intelligence-based detection of lymph node metastases by PET/CT predicts prostate cancer-specific survival.

INTRODUCTION: Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions. METHODS: A group of 399 patients with biopsy-proven PCa who had undergone 18 F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated. RESULTS: The AI-based tool detected more lymph node lesions than Reader B (98 vs. 87/117; p = .045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs. 87/111; p = .63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment was significantly associated with PCa-specific survival. CONCLUSION: This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers and prognostic information in PCa patients.