Automated Detection, Segmentation, and Classification of Pleural Effusion From Computed Tomography Scans Using Machine Learning.

OBJECTIVE: This study trained and evaluated algorithms to detect, segment, and classify simple and complex pleural effusions on computed tomography (CT) scans. MATERIALS AND METHODS: For detection and segmentation, we randomly selected 160 chest CT scans out of all consecutive patients (January 2016-January 2021, n = 2659) with reported pleural effusion. Effusions were manually segmented and a negative cohort of chest CTs from 160 patients without effusions was added. A deep convolutional neural network (nnU-Net) was trained and cross-validated (n = 224; 70%) for segmentation and tested on a separate subset (n = 96; 30%) with the same distribution of reported pleural complexity features as in the training cohort (eg, hyperdense fluid, gas, pleural thickening and loculation). On a separate consecutive cohort with a high prevalence of pleural complexity features (n = 335), a random forest model was implemented for classification of segmented effusions with Hounsfield unit thresholds, density distribution, and radiomics-based features as input. As performance measures, sensitivity, specificity, and area under the curves (AUCs) for detection/classifier evaluation (per-case level) and Dice coefficient and volume analysis for the segmentation task were used. RESULTS: Sensitivity and specificity for detection of effusion were excellent at 0.99 and 0.98, respectively (n = 96; AUC, 0.996, test data). Segmentation was robust (median Dice, 0.89; median absolute volume difference, 13 mL), irrespective of size, complexity, or contrast phase. The sensitivity, specificity, and AUC for classification in simple versus complex effusions were 0.67, 0.75, and 0.77, respectively. CONCLUSION: Using a dataset with different degrees of complexity, a robust model was developed for the detection, segmentation, and classification of effusion subtypes. The algorithms are openly available at https://github.com/usb-radiology/pleuraleffusion.git.

Antibiotic prophylaxis in transurethral resection of bladder tumours: study protocol for a systematic review and meta-analysis.

BACKGROUND: The necessity of antibiotic prophylaxis for postoperative urinary tract infections (UTIs) after transurethral resection of bladder tumours is controversial. This potentially leads to the overuse of antibiotic prophylaxis and rising antimicrobial resistance rates. The objective of this systematic review and meta-analysis is to compare the impact of different antimicrobial prophylaxis schemes versus placebo on the prevention of postoperative UTI and asymptomatic bacteriuria. METHODS: We designed and registered a study protocol for a systematic review and meta-analysis of randomized controlled trials and non-randomized (e.g. cohort, case-control) studies examining any form of antibiotic prophylaxis in patients with transurethral resection of bladder tumours. Literature searches will be conducted in several electronic databases (from inception onwards), including MEDLINE (Ovid), EMBASE (Ovid), and the Cochrane Central Register of Controlled Trials (CENTRAL). Grey literature will be identified through searching conference abstracts. The primary outcome will be postoperative urinary tract infections. The secondary outcome will be asymptomatic bacteriuria. Two reviewers will independently screen all citations, full-text articles, and abstract data. Potential conflicts will be resolved through discussion. The study methodological quality (or bias) will be appraised using appropriate tools (e.g. Risk of Bias 2.0 tool and Newcastle-Ottawa Scale). If feasible, we will conduct random-effects meta-analysis of outcome data. Additional analyses will be conducted to explore the potential sources of heterogeneity (e.g. study design, publication year, the setting of the study, and antibiotics regimen). We will also search, identify, and discuss potential risk factors for urinary tract infections following transurethral resection of bladder tumours. This may serve as basis for a scoping review. DISCUSSION: In times of rising antimicrobial resistance rates, sound evidence on the necessity of antibiotic prophylaxis is essential for implementation into guideline recommendations and for decision-making in clinical practice. SYSTEMATIC REVIEW REGISTRATION: PROSPERO, CRD42019131733.

Overuse of antimicrobial prophylaxis in low-risk patients undergoing transurethral resection of the prostate.

OBJECTIVE: To evaluate the current antimicrobial prophylaxis practices for low-risk patients undergoing transurethral resection of the prostate (TURP) or photoselective vaporisation of the prostate (PVP) in comparison with the antimicrobial prophylaxis recommendations of the European Association of Urology (EAU), which have been shown to effectively reduce infectious complications and antimicrobial resistance rates. METHODS: In May 2017, we sent an anonymous online -survey to board-certified urologists in Germany, Austria and Switzerland, by use of the database directory of the respective urology associations. Besides demographical questions, urologists were asked about their sources of information on antimicrobial prophylaxis prescription and their prescribing patterns before, during and after surgery in patients without an indwelling catheter or significant bacteriuria undergoing TURP or PVP. RESULTS: Overall, 374 of 5825 urologists responded, of whom 76% (286/374) performed TURP and 16% (60/374) PVP. For TURP and PVP, respectively: (i) 42% (119/286) and 33% (20/60) reported routine use of preoperative antimicrobial prophylaxis, which does not conform to guideline recommendations; (ii) 43% (124/286) and 52% (31/60) reported prescribing non-recommended perioperative antimicrobial prophylaxis regimens; and (iii) 60% (172/286) and 65% (39/60) routinely extended antimicrobial prophylaxis after surgery for up to one week. In summary, of the urologists who responded to the questionnaire, 74% (211/286) reported nonadherence to guidelines on antimicrobial prophylaxis for TURP. CONCLUSION: A low adherence to guidelines for low-risk patients undergoing TURP or PVP was reported. Given these preliminary data, there is an urgent need to monitor adherence to antimicrobial prophylaxis guidelines in urology to reduce antimicrobial resistance rates.