Explainable artificial intelligence (XAI): closing the gap between image analysis and navigation in complex invasive diagnostic procedures.

LITERATURE REVIEW: Cystoscopy is the gold standard for initial macroscopic assessments of the human urinary bladder to rule out (or diagnose) bladder cancer (BCa). Despite having guidelines, cystoscopic findings are diverse and often challenging to classify. The extent of the false negatives and false positives in cystoscopic diagnosis is currently unknown. We suspect that there is a certain degree of under-diagnosis (like the failure to detect malignant tumours) and over-diagnosis (e.g. sending the patient for unnecessary transurethral resection of bladder tumors with anesthesia) that put the patient at risk. CONCLUSIONS: XAI robot-assisted cystoscopes would help to overcome the risks/flaws of conventional cystoscopy. Cystoscopy is considered a less life-threatening starting point for automation than open surgical procedures. Semi-autonomous cystoscopy requires standards and cystoscopy is a good procedure to establish a model that can then be exported/copied to other procedures of endoscopy and surgery. Standards also define the automation levels-an issue for medical product law. These cystoscopy skills do not give full autonomy to the machine, and represent a surgical parallel to 'Autonomous Driving' (where a standard requires a human supervisor to remain in the 'vehicle'). Here in robotic cystoscopy, a human supervisor remains bedside in the 'operating room' as a 'human-in-the-loop' in order to safeguard patients. The urologists will be able to delegate personal- and time-consuming cystoscopy to a specialised nurse. The result of automated diagnostic cystoscopy is a short video (with pre-processed photos from the video), which are then reviewed by the urologists at a more convenient time.

[Positron emission tomography in germ cell tumors in men : Possibilities and limitations]. / Positronenemissionstomographie bei Keimzelltumoren des Mannes : Einsatzmöglichkeiten und Grenzen.

BACKGROUND: Conventional radiographic imaging may fail to safely distinguish clinical stage I from stage IIA germ cell cancer, to localize isolated tumor marker relapses, and to equivocally identify the viability of postchemotherapy residual masses. OBJECTIVES: To provide an overview of the diagnostic value and limitations of functional imaging by positron emission tomography with 2­deoxy-2-[fluorine-18]fluoro-D-glucose with computed tomography (18F-FDG-PET-CT) in male germ cell cancer. MATERIALS AND METHODS: A narrative review based on a literature search of PubMed/MEDLINE for original articles published from 1990-2018 and conference proceedings of ASCO (American Society of Clinical Oncology) and EAU (European Association of Urology) annual meetings 2014-2017 is presented. RESULTS: 18F-FDG-PET-CT does not improve diagnostic accuracy compared to conventional CT imaging clinical stage (CS) I disease. Particularly PET-negativity of postchemotherapy residual masses of seminomas >3 cm in size guide decision-making against further additional treatment. Even PET-positive residues must not result in relapse. For nonseminoma, the value of PET imaging is reduced by potential mature teratoma components, which are commonly PET negative. CONCLUSIONS: Current guidelines recommend 18F-FDG-PET-CT 6-8 weeks postchemotherapy for viability assessment of seminoma residues >3 cm in size. Exceptional circumstances, in which 18F-FDG-PET-CT may be helpful, include: (1) detection of active disease in CS IS, (2) viability assessment of residual masses >1 cm where complete secondary resection is impossible, (3) staging at marker relapse with unconspicuous conventional CT scan, (4) early response assessment during chemotherapy.

Minimally invasive surgery and its impact on 30-day postoperative complications, unplanned readmissions and mortality.

BACKGROUND: A critical appraisal of the benefits of minimally invasive surgery (MIS) is needed, but is lacking. This study examined the associations between MIS and 30-day postoperative outcomes including complications graded according to the Clavien-Dindo classification, unplanned readmissions, hospital stay and mortality for five common surgical procedures. METHODS: Patients undergoing appendicectomy, colectomy, inguinal hernia repair, hysterectomy and prostatectomy were identified in the American College of Surgeons National Surgical Quality Improvement Program database. Non-parsimonious propensity score methods were used to construct procedure-specific matched-pair cohorts that reduced baseline differences between patients who underwent MIS and those who did not. Bonferroni correction for multiple comparisons was applied and P < 0·006 was considered significant. RESULTS: Of the 532 287 patients identified, 53·8 per cent underwent MIS. Propensity score matching yielded an overall sample of 327 736 patients (appendicectomy 46 688, colectomy 152 114, inguinal hernia repair 59 066, hysterectomy 59 066, prostatectomy 10 802). Within the procedure-specific matched pairs, MIS was associated with significantly lower odds of Clavien-Dindo grade I-II, III and IV complications (P ≤ 0·004), unplanned readmissions (P < 0·001) and reduced hospital stay (P < 0·001) in four of the five procedures studied, with the exception of inguinal hernia repair. The odds of death were lower in patients undergoing MIS colectomy (P < 0·001), hysterectomy (P = 0·002) and appendicectomy (P = 0·002). CONCLUSION: MIS was associated with significantly fewer 30-day postoperative complications, unplanned readmissions and deaths, as well as shorter hospital stay, in patients undergoing colectomy, prostatectomy, hysterectomy or appendicectomy. No benefits were noted for inguinal hernia repair.

Soil-atmosphere trace gas exchange in semiarid and arid zones.

A review is presented on trace gas exchange of CH4, CO, N2O, and NOx arising from agriculture and natural sources in the world's semiarid and arid zones due to soil processes. These gases are important contributors to the radiative forcing and the chemistry of the atmosphere. Quantitative information is summarized from the available studies. Between 5 and 40% of the global soil-atmosphere exchange for these gases (CH4, CO, N2O, and NOx) may occur in semiarid and arid zones, but for each of these gases there are fewer than a dozen studies to support the individual estimates, and these are from a limited number of locations. Significant differences in the biophysical and chemical processes controlling these trace gas exchanges are identified through the comparison of semiarid and arid zones with the moist temperate or wet/dry savanna land regions. Therefore, there is a poorly quantified understanding of the contribution of these regions to the global trace gas cycles and atmospheric chemistry. More importantly, there is a poor understanding of the feedback between these exchanges, global change, and regional land use and air pollution issues. A set of research issues is presented.