Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach.

PURPOSE: Radiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data. METHODS: Our study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5-25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time. RESULTS: Results showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90). CONCLUSIONS: The iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

Feasibility of 3 Tesla MRI for the assessment of mid-palatal suture maturation: a retrospective pilot study.

The maxilla occupies a key position in dentofacial orthopaedics, since its transversal development can be directly influenced by orthodontic therapy. The maturation stages of the mid-palatal suture, which are obtained from cone-beam computed tomography images (CBCT), present an addition to clinical decision-making in transversal discrepancies of the upper jaw. In an endeavour to reduce ionizing radiation in adolescents and young adults, who are particularly susceptible to long term stochastic irradiation effects, we investigated the feasibility of 3 Tesla (3T) MRI in detecting the maturation stages of the mid-palatal suture. A collective of 30 patients aged 24-93 years with routine neck MRI at 3T, underwent an additional three-dimensional isotropic T1 weighted study sequence of the midface. Image evaluation was performed on axial, multi-planar formatted reconstructions of the dataset aligned to the midline axis of the palate, and curved reconstructions aligned to the concavity of the palate. Inverted images helped to achieve an image impression similar to the well-known CBCT appearance. All datasets were reviewed by three readers and mid-palatal maturation was scored twice according to Angelieri et al. Intra- and inter-rater agreement were evaluated to measure the robustness of the images for clinical evaluation. 3T MRI deemed reliable for the assessment of mid-palatal suture maturation and hence for the appraisal of the hard palate and its adjacent sutures. The data of this pilot study display the feasibility of non-ionizing cross-sectional MRI for the determination of sutural maturation stages. These findings underline the potential of MRI for orthodontic treatment planning, further contributing to the avoidance of unnecessary radiation doses.

Evaluation of hard palate and cleft morphology in neonates with Pierre Robin Sequence and Cleft Palate Only.

OBJECTIVES: This study aimed to establish a fully digital measurement protocol for standardizing the description of hard palate and cleft morphology in neonates with an isolated cleft palate (CPO) and Pierre Robin sequence (PRS). MATERIALS AND METHODS: A total of 20 digitized plaster models of neonates with CPO and 20 digitized plaster models of neonates with PRS were retrospectively investigated. For the control group, the hard palate was segmented from 21 pre-existing 1.5 T MRI datasets of neonates and exported as an STL file. The digital models were marked with predefined reference points by three raters. Distance, angular, and area measurements were performed using Blender and MeshLab. RESULTS: Neonates with CPO (20.20 ± 2.33 mm) and PRS (21.41 ± 1.81 mm) had a significantly shorter hard palate than the control group (23.44 ± 2.24 mm) (CPO vs. control: P < .001; PRS vs. control: P = .014). Notably, neonates with PRS (33.05 ± 1.95 mm) demonstrated a significantly wider intertuberosity distance than those with CPO (30.52 ± 2.28 mm) (P = .012). Furthermore, there were also significant differences measured between the cleft and control groups (25.22 ± 2.50 mm) (P < .001). CONCLUSIONS: The data from this study demonstrate the feasibility of using MRI datasets to generate digital models of the hard palate. The presence of a cleft palate leads to pronounced adaptations of the total palatal surface area, dorsal width, and length of the hard palate. Mandibular retrognathia and altered tongue position in PRS, as opposed to CPO, might further impact palatal morphology and intertuberosity distance.

Long-Term Follow-Up of Peritoneal Interposition Flap in Symptomatic Lymphocele Reduction following Robot-Assisted Radical Prostatectomy: Insights from the PIANOFORTE Trial.

The available randomised controlled trials (RCTs) assessing the influence of peritoneal interposition flaps (PIF) on the reduction of symptomatic lymphoceles (sLCs) post robot-assisted radical prostatectomy (RARP) do not constitute a sufficient follow-up (FU) to assess the long-term effects. The PIANOFORTE trial was the first of these RCTs, showing no sLC reduction at the 3-month FU. Therefore, all 232 patients from the PIANOFORTE trial were invited for long-term FU. One hundred seventy-six patients (76%) presented themselves for FU and constituted the study group (SG). The median FU duration was 43 months. No significant differences in group allocation or LC endpoints at 90 days were observed between SG patients and patients not presenting themselves for the FU. During the FU period, four patients (2.3%) in the SG developed sLCs, and six patients (3.4%) developed asymptomatic lymphoceles (aLCs), which persisted in five patients (2.9%). There were no significant differences between PIF and non-PIF regarding sLC/aLC formation or persistence, newly developed complications, stress urinary incontinence or biochemical/clinical tumour recurrence. Therefore, this long-term FU confirms the primary outcomes of the PIANOFORTE trial that, while PIF does not impact complications or functionality, it does not reduce sLC/aLC rates. Furthermore, it shows the potential occurrence of LC after the third postoperative month.

Evaluating the Efficacy of AI Chatbots as Tutors in Urology: A Comparative Analysis of Responses to the 2022 In-Service Assessment of the European Board of Urology.

INTRODUCTION: This study assessed the potential of Large Language Models (LLMs) as educational tools by evaluating their accuracy in answering questions across urological subtopics. METHODS: Three LLMs (ChatGPT-3.5, ChatGPT-4, and Bing AI) were examined in two testing rounds, separated by 48-hours, using 100 Multiple-Choice Questions (MCQs) from the 2022 European Board of Urology (EBU) In-Service Assessment (ISA), covering five different subtopics. The correct answer was defined as "formal accuracy" (FA) representing the designated single best answer (SBA) among four options. Alternative answers selected from LLMs, which may not necessarily be the SBA but are still deemed correct, were labeled as "extended accuracy" (EA). Their capacity to enhance the overall accuracy rate when combined with FA was examined. RESULTS: In two rounds of testing, the FAs scores were achieved as follows: ChatGPT-3.5: 58% and 62%, ChatGPT-4: 63% and 77%, and BING AI: 81% and 73%. The incorporation of EA did not yield a significant enhancement in overall performance. The achieved gains for ChatGPT-3.5, ChatGPT-4, and BING AI were as a result 7% and 5%, 5% and 2%, and 3% and 1%, respectively (p>0.3). Within urological subtopics, LLMs showcased best performance in Pediatrics/Congenital and comparatively less effectiveness in Functional/BPS/Incontinence. CONCLUSION: LLMs exhibit suboptimal urology knowledge and unsatisfactory proficiency for educational purposes. The overall accuracy did not significantly improve when combining EA to FA. The error rates remained high ranging from 16 to 35%. Proficiency levels vary substantially across subtopics. Further development of medicine specific LLMs is required before integration into urological training programs.

Urine-Based Biomarker Test Uromonitor® in the Detection and Disease Monitoring of Non-Muscle-Invasive Bladder Cancer-A Systematic Review and Meta-Analysis of Diagnostic Test Performance.

Optimal urine-based diagnostic tests (UBDT) minimize unnecessary follow-up cystoscopies in patients with non-muscle-invasive bladder-cancer (NMIBC), while accurately detecting high-grade bladder-cancer without false-negative results. Such UBDTs have not been comprehensively described upon a broad, validated dataset, resulting in cautious guideline recommendations. Uromonitor®, a urine-based DNA-assay detecting hotspot alterations in TERT, FGFR3, and KRAS, shows promising initial results. However, a systematic review merging all available data is lacking. Studies investigating the diagnostic performance of Uromonitor® in NMIBC until November 2023 were identified in PubMed, Embase, Web-of-Science, Cochrane, Scopus, and medRxiv databases. Within aggregated analyses, test performance and area under the curve/AUC were calculated. This project fully implemented the PRISMA statement. Four qualifying studies comprised a total of 1190 urinary tests (bladder-cancer prevalence: 14.9%). Based on comprehensive analyses, sensitivity, specificity, positive-predictive value/PPV, negative-predictive value/NPV, and test accuracy of Uromonitor® were 80.2%, 96.9%, 82.1%, 96.6%, and 94.5%, respectively, with an AUC of 0.886 (95%-CI: 0.851-0.921). In a meta-analysis of two studies comparing test performance with urinary cytology, Uromonitor® significantly outperformed urinary cytology in sensitivity, PPV, and test accuracy, while no significant differences were observed for specificity and NPV. This systematic review supports the use of Uromonitor® considering its favorable diagnostic performance. In a cohort of 1000 patients with a bladder-cancer prevalence of ~15%, this UBDT would avert 825 unnecessary cystoscopies (true-negatives) while missing 30 bladder-cancer cases (false-negatives). Due to currently limited aggregated data from only four studies with heterogeneous quality, confirmatory studies are needed.

The relevance of structural variability in the time-domain for computational reflection anisotropy spectroscopy at solid-liquid interfaces.

In electrochemistry, reactions and charge-transfer are to a large extent determined by the atomistic structure of the solid-liquid interface. Yet due to the presence of the liquid electrolyte, many surface-science methods cannot be applied here. Hence, the exact microscopic structure that is present under operating conditions often remains unknown. Reflection anisotropy spectroscopy (RAS) is one of the few techniques that allow for anin operandoinvestigation of the structure of solid-liquid interfaces. However, an interpretation of RAS data on the atomistic scale can only be obtained by comparison to computational spectroscopy. While the number of computational RAS studies related to electrochemical systems is currently still limited, those studies so far have not taken into account the dynamic nature of the solid-liquid interface. In this work, we investigate the temporal evolution of the spectroscopic response of the Au(110) missing row reconstruction in contact with water by combiningab initiomolecular dynamics with computational spectroscopy. Our results show significant changes in the time evolution of the RA spectra, in particular providing an explanation for the typically observed differences in intensity when comparing theory and experiment. Moreover, these findings point to the importance of structural surface/interface variability while at the same time emphasising the potential of RAS for probing these dynamic interfaces.

The landscape of penile cancer research in Germany and Austria: a survey among professors in academic centers holding chair positions and results of a literature search.

BACKGROUND: Research on penile cancer (PeCa) is predominantly conducted in countries with centralized treatment of PeCa-patients. In Germany and Austria (G + A), no state-regulated centralization is established, and no information is available on how PeCa-research is organized. METHODS: Current research competence in PeCa was assessed by a 36-item questionnaire sent to all chairholders of urological academic centers in G + A. Based on PubMed records, all scientific PeCa-articles of 2012-2022 from G + A were identified. Current research trends were assessed by dividing the literature search into two periods (P1: 2012-2017, P2: 2018-2022). A bibliometric analysis was supplemented. RESULTS: Response rate of the questionnaire was 75%, a median of 13 (IQR: 9-26) PeCa-patients/center was observed in 2021. Retrospective case series were conducted by 38.9% of participating clinics, while involvement in randomized-controlled trials was stated in 8.3% and in basic/fundamental research in 19.4%. 77.8% declared an interest in future multicenter projects. 205 PeCa-articles were identified [median impact factor: 2.77 (IQR: 0.90-4.37)]. Compared to P1, P2 showed a significant increase in the median annual publication count (29 (IQR: 13-17) vs. 15 (IQR: 19-29), p < 0.001), in multicenter studies (79.1% vs. 63.6%, p = 0.018), and in multinational studies (53% vs. 28.9%, p < 0.001); the proportion of basic/fundamental research articles significantly declined (16.5% vs. 28.9%, p = 0.041). Four of the top-5 institutions publishing PeCa-articles are academic centers. Bibliometric analyses revealed author networks, primary research areas in PeCa, and dominant journals for publications. CONCLUSIONS: Given the lack of centralization in G + A, this analysis highlights the need for research coordination within multicenter PeCa-projects. The decline in basic/fundamental research should be effectively addressed by the allocation of funded research projects.

How does artificial intelligence master urological board examinations? A comparative analysis of different Large Language Models' accuracy and reliability in the 2022 In-Service Assessment of the European Board of Urology.

PURPOSE: This study is a comparative analysis of three Large Language Models (LLMs) evaluating their rate of correct answers (RoCA) and the reliability of generated answers on a set of urological knowledge-based questions spanning different levels of complexity. METHODS: ChatGPT-3.5, ChatGPT-4, and Bing AI underwent two testing rounds, with a 48-h gap in between, using the 100 multiple-choice questions from the 2022 European Board of Urology (EBU) In-Service Assessment (ISA). For conflicting responses, an additional consensus round was conducted to establish conclusive answers. RoCA was compared across various question complexities. Ten weeks after the consensus round, a subsequent testing round was conducted to assess potential knowledge gain and improvement in RoCA, respectively. RESULTS: Over three testing rounds, ChatGPT-3.5 achieved RoCa scores of 58%, 62%, and 59%. In contrast, ChatGPT-4 achieved RoCA scores of 63%, 77%, and 77%, while Bing AI yielded scores of 81%, 73%, and 77%, respectively. Agreement rates between rounds 1 and 2 were 84% (κ = 0.67, p < 0.001) for ChatGPT-3.5, 74% (κ = 0.40, p < 0.001) for ChatGPT-4, and 76% (κ = 0.33, p < 0.001) for BING AI. In the consensus round, ChatGPT-4 and Bing AI significantly outperformed ChatGPT-3.5 (77% and 77% vs. 59%, both p = 0.010). All LLMs demonstrated decreasing RoCA scores with increasing question complexity (p < 0.001). In the fourth round, no significant improvement in RoCA was observed across all three LLMs. CONCLUSIONS: The performance of the tested LLMs in addressing urological specialist inquiries warrants further refinement. Moreover, the deficiency in response reliability contributes to existing challenges related to their current utility for educational purposes.

MRI of Temporomandibular Joint Disorders: A Comparative Study of 0.55 T and 1.5 T MRI.

OBJECTIVES: Temporomandibular disorders (TMDs) are common and may cause persistent functional limitations and pain. Magnetic resonance imaging (MRI) at 1.5 and 3 T is commonly applied for the evaluation of the temporomandibular joint (TMJ). No evidence is available regarding the feasibility of modern low-field MRI for the assessment of TMDs. The objective of this prospective study was to evaluate the image quality (IQ) of 0.55 T MRI in direct comparison with 1.5 T MRI. MATERIALS AND METHODS: Seventeen patients (34 TMJs) with suspected intraarticular TMDs were enrolled, and both 0.55 and 1.5 T MRI were performed on the same day. Two senior readers independently evaluated the IQ focusing on the conspicuity of disc morphology (DM), disc position (DP), and osseous joint morphology (OJM) for each joint. We analyzed the IQ and degree of artifacts using a 4-point Likert scale (LS) at both field strengths. A fully sufficient IQ was defined as an LS score of ≥3. Nonparametric Wilcoxon test for related samples was used for statistical comparison. RESULTS: The median IQ for the DM and OJM at 0.55 T was inferior to that at 1.5 T (DM: 3 [interquartile range {IQR}, 3-4] vs 4 [IQR, 4-4]; OJM: 3 [IQR, 3-4] vs 4 [IQR 4-4]; each P < 0.001). For DP, the IQ was comparable (4 [IQR 3-4] vs 4 [IQR 4-4]; P > 0.05). A sufficient diagnostic IQ was maintained for the DM, DP, and OJM in 92% of the cases at 0.55 T and 100% at 1.5 T. Minor image artifacts (LS score of ≥3) were more prevalent at 0.55 T (29%) than at 1.5 T (12%). CONCLUSIONS: Magnetic resonance imaging of the TMJ at 0.55 T yields a lower IQ than does MRI at 1.5 T but maintains sufficient diagnostic confidence in the majority of patients. Further improvements are needed for reliable clinical application.

Lung Nodule Detection With Modern Low-Field MRI (0.55 T) in Comparison to CT.

OBJECTIVES: The aim of this study was to evaluate the accuracy of modern low-field magnetic resonance imaging (MRI) for lung nodule detection and to correlate nodule size measurement with computed tomography (CT) as reference. MATERIALS AND METHODS: Between November 2020 and July 2021, a prospective clinical trial using low-field MRI at 0.55 T was performed in patients with known pulmonary nodules from a single academic medical center. Every patient underwent MRI and CT imaging on the same day. The primary aim was to evaluate the detection accuracy of pulmonary nodules using MRI with transversal periodically rotated overlapping parallel lines with enhanced reconstruction in combination with coronal half-Fourier acquired single-shot turbo spin-echo MRI sequences. The secondary outcome was the correlation of the mean lung nodule diameter with CT as reference according to the Lung Imaging Reporting and Data System. Nonparametric Mann-Whitney U test, Spearman rank correlation coefficient, and Bland-Altman analysis were applied to analyze the results. RESULTS: A total of 46 participants (mean age ± SD, 66 ± 11 years; 26 women) were included. In a blinded analysis of 964 lung nodules, the detection accuracy was 100% for those ≥6 mm (126/126), 80% (159/200) for those ≥4-<6 mm, and 23% (147/638) for those <4 mm in MRI compared with reference CT. Spearman correlation coefficient of MRI and CT size measurement was r = 0.87 ( P < 0.001), and the mean difference was 0.16 ± 0.9 mm. CONCLUSIONS: Modern low-field MRI shows excellent accuracy in lesion detection for lung nodules ≥6 mm and a very strong correlation with CT imaging for size measurement, but could not compete with CT in the detection of small nodules.

Impact of Peritoneal Interposition Flap on Patients Undergoing Robot-assisted Radical Prostatectomy and Pelvic Lymph Node Dissection: A Systematic Review and Meta-analysis of Randomized Controlled Trials.

CONTEXT: Symptomatic lymphocele (sLC) occurs at a frequency of 2-10% after robot-assisted radical prostatectomy (RARP) with pelvic lymph node dissection (PLND). Construction of bilateral peritoneal interposition flaps (PIFs) subsequent to completion of RARP + PLND has been introduced to reduce the risk of lymphocele, and was initially evaluated on the basis of retrospective studies. OBJECTIVE: To conduct a systematic review and meta-analysis of only randomized controlled trials (RCTs) evaluating the impact of PIF on the rate of sLC (primary endpoint) and of overall lymphocele (oLC) and Clavien-Dindo grade ≥3 complications (secondary endpoints) to provide the best available evidence. EVIDENCE ACQUISITION: In accordance with the Preferred Reporting Items for Meta-Analyses statement for observational studies in epidemiology, a systematic literature search using the MEDLINE (PubMed), Cochrane Central Register of Controlled Trials (CENTRAL), and EMBASE databases up to February 3, 2023 was performed to identify RCTs. The risk of bias (RoB) was assessed using the revised Cochrane RoB tool for randomized trials. Meta-analysis used random-effect models to examine the impact of PIF on the primary and secondary endpoints. EVIDENCE SYNTHESIS: Four RCTs comparing outcomes for patients undergoing RARP + PLND with or without PIF were identified: PIANOFORTE, PerFix, ProLy, and PLUS. PIF was associated with odds ratios of 0.46 (95% confidence interval [CI] 0.23-0.93) for sLC, 0.51 (95% CI 0.38-0.68) for oLC, and 0.41 (95% CI 0.21-0.83) for Clavien-Dindo grade ≥3 complications. Functional impairment resulting from PIF construction was not observed. Heterogeneity was low to moderate, and RoB was low. CONCLUSIONS: PIF should be performed in patients undergoing RARP and simultaneous PLND to prevent or reduce postoperative sLC. PATIENT SUMMARY: A significant proportion of patients undergoing prostate cancer surgery have regional lymph nodes removed. This part of the surgery is associated with a risk of postoperative lymph collections (lymphocele). The risk of lymphocele can be halved via a complication-free surgical modification called a peritoneal interposition flap.