Magnetic Resonancy Imaging Safety in Active Osseointegrated (Osia®) and Cochlear Implants: New Technology Creating Confusion.

OBJECTIVE: There is increased confusion regarding MRI-compatible CIs and BAHAs. This report describes two cases when patients underwent MRIs with non-MRI compatible devices. RESULTS: One patient with bilateral Cochlear Osias experienced dislocation of both internal magnets after 1.5 Tesla MRI. Both magnets were outside the silastic sheath, with the left magnet flipped. A second patient with a legacy CI experienced similar internal magnet dislocation and inversion after 3 Tesla MRI. CONCLUSIONS: This study describes internal magnet dislocation/inversion with the Cochlear Osia and a legacy CI after MRI. Our findings suggest the need for improved patient education and simplified radiology guidelines. Laryngoscope, 134:393-396, 2024.

AI-generated R.E.N.A.L.+ Score Surpasses Human-generated Score in Predicting Renal Oncologic Outcomes.

OBJECTIVE: To determine whether we can surpass the traditional R.E.N.A.L. nephrometry score (H-score) prediction ability of pathologic outcomes by creating artificial intelligence (AI)-generated R.E.N.A.L.+ score (AI+ score) with continuous rather than ordinal components. We also assessed the AI+ score components' relative importance with respect to outcome odds. METHODS: This is a retrospective study of 300 consecutive patients with preoperative computed tomography scans showing suspected renal cancer at a single institution from 2010 to 2018. H-score was tabulated by three trained medical personnel. Deep neural network approach automatically generated kidney segmentation masks of parenchyma and tumor. Geometric algorithms were used to automatically estimate score components as ordinal and continuous variables. Multivariate logistic regression of continuous R.E.N.A.L. components was used to generate AI+ score. Predictive utility was compared between AI+, AI, and H-scores for variables of interest, and AI+ score components' relative importance was assessed. RESULTS: Median age was 60years (interquartile range 51-68), and 40% were female. Median tumor size was 4.2 cm (2.6-6.12), and 92% were malignant, including 27%, 37%, and 23% with high-stage, high-grade, and necrosis, respectively. AI+ score demonstrated superior predictive ability over AI and H-scores for predicting malignancy (area under the curve [AUC] 0.69 vs 0.67 vs 0.64, respectively), high stage (AUC 0.82 vs 0.65 vs 0.71, respectively), high grade (AUC 0.78 vs 0.65 vs 0.65, respectively), pathologic tumor necrosis (AUC 0.81 vs 0.72 vs 0.74, respectively), and partial nephrectomy approach (AUC 0.88 vs 0.74 vs 0.79, respectively). Of AI+ score components, the maximal tumor diameter ("R") was the most important outcomes predictor. CONCLUSION: AI+ score was superior to AI-score and H-score in predicting oncologic outcomes. Time-efficient AI+ score can be used at the point of care, surpassing validated clinical scoring systems.

The Incidence of Velopharyngeal Insufficiency in Stickler Syndrome.

OBJECTIVE: Stickler Syndrome (SS) is an inherited collagenopathy characterized by heterogenous orofacial, ocular, auditory, and skeletal abnormalities. The orofacial manifestations are variable and some patients present with cleft palate and velopharyngeal insufficiency (VPI). The incidence of VPI in SS is poorly studied and no studies have compared the incidence of VPI between Type I (COL2A1) and Type II (COL11A1) SS. The objective of this study is to compare the incidence of VPI between SS subtypes and discuss the surgical techniques used to treat them. DESIGN: Single-institution, retrospective chart review. SETTING: Tertiary pediatric hospital. PATIENTS/PARTICIPANTS: Forty-three children were diagnosed with SS between January 2003 and December 2018. Genetic testing results, genetics notes, craniofacial clinic notes, and operative reports were reviewed. Patients without genetic testing or craniofacial/otolaryngologic evaluation were excluded. Thirty-one patients met criteria and were included. MAIN OUTCOME MEASURE: Primary outcome was VPI incidence. RESULTS: There were 18 patients with Type I SS and 13 with Type II SS. Five (16%) patients had VPI, 2 (11%) with Type I SS compared to 3 (23%) with Type II SS (P > .05). All patients with VPI underwent surgery with either sphincter pharyngoplasty (3) or pharyngeal flap (2). Two patients with Type II SS underwent revision sphincter pharyngoplasty, with one conversion to pharyngeal flap. CONCLUSION: VPI is common for patients with SS. In this study, there was no significant difference in the incidence of VPI between SS subtypes. Future studies are needed to confirm these findings, which could be important for patient counseling and treatment planning.

The Growing Role for Semantic Segmentation in Urology.

As the quantity and quality of cross-sectional imaging data increase, it is important to be able to make efficient use of the information. Semantic segmentation is an emerging technology that promises to improve the speed, reproducibility, and accuracy of analysis of medical imaging, and to allow visualization methods that were previously impossible. Manual image segmentation often requires expert knowledge and is both time- and cost-prohibitive in many clinical situations. However, automated methods, especially those using deep learning, show promise in alleviating this burden to make segmentation a standard tool for clinical intervention in the future. It is therefore important for clinicians to have a functional understanding of what segmentation is and to be aware of its uses. Here we include a number of examples of ways in which semantic segmentation has been put into practice in urology. PATIENT SUMMARY: This mini-review highlights the growing role of segmentation methods for medical images in urology to inform clinical practice. Segmentation methods show promise in improving the reliability of diagnosis and aiding in visualization, which may become a tool for patient education.

Violence prevention emergency tool (VPET) screening of youth in the pediatric ED.

Background Violence is an increasingly common and significant problem for youth worldwide. Youth who rely on treatment at urban EDs are more likely to die as the result of violence than any other disease/condition for which they seek care. The first step in helping youth that are at risk, is identifying them. We developed a 7-item screening tool called VPET. The purpose of this study is to validate the VPET screening tool in identifying high-risk youth. Methods and findings We prospectively enrolled a convenience sample of children during the index ED visit who were called 3 months and 6 months after this visit. 269 youth (33%) completed 3-month follow up (44.2% male); 240 youth (29.4%) completed 6-month follow up (45% male); 84.0% reported some level of violence exposure after 3-months and 84.2% (n = 240) reported some level of violence exposure after 6-months. Predictive validity was assessed by Spearman's correlation between VPET score and follow-up score at 3-months and 6-months post-enrollment; logistic regression to calculate odds ratios between positive VPET item responses and positive follow-up score; ROC curve analysis. VPET score had internal consistency, as tested by Cronbach's alpha (α = 0.642). Children who were male, non-white, and had been hurt at home or school reported the highest VPET scores. Conclusion VPET has sufficiently strong psychometric function and performs well as a screening tool to predict future violence exposure for youth ages 8-17. Five questions on the VPET screening tool are independently predictive of violence reported at 6 months and four questions at 3 months.