Search

Background: Petrous temporal bone cone-beam computed tomography scans help aid diagnosis and accurate identification of key operative landmarks in temporal bone and mastoid surgery. Our primary objective was to determine the accuracy of using a deep learning convolutional neural network algorithm to augment identification of structures on petrous temporal bone cone-beam computed tomography. Our secondary objective was to compare the accuracy of convolutional neural network structure identification when trained by a senior versus junior clinician., Methods: A total of 129 petrous temporal bone cone-beam computed tomography scans were obtained from an Australian public tertiary hospital. Key intraoperative landmarks were labeled in 68 scans using bounding boxes on axial and coronal slices at the level of the malleoincudal joint by an otolaryngology registrar and board-certified otolaryngologist. Automated structure identification was performed on axial and coronal slices of the remaining 61 scans using a convolutional neural network (Microsoft Custom Vision) trained using the labeled dataset. Convolutional neural network structure identification accuracy was manually verified by an otolaryngologist, and accuracy when trained by the registrar and otolaryngologist labeled datasets respectively was compared., Results: The convolutional neural network was able to perform automated structure identification in petrous temporal bone cone-beam computed tomography scans with a high degree of accuracy in both axial (0.958) and coronal (0.924) slices (P < .001). Convolutional neural network accuracy was proportionate to the seniority of the training clinician in structures with features more difficult to distinguish on single slices such as the cochlea, vestibule, and carotid canal., Conclusion: Convolutional neural networks can perform automated structure identification in petrous temporal bone cone-beam computed tomography scans with a high degree of accuracy, with the performance being proportionate to the seniority of the training clinician. Training of the convolutional neural network by the most senior clinician is desirable to maximize the accuracy of the results.

Aim: To assess the variability in Australian screening guidelines for developmental dysplasia of the hip (DDH)., Methods: Ovid MEDLINE®, EMBASE, EMB Reviews-Cochrane, CINAHL, TRIP and grey literature were searched to identify screening guidelines for DDH. Key data items related to recommendations for timing and method of screening were extracted and summarised in a table format for qualitative analysis., Results: Seventeen guidelines met inclusion criteria, comprising nine Australian DDH screening guidelines and eight Child Health Books. The guidelines showed variation in recommendations for the examiner, specific screening methods used for high-risk groups, timing of examinations and recommendations for referral., Conclusions: Variability exists within Australian DDH screening guidelines. Lack of knowledge regarding local screening guidelines may contribute to the current trend of increased incidence of late diagnosed DDH in Australia, reported in New South Wales, South Australia, and Western Australia. An evidence-based and consistent approach to DDH screening is necessary to minimise late detected cases., (© 2021 Paediatrics and Child Health Division (The Royal Australasian College of Physicians).)

Background: The International Duration Evaluation of Adjuvant Chemotherapy (IDEA) collaboration aimed to evaluate whether 3 months of adjuvant chemotherapy are noninferior to 6 months. Our study objectives were to characterize medical oncologists' perspectives toward the results of the IDEA collaboration and to evaluate how IDEA impacted prescribing patterns of adjuvant FOLFOX and CAPOX in colon cancer., Materials and Methods: A list of questions developed by four medical oncologists regarding IDEA results were formulated and distributed online to gastrointestinal medical oncologists globally. Descriptive statistics and chi-square tests were used to summarize information., Results: Of 174 responses, 145 were complete and analyzed. Responses were obtained globally from South America (53%); the U.S. and Canada (28%); Europe, Australia, and New Zealand (12%); and Asia (7%). Most clinicians (98%) were aware of the IDEA study. Prior to IDEA, clinicians preferred FOLFOX over CAPOX (81% vs. 19%). Subsequent to IDEA, 55% of clinicians preferred CAPOX over FOLFOX (odds ratio, 5.0; 95% confidence interval, 3.0-8.5; p < .01 compared with pre-IDEA). Two thirds (68%) of responders tailored duration of adjuvant therapy based on risk stratification. Most oncologists (76%) were more willing to discontinue oxaliplatin early if toxicities develop after the results of IDEA. Half of responders (50%) found that IDEA increased their confidence in decision making for adjuvant treatment; 36% were unchanged, and 15% indicated decreased confidence. Less than half (48%) were comfortable communicating the study results and the concept of a noninferiority trial with patients., Conclusion: IDEA appears to have shifted clinician preference from FOLFOX to CAPOX for adjuvant therapy, and most clinicians now use a risk-stratified approach in determining duration of adjuvant therapy. Patient education resources may facilitate better communication of IDEA results to patients., Implications for Practice: This global survey illustrates that most gastrointestinal medical oncologists now use a risk-stratified approach for determining the duration of adjuvant chemotherapy for stage III colon cancer. Clinicians are five times more likely to choose CAPOX over FOLFOX after the International Duration Evaluation of Adjuvant Chemotherapy (IDEA) collaboration results., (© AlphaMed Press 2019.)