ABSTRACT
BACKGROUND: Current intraoperative orientation methods either rely on preoperative imaging, are resource-intensive to implement, or difficult to interpret. Real-time, reliable anatomic recognition would constitute another strong pillar on which neurosurgeons could rest for intraoperative orientation. OBJECTIVE: To assess the feasibility of machine vision algorithms to identify anatomic structures using only the endoscopic camera without prior explicit anatomo-topographic knowledge in a proof-of-concept study. METHODS: We developed and validated a deep learning algorithm to detect the nasal septum, the middle turbinate, and the inferior turbinate during endoscopic endonasal approaches based on endoscopy videos from 23 different patients. The model was trained in a weakly supervised manner on 18 and validated on 5 patients. Performance was compared against a baseline consisting of the average positions of the training ground truth labels using a semiquantitative 3-tiered system. RESULTS: We used 367 images extracted from the videos of 18 patients for training, as well as 182 test images extracted from the videos of another 5 patients for testing the fully developed model. The prototype machine vision algorithm was able to identify the 3 endonasal structures qualitatively well. Compared to the baseline model based on location priors, the algorithm demonstrated slightly but statistically significantly (P < .001) improved annotation performance. CONCLUSION: Automated recognition of anatomic structures in endoscopic videos by means of a machine vision model using only the endoscopic camera without prior explicit anatomo-topographic knowledge is feasible. This proof of concept encourages further development of fully automated software for real-time intraoperative anatomic guidance during surgery.
Subject(s)
Algorithms , Endoscopy , Humans , Pituitary Gland , SoftwareABSTRACT
OBJECTIVES: To evaluate facial attractiveness of treated cleft patients and controls by artificial intelligence (AI) and to compare these results with panel ratings performed by laypeople, orthodontists, and oral surgeons. MATERIALS AND METHODS: Frontal and profile images of 20 treated left-sided cleft patients (10 males, mean age: 20.5 years) and 10 controls (5 males, mean age: 22.1 years) were evaluated for facial attractiveness with dedicated convolutional neural networks trained on >17 million ratings for attractiveness and compared to the assessments of 15 laypeople, 14 orthodontists, and 10 oral surgeons performed on a visual analogue scale (n = 2323 scorings). RESULTS: AI evaluation of cleft patients (mean score: 4.75 ± 1.27) was comparable to human ratings (laypeople: 4.24 ± 0.81, orthodontists: 4.82 ± 0.94, oral surgeons: 4.74 ± 0.83) and was not statistically different (all Ps ≥ 0.19). Facial attractiveness of controls was rated significantly higher by humans than AI (all Ps ≤ 0.02), which yielded lower scores than in cleft subjects. Variance was considerably large in all human rating groups when considering cases separately, and especially accentuated in the assessment of cleft patients (coefficient of variance-laypeople: 38.73 ± 9.64, orthodontists: 32.56 ± 8.21, oral surgeons: 42.19 ± 9.80). CONCLUSIONS: AI-based results were comparable with the average scores of cleft patients seen in all three rating groups (with especially strong agreement to both professional panels) but overall lower for control cases. The variance observed in panel ratings revealed a large imprecision based on a problematic absence of unity. IMPLICATION: Current panel-based evaluations of facial attractiveness suffer from dispersion-related issues and remain practically unavailable for patients. AI could become a helpful tool to describe facial attractiveness, but the present results indicate that important adjustments are needed on AI models, to improve the interpretation of the impact of cleft features on facial attractiveness.
