Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children.

BACKGROUND: Advances have been made in the use of artificial intelligence (AI) in the field of diagnostic imaging, particularly in the detection of fractures on conventional radiographs. Studies looking at the detection of fractures in the pediatric population are few. The anatomical variations and evolution according to the child's age require specific studies of this population. Failure to diagnose fractures early in children may lead to serious consequences for growth. OBJECTIVE: To evaluate the performance of an AI algorithm based on deep neural networks toward detecting traumatic appendicular fractures in a pediatric population. To compare sensitivity, specificity, positive predictive value and negative predictive value of different readers and the AI algorithm. MATERIALS AND METHODS: This retrospective study conducted on 878 patients younger than 18 years of age evaluated conventional radiographs obtained after recent non-life-threatening trauma. All radiographs of the shoulder, arm, elbow, forearm, wrist, hand, leg, knee, ankle and foot were evaluated. The diagnostic performance of a consensus of radiology experts in pediatric imaging (reference standard) was compared with those of pediatric radiologists, emergency physicians, senior residents and junior residents. The predictions made by the AI algorithm and the annotations made by the different physicians were compared. RESULTS: The algorithm predicted 174 fractures out of 182, corresponding to a sensitivity of 95.6%, a specificity of 91.64% and a negative predictive value of 98.76%. The AI predictions were close to that of pediatric radiologists (sensitivity 98.35%) and that of senior residents (95.05%) and were above those of emergency physicians (81.87%) and junior residents (90.1%). The algorithm identified 3 (1.6%) fractures not initially seen by pediatric radiologists. CONCLUSION: This study suggests that deep learning algorithms can be useful in improving the detection of fractures in children.

Performance of AI for preoperative CT assessment of lung metastases: Retrospective analysis of 167 patients.

OBJECTIVES: To evaluate the performance of artificial intelligence (AI) in the preoperative detection of lung metastases on CT. MATERIALS AND METHODS: Patients who underwent lung metastasectomy in our institution between 2016 and 2020 were enrolled, their preoperative CT reports having been performed before an AI solution (Veye Lung Nodules, version 3.9.2, Aidence) became available as a second reader in our department. All CT scans were retrospectively processed by AI. The sensitivities of unassisted radiologists (original CT radiology reports), AI reports alone and both combined were compared. Ground truth was established by a consensus reading of two radiologists, who analyzed whether the nodules mentioned in the pathology report were retrospectively visible on CT. Multivariate analysis was performed to identify nodule characteristics associated with detectability. RESULTS: A total of 167 patients (men: 62.9 %; median age, 59 years [47-68]) with 475 resected nodules were included. AI detected an average of 4 nodules (0-17) per CT, of which 97 % were true nodules. The combination of radiologist plus AI (92.4 %) had significantly higher sensitivity than unassisted radiologists (80.4 %) (p < 0.001). In 27/57 (47.4 %) patients who had multiple preoperative CT scans, AI detected lung nodules earlier than the radiologist. Vascular contact was associated with non-detection by radiologists (OR:0.32[0.19, 0.54], p < 0.001), whilst the presence of cavitation (OR:0.26[0.13, 0.54], p < 0.001) or pleural contact (OR:0.10[0.04, 0.22], p < 0.001) was associated with non-detection by AI. CONCLUSION: AI significantly increases the sensitivity of preoperative detection of lung metastases and enables earlier detection, with a significant potential benefit for patient management.