RESUMO
INTRODUCTION: Prosthetic complications that occur to some implant prosthetics may require removal of the prosthesis for replacement or repair. Therefore, the presence of a technique to identify the type of dental implant is mandatory to provide the suitable components. Hence, the aim of the current study was to evaluate the accuracy of YOLOv8 object detection algorithm in automatic identification of the type of dental implant from digital periapical radiographs. METHODS: YOLOv8m-seg object detection algorithm was used to build a model to automatically identify the type of dental implant. A set of 2573 digital periapical radiographs for six distinct dental implants manufacturers were used to train the model. The outcomes were evaluated using precision, recall, F1 score and mAP. RESULTS: The overall accuracy of the YOLOv8m-seg model in terms of precision, recall, F1 score and mAP revealed values of 0.919, 0.98, 0.95 and 0.972 respectively. The average detection speed of the images was 1.3 seconds. The model was able to detect and identify multiple implants simultaneously on the same image. CONCLUSIONS: YOLOv8m-seg object detection algorithm is promising in identification of dental implants from periapical radiographs with high detection accuracy (97.2%), fast detection results and multi-implant detection from the same image. CLINICAL SIGNIFICANCE: This AI system can accurately identify the type of osseointegrated dental implants enabling dentists to provide the appropriate prosthetic components even if different implant systems are used within the same patient. This can save tremendous amounts of time, effort and cost for both the dentist and the patient.
RESUMO
BACKGROUND: Infection is the most common complication of stroke. AIM: To determine the risk factors and predictors of post-stroke infection (PSI), which developed within 7 days from the onset of acute ischemic stroke. SUBJECTS: The study included 60 ischemic stroke patients admitted in the Neurology Department of Zagazig University, Egypt, who were subdivided into: [Non Stroke Associated Infection group (nSAI); 30 patients having stroke without any criteria of infection within 7 days from the onset and Stroke Associated Infection group (SAI); 30 patients having stroke with respiratory tract infection (RTI) or urinary tract infection within 7 days], in addition to 30 healthy sex and age-matching subjects as control. METHODS: All the patients had a detailed history taking, thorough clinical general and neurological examination, laboratory tests (Urine analysis & urine culture, blood sugar, lipid profile and serum tumor necrosis factor-alpha (TNF-α) and interleukin (IL)-10), a chest radiography to assess RTI and brain computed tomography (CT) to exclude the hemorrhagic stroke and to confirm the ischemic stroke. RESULTS: SAI patients were found to be significantly older with higher baseline blood glucose level. Also the number of patients with tube feeding, lower conscious level, more stroke severity and more large size infarcts were significantly higher in SAI patients. There was a significant elevation in the IL-10, a significant decrease in the TNF-α and a significant decrease in the TNF-α/ IL-10 ratio, in the SAI group. The baseline serum level of IL-10 ≥ 14.5 pg/ ml and size of infarct area > 3.5 cm3 were found to be the independent predictors of PSI. CONCLUSION: Patients with older age, tube feeding, lower conscious level, worse baseline stroke severity, large cerebral infarcts in CT scan, and increased IL-10 serum level were more susceptible to infection. The baseline serum level of IL-10 ≥ 14.5 pg/ ml and the size of infarct area > 3.5 cm3 were the independent predictors of PSI.
