Technical Name 即時危險辨識系統
Project Operator National Taiwan University
Project Host 王偉仲
“MeDA OXR: Real-time Hazard Recognition System,” which can automatically screeninterpret the medical images in real-time, is designed for emergency rooms to assist physicians in diagnosis, reducing medical risks,improving overall efficiency. Combining portable X-RayAI algorithms, the system performs real-timeaccurate preliminary screeningdiagnoses of diseases, such as pneumothorax, pneumonia,tuberculosis. It can also locate the nasogastric tube, endotracheal tube,central venous catheter, while misplacement of that is sent to the physicians when detected.
Scientific Breakthrough
"MeDA OXR Real-time Hazard Recognition System" regards iPad as a mobile medical imaging server that interprets the diseasecatheter position. Comparison of originalanalyzed images are shown side by side on the iPad for the doctors’ reference. With the system, diagnosistreatment can be determined rapidly in the emergency department. In terms of telemedicine, the system can be installed in mobile health vehiclesremote medical centers to conduct consultations, diagnoses,arrange referrals for patients in the first place, thereby enhancing the scope of precision medicine.
Industrial Applicability
"MeDA OXR: Real-time Hazard Recognition System" allows emergency physicians to use a handiermore user-friendly mobile tablet (iPad) to obtain the results of AI interpretation. The value of diagnosisfollow-up treatment based on the results are improved,the ease of useapplication value are also raised. In the future, rapid screening can be carried out in ruralregional hospitals to achieve preliminary levels of care classificationshunting. Moreover, interpreting large amounts of data of monitoring systems at long-term care can improve clinical efficiency.
Matching Needs
Keyword Portable X-ray Deep learning Edge computing Object detection Coarse-to-Fine Neural Architecture Search (C2FNAS) Convolutional Neural Network (CNN) Image Segmentation Emergency department/ room Classification and diagnosis Telemedicine
  • Contact
other people also saw