Medical research: AI tracks blood flow through heart
Nature Machine Intelligence
2020년4월14일
An artificial intelligence (AI) system capable of speeding up cardiovascular blood flow scans is reported in a paper published in Nature Machine Intelligence . This deep learning model may improve diagnostic workflows by allowing clinicians to view blood flow in real time while the patient is still in an MRI scanner.
4D MRI scans can be used to reconstruct cardiovascular blood flow over time, and are important for diagnosing a range of cardiovascular diseases. However, these scans typically take up to 20 minutes to process, meaning that decisions about further imaging assessments cannot be made during an exam session. Speeding up these scans would allow real-time assessment while the patient is still in the scanner, potentially freeing up a clinician’s time and decreasing patient discomfort.
Valery Vishnevskiy and colleagues developed a deep-learning AI model that reconstructs 4D blood flow through the heart in a matter of seconds. The authors trained a neural network on 11 example scans and found the network could accurately reconstruct aortic flow in healthy patients and in patients with abnormal blood flow with the same level of accuracy as conventional approaches. The AI system could also reconstruct a scan in around 20 seconds, which is 30 times faster than current state-of-the art conventional methods and 4.2 times faster than previous deep learning approaches.
doi: 10.1038/s42256-020-0165-6
리서치 하이라이트
-
6월24일
Sport science: New wearable sensor to measure neck strain may detect potential concussionScientific Reports
-
6월23일
Scientific community: Women credited less than men in scientific paper authorshipNature
-
6월17일
Health technology: New cost-effective smartphone test for middle ear functionCommunications Medicine
-
6월16일
An exercise-inducible molecule that suppresses appetiteNature
-
6월16일
Cancer: Signatures of structural genomic variation in cancerNature
-
6월10일
Animals: Genetic clues to how dogs became man’s best friendsScientific Reports