- What is the impact of AI and deep learning on clinical workflows for neuroradiology? Dr. Greg Zaharchuk will offer an overview of AI and deep learning technologies invented at Stanford and applied in the clinical neuroimaging workflow at Stanford Hospital, where they have provided faster, safer, cheaper, and smarter medical imaging and treatment decision making.
- For general neuroradiology practice, Deep Learning (DL) methods are introduced to accelerate 4x MRI exams, reduce >95% radiation dose for PET/CT and PET/MRI, and >90% Gadolinium contrast dose for contrast-enhanced MRI. In addition, Deep Learning also shows promising results in segmentation and detection tasks for neuroimaging applications.
- Machine Learning (ML) and Deep Learning (DL) methods also provide innovative ways to improve the triage, treatment and prognosis assessment of neurological diseases. As an example, Dr. Zaharchuk will introduce recent development of ML/DL Deep Learning algorithms to predict the outcome of stroke patients and final infarct from acute stroke MRI scans. Similar methods can also be applied to CT exams. This work was ranked among the top solutions in MICCAI 2017 ISLES competition and is presented in ISC 2018, ASNR 2018 and ISMRM 2018.
March 22, 2018
For more details, please refer to AI and deep learning for improved neuroimaging and treatment decision supports