Keywords: Diagnosis/Prediction, Segmentation, Acute Ischemic Stroke
Motivation: Automatic annotation of ischemic core is essential for rapid identification of the extent of tissue damage and amount of salvageable tissue. DWI images and derived ADC maps are widely used for identification of ischemic core; however, its automatic segmentation is still challenging.
Goal(s): To develop an automatic framework for identification of stroke affected slices and segmentation of ischemic core using DWI and ADC maps.
Approach: Inception-v3 and MultiResU-Net were cascaded to first detect the stroke-affected slices and then perform segmentation. Different combinations of DWI and ADC maps were tested.
Results: Optimized framework achieved a classification accuracy of 92.88% and a dice score 0.70±0.14.
Impact: The proposed deep-learning framework combines DWI images and ADC maps to enable automatic, rapid ischemic core segmentation with high accuracy, supporting radiologists in the objective evaluation and planning of stroke treatment.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords