CT Image Registration in Acute Stroke Monitoring
This work addresses the need for improved acute stroke monitoring in medical imaging, though it appears incremental as it builds on existing image registration techniques with a new similarity measure.
The authors tackled the problem of monitoring acute stroke lesions by developing a system that uses image registration to compare past and recent CT exams, enabling evaluation of non-stroke lesions and tracking lesion evolution over time, resulting in a cheaper, faster, and more accessible assessment.
We present a new system based on tracking the temporal evolution of stroke lesions using an image registration technique on CT exams of the patient's brain. The system is able to compare past CT exams with the most recent one related to stroke event in order to evaluate past lesions which are not related to stroke. Then, it can compare recent CT exams related to the current stroke for assessing the evolution of the lesion over time. A new similarity measure is also introduced for the comparison of the source and target images during image registration. It will result in a cheaper, faster and more accessible evaluation of the acute phase of the stroke overcoming the current limitations of the proposed systems in the state-of-the-art.