Researchers at MIT have developed a new deep learning technique to address motion interference in MRI scans. Motion artifacts can disrupt the accuracy of medical images, leading to potential misdiagnosis and less effective treatment. The integrated approach combines deep learning with physics to computationally construct motion-free images from motion-corrupted data, without altering the scanning procedure. This alignment between the resulting images and the factual measurements is crucial for accurate representation in medical imaging. The researchers also highlighted the potential for future studies to explore more complex forms of motion and enhance MRI applications across different anatomical scenarios.
Tue, 22 Aug 2023 09:00:00 GMT | MarkTechPost