![]() To go one step further, artefact detection could be integrated into the machine to automatically decide whether it is necessary to repeat the scan without human interaction and without requiring a specialist to check the quality of the scan. In a clinical context, motion artefact detection would allow a clinician to have real-time feedback on whether a scan should be repeated while the patient is still in the scanner, reducing the necessity to reinvite the patient if the image quality is found to be insufficient due to motion artefacts. The ability to detect motion artefacts in MR scans could be employed for a multitude of applications. Image artefacts degrade the image quality and can challenge the diagnostic value of an image, sometimes requiring repeating the scan. With living subjects it is inevitable to have artefacts to some degree in the resulting images. Motion artefacts occur as effects of motion during the acquisition and appear as ghosting, blurring, and smearing. In fact, the scanning time is far longer than most types of physiological motion such as involuntary bulk movements and cardiac and respiratory motion, as well as the flow of blood. IntroductionÄespite producing excellent soft tissue contrast images, the acquisition of an MR scan usually takes longer than subjects, and in particular patients, can remain still. ![]() The results suggest that a machine learning approach is well capable of learning the characteristics of motion artefacts and subsequently detecting motion artefacts with a confidence that depends on the sampling pattern. Evaluation is performed on synthetic images where motion artefacts have been introduced by altering the -space data according to a motion trajectory, using the three common -space sampling patterns: Cartesian, radial, and spiral. Both the effects of bulk patient motion occurring at various time points in the acquisition on head scans and the effects of respiratory motion on cardiac scans are studied. This work focuses on the effect of motion on the reconstructed slices and the detection of motion artefacts in the reconstruction by using a supervised learning approach based on random decision forests. Movement of the subject such as bulk patient motion or respiratory motion degrades the image quality and its diagnostic value by producing image artefacts like ghosting, blurring, and smearing. The acquisition of a Magnetic Resonance (MR) scan usually takes longer than subjects can remain still.
0 Comments
Leave a Reply. |