Skip to Main content Skip to Navigation
Conference papers

Manifold learning for patient position detection in MRI

Abstract : Magnetic resonance imaging is performed without ionizing radiation, however, the applied radio frequency power leads to heating, which is dependent on the body part being im-aged. Determining the patient position in the scanner allows to better monitor the absorbed power and therefore optimize the image acquisition. Low-resolution images, acquired during the initial placement of the patient in the scanner, are exploited for detecting the patient position. We use Laplacian eigenmaps, a manifold learning technique, to learn the low-dimensional manifold embedded in the high-dimensional image space. Our experiments clearly show that the presumption of the slices lying on a low dimensional manifold is justified and that the proposed integration of neighborhood slices and image normalization improves the method. We obtain very good classification results with a nearest neighbor classifier operating on the low-dimensional embedding.
Complete list of metadata

https://hal.inria.fr/hal-01690309
Contributor : Diana Mateus <>
Submitted on : Monday, January 22, 2018 - 9:27:44 PM
Last modification on : Wednesday, January 24, 2018 - 9:32:21 PM

Links full text

Identifiers

Citation

Diana Mateus, Christian Wachinger, Andreas Keil, Nassir Navab. Manifold learning for patient position detection in MRI. 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Apr 2010, Rotterdam, France. ⟨10.1109/ISBI.2010.5490248⟩. ⟨hal-01690309⟩

Share

Metrics

Record views

302