Meeting Banner
Abstract #3789

A Clinical Evaluation of a Novel, Retrospective and Entropy-Based Intensity Inhomogeneity Correction Method in 3T MRI

Sven Jaeschke1, 2, Alexander Hubert3, Andreas J. Bartsch4, Antje Kickhefel2, Aleksandar Petrovic2

1HAW Hamburg, Hamburg, Germany; 2Healthcare Sector, Siemens AG, Erlangen, Germany; 3Neuroradiology, Universittsklinikum Heidelberg, Heidelberg, Germany; 4Neuroradiology, University of Heidelberg, Heidelberg, Germany

Intensity inhomogeneities remain an issue in high-field MRI and can degrade clinical interpretability of images. To improve image quality in a fast, robust and fully automated fashion, we developed and clinically validated a novel image inhomogeneity correction method, based on entropy minimization. A wide range of different MR-contrasts/sequences in healthy-control and images with pathological findings were assessed. Two trained radiologists evaluated each image in a blind fashion and both agreed on each rating. We show that the combination of the 3D implementation of our method and the current built-in Siemens solution significantly improves the clinical impression of 3T neuroradiological MRI.

Abstract PDF Presentation Video

Keywords

able addition adequate adjustments agreed alike almost already anal application assessed assessment audience automated background besides best bias blind body bounded brain builds built classes clinical clinically clinicians coefficients coil combination contains content contrasts controls core coronal correction criteria cubic dataset datasets degenerates degrade developed direct divided either eliminate entropy evaluated evaluation excellent except existing fashion fast field findings five flair freedman fully good gradient hamburg healthy hemispheres histogram homogeneity implementation implementations implies impression improve improvements improves included inhomogeneities inhomogeneity initialization inputs intensities intensity inter interaction interpolate intra issue kernel matrix mead metastasis minimize model neurological normalize normalized novel optimization optimizer overall paired pathological pathologies poor post prefer presence process processed processing propose proposed quality radiologists rating ratings reasonable remain removal remove resolution retrospective robust sector side simplex slice slices sole solution specifically splines stroke substitute symmetry target threaded thresholding tissue trained trans transversal upon user validated validity white whole wide