An advanced MRI and MRSI data fusion scheme for enhancing unsupervised brain tumor differentiation. (1st February 2017)

• Record Type: Journal Article
• Authors: Li, Yuqian; Liu, Xin; Wei, Feng; Sima, Diana M.; Van Cauter, Sofie; Himmelreich, Uwe; Pi, Yiming; Hu, Guang; Yao, Yi; Van Huffel, Sabine
• Is Part Of: Computers in biology and medicine. Volume 81(2017)
• Page Start: 121
• Page End: 129
• Publication Date: 2017-02-01
• Subjects: Data fusion -- Magnetic resonance spectroscopic imaging (MRSI) -- Magnetic resonance imaging (MRI) -- Non-negative matrix factorization (NMF); Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2016.12.017
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Proton Magnetic Resonance Spectroscopic Imaging ( 1 H MRSI) has shown great potential in tumor diagnosis since it provides localized biochemical information discriminating different tissue types, though it typically has low spatial resolution. Magnetic Resonance Imaging (MRI) is widely used in tumor diagnosis as an in vivo tool due to its high resolution and excellent soft tissue discrimination. This paper presents an advanced data fusion scheme for brain tumor diagnosis using both MRSI and MRI data to improve the tumor differentiation accuracy of MRSI alone. Non-negative Matrix Factorization (NMF) of the spectral feature vectors from MRSI data and the image fusion with MRI based on wavelet analysis are implemented jointly. Hence, it takes advantage of the biochemical tissue discrimination of MRSI as well as the high resolution of MRI. The feasibility of the proposed frame work is validated by comparing with the expert delineations, giving mean correlation coefficients for the tumor source of 0.97 and the Dice score of tumor region overlap of 0.90. These results compare favorably against those obtained with a previously proposed NMF method where MRSI and MRI are integrated by stacking the MRSI and MRI features. Highlights: We propose an automated multi-modality/dimension data fusion scheme for enhancing unsupervised brain tumor differentiation. Decomposition of spectral features from MRSI and image fusion with MRI are implemented jointly. Different fusion rules are applied to the different frequencies within the image fusion steps. The proposed fusion scheme gives the flexibility to choose different implementations for its substeps. The proposed fusion scheme compares favorably to the fusion scheme of early integration.