Brain Tissue Clustering Based on Cross-Correlation of Magnetic Resonance Fingerprinting
Mu Lin1, Xiaozhi Cao1, Congyu Liao1, Xu Yan2, and Jianhui Zhong1

1Center for Brain Imaging Science and Technology, Zhejiang University, Hangzhou, China, People's Republic of, 2MR Collaboration NE Asia, Siemens Healthcare, Hangzhou, China, People's Republic of


Multi-component tissue model with priori T1 and T2 have been used to decompose MRF data. We propose that tissue classification can be improved when the selection uses clustering method based on cross-correlation. Our results from phantom and in vivo measurements show that the method successfully separates signal from different tissue types, allows extraction of tissue fractions, and results are more robust with image quality.


Magnetic Resonance Fingerprinting (MRF) framework can be used in acquiring quantitative mappings of multiple parameters (i.e. T1, T2 and proton density) in a very rapid way [1]. The huge data provided by MRF contains abundant biological information including tissue composition. The signal evolution in a single voxel can be regarded as a superposition of the signal from several tissue types, such as gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). Based on modeling this multicomponent nature of signal, the relative fractions of each tissue can be obtained, which is of potential diagnosis value [2]. In order to decompose signal, a multi-component model should be built and it requires a priori knowledge of T1 and T2 of each component. However, in practice the system instability and individual differences can make the selection of T1 and T2 problematic, and inaccurate parameters can lead to biased fractions as well as great fitting residuals. To optimize the selection of T1 and T2 for decomposing brain tissue, we propose to correlate the signals with themselves in a data-driven way and cluster them based on the correlation map. The T1 and T2 are extracted from the centers of each cluster as the optimized value. Using both phantom and in-vivo measurement, we demonstrate that the tissue fraction maps based on the proposed method can provide both good tissue differentiation and improved robustness.


MRF measurements were performed on a 3T system (MAGNETOM Prisma, Siemens Healthcare, Erlangen, Germany) with an inversion-prepared FISP MRF sequence [3]. The TR varied from 10 to 12 ms and the flip angle varied from 5 to 80 degrees. The total scanning time was 10s. A PVP water solution phantom was made with concentration of 0%, 5%, 10%, 15%, 20%, 30% of PVP in separate compartments respectively. The cross-correlation are performed for each pair of voxels. The calculated correlation coefficients are used as the distance function for fuzzy c-means (FCM) method. In every step of FCM, the centers of clusters are adjusted until they can represent the members optimally. When the clustering is completed, each center is matched to MRF dictionary so that their T1 and T2 can be obtained. We first cluster the voxels into five categories and then choose three of them that can best represent WM, GM and CSF. The extracted T1 and T2 are then used to decompose MRF signal with a three-component model as described in [1]. Our methods are compared with the method proposed in the original MRF paper [1], in which the signal model uses empirical values of T1/T2 for each type of tissue: white matter (660/70 ms), gray matter (1200/90 ms) and CSF (5000/700 ms). The relative residual is calculated as 2-norm of fitting residual divided by the 2-norm of signal.

Results & Discussion

The phantom result shows that the similarity between signal are negatively correlated with the concentration difference, as clearly demonstrated in the correlation map (Fig. 1b). The diagonal positions provide the intra-sample similarity and are much brighter than the rest that represent the inter-sample similarity. The darkest blocks are at the left bottom and right top corners, which represents the dissimilarity between 30% PVP and water. The brain tissues are clustered according to their correlation into five types (Fig. 2). From their T1 and T2 values and spatial distribution, they can be identified as pure WM (Fig. 2c), pure GM (Fig. 2d), pure CSF (Fig. 2g) and two partial volume types of GM and CSF (Fig. 2e and 2f) respectively. The T1/T2 of pure WM (800/90 ms), GM (1100/110 ms) and CSF (3500/2000 ms) are chosen as the optimized value to do decomposition. Compared to the anatomic picture (Fig. 3g), both our and Ma D et al.’s method can provide a good contrast between WM and GM as shown in Fig. 3a and 3d. In the forehead, some parts of gray matter are missing in the previous method but not in our image (Fig. 3b and 3e). The relative residual of our method is also lower, which means less anatomic information is lost (Fig. 3h and 3i). We believe these improvements come from the use of optimized T1 and T2 to represent the signal rather than empirical values. We also tried more than five clusters in the first step but there is no further improvement.


Compared to the original method of using a model of empirical T1 and T2, the proposed method makes full use of the similarity between signal in voxels, which results in a more robust brain segmentation and tissue fraction estimation.


No acknowledgement found.


[1] Ma D et al. Nature 495:187-92; 2013.

[2] Badve C et al. Proc ISMRM 22 (2014) p.3234.

[3] Jiang Y. et al. MRM 2014, DOI: 10.1002/mrm.25559.


The PVP phantom validation of signal correlation. The arrangement of phantom (a). The correlation map of different PVP concentration (b). The averaged signal in each sample (c).

Clustering the voxels into five types. The correlation maps before (a) and after (b) clustering. Besides pure WM (c), pure GM (d) and pure CSF (g), another two components are extracted (e and f). Based on their T1, T2 and distributions, they are likely partial volume between CSF and GM.

Brain tissue fraction maps based on proposed (a-c) and conventional (d-f) methods. The referenced anatomic picture (g). The relative residual maps of proposed (h) and previous (i) methods.

Proc. Intl. Soc. Mag. Reson. Med. 24 (2016)