Automatic MR-based Skull Segmentation using Local Shape and Global Topology Priors
Max W.K. Law1, Calvin M.H. Lee1, Gladys G. Lo2, Jing Yuan1, Oilei Wong1, Abby Y. Ding1, and Siu Ki Yu1

1Medical Physics and Research Department, Hong Kong Sanatorium & Hospital, Hong Kong, Hong Kong, 2Department of Diagnostic and Interventional Radiology, Hong Kong Sanatorium & Hospital, Hong Kong, Hong Kong

### Synopsis

This abstract proposes a new algorithm that automatically segments the skull from gradient echo based magnetic resonance images to facilitate MR-based radiotherapy planning. The proposed algorithm compared the neighboring voxel intensity to capture local structural information of bone. The structural information was incorporated in a topology template which encapsulated global topology prior of skulls to achieve automatic segmentation. With the sequence-independent structural and topology priors, this method is potentially applicable to other scanning sequences. The segmented skull will be helpful for clinical applications such as cephalometry and MR-based radiotherapy planning to reduce ionizing-radiation received by patients.

### Introduction

MR-based radiation therapy (RT) simulation has been receiving considerable attention in the recent decade, owing to the advantage of protecting radiosensitive tissues and superior soft-tissue contrast. One major challenge of MR-simulation is its inefficacy to identify bone which is essential for RT simulation and planning.

Conventional skull segmentation approaches (e.g. [1]) concern absolute intensity information which can be inconsistent in same types of tissues in MR images. It is mainly due to B1/B0 inhomogeneity and imaging artifacts. In particular, B1 inhomogeneity is more pronounced in MR scans for RT simulation purpose because surface coils have to be used in the presence of RT immobilisation devices.

This abstract presented a framework that used local shape prior information to analyze structure shape within local regions, along with global topology prior information to automatically segment the skull. Both prior information was robust to inhomogeneous intensity and required neither training nor case dependent data. The ultimate goal of skull segmentation is to assign electron density information based on the segmented skull to facilitate MR-based RT simulation and planning. In addition, the proposed method is possible to enhance bone-image contrast, perform noise reduction or bone segmentation in various RT-oriented bone imaging sequences.

### Method

Four healthy volunteers were immobilised with personally customized thermoplastic mask and scanned on a dedicated 1.5T wide-bore MR simulator (Optima MR450w, GE Healthcare, Milwaukee, WI, US) using surface array coils. We used a low flip angle gradient echo sequence [3] which minimized the intensity contrast among soft tissues (TR/TE=8.6/4.2ms, flip angle=5o, FOV=24cm, 1.2mm isotropic voxel). A researcher manually segmented the skull of the first volunteer as a reference to quantify automatic segmentation accuracy.

Local skull patches produced much stronger intensity changes along its normal direction than along its tangent plane. At each patch, the second order statistics analyzed by eigen-decomposition [2] yielded one significant principle direction with strong intensity changes, and two principle directions returning minor ones (Fig. 1). This analysis gave large positive eigenvalues inside the skull, small negative values in the vicinity of the skull and insignificant random values the rest of the regions. The local patches detection result (computed as the largest-magnitude eigenvalues of the second order statistics [1]) $R(\vec x)$ at each position $\vec x$ was registered with the manually defined topology template $T(\vec x)$ to acquire the optimal transformation field $F(\vec x)$. The topology template is an image encapsulating whether a local patch at $\vec x$ had lower, higher or unknown intensity compared to the neighbor. It was represented using $T(x)=$ +1, -1 or 0 respectively (see Fig.2 for the iso-surface of the template). Mathematically, the registration obtained

$arg max$F(x)$T(F(x))R(x)$.

In our experiments, $F(x)$ is computed using B-Spline [3]. A diffeomorphic regularization [4] was added to maintain template topology during registration. The segmentation framework was performed using customized MatLab (2014b, Natick, MA, US) scripts.

### Results and Discussion

Automatic segmentation was successful in all subjects (Fig. 3). The dice similarity score was 83.4% for the manually segmented case (the left case in Fig.3). Fig. 4 presented the absolute intensity and image gradient histograms within the segmented skulls and brain regions. The histograms echoed the wide-spread of intensity and gradient, imposing a major barrier on MR-based bone segmentation in existing approaches. Nonetheless, the presented framework well-handled the inhomogeneous intensity and gradient because of the absolute intensity-independent structural and topology priors.

Furthermore, the topology template (Fig. 2) had a shape considerably different from all segmented skulls. It showed that the presented skull segmentation framework tolerated significant shape difference between the topology template and target, thus enabling one topology template to suit different cases.

Separating air cavity from cortical bone is yet challenging due to the indistinguishable MR signal of these two regions. One may consider incorporating the proposed framework in ultra-short TE sequence [5]. On the other hand, CT scans could be obtained to evaluate segmentation accuracy. However, attention will be needed to handle MR geometric distortion when comparing MR and CT images.

### Conclusion

In conclusion, a novel automatic skull segmentation method based on local structural prior and global topology prior was proposed. The former was computed using eigen-decomposition on second order intensity statistics to extract local planar patches. The latter was accomplished through registration to maximize the number of patches that a topology template connected, without changing the topology of the template. They jointly yielded an effective framework to perform automatic MR-based skull segmentation. This method is beneficial for MR-based RT planning to reduce ionizing radiation in radiotherapy.

### References

[1] K.A. Eley, A.G. McIntyre, S.R. Watt-Smith, S.J. Golding "Black bone" MRI: a partial flip angle technique for radiation reduction in craniofacial imaging", Br J Radiol. 2012.

[2] Max W.K. Law, Albert C.S. Chung, "An oriented flux symmetry based active contour model for three dimensional vessel segmentation", Euro. Conf. Comp. Vis. 2010.

[3] D. Rueckert, L.I. Sonoda, C. Hayes, D.L. Hill, Leach MO, D.J. Hawkes "Nonrigid Registration Using Free-Form Deformations: Application to Breast MR Images", IEEE Trans. Med. Imag. 1999.

[4] J. Ashburner "A fast diffeomorphic image registration algorithm", NeuroImage 2007.

[5] S.-H. Hsu, Y. Cao, T.S. Lawrence, C. Tsien, M. Feng, D.M. Grodzki, J.M. Balter, "Quantitative characterizations of ultrashort echo (UTE) images for supporting air–bone separation in the head", Phys. Med. Bio. 2015.

### Figures

Fig. 1 Local structure prior of local blob (left), linear (middle) and planar (right) structures. Intensity variation of these structures are strongest (weakest) along 3(0), 2(1) and 1(2) principle directions of eigen-decomposition of second order intensity statistics.

Fig. 2 (Top, left to right) Coronal slide of the original image; Eigenvalue image highlighting patch-like structures (local structural prior). (Bottom, left to right) Zero-crossing surface of the manually defined topology template (global topology prior); A deforming template; Final segmentation result.

Fig. 3 The automatic skull segmentation results.

Fig. 4 The histograms of voxel intensity gradient and voxel intensity in the manually segmented skull region and the brain region.

Proc. Intl. Soc. Mag. Reson. Med. 24 (2016)
1915