Volume XLII-2/W12
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W12, 37-45, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W12-37-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W12, 37-45, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W12-37-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  09 May 2019

09 May 2019

RAY-BASED SEGMENTATION ALGORITHM FOR MEDICAL IMAGING

V. V. Danilov1,2, I. P. Skirnevskiy1, R. A. Manakov1, D. Y. Kolpashchikov1, O. M. Gerget1, and A. F. Frangi2 V. V. Danilov et al.
  • 1Medical Devices Design Laboratory, Tomsk Polytechnic University, 634050, Tomsk, Russia
  • 2Center for Computational Imaging and Simulation Technologies in Biomedicine, University of Leeds, LS2 9JT, Leeds, United Kingdom

Keywords: Segmentation, Medical Imaging, AdaBoost.M2, RUSBoost, UnderBagging, SMOTEBagging, SMOTEBoost

Abstract. In this study, we present a segmentation algorithm based on ray casting and border point detection. The algorithm’s main parameter is the number of emitted rays, which defines the resolution of the object’s boundary. The value of this parameter depends on the shape of the target region. For instance, 8 rays are enough to segment the left ventricle with the average Dice similarity coefficient approximately equal to 85%. Having gathered the data of rays, the training datasets had a relatively high level of class imbalance (up to 90%). To cope with this issue, ensemble-based classifiers used to manage imbalanced datasets such as AdaBoost.M2, RUSBoost, UnderBagging, SMOTEBagging, SMOTEBoost were used for border detection. For estimation of the accuracy and processing time, the proposed algorithm used a cardiac MRI dataset of the University of York and brain tumour dataset of Southern Medical University. The highest Dice similarity coefficients for the heart and brain tumour segmentation, equal to 86.5 ± 6.9% and 89.5 ± 6.7%, respectively, were achieved by the proposed algorithm. The segmentation time of a cardiac frame equals 4.1 ± 2.3 ms and 20.2 ± 23.6 ms for 8 and 64 rays, respectively. Brain tumour segmentation took 5.1 ± 1.1 ms and 16.0 ± 3.0 ms for 8 and 64 rays respectively. By testing the different medical imaging cases, the proposed algorithm is not time-consuming and highly accurate for convex and closed objects. The scalability of the algorithm allows implementing different border detection techniques working in parallel.