Application of Survival Tree Based on Texture Features Obtained through MRI of Patients with Brain Metastases from Breast Cancer

Authors

  • Asanao Shimokawa Department of Mathematical Information, Tokyo University of Science, 1-3 Kagurazaka, Shinjuku-ku, Tokyo 162-8601, Japan
  • Yoshitaka Narita Department of Neurosurgery and Neuro-Oncology, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan
  • Soichiro Shibui Department of Neurosurgery and Neuro-Oncology, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan
  • Etsuo Miyaoka Department of Mathematical Information, Tokyo University of Science, 1-3 Kagurazaka, Shinjuku-ku, Tokyo 162-8601, Japan

DOI:

https://doi.org/10.6000/1929-6029.2014.03.04.2

Keywords:

GLCM, wavelet transformation, recursive partitioning, binary tree, prognosis modeling, image analysis.

Abstract

The information obtained by magnetic resonance imaging (MRI) is considered to possess great potential for providing the prognosis of cancer patients, although not been established. The goal of this study was to evaluate the covariates of the texture patterns obtained from MRI scans of patients with breast cancer brain metastases, which influence the survival time prognosis. The data of forty patients were analyzed using 29 covariates. Twenty-six covariates, which are focused on the texture patterns, were calculated from the gray-level co-occurrence matrix and wavelet coefficients obtained by transform of preoperative T1-weighted MRI scans. The remaining three covariates were age, Karnofsky Performance Scale, and the indicator of whether solitary or multiple metastases were present. These covariates are commonly used as the prognostic factors in medical research. The tree structure prognosis models were constructed by applying the survival tree method to these covariates. The obtained survival trees separated the patients into two or three groups between which there was a statistically significant distance. For the purpose of comparison, Cox regression analyses were performed to determine which covariates showed significant predictive values. All the covariates selected in the Cox analysis and survival tree method were texture features only. In particular, the energy of the gray-level co-occurrence matrix and wavelet coefficients showed a high performance in tree structure analysis. From these results, we conclude that the features obtained from simple medical images can be used to estimate the prognosis of brain metastases patients.

Author Biographies

Asanao Shimokawa, Department of Mathematical Information, Tokyo University of Science, 1-3 Kagurazaka, Shinjuku-ku, Tokyo 162-8601, Japan

Mathematical Information

Yoshitaka Narita, Department of Neurosurgery and Neuro-Oncology, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan

Neurosurgery and Neuro-Oncology

Soichiro Shibui, Department of Neurosurgery and Neuro-Oncology, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan

Neurosurgery and Neuro-Oncology

Etsuo Miyaoka, Department of Mathematical Information, Tokyo University of Science, 1-3 Kagurazaka, Shinjuku-ku, Tokyo 162-8601, Japan

Mathematical Information

References

Narita Y, Shibui S. Strategy of surgery and radiation therapy for brain metastases. Int J ClinOncol 2009; 14(4): 275-280. http://dx.doi.org/10.1007/s10147-009-0917-0 DOI: https://doi.org/10.1007/s10147-009-0917-0

Gaspar L, Scott C, Rotman M, et al. Recursive partitioning analysis (RPA) of prognostic factors in three Radiation Therapy Oncology Group (RTOG) brain metastases trials. Int J Radiat Oncol Biol Phys 1997; 37(4): 745-751. http://dx.doi.org/10.1016/S0360-3016(96)00619-0 DOI: https://doi.org/10.1016/S0360-3016(96)00619-0

Arita H, Narita Y, Miyakita Y, et al. Risk factors for early death after surgery in patients with brain metastases: reevaluation of the indications for and role of surgery. J Neurooncol 2014; 116: 145-152. http://dx.doi.org/10.1007/s11060-013-1273-5 DOI: https://doi.org/10.1007/s11060-013-1273-5

Sperduto PW, Kased N, Roberge D, et al. Summary Report on the Graded Prognostic Assessment: An Accurate and Facile Diagnosis-Specific Tool to Estimate Survival for Patients With Brain Metastases. J Clin Oncol 2012; 30: 419-425. http://dx.doi.org/10.1200/JCO.2011.38.0527 DOI: https://doi.org/10.1200/JCO.2011.38.0527

Li X, Jin H, Lu Y, et al. J. Identification of MRI and 1H MRSI parameters that may predict survival for patients with malignant gliomas. NMR Biomed 2004; 17(1): 10-20. http://dx.doi.org/10.1002/nbm.858 DOI: https://doi.org/10.1002/nbm.858

Sanz-Requena R, Revert-Ventura A, Martí-Bonmatí L, Alverich-BayarriÁ, García a-MartíG. Quantitative MR perfusion parameters related to survival time in high-grade gliomas. Eur Radiol 2013; 23: 3456-3465. http://dx.doi.org/10.1007/s00330-013-2967-y DOI: https://doi.org/10.1007/s00330-013-2967-y

Breiman L, Friedman JH, Olshen RA, Stone C. Classification and Regression Trees. Wadsworth, California 1984.

Shimokawa A, Kawasaki Y, Miyaoka E. Comparison of the splitting criterions of survival tree. Proceedings of the 27th Symposium of Japanese Society of Computational Statistics 2013 (in Japanese): Nov 15-16; Kumamoto, Japan: p. 217-220.

Daubechies I. Orthonormal Bases of Compactly Supported Wavelets. Commun Pure Appl Math 1988; 41: 909-996. http://dx.doi.org/10.1002/cpa.3160410705 DOI: https://doi.org/10.1002/cpa.3160410705

Laine A, Fan J. Texture Classification by Wavelet Packet Signatures. IEEE Trans Pattern Anal Mach Intell 1993; 15: 1186-1191. http://dx.doi.org/10.1109/34.244679 DOI: https://doi.org/10.1109/34.244679

Horst KH, Heinz OP. The Skull Stripping Problem in MRI Solved by a Single 3D Watershed Transform. Med Image Comput Comput Assist Interv 2000; 1935: 134-143. http://link.springer.com/chapter/10.1007%2F978-3-540-40899-4_14

Shimokawa A, Miyaoka E. Application of genetic algorithm for classification of medical images. Adv Appl Stat 2012; 29(1): 1-31. http://www.pphmj.com/abstract/7063.htm

Gordon L, Olshen RA.Tree-Structured Survival Analysis. Cancer Treat Rep1985; 69(10): 1065-1069. http://test.europepmc.org/abstract/MED/4042086/reload=2;jsessionid=17D76A53C8A374608ABEE95C001879EA

Ciampi A, Hogg SA, Mckinney S, Thiffault J. RECPAM: A Computer Program for Recursive Partition and Amalgamation for Censored Survival Data and Other Situations Frequently Occurring in Biostatistics. I Methods and Program Features. Comput Methods Programs Biomed 1988; 26(3): 239-256. http://dx.doi.org/10.1016/0169-2607(88)90004-1 DOI: https://doi.org/10.1016/0169-2607(88)90004-1

Segal MR. Regression Trees for Censored Data. Biometrics 1988; 44: 35-47. http://dx.doi.org/10.2307/2531894 DOI: https://doi.org/10.2307/2531894

Davis RB, Anderson JR. Exponential Survival Trees. Stat Med 1989; 8: 947-961. http://dx.doi.org/10.1002/sim.4780080806 DOI: https://doi.org/10.1002/sim.4780080806

Therneau TM, Grambsch PM, Fleming TR. Martingale-Based Residual for Survival Models. Biometrika 1990; 77: 147-160. http://dx.doi.org/10.1093/biomet/77.1.147 DOI: https://doi.org/10.1093/biomet/77.1.147

Leblanc M, Crowley J. Relative Risk Trees for Censored Survival Data. Biometrics1992; 48: 411-425. http://dx.doi.org/10.2307/2532300 DOI: https://doi.org/10.2307/2532300

Zhang HP. Splitting Criteria in Survival Trees. In: Seeber G, Francis BJ, Hatzinger R, Steckel-Berger G, editors. Proceedings of the 10th International Workshop on Statistical Modeling; 1995: July 10-14; Innsbruck, Australia: p. 305-314. http://www.springer.com/mathematics/probability/book/978-0-387-94565-1

Keles S, Segal MR. Residual-based tree-structured survival analysis. Stat Med 2002; 21(2): 313-326. http://dx.doi.org/10.1002/sim.981 DOI: https://doi.org/10.1002/sim.981

Cox DR. Regression Models and Life-Tables. J R Stat Soc Series B Stat Methodol 1972; 34: 187-220. DOI: https://doi.org/10.1111/j.2517-6161.1972.tb00899.x

Ciampi A, Thiffault J, Nakache JP, Asselain B. Stratification by stepwise regression, correspondence analysis and recursive partition: A comparison of three methods of analysis for survival data with covariates. Comput Stat Data Anal 1986; 4(3): 185-204. http://dx.doi.org/10.1016/0167-9473(86)90033-2 DOI: https://doi.org/10.1016/0167-9473(86)90033-2

Downloads

Published

2014-11-06

How to Cite

Shimokawa, A., Narita, Y., Shibui, S., & Miyaoka, E. (2014). Application of Survival Tree Based on Texture Features Obtained through MRI of Patients with Brain Metastases from Breast Cancer. International Journal of Statistics in Medical Research, 3(4), 340–347. https://doi.org/10.6000/1929-6029.2014.03.04.2

Issue

Section

General Articles