Prediction of the early recurrence in spinal giant cell tumor of bone using radiomics of preoperative CT: Long-term outcome of 62 consecutive patients

Qizheng Wang; Yang Zhang; Enlong Zhang; Xiaoying Xing; Yongye Chen; Min-Ying Su; Ning Lang

doi:10.1016/j.jbo.2021.100354

Prediction of the early recurrence in spinal giant cell tumor of bone using radiomics of preoperative CT: Long-term outcome of 62 consecutive patients

J Bone Oncol. 2021 Mar 16:27:100354. doi: 10.1016/j.jbo.2021.100354. eCollection 2021 Apr.

Authors

Qizheng Wang¹, Yang Zhang^{2

3}, Enlong Zhang⁴, Xiaoying Xing¹, Yongye Chen¹, Min-Ying Su^{2

5}, Ning Lang¹

Affiliations

¹ Department of Radiology, Peking University Third Hospital, 49 North Garden Road, Haidian District, Beijing 100191, China.
² 164 Irvine Hall, Center for Functional Onco-Imaging, University of California, Irvine, CA 92697-5020, USA.
³ Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ, United States.
⁴ Department of Radiology, Peking University International Hospital, Life Park Road No.1 Life Science Park of Zhong Guancun, Chang Ping District, Beijing 100191, China.
⁵ Department of Medical Imaging and Radiological Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan.

Abstract

Objectives: To determine if radiomics analysis based on preoperative computed tomography (CT) can predict early postoperative recurrence of giant cell tumor of bone (GCTB) in the spine.

Methods: In a retrospective review, 62 patients with pathologically confirmed spinal GCTB from March 2008 to February 2018, with a minimum follow-up of 24 months, were identified. The mean follow-up was 73.7 months (range, 28.7-152.1 months). The clinical information including age, gender, lesion location, multi-vertebral involvement, and surgical methods, were obtained. CT images acquired before the operation were retrieved for radiomics analysis. For each case, the tumor regions of interest (ROI) was manually outlined, and a total of 107 radiomics features were extracted. The features were selected via the sequential selection process by using the support vector machine (SVM), then used to construct classification models with Gaussian kernels. The differentiation between recurrence and non-recurrence groups was evaluated by ROC analysis, using 10-fold cross-validation.

Results: Of the 62 patients, 17 had recurrence with a recurrence rate of 27.4%. None of the clinical information was significantly different between the two groups. Patients receiving curettage had a higher recurrence rate (6/16 = 37.5%) compared to patients receiving TES (6/26 = 23.1%) or intralesional spondylectomy (5/20 = 25%). The final radiomics model was built using 10 selected features, which achieved an accuracy of 89% with AUC of 0.78.

Conclusions: The radiomics model developed based on pre-operative CT can achieve a high accuracy to predict the recurrence of spinal GCTB. Patients who have a high risk of early recurrence should be treated more aggressively to minimize recurrence.

Keywords: CT texture analysis; CT, Computed Tomography; DICOM, Digital Imaging and Communications in Medicine; GCTB, Giant Cell Tumor of Bone; GLCM, Gray Level Co-occurrence Matrix; GLDM, Gray Level Dependence Matrix; GLRLM, Gray Level Run Length Matrix; GLSZM, Gray Level Size Zone Matrix; Giant cell tumor of bone; MRI, Magnetic Resonance Imaging; NGTDM, Neighborhood Gray Tone Difference Matrix; OPG, Osteoprotegerin; PACS, Picture Archiving and Communication System; Prognosis; RANK, Receptor Activator of Nuclear factor Kappa-Β; RANKL, Receptor Activator of Nuclear factor Kappa-Β Ligand; ROC, Receiver Operating Characteristic; ROI, Regions of Interest; Radiomics; SVM, Support Vector Machine; Spine.