A Computed Tomography Radiomics Nomogram in Differentiating Chordoma From Giant Cell Tumor in the Axial Skeleton

被引:3
作者
Nie, Pei [1 ]
Zhao, Xia [2 ]
Wang, Ning [3 ]
Ma, Jinlong [2 ]
Zuo, Panli [4 ]
Hao, Dapeng [1 ,6 ]
Yu, Tengbo [2 ,5 ]
机构
[1] Qingdao Univ, Affiliated Hosp, Dept Radiol, Qingdao, Peoples R China
[2] Qingdao Univ, Affiliated Hosp, Dept Sports Med, Qingdao, Peoples R China
[3] Shandong Prov Hosp, Dept Radiol, Jinan, Peoples R China
[4] Huiying Med Technol Co Ltd, Beijing, Peoples R China
[5] 59 Haier Rd, Qingdao 266000, Shandong, Peoples R China
[6] 16 Jiangsu Rd, Qingdao 266000, Shandong, Peoples R China
关键词
chordoma; giant cell tumor of bone; axial skeleton; tomography; x-ray computed; radiomics; FEATURES; PREDICT;
D O I
10.1097/RCT.0000000000001436
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
ObjectiveThe aim of the study is to develop and validate a computed tomography (CT) radiomics nomogram for preoperatively differentiating chordoma from giant cell tumor (GCT) in the axial skeleton.MethodsSeventy-three chordomas and 38 GCTs in axial skeleton were retrospectively included and were divided into a training cohort (n = 63) and a test cohort (n = 48). The radiomics features were extracted from CT images. A radiomics signature was developed by using the least absolute shrinkage and selection operator model, and a radiomics score (Rad-score) was acquired. By combining the Rad-score with independent clinical risk factors using multivariate logistic regression model, a radiomics nomogram was established. Calibration and receiver operator characteristic curves were used to assess the performance of the nomogram.ResultsFive features were selected to construct the radiomics signature. The radiomics signature showed favorable discrimination in the training cohort (area under the curve [AUC], 0.860; 95% confidence interval [CI], 0.760-0.960) and the test cohort (AUC, 0.830; 95% CI, 0.710-0.950). Age and location were the independent clinical factors. The radiomics nomogram combining the Rad-score with independent clinical factors showed good discrimination capability in the training cohort (AUC, 0.930; 95% CI, 0.880-0.990) and the test cohort (AUC, 0.980; 95% CI, 0.940-1.000) and outperformed the radiomics signature (z = 2.768, P = 0.006) in the test cohort.ConclusionsThe CT radiomics nomogram shows good predictive efficacy in differentiating chordoma from GCT in the axial skeleton, which might facilitate clinical decision making.
引用
收藏
页码:453 / 459
页数:7
相关论文
共 28 条
[1]  
[Anonymous], 2020, NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) Breast Cancer
[2]   Development and external validation of an MRI-based radiomics nomogram for pretreatment prediction for early relapse in osteosarcoma: A retrospective multicenter study [J].
Chen, Haimei ;
Liu, Jin ;
Cheng, Zixuan ;
Lu, Xing ;
Wang, Xiaohong ;
Lu, Ming ;
Li, Shaolin ;
Xiang, Zhiming ;
Zhou, Quan ;
Liu, Zaiyi ;
Zhao, Yinghua .
EUROPEAN JOURNAL OF RADIOLOGY, 2020, 129
[3]   The two faces of giant cell tumor of bone [J].
di Carlo, Federica Scotto ;
Whyte, Michael P. ;
Gianfrancesco, Fernando .
CANCER LETTERS, 2020, 489 :1-8
[4]  
Flemming D J, 2000, Semin Musculoskelet Radiol, V4, P299, DOI 10.1055/s-2000-9340
[5]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577
[6]   MRI radiomics-based machine -learning classification of bone chondrosarcoma [J].
Gitto, Salvatore ;
Cuocolo, Renato ;
Albano, Domenico ;
Chianca, Vito ;
Messina, Carmelo ;
Gambino, Angelo ;
Ugga, Lorenzo ;
Cortese, Maria Cristina ;
Lazzara, Angelo ;
Ricci, Domenico ;
Spairani, Riccardo ;
Zanchetta, Edoardo ;
Luzzati, Alessandro ;
Brunetti, Arturo ;
Parafioriti, Antonina ;
Sconfienza, Luca Maria .
EUROPEAN JOURNAL OF RADIOLOGY, 2020, 128
[7]   Convolutional neural network to predict the local recurrence of giant cell tumor of bone after curettage based on pre-surgery magnetic resonance images [J].
He, Yifeng ;
Guo, Jiapan ;
Ding, Xiaoyi ;
van Ooijen, Peter M. A. ;
Zhang, Yaping ;
Chen, An ;
Oudkerk, Matthijs ;
Xie, Xueqian .
EUROPEAN RADIOLOGY, 2019, 29 (10) :5441-5451
[8]   Morphological and dynamic contrast enhanced MR imaging features for the differentiation of chordoma and giant cell tumors in the Axial Skeleton [J].
Lang, Ning ;
Su, Min-Ying ;
Xing, Xiaoying ;
Yu, Hon J. ;
Yuan, Huishu .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2017, 45 (04) :1068-1075
[9]   Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma [J].
Li, Longfei ;
Wang, Ke ;
Ma, Xiujian ;
Liu, Zhenyu ;
Wang, Shuo ;
Du, Jiang ;
Tian, Kaibing ;
Zhou, Xuezhi ;
Wei, Wei ;
Sun, Kai ;
Lin, Yusong ;
Wu, Zhen ;
Tian, Jie .
EUROPEAN JOURNAL OF RADIOLOGY, 2019, 118 :81-87
[10]   Diagnostic value of MRI-based 3D texture analysis for tissue characterisation and discrimination of low-grade chondrosarcoma from enchondroma: a pilot study [J].
Lisson, Catharina S. ;
Lisson, Christoph G. ;
Flosdorf, Kerstin ;
Mayer-Steinacker, Regine ;
Schultheiss, Markus ;
von Baer, Alexandra ;
Barth, Thomas F. E. ;
Beer, Ambros J. ;
Baumhauer, Matthias ;
Meier, Reinhard ;
Beer, Meinrad ;
Schmidt, Stefan A. .
EUROPEAN RADIOLOGY, 2018, 28 (02) :468-477