Radiomics of Brain MRI: Utility in Prediction of Metastatic Tumor Type

被引:183
作者
Kniep, Helge C. [1 ]
Madesta, Frederic [2 ,4 ]
Schneider, Tanja [1 ]
Hanning, Uta [1 ]
Schoenfeld, Michael H. [1 ]
Schoen, Gerhard [3 ]
Fiehler, Jens [1 ]
Gauer, Tobias [2 ]
Werner, Rene [4 ]
Gellissen, Susanne [1 ]
机构
[1] Univ Med Ctr Hamburg Eppendorf, Dept Diagnost & Intervent Neuroradiol, Martinistr 52, D-20246 Hamburg, Germany
[2] Univ Med Ctr Hamburg Eppendorf, Dept Radiotherapy & Radiat Oncol, Martinistr 52, D-20246 Hamburg, Germany
[3] Univ Med Ctr Hamburg Eppendorf, Inst Med Biometry & Epidemiol, Martinistr 52, D-20246 Hamburg, Germany
[4] Univ Med Ctr Hamburg Eppendorf, Inst Computat Neurosci, Martinistr 52, D-20246 Hamburg, Germany
关键词
DIAGNOSIS; SYSTEM;
D O I
10.1148/radiol.2018180946
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
Purpose: To investigate the feasibility of tumor type prediction with MRI radiomic image features of different brain metastases in a multiclass machine learning approach for patients with unknown primary lesion at the time of diagnosis. Materials and methods: This single-center retrospective analysis included radiomic features of 658 brain metastases from T1-weighted contrast material-enhanced, T1-weighted nonenhanced, and fluid-attenuated inversion recovery (FLAIR) images in 189 patients (101 women, 88 men; mean age, 61 years; age range, 32-85 years). Images were acquired over a 9-year period (from September 2007 through December 2016) with different MRI units, reflecting heterogeneous image data. Included metastases originated from breast cancer (n = 143), small cell lung cancer (n = 151), non-small cell lung cancer (n = 225), gastrointestinal cancer (n = 50), and melanoma (n = 89). A total of 1423 quantitative image features and basic clinical data were evaluated by using random forest machine learning algorithms. Validation was performed with model-external fivefold cross validation. Comparative analysis of 10 randomly drawn cross-validation sets verified the stability of the results. The classifier performance was compared with predictions from a respective conventional reading by two radiologists. Results: Areas under the receiver operating characteristic curve of the five-class problem ranged between 0.64 (for non-small cell lung cancer) and 0.82 (for melanoma); all P values were less than.01. Prediction performance of the classifier was superior to the radiologists' readings. Highest differences were observed for melanoma, with a 17-percentage-point gain in sensitivity compared with the sensitivity of both readers; P values were less than.02. Conclusion: Quantitative features of routine brain MR images used in a machine learning classifier provided high discriminatory accuracy in predicting the tumor type of brain metastases. (c) RSNA, 2018
引用
收藏
页码:479 / 487
页数:9
相关论文
共 35 条
[1]   The Potential of Radiomic-Based Phenotyping in PrecisionMedicine A Review [J].
Aerts, Hugo J. W. L. .
JAMA ONCOLOGY, 2016, 2 (12) :1636-1642
[2]   Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].
Aerts, Hugo J. W. L. ;
Velazquez, Emmanuel Rios ;
Leijenaar, Ralph T. H. ;
Parmar, Chintan ;
Grossmann, Patrick ;
Cavalho, Sara ;
Bussink, Johan ;
Monshouwer, Rene ;
Haibe-Kains, Benjamin ;
Rietveld, Derek ;
Hoebers, Frank ;
Rietbergen, Michelle M. ;
Leemans, C. Rene ;
Dekker, Andre ;
Quackenbush, John ;
Gillies, Robert J. ;
Lambin, Philippe .
NATURE COMMUNICATIONS, 2014, 5
[3]   Prediction of Response to Neoadjuvant Chemotherapy and Radiation Therapy with Baseline and Restaging 18F-FDG PET Imaging Biomarkers in Patients with Esophageal Cancer [J].
Beukinga, Roelof J. ;
Hulshoff, Jan Binne ;
Mul, Veronique E. M. ;
Noordzij, Walter ;
Kats-Ugurlu, Gursah ;
Slart, Riemer H. J. A. ;
Plukker, John T. M. .
RADIOLOGY, 2018, 287 (03) :983-992
[4]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[5]   Quantitative Imaging Test Approval and Biomarker Qualification: Interrelated but Distinct Activities [J].
Buckler, Andrew J. ;
Bresolin, Linda ;
Dunnick, N. Reed ;
Sullivan, Daniel C. .
RADIOLOGY, 2011, 259 (03) :875-884
[6]   Incidence and prognosis of patients with brain metastases at diagnosis of systemic malignancy: a population-based study [J].
Cagney, Daniel N. ;
Martin, Allison M. ;
Catalano, Paul J. ;
Redig, Amanda J. ;
Lin, Nancy U. ;
Lee, Eudocia Q. ;
Wen, Patrick Y. ;
Dunn, Ian F. ;
Bi, Wenya Linda ;
Weiss, Stephanie E. ;
Haas-Kogan, Daphne A. ;
Alexander, Brian M. ;
Aizer, Ayal A. .
NEURO-ONCOLOGY, 2017, 19 (11) :1511-1521
[7]   Paramagnetic metal scavenging by melanin: MR imaging [J].
Enochs, WS ;
Petherick, P ;
Bogdanova, A ;
Mohr, U ;
Weissleder, R .
RADIOLOGY, 1997, 204 (02) :417-423
[8]  
Fonov VS., 2009, Neuroimage, V47, pS102, DOI [DOI 10.1016/S1053-8119(09)70884-5, 10.1016/S1053-8119(09)70884-5]
[9]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577
[10]   Radiomics Signature: A Potential Biomarker for the Prediction of Disease-Free Survival in Early-Stage (I or II) Non-Small Cell Lung Cancer [J].
Huang, Yanqi ;
Liu, Zaiyi ;
He, Lan ;
Chen, Xin ;
Pan, Dan ;
Ma, Zelan ;
Liang, Cuishan ;
Tian, Jie ;
Liang, Changhong .
RADIOLOGY, 2016, 281 (03) :947-957