Share：
Share this content in WeChat
X
[Chinese][PDF]4312
• Clinical Article •
Efficacy of different machine learning models for contrast-enhanced T1-weighted image radiomics in classifying brain metastases by their primary site of origin
SUI Lianyu  REN Jialiang  WANG Jianing  YIN Xiaoping 

Cite this article as: Sui LY, Ren JL, Wang JN, et al. Efficacy of different machine learning models for contrast-enhanced T1-weighted image radiomics in classifying brain metastases by their primary site of origin[J]. Chin J Magn Reson Imaging, 2022, 13(12): 74-80. DOI:10.12015/issn.1674-8034.2022.12.013.


[Abstract] Objective To establish radiomics of different machine learning algorithms models based on enhanced T1-weighted images,and to explore the value of the models for distinguishing lung cancer brain metastases and non-Lung cancer brain metastases.Materials and Methods Totally 728 patients with lung cancer brain metastases and 126 patients with non-Lung cancer brain metastases were randomly divided into training set (n=599) and testing set (n=255) according to the ratio of 7∶3. Enhanced MRI data were imported into ITK-SNAP software, and the tumor's region of interest (ROI) in the enhanced T1WI was manually delineated to ROI. Radiomics feature extraction and screening using the least absolute shrinkage selection operator based on ROI. Support vector machine (SVM) model, random forest model and logistic regression model based on salient features were established respectively. Receiver operating characteristic (ROC) curve was used to assess the diagnostic efficiency of the models for distinguishing lung cancer brain metastases and non-Lung cancer brain metastases.Results After feature screening, 5 salient features were finally retained. The most effective radiomics model was the SVM model. In the training set. The area under the curve (AUC) of SVM was 0.796, accuracy value of 85.3%, sensitivity value of 87.8%, specificity value of 70.8%. In the testing set, AUC value of 0.789, accuracy of 90.2%, sensitivity of 95.4%, specificity of 59.5%.Conclusions Radiomics models based on enhanced MRI can be used for effectively predicting the lung cancer and non-lung cancer primary focus of brain metastatic cancer with unknown primary tumor. SVM model has higher diagnostic value than random forest model and logistic regression models.
[Keywords] brain metastases；lung cancer；radiomics；contrast-enhanced T1-weighted images；magnetic resonance imaging

SUI Lianyu1   REN Jialiang2   WANG Jianing1   YIN Xiaoping1*  

1 Department of Radiology, Affiliated Hospital of Hebei University, Baoding 071000, China

2 General Electric Pharmaceutical (Shanghai) Co., Ltd., Shanghai 200203, China

Yin XP, E-mail: yinxiaoping78@sina.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Post-graduate's Innovation Fund Project of Hebei University (No. HBU2022ss024).
Received  2022-07-17
Accepted  2022-11-14
DOI: 10.12015/issn.1674-8034.2022.12.013
Cite this article as: Sui LY, Ren JL, Wang JN, et al. Efficacy of different machine learning models for contrast-enhanced T1-weighted image radiomics in classifying brain metastases by their primary site of origin[J]. Chin J Magn Reson Imaging, 2022, 13(12): 74-80. DOI:10.12015/issn.1674-8034.2022.12.013.

[1]
Lamba N, Wen PY, Aizer AA. Epidemiology of brain metastases and leptomeningeal disease[J]. Neuro Oncol, 2021, 23(9): 1447-1456. DOI: 10.1093/neuonc/noab101.
[2]
Soffietti R, Ahluwalia M, Lin N, et al. Management of brain metastases according to molecular subtypes[J]. Nat Rev Neurol, 2020, 16(10): 557-574. DOI: 10.1038/s41582-020-0391-x.
[3]
le Rhun E, Guckenberger M, Smits M, et al. EANO-ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up of patients with brain metastasis from solid tumours[J]. Ann Oncol, 2021, 32(11): 1332-1347. DOI: 10.1016/j.annonc.2021.07.016.
[4]
Siegel RL, Miller KD, Fuchs HE, et al. Cancer statistics, 2022[J]. CA Cancer J Clin, 2022, 72(1): 7-33. DOI: 10.3322/caac.21708.
[5]
Fecci PE, Champion CD, Hoj J, et al. The evolving modern management of brain metastasis[J]. Clin Cancer Res, 2019, 25(22): 6570-6580. DOI: 10.1158/1078-0432.CCR-18-1624.
[6]
Vogelbaum MA, Brown PD, Messersmith H, et al. Treatment for brain metastases: ASCO-SNO-ASTRO guideline[J]. J Clin Oncol, 2022, 40(5): 492-516. DOI: 10.1200/JCO.21.02314.
[7]
Kickingereder P, Andronesi OC. Radiomics, metabolic, and molecular MRI for brain tumors[J]. Semin Neurol, 2018, 38(1): 32-40. DOI: 10.1055/s-0037-1618600.
[8]
Goncalves PH, Peterson SL, Vigneau FD, et al. Risk of brain metastases in patients with nonmetastatic lung cancer: analysis of the Metropolitan Detroit Surveillance, Epidemiology, and End Results (SEER) data[J]. Cancer, 2016, 122(12): 1921-1927. DOI: 10.1002/cncr.30000.
[9]
Zhang EL, Li Y, Lang N, et al. Progress of MRI in identifying the origin of brain metastases[J]. Int J Med Radiol, 2020, 43(4): 442-446. DOI: 10.19300/j.2020.Z17962.
[10]
Abrol S, Kotrotsou A, Salem A, et al. Radiomic phenotyping in brain cancer to unravel hidden information in medical images[J]. Top Magn Reson Imaging, 2017, 26(1): 43-53. DOI: 10.1097/RMR.0000000000000117.
[11]
Dregely I, Prezzi D, Kelly-Morland C, et al. Imaging biomarkers in oncology: basics and application to MRI[J]. J Magn Reson Imaging, 2018, 48(1): 13-26. DOI: 10.1002/jmri.26058.
[12]
Fan B, Li MJ, Wang XY, et al. Diagnostic value of gadobutrol versus gadopentetate dimeglumine in enhanced MRI of brain metastases[J]. J Magn Reson Imaging, 2017, 45(6): 1827-1834. DOI: 10.1002/jmri.25491.
[13]
Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[14]
Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[15]
Cao X, Tan D, Liu Z, et al. Differentiating solitary brain metastases from glioblastoma by radiomics features derived from MRI and 18F-FDG-PET and the combined application of multiple models[J/OL]. Sci Rep, 2022, 12(1): 5722 [2022-07-16]. https://www.nature.com/articles/s41598-022-09803-8. DOI: 10.1038/s41598-022-09803-8.
[16]
Mărginean L, Ștefan PA, Lebovici A, et al. CT in the differentiation of gliomas from brain metastases: the radiomics analysis of the peritumoral zone[J]. Brain Sci, 2022, 12(1): 109. DOI: 10.3390/brainsci12010109.
[17]
Li R, Ge YQ, Zhang MZ, et al. Identification of pathological types of brain metastasis from lung cancer based on whole tumor region MRI texture analysis[J]. Radiol Pract, 2021, 36(2): 176-180. DOI: 10.13609/j.cnki.1000-0313.2021.02.006.
[18]
Zhang J, Jin JB, Ai Y, et al. Differentiating the pathological subtypes of primary lung cancer for patients with brain metastases based on radiomics features from brain CT images[J]. Eur Radiol, 2021, 31(2): 1022-1028. DOI: 10.1007/s00330-020-07183-z.
[19]
Wang GY, Wang BM, Wang Z, et al. Radiomics signature of brain metastasis: prediction of EGFR mutation status[J]. Eur Radiol, 2021, 31(7): 4538-4547. DOI: 10.1007/s00330-020-07614-x.
[20]
Park YW, An C, Lee J, et al. Diffusion tensor and postcontrast T1-weighted imaging radiomics to differentiate the epidermal growth factor receptor mutation status of brain metastases from non-small cell lung cancer[J]. Neuroradiology, 2021, 63(3): 343-352. DOI: 10.1007/s00234-020-02529-2.
[21]
Wang YZ, Wan Q, Xia XY, et al. Value of radiomics model based on multi-parametric magnetic resonance imaging in predicting epidermal growth factor receptor mutation status in patients with lung adenocarcinoma[J]. J Thorac Dis, 2021, 13(6): 3497-3508. DOI: 10.21037/jtd-20-3358.
[22]
Ortiz-Ramón R, Larroza A, Ruiz-España S, et al. Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study[J]. Eur Radiol, 2018, 28(11): 4514-4523. DOI: 10.1007/s00330-018-5463-6.
[23]
Béresová M, Larroza A, Arana E, et al. 2D and 3D texture analysis to differentiate brain metastases on MR images: proceed with caution[J]. MAGMA, 2018, 31(2): 285-294. DOI: 10.1007/s10334-017-0653-9.
[24]
Ortiz-Ramón R, Ruiz-España S, Mollá-Olmos E, et al. Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach[J]. Phys Med, 2020, 76: 44-54. DOI: 10.1016/j.ejmp.2020.06.016.
[25]
Cao GQ, Zhang J, Lei XY, et al. Differentiating primary tumors for brain metastasis with integrated radiomics from multiple imaging modalities[J/OL]. Dis Markers, 2022: 5147085 [2022-07-16]. https://doi.org/10.1155/2022/5147085. DOI: 10.1155/2022/5147085.
[26]
Li ZJ, Mao Y, Li HS, et al. Differentiating brain metastases from different pathological types of lung cancers using texture analysis of T1 postcontrast MR[J]. Magn Reson Med, 2016, 76(5): 1410-1419. DOI: 10.1002/mrm.26029.
[27]
An C, Park YW, Ahn SS, et al. Radiomics machine learning study with a small sample size: single random training-test set split may lead to unreliable results[J/OL]. PLoS One, 2021, 16(8): e0256152. [2022-07-16]. https://doi.org/10.1371/journal.pone.0256152. DOI: 10.1371/journal.pone.0256152.
[28]
Kniep HC, Madesta F, Schneider T, et al. Radiomics of brain MRI: utility in prediction of metastatic tumor type[J]. Radiology, 2019, 290(2): 479-487. DOI: 10.1148/radiol.2018180946.
[29]
Ahn SJ, Kwon H, Yang JJ, et al. Contrast-enhanced T1-weighted image radiomics of brain metastases may predict EGFR mutation status in primary lung cancer[J/OL]. Sci Rep, 2020, 10(1): 8905 [2022-07-16]. https://www.nature.com/articles/s41598-020-65470-7. DOI: 10.1038/s41598-020-65470-7.
[30]
Zhao LM, Hu R, Xie FF, et al. Radiomic-based MRI for classification of solitary brain metastases subtypes from primary lymphoma of the central nervous system[J/OL]. J Magn Reson Imaging, 2022 [2022-07-27]. https://doi.org/10.1002/jmri.28276. DOI: 10.1002/jmri.28276.
[31]
Huang SJ, Cai NG, Pacheco PP, et al. Applications of support vector machine (SVM) learning in cancer genomics[J]. Cancer Genomics Proteomics, 2018, 15(1): 41-51. DOI: 10.21873/cgp.20063.
[32]
Artzi M, Bressler I, Ben Bashat D. Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis[J]. J Magn Reson Imaging, 2019, 50(2): 519-528. DOI: 10.1002/jmri.26643.
[33]
Qian ZH, Li YM, Wang YZ, et al. Differentiation of glioblastoma from solitary brain metastases using radiomic machine-learning classifiers[J]. Cancer Lett, 2019, 451: 128-135. DOI: 10.1016/j.canlet.2019.02.054.
[34]
Su CQ, Chen XT, Duan SF, et al. A radiomics-based model to differentiate glioblastoma from solitary brain metastases[J/OL]. Clin Radiol, 2021, 76(8): 629.e11-629.e18 [2022-07-16]. https://doi.org/10.1016/j.crad.2021.04.012. DOI: 10.1016/j.crad.2021.04.012.

PREV Evaluation and prognosis of collateral circulation with modified MRA-MTC-RLMC score in patients with chronic middle cerebral artery occlusion
NEXT Voxel-based morphological study on the changes of brain structure during radiotherapy of nasopharyngeal carcinoma
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn