Abstract
The objective of this study is to develop a machine-learning model that can accurately distinguish between different histologic types of brain lesions in patients with non-small cell lung cancer (NSCLC) when it is not safe or feasible to perform a biopsy. To achieve this goal, the study utilized data from two patient cohorts: 116 patients from Xiangya Hospital and 35 patients from Yueyang Central Hospital. A total of eight machine learning algorithms, including Xgboost, were compared. Additionally, a 3-dimensional convolutional neural network was trained using transfer learning to further evaluate the performance of these models. The SHapley Additive exPlanations (SHAP) method was developed to determine the most important features in the best-performing model after hyperparameter optimization. The results showed that the area under the curve (AUC) for the classification of brain lesions as either lung adenocarcinoma or squamous carcinoma ranged from 0.60 to 0.87. The model based on single radiomics features extracted from contrast-enhanced T1 MRI and utilizing the Xgboost algorithm demonstrated the highest performance (AUC: 0.85) in the internal validation set and adequate performance (AUC: 0.80) in the independent external validation set. The SHAP values also revealed the impact of individual features on the classification results. In conclusion, the use of a radiomics model incorporating contrast-enhanced T1 MRI, Xgboost, and SHAP algorithms shows promise in accurately and interpretably identifying brain lesions in patients with NSCLC.
Similar content being viewed by others
Data Availability
The code is open source and freely available at https://github.com/BboyT/BM_NSCLC_subpathology. Data supporting the findings of this study can be provided upon journal request.
References
Lamba N, Wen PY, Aizer AA (2021) Epidemiology of brain metastases and leptomeningeal disease. Neuro Oncol 23(9):1447–1456
Cagney DN, Martin AM, Catalano PJ, Redig AJ, Lin NU, Lee EQ, Wen PY, Dunn IF, Bi WL, Weiss SE et al (2017) Incidence and prognosis of patients with brain metastases at diagnosis of systemic malignancy: a population-based study. Neuro Oncol 19(11):1511–1521
Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, Bray F (2021) Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and Mortality Worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71(3):209–249
Molina JR, Yang P, Cassivi SD, Schild SE, Adjei AA (2008) Non-small cell lung cancer: epidemiology, risk factors, treatment, and survivorship. Mayo Clin Proc 83(5):584–594
Relli V, Trerotola M, Guerra E, Alberti S (2019) Abandoning the notion of Non-Small Cell Lung Cancer. Trends Mol Med 25(7):585–594
Kim HS, Mitsudomi T, Soo RA, Cho BC (2013) Personalized therapy on the horizon for squamous cell carcinoma of the lung. Lung Cancer 80(3):249–255
Planchard D, Besse B, Groen HJM, Souquet PJ, Quoix E, Baik CS, Barlesi F, Kim TM, Mazieres J, Novello S et al (2016) Dabrafenib plus trametinib in patients with previously treated BRAF(V600E)-mutant metastatic non-small cell lung cancer: an open-label, multicentre phase 2 trial. Lancet Oncol 17(7):984–993
Stein MK, Pandey M, Xiu J, Tae H, Swensen J, Mittal S, Brenner AJ, Korn WM, Heimberger AB, Martin MG (2019) Tumor Mutational Burden is Site Specific in Non-Small-Cell Lung Cancer and is highest in Lung Adenocarcinoma Brain Metastases. JCO Precis Oncol 3:1–13
Sperduto PW, De B, Li J, Carpenter D, Kirkpatrick J, Milligan M, Shih HA, Kutuk T, Kotecha R, Higaki H et al (2022) Graded Prognostic Assessment (GPA) for patients with Lung Cancer and Brain Metastases: initial report of the small cell Lung Cancer GPA and Update of the Non-Small Cell Lung Cancer GPA including the effect of programmed death ligand 1 and other prognostic factors. Int J Radiat Oncol Biol Phys 114(1):60–74
Goldberg SB, Schalper KA, Gettinger SN, Mahajan A, Herbst RS, Chiang AC, Lilenbaum R, Wilson FH, Omay SB, Yu JB et al (2020) Pembrolizumab for management of patients with NSCLC and brain metastases: long-term results and biomarker analysis from a non-randomised, open-label, phase 2 trial. Lancet Oncol 21(5):655–663
Herbst RS, Morgensztern D, Boshoff C (2018) The biology and management of non-small cell lung cancer. Nature 553(7689):446–454
Kumar V, Gu Y, Basu S, Berglund A, Eschrich SA, Schabath MB, Forster K, Aerts HJ, Dekker A, Fenstermacher D (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30(9):1234–1248
Zhang L, Wang Y, Peng Z, Weng Y, Fang Z, Xiao F, Zhang C, Fan Z, Huang K, Zhu Y et al (2022) The progress of multimodal imaging combination and subregion based radiomics research of cancers. Int J Biol Sci 18(8):3458–3469
Wang H, Wang Y, Zhang H, Han Y, Li Q, Ye Z (2020) Preoperative CT features for prediction of ALK gene rearrangement in lung adenocarcinomas. Clin Radiol 75(7):562e521–562e529
Sibille L, Seifert R, Avramovic N, Vehren T, Spottiswoode B, Zuehlsdorff S, Schäfers M (2020) (18)F-FDG PET/CT uptake classification in Lymphoma and Lung Cancer by using deep convolutional neural networks. Radiology 294(2):445–452
He R, Yang X, Li T, He Y, Xie X, Chen Q, Zhang Z, Cheng T (2022) A Machine Learning-Based Predictive Model of Epidermal Growth Factor Mutations in Lung Adenocarcinomas. Cancers (Basel) 14(19)
Li Y, Liu Y, Liang Y, Wei R, Zhang W, Yao W, Luo S, Pang X, Wang Y, Jiang X et al (2022) Radiomics can differentiate high-grade glioma from brain metastasis: a systematic review and meta-analysis. Eur Radiol 32(11):8039–8051
Wood DA, Kafiabadi S, Busaidi AA, Guilhem E, Montvila A, Lynch J, Townend M, Agarwal S, Mazumder A, Barker GJ et al (2022) Accurate brain-age models for routine clinical MRI examinations. NeuroImage 249:118871
Su C, Jiang J, Zhang S, Shi J, Xu K, Shen N, Zhang J, Li L, Zhao L, Zhang J et al (2019) Radiomics based on multicontrast MRI can precisely differentiate among glioma subtypes and predict tumour-proliferative behaviour. Eur Radiol 29(4):1986–1996
Cao R, Pang Z, Wang X, Du Z, Chen H, Liu J, Yue Z, Wang H, Luo Y, Jiang X (2022) Radiomics evaluates the EGFR mutation status from the brain metastasis: a multi-center study. Phys Med Biol 67(12)
Liu Z, Jiang Z, Meng L, Yang J, Liu Y, Zhang Y, Peng H, Li J, Xiao G, Zhang Z et al (2021) Handcrafted and Deep Learning-Based Radiomic Models Can Distinguish GBM from Brain Metastasis. J Oncol. 2021:5518717
Kniep HC, Madesta F, Schneider T, Hanning U, Schonfeld MH, Schon G, Fiehler J, Gauer T, Werner R, Gellissen S (2019) Radiomics of Brain MRI: utility in prediction of metastatic tumor type. Radiology 290(2):479–487
Joo B, Ahn SS, An C, Han K, Choi D, Kim H, Park JE, Kim HS, Lee SK (2022) Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis. J Neuroradiol
Zhao X, Huang W, Huang X, Robu V, Flynn D (2021) Baylime: bayesian local interpretable model-agnostic explanations. In: de Campos, C, Maathuis, MH (eds) Proceedings of the thirty-seventh Conference on Uncertainty in Artificial Intelligence. PLMR, p 887-896
Johnson PM, Barbour W, Camp JV, Baroud H (2022) Using machine learning to examine freight network spatial vulnerabilities to disasters: a new take on partial dependence plots. Transp Res Interdisciplinary Perspect 14:100617
Castro J, Gómez D, Tejada J (2009) Polynomial calculation of the Shapley value based on sampling. Comput Oper Res 36(5):1726–1730
Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 30
Yaniv Z, Lowekamp BC, Johnson HJ, Beare R (2018) SimpleITK Image-Analysis Notebooks: a collaborative environment for Education and Reproducible Research. J Digit Imaging 31(3):290–303
van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, Beets-Tan RGH, Fillion-Robin J-C, Pieper S, Aerts HJWL (2017) Computational Radiomics System to Decode the Radiographic phenotype. Cancer Res 77(21):e104–e107
Zwanenburg A, Vallières M, Abdalah MA, Aerts HJWL, Andrearczyk V, Apte A, Ashrafinia S, Bakas S, Beukinga RJ, Boellaard R et al (2020) The image Biomarker Standardization Initiative: standardized quantitative Radiomics for High-Throughput Image-based phenotyping. Radiology 295(2):328–338
Spearman C (1904) The Proof and Measurement of Association between two things. Am J Psychol 15(1):72–101
Zheng B, Agresti A (2000) Summarizing the predictive power of a generalized linear model. Stat Med 19(13):1771–1781
Paul A, Mukherjee DP, Das P, Gangopadhyay A, Chintha AR, Kundu S (2018) Improved random forest for classification. IEEE Trans Image Process 27(8):4012–4024
Suthaharan S (2016) Support vector machine. In: Machine learning models and algorithms for big data classification: thinking with examples for effective learning. Springer US, p 207–235
Swain PH, Hauska H (1977) The decision tree classifier: design and potential. IEEE Trans Geoscience Electron 15(3):142–147
Natekin A, Knoll A (2013) Gradient boosting machines, a tutorial. Front Neurorobotics 7:21
Kim T, Adali T (2002) Fully complex multi-layer perceptron network for nonlinear signal processing. J VLSI signal Process Syst signal image video Technol 32(1):29–43
Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, Chen K (2015) Xgboost: extreme gradient boosting. R package version 04 – 2 1(4):1–4
Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T-Y (2017) Lightgbm: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst 30
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Artzi M, Bressler I, Ben Bashat D (2019) Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis. J Magn Reson Imaging 50(2):519–528
Qian Z, Li Y, Wang Y, Li L, Li R, Wang K, Li S, Tang K, Zhang C, Fan X et al (2019) Differentiation of glioblastoma from solitary brain metastases using radiomic machine-learning classifiers. Cancer Lett 451:128–135
Ortiz-Ramon R, Ruiz-Espana S, Molla-Olmos E, Moratal D (2020) Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach. Phys Med 76:44–54
Carloni G, Garibaldi C, Marvaso G, Volpe S, Zaffaroni M, Pepa M, Isaksson LJ, Colombo F, Durante S, Lo Presti G et al (2022) Brain metastases from NSCLC treated with stereotactic radiotherapy: prediction mismatch between two different radiomic platforms. Radiother Oncol 178:109424
Young RJ, Knopp EA (2006) Brain MRI: tumor evaluation. J Magn Reson Imaging 24(4):709–724
Acknowledgements
This work was supported in part by the High Performance Computing Center of Central South University.
Funding
The work was supported in part by the Science Foundation of Hunan Province (grant number: 2022JJ30992); The work was supported in part by the Project Program of the National Clinical Research Center for Geriatric Disorders(Xiangya Hospital, Grant No. 2022LNJJ10); The work was supported in part by the ERC IMI (101005122), the H2020 (952172), the MRC (MC/PC/21013), the Royal Society (IEC/NSFC/211235), the NVIDIA Academic Hardware Grant Program, NIHR Imperial Biomedical Research Centre (RDA01), Imperial–Nanyang Technological University Collaboration Fund, UKRI MRC with MSIT and NRF Fund, and the UKRI Future Leaders Fellowship (MR/V023799/1).
Author information
Authors and Affiliations
Contributions
Fuxing Deng: Statistical analysis, machine learning model and writing the paper. Zhiyuan Liu: Identifying cases, experiments. Wei Fang; Identifying cases. Lishui Niu: Discussion and editing the paper. Xianjing Chu: Paper editing and identifying cases. Quan Cheng: Identifying cases and discussion. Zijian Zhang: study design, analysis and editing the paper. RongRong Zhou: Study design, paper editing, financial support and overall study supervision. Zijian Zhang and RongRong Zhou are senior and corresponding authors who contributed equally to this study. Guang Yang: Supervision and writing—review and editing. All authors have read and agreed to the published version of the manuscript.
Corresponding authors
Ethics declarations
Competing Interests
The authors declare no conflict of interest.
Ethics approval
The multicenter study was conducted in accordance with the Declaration of Helsinki and was based on retrospectively identified or prospectively acquired brain metastasis MRI data collection in the participating centers, according to the local institutional review boards guidelines and the Central South University, Xiangya hospital institution ethical committees’ approvals. (Referencenumber:202210235).
Consent for publication
Not applicable.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Deng, F., Liu, Z., Fang, W. et al. MRI radiomics for brain metastasis sub-pathology classification from non-small cell lung cancer: a machine learning, multicenter study. Phys Eng Sci Med 46, 1309–1320 (2023). https://doi.org/10.1007/s13246-023-01300-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-023-01300-0