Objective To predict epidermal growth factor receptor (EGFR) mutation status and human epidermal growth factor receptor 2 (HER2) expression status of brain metastasis based on different radiomics interpolator and to explore the optimal interpolator for prediction. Methods Data from 100 patients with brain metastasis from adenocarcinoma (56 with mutant EGFR/HER2+, 44 with wild-type EGFR/HER2-) from 2 institutions were retrospectively reviewed and analyzed. Contrast-enhanced T1-weighted imaging (T1-CE) sequence was selected for radiomics features extraction by using 3 different interpolators (sitkNearestNeighbor, sitkLinear and sitkBSplines). A total of 1409 radiomics features were extracted from each MR interpolator. The patients were randomly divided into training coherent and independent testing coherent according to 7:3. The least absolute shrinkage selection operator (LASSO) was used to select informative features, a radiomics signature was built with the support vector machine (SVM) model of the training cohort, and the radiomics signature performance was evaluated by using an independent testing data set. The accuracy, sensitivity and specificity of the model was calculated by the ROC curve. The predictive performance of the model was assessed by the ROC area under curve (AUC). Results Nineteen selected radiomics features based on sitkBSplines interpolator showed good discrimination in both the training and independent test cohorts. The radiomics signature yielded an AUC of 0.99, a classification accuracy of 0.95, sensitivity of 0.92, and specificity of 0.97 in the training cohort, and an AUC of 0.86, a classification accuracy of 0.8, sensitivity of 0.82, and specificity of 0.78 in the independent testing data set. SitkBSplines showed better discrimination performance than other interpolations in both Center 1 and Center 2 modeling. Nine selected radiomics signature features based on sitkLinear interpolator yielded an AUC of 0.74 in training cohort and an AUC of 0.53 in the independent testing cohort. Conclusions Radiomics signature model has certain application value in predicting EGFR mutation /HER2 status in adenocarcinoma brain metastases, among which radiomics features based on sitkBSplines interpolation is the most effective in discrimination performance.
Key words
Brain metastasis; /
/
Radiomics; /
/
EGFR; /
/
HER2
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] Lemmon MA, Schlessinger J. Cell signaling by receptor tyrosine kinases[J]. Cell,2010, 141(7): 1117-1134. DOI: 10.1016/j.cell. 2010. 06.011.
[2] Avraham R, Yarden Y. Feedback regulation of EGFR signalling: decision making by early and delayed loops[J]. Nat Rev Mol Cell Biol, 2011, 12(2): 104-117. DOI: 10.1038/nrm3048.
[3] Borrero-García LD, Del Mar Maldonado M, Medina-Velázquez J, et al. Rac inhibition as a novel therapeutic strategy for EGFR/HER2 targeted therapy resistant breast cancer[J]. BMC Cancer, 2021, 21(1): 652. DOI: 10.1186/s12885-021-08366-7.
[4] Karami E, Soliman H, Ruschin M, et al. Quantitative MRI biomarkers of stereotactic radiotherapy outcome in brain metastasis[J]. Sci Rep, 2019, 9(1): 19830. DOI: 10.1038/s41598-019-56185-5.
[5] Galldiks N, Kocher M, Ceccon G, et al. Imaging challenges of immunotherapy and targeted therapy in patients with brain metastases: response, progression, and pseudoprogression[J]. Neuro Oncol, 2020, 22(1): 17-30. DOI: 10.1093/neuonc/noz147.
[6] Koay EJ, Lee Y, Cristini V, et al. A visually apparent and quantifiable CT imaging feature identifies biophysical subtypes of pancreatic ductal adenocarcinoma[J]. Clin Cancer Res, 2018, 24(23): 5883-5894. DOI: 10.1158/1078-0432.Ccr-17-3668.
[7] Grossmann P, Stringfield O, EL-Hachem N, et al. Defining the biological basis of radiomic phenotypes in lung cancer[J]. Elife, 2017, 6: e23421. DOI: 10.7554/eLife.23421.
[8] Tu W, Sun G, Fan L, et al. Radiomics signature: a potential and incremental predictor for EGFR mutation status in NSCLC patients, comparison with CT morphology[J]. Lung Cancer, 2019, 132: 28-35. DOI: 10.1016/j.lungcan.2019.03.025.
[9] Mei D, Luo Y, Wang Y, et al. CT texture analysis of lung adenocarcinoma: can Radiomic features be surrogate biomarkers for EGFR mutation statuses[J]. Cancer Imaging, 2018, 18(1): 52. DOI: 10.1186/s40644-018-0184-2.
[10]Zhou J, Tan H, Li W, et al. Radiomics signatures based on multiparametric MRI for the preoperative prediction of the HER2 status of patients with breast cancer[J]. Acad Radiol, 2021, 28(10): 1352-1360. DOI: 10.1016/j.acra.2020.05.040.
[11]An Z, Aksoy O, Zheng T, et al. Epidermal growth factor receptor and EGFRvIII in glioblastoma: signaling pathways and targeted therapies[J]. Oncogene, 2018, 37(12): 1561-1575. DOI: 10.1038/s41388-017-0045-7.
[12]Sabbah DA, Hajjo R, Sweidan K. Review on epidermal growth factor receptor (EGFR) structure, signaling pathways, interactions, and recent updates of EGFR inhibitors[J]. Curr Top Med Chem, 2020, 20(10): 815-834. DOI: 10.2174/1568026620666200303123102.
[13]Cruz RGB, Madden SF, Brennan K, et al. A transcriptional link between HER2, JAM-A and FOXA1 in breast cancer[J]. Cells, 2022, 11(4): 735. DOI: 10.3390/cells11040735.
[14]Roviello G, Catalano M, Iannone LF, et al. Current status and future perspectives in HER2 positive advanced gastric cancer[J]. Clin Transl Oncol, 2022, 24(6): 981-996. DOI: 10.1007/s12094-021-02760-0.
PDF(2357 KB)
