A Radiomics-Based Model for Potentially More Accurate Identification of Subtypes of Breast Cancer Brain Metastases
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Purpose: Breast cancer brain metastases (BCBM) may involve subtypes that differ from the primary breast cancer lesion. This study aimed to develop a radiomics-based model that utilizes preoperative brain MRI for multiclass classification of BCBM sub types and to investigate whether the model offers better prediction accuracy than the assumption that primary lesions and their BCBMs would be of the same subtype (non-conversion model) in an external validation set. Materials and Methods: The training and external validation sets each comprised 51 cases (102 cases total). Four machine learn ing classifiers combined with three feature selection methods were trained on radiomic features and primary lesion subtypes for prediction of the following four subtypes: 1) hormone receptor (HR)+/human epidermal growth factor receptor 2 (HER2)-, 2) HR+/HER2+, 3) HR-/HER2+, and 4) triple-negative. After training, the performance of the radiomics-based model was compared to that of the non-conversion model in an external validation set using accuracy and F1-macro scores. Results: The rate of discrepant subtypes between primary lesions and their respective BCBMs were 25.5% (n=13 of 51) in the training set and 23.5% (n=12 of 51) in the external validation set. In the external validation set, the accuracy and F1-macro score of the radiomics-based model were significantly higher than those of the non-conversion model (0.902 vs. 0.765, p=0.004; 0.861 vs. 0.699, p=0.002). Conclusion: Our radiomics-based model represents an incremental advance in the classification of BCBM subtypes, thereby fa cilitating a more appropriate personalized therapy.
Abstract
Purpose: Breast cancer brain metastases (BCBM) may involve subtypes that differ from the primary breast cancer lesion. This study aimed to develop a radiomics-based model that utilizes preoperative brain MRI for multiclass classification of BCBM sub types and to investigate whether the model offers better prediction accuracy than the assumption that primary lesions and their BCBMs would be of the same subtype (non-conversion model) in an external validation set. Materials and Methods: The training and external validation sets each comprised 51 cases (102 cases total). Four machine learn ing classifiers combined with three feature selection methods were trained on radiomic features and primary lesion subtypes for prediction of the following four subtypes: 1) hormone receptor (HR)+/human epidermal growth factor receptor 2 (HER2)-, 2) HR+/HER2+, 3) HR-/HER2+, and 4) triple-negative. After training, the performance of the radiomics-based model was compared to that of the non-conversion model in an external validation set using accuracy and F1-macro scores. Results: The rate of discrepant subtypes between primary lesions and their respective BCBMs were 25.5% (n=13 of 51) in the training set and 23.5% (n=12 of 51) in the external validation set. In the external validation set, the accuracy and F1-macro score of the radiomics-based model were significantly higher than those of the non-conversion model (0.902 vs. 0.765, p=0.004; 0.861 vs. 0.699, p=0.002). Conclusion: Our radiomics-based model represents an incremental advance in the classification of BCBM subtypes, thereby fa cilitating a more appropriate personalized therapy.
참고문헌 (40)
- Sung H, "Global cancer statistics 2020 : GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries", CA Cancer J Clin, 71, pp.209~249 (2021)
- Achrol AS, "Brain metastases", Nat Rev Dis Primers, 5, pp.5~ (2019)
- Harbeck N, "Breast cancer", Lancet, 389, pp.1134~1150 (2017)
- Higgins MJ, "Targeted therapies for breast cancer", J Clin Invest, 121, pp.3797~3803 (2011)
- Li Y, "Recent advances in therapeutic strategies for triple-negative breast cancer", J Hematol Oncol, 15, pp.121~ (2022)
- Chen R, "Receptor conversion in metastatic breast cancer : analysis of 390 cases from a single institution", Mod Pathol, 33, pp.2499~2506 (2020)
- Yeung C, "Estrogen, progesterone, and HER2", neu receptor discordance between primary and metastatic breast tumours-a review, 2016, pp.35, 427~437
- Priedigkeit N, "Intrinsic subtype switching and acquired ERBB2", HER2 amplifications and mutations in breast cancer brain metastases, 2017, pp.3, 666~671
- Timmer M, "Discordance and conversion rates of progesterone-, estrogen-, and HER2", neu-receptor status in primary breast cancer and brain metastasis mainly triggered by hormone therapy, 2017, pp.37, 4859~4865
- Pedrosa RMSM, "Breast cancer brain metastasis : molecular mechanisms and directions for treatment", Neuro Oncol, 20, pp.1439~1449 (2018)
- Hulsbergen AFC, "Subtype switching in breast cancer brain metastases : a multicenter analysis", Neuro Oncol, 22, pp.1173~1181 (2020)
- Sperduto PW, "Estrogen", progesterone receptor and HER2 discordance between primary tumor and brain metastases in breast cancer and its effect on treatment and survival, 2020, pp.22, 1359~1367
- Morgan AJ, "The genomic landscape of breast cancer brain metastases : a systematic review", Lancet Oncol, 22, pp.e7~e17 (2021)
- Karagöz Özen DS, "Receptor expression discrepancy between primary and metastatic breast cancer lesions", Oncol Res Treat, 37, pp.622~626 (2014)
- Lu Y, "Association of biomarker discrepancy and treatment decision, disease outcome in recurrent", metastatic breast cancer patients, 2021, pp.11, 638619~
- Schrijver WAME, "Receptor conversion in distant breast cancer metastases : a systematic review and meta-analysis", J Natl Cancer Inst, 110, pp.568~580 (2018)
- Hanley BP, "The significance of receptor status discordance between breast cancer primary and brain metastasis", Breast J, 24, pp.683~685 (2018)
- Xiao W, "Analysis of prognostic factors affecting the brain metastases free survival and survival after brain metastases in breast cancer", Front Oncol, 10, pp.431~ (2020)
- Yi ZB, "Profile and outcome of receptor conversion in breast cancer metastases : a nation-wide multicenter epidemiological study", Int J Cancer, 148, pp.692~701 (2021)
- Zhao W, "Receptor conversion impacts outcomes of different molecular subtypes of primary breast cancer", Ther Adv Med Oncol, 13, pp.17588359211012982~ (2021)
- Gennari A, "ESMO clinical practice guideline for the diagnosis, staging and treatment of patients with metastatic breast cancer", Ann Oncol, 32, pp.1475~1495 (2021)
- Van Poznak C, "Use of biomarkers to guide decisions on systemic therapy for women with metastatic breast cancer : American Society of Clinical Oncology clinical practice guideline", J Clin Oncol, 33, pp.2695~2704 (2015)
- Lambin P, "Radiomics : the bridge between medical imaging and personalized medicine", Nat Rev Clin Oncol, 14, pp.749~762 (2017)
- Crivelli P, "A new challenge for radiologists : radiomics in breast cancer", Biomed Res Int, 2018, pp.6120703~ (2018)
- Davey MG, "Radiomic differentiation of breast cancer molecular subtypes using pre-operative breast imaging-A systematic review and metaanalysis", Eur J Radiol, 144, pp.109996~ (2021)
- Leithner D, "Radiomic signatures with contrastenhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes : initial results", Breast Cancer Res, 21, pp.106~ (2019)
- Son J, "Prediction of breast cancer molecular subtypes using radiomics signatures of synthetic mammography from digital breast tomosynthesis", Sci Rep, 10, pp.21566~ (2020)
- Hammond ME, "American Society of Clinical Oncology", College of American Pathologists guideline recommendations for immunohistochemical testing of estrogen and progesterone receptors in breast cancer(unabridged version), 2010, pp.134, e48~e72
- Avants BB, "A reproducible evaluation of ANTs similarity metric performance in brain image registration", Neuroimage, 54, pp.2033~2044 (2011)
- van Griethuysen JJM, "Computational radiomics system to decode the radiographic phenotype", Cancer Res, 77, pp.e104~e107 (2017)
- "Image biomarker standardisation initiative" (2016)[URL]
- "A unified approach to interpreting model predictions" (2017)[URL]
- Gillies RJ, "Radiomics : images are more than pictures, they are data", Radiology, 278, pp.563~577 (2016)
- Leithner D, "Radiomic signatures derived from diffusionweighted imaging for the assessment of breast cancer receptor status and molecular subtypes", Mol Imaging Biol, 22, pp.453~461 (2020)
- Jiang L, "Radiogenomic analysis reveals tumor heterogeneity of triple-negative breast cancer", Cell Rep Med, 3, pp.100694~ (2022)
- Cheng X, "A pre-operative MRI-based brain metastasis risk-prediction model for triple-negative breast cancer", Gland Surg, 10, pp.2715~2723 (2021)
- Luo X, "Radiomic signatures for predicting receptor status in breast cancer brain metastases", Front Oncol, 12, pp.878388~ (2022)
- Erickson BJ, "Magician’s corner : 9. Performance metrics for machine learning models", Radiol Artif Intell, 3, pp.e200126~ (2021)
- Nyúl LG, "New variants of a method of MRI scale standardization", IEEE Trans Med Imaging, 19, pp.143~150 (2000)
- Shinohara RT, "Statistical normalization techniques for magnetic resonance imaging", Neuroimage Clin, 6, pp.9~19 (2014)