Düşük evreli gliomların radiomic ve alan bilgisi temelli öznitelikler aracılığı ile manyetik rezonans görüntülerinden izositrat dehidrogenaz mutasyon durumunun otomatik tahmini

Yıl 2024, , 178 - 186, 29.05.2024

İlker Özgür Koska , Çağan Koska , Antonio Fernandes

https://doi.org/10.21673/anadoluklin.1378673

Öz

Amaç: En yaygın ve en ölümcül birincil merkezi sinir tümörleri olan glial tümörler, heterojen hücre klonları barındırırlar. Glial tümörlerin genomik profillerinin invazif olmayan bir şekilde belirlenmesi, bu tümörlerin sınıflandırılması, yönetimi ve prognostikasyonu ile ilgili önemli etkilere sahip olacaktır. İzositrat dehidrogenaz mutasyonu varlığı bu tümörler için önemli bir genetik belirteç olup daha iyi prognoz göstergesidir. Radyomik yöntemler, lezyonların non invazif sınıflandırılması için umut verici bir araçtır. Bu çalışmada radyomik özelliklerin yanı sıra alan bilgisinden ilham alan özelliklerle, yapay zekâ ile manyetik rezonans görüntüleme (MRI), görüntülerinden İzositrat Dehidrogenaz (IDH) mutasyon tahmini yapacak bir model geliştirilmesi amaçlanmıştır.

Yöntemler: Radyomik öznitelik kümesi çıkarılmış buna ek olarak radyologların lezyon tariflemede kullandığı belirteçler kodlanarak otomatik olarak elde edilmeye çalışılmıştır. Her iki yöntem ile elde edilen öznitelikler ile sınıflayıcı modeler geliştirilmiştir.

Bulgular: Radyomik ve radyolog bilgisinden ilham alan özelliklerin kombinasyonundan oluşan en iyi modelimiz 0,93 f1 puanı (Standart Sapma (SD): 0,03), 0,93 doğruluk (SD:0,03) ve 0,98 eğri altındaki alan (EAA)'ya (SD:0,02) ulaştı.

Sonuç: Bu çalışmada kullanılan çok parametreli ve çok bölgeli yaklaşım hem radyomik hem de alan bilgisinden ilham alan özelliklerin entegrasyonu ile birleştiğinde, nihai sonuç için her bir stratejinin katkısını vurgulayan yüksek performanslı bir modelle sonuçlandı.

Anahtar Kelimeler

Glial hücreli tümörler, mutasyon, yapay zeka

Automatic prediction of isocitrate dehydrogenase mutation status of low-grade gliomas using radiomics and domain knowledge inspired features in magnetic resonance imaging

Öz

Aim: Most common and most deadly primary central nervous tumors, glial tumors harbor many heterogeneous clones of cells. Noninvasive determination of the genomic profiles of these tumors would have important implications regarding the classification, management, and prognostication of these tumors. Isocitrate dehydrogenase mutation is a key genomic signature that can downgrade the expected dismal course of these tumors. In this study we aimed to build a performant prediction model which can determine the Isocitrate Dehydrogenase (IDH) mutation status of glial tumors, using radiomics and leveraging automatic computation of domain knowledge-inspired features.

Methods: Radiomics methods based on high throughput feature extraction and application of data science principles to these extracted features are promising tools for the noninvasive classification of lesions. Domain knowledge-inspired features besides radiomics features can contribute positively to the performance of the models. Some efforts particularly a joint approach to standardize the magnetic resonance imaging (MRI), reporting of glial tumors are mainstay for domain knowledge-inspired features. However, this requires active involvement and reporting of the radiologist which hampers automatization efforts. Additionally, this feature set evaluates a small subset of all possible signal and spatial-based computations. In this study, we combined domain knowledge-inspired features with radiomics features along with a multiparametric multihabitat comprehensive lesion description strategy.

Results: Our best model which consisted of a combination of radiomics, and radiologist knowledge-inspired features reached a 0.93 f1 score (standard deviation (SD): 0.03), 0.93 accuracy (SD:0.03), and 0.98 area under curve (AUC), (SD:0.02).

Conclusion: The multiparametric and multiregional approach employed in this study coupled with the integration of both radiomics and domain knowledge-inspired features resulted in a high-performance model emphasizing the contribution of each strategy to the outcome.

Anahtar Kelimeler

Glial cell tumors, mutation, radiomics

Kaynakça

• Bakas S, Akbari H, Sotiras A, et al. Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data. 2017;4:170117.
• Parsons DW, Jones S, Zhang X, et al. An Integrated Genomic Analysis of Human Glioblastoma Multiforme. Science. 2008;321:1807-12.
• Eckel-Passow JE, Lachance DH, Molinaro AM, et al. Glioma Groups Based on 1p/19q, IDH, and TERT Promoter Mutations in Tumors. N Engl J Med. 2015;372:2499-508.
• Hartmann C, Hentschel B, Wick W, et al. Patients with IDH1 wild type anaplastic astrocytomas exhibit worse prognosis than IDH1-mutated glioblastomas, and IDH1 mutation status accounts for the unfavorable prognostic effect of higher age: implications for classification of gliomas. Acta Neuropathol. 2010;120:707-18.
• Louis DN, Perry A, Reifenberger G, et al. The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol. 2016;131:803-20.
• Berger TR, Wen PY, Lang-Orsini M, Chukwueke UN. World Health Organization 2021 Classification of Central Nervous System Tumors and Implications for Therapy for Adult-Type Gliomas: A Review. JAMA Oncol. 2022;8(10):1493-501.
• van Kempen EJ, Post M, Mannil M, et al. Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis. Cancers (Basel). 2021;13(11):2606.
• Yang H, Ye D, Guan K-L, Xiong Y. IDH1 and IDH2 Mutations in Tumorigenesis: Mechanistic Insights and Clinical Perspectives. Clin Cancer Res. 2012;18:5562-71.
• Sottoriva A, Spiteri I, Piccirillo SG, et al. Intratumor heterogeneity in human glioblastoma reflects cancer evolutionary dynamics. Proc Natl Acad Sci. 2013;110:4009-14.
• Patel AP, Tirosh I, Trombetta JJ, et al. Single‐cell RNA‐seq highlights intratumoral heterogeneity in primary glioblastoma. Science. 2014;344:1396-401.
• Molenaar RJ, Botman D, Smits MA, et al. Radioprotection of IDH1-Mutated Cancer Cells by the IDH1-Mutant Inhibitor AGI-5198. Cancer Res. 2015;75:4790-802.
• Patel SH, Poisson LM, Brat DJ, et al. T2–FLAIR Mismatch, an Imaging Biomarker for IDH and 1p/19q Status in Lower-grade Gliomas: A TCGA/TCIA Project. Clin Cancer Res. 2017;23(20):6078-85.
• Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJWL. Radiomic feature robustness and reproducibility in volumetric radiomic analysis. Sci Rep. 2015;5:13087.
• Chang K, Bai HX, Zhou H, et al. Residual Convolutional Neural Network for the Determination of IDH Status in Low- and High-Grade Gliomas from MR Imaging. Clin Cancer Res. 2018;24(5):1073-81.
• Zhou H, Vallières M, Bai HX, et al. MRI features predict survival and molecular markers in diffuse lower-grade gliomas. Neuro Oncol. 2017;19(6):862-70.
• VASARI Research Project. [homepage on the Internet]. https://wiki.cancerimagingarchive.net/display/Public/VASARI+Research+Project. Accessed June 21, 2018.
• Julesz B, Gilbert EN, Shepp LA, Frisch HL. Inability of Humans to Discriminate between Visual Textures That Agree in Second Order Statistics Revisited. Perception. 1973;2(4):391-405.
• Lambin P, Leijenaar RT, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14:749-62.
• Smits M, van den Bent MJ. Imaging Correlates of Adult Glioma Genotypes. Radiology. 2017;284:316-31.
• Hu LS, Eschbacher JM, Heiserman JE, et al. Radiogenomics to characterize regional genetic heterogeneity in glioblastoma. Neuro Oncol. 2017;19(1):128-37.
• Zhang B, Tian Q, Wang L, et al. Radiomics strategy for molecular subtype stratification of lower‐grade glioma: detecting IDH and TP53 mutations based on multimodal MRI. J Magn Reson Imaging. 2018;48:916-26.
• Li ZC, Bai H, Sun Q, et al. Multiregional radiomics profiling from multiparametric MRI: Identifying an imaging predictor of IDH1 mutation status in glioblastoma. Cancer Med. 2018;7(12):5999-6009.
• Zhang B, Chang K, Ramkissoon S, et al. Multimodal MRI features predict isocitrate dehydrogenase genotype in high‐grade gliomas. Neuro Oncol. 2017;19(1):109-17.
• Yu J, Shi Z, Lian Y, et al. Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol. 2017;27(8):3509-22.
• Andronesi OC, Rapalino O, Gerstner E, et al. Detection of oncogenic IDH1 mutations using magnetic resonance spectroscopy of 2-hydroxyglutarate. J Clin Invest. 2013;123(9):3659-63.
• Lee S, Choi SH, Ryoo I, et al. Evaluation of the microenvironmental heterogeneity in high-grade gliomas with IDH1/2 gene mutation using histogram analysis of diffusion-weighted imaging and dynamic-susceptibility contrast perfusion imaging. J Neurooncol. 2015;121(1):141-50.
• Yamashita K, Hiwatashi A, Togao O, et al. MR Imaging-Based Analysis of Glioblastoma Multiforme: Estimation of IDH1 Mutation Status. AJNR Am J Neuroradiol. 2016;37(1):58-65.
• Kickingereder P, Sahm F, Radbruch A, et al. IDH mutation status is associated with a distinct hypoxia/angiogenesis transcriptome signature which is non-invasively predictable with rCBV imaging in human glioma. Sci Rep. 2015;5:16238.
• Zhao J, Huang Y, Song Y, et al. Diagnostic accuracy and potential covariates for machine learning to identify IDH mutations in glioma patients: evidence from a meta-analysis. Eur Radiol. 2020;30(8):4664-74.
• Choi Y, Nam Y, Lee YS, et al. IDH1 mutation prediction using MR-based radiomics in glioblastoma: comparison between manual and fully automated deep learning-based approach of tumor segmentation. Eur J Radiol. 2020;128:109031.
• Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273-97.
• Ho TK. Random decision forests. In: Proceedings of 3rd international conference on document analysis and recognition. 1995. p. 278-282.
• Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. Smote: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321-57.
• Chandrashekar G, Sahin F. A survey on feature selection methods. Comput Electr Eng. 2013;40(1):16-28.
• Kumar V, Minz S. Feature Selection: A literature review. Smart Comput Rev. 2014;4(3):211-29.