Evaluating Maximum Diameters of Tumor Sub-regions for Survival Prediction in Glioblastoma Patients via Machine Learning, Considering Resection Status

Source:
By:Author(s)

DOI: https://doi.org/10.30564/jeis.v6i1.6174

Abstract:

In recent decades, there have been significant advancements in medical diagnosis and treatment techniques. However, there is still much progress to be made in effectively managing a wide range of diseases, particularly cancer. Timely diagnosis of cancer remains a critical step towards successful treatment, as it significantly impacts patients’ chances of survival. Among various types of cancer, glioma stands out as the most common primary brain tumor, exhibiting different levels of aggressiveness. One of the monitoring techniques is magnetic resonance imaging (MRI) that provides a precise visual representation of the tumor and its sub-regions (edema (ED), enhancing tumor (ET), and non-enhancing necrotic tumor core (NEC)), enabling monitoring of its location, shape, and sub- regional characteristics. In this study, we aim to investigate the underlying relationship between the maximumdiameters of tumor sub-regions and patients’ overall survival (OS) in glioblastoma cases. Using an MRI dataset of glioblastoma patients, we categorized them based on resection status: gross total resection (GTR) and unknown (NA). By employing the Euclidean distance algorithm, we estimated sub-regions’ maximum diameters. Machine learning algorithms were used to explore the correlation between sub-regions’ maximum diameters and survival outcomes.  The results of the univariate prediction models showed that tumor sub-regions’ maximum diameters have a noticeable correlation with the survival rates among patients with unknown resection status with the average spearman correlation of -0.254. Also, addition of the sub-regions’ maximum diameter feature to the radiomics increased the accuracy of ML algorithms in predicting the survival rates with an average of 4.58%.

References:

[1] Garanti, T., Alhnan, M.A., Wan, K.W., 2021. The potential of nanotherapeutics to target brain tumors: Current challenges and future opportunities. Nanomedicine. 16(21), 1833–1837. DOI: https://doi.org/10.2217/nnm-2021-0134 [2] Goodenberger, M.L., Jenkins, R.B., 2012. Genetics of adult glioma. Cancer Genetics. 205(12), 613–621. DOI: https://doi.org/10.1016/j.cancergen.2012.10.009 [3] Atkinson, M., Juhász, C., Shah, J., et al., 2008. Paradoxical imaging findings in cerebral gliomas. Journal of the Neurological Sciences. 269(1–2), 180–183. DOI: https://doi.org/10.1016/j.jns.2007.12.029 [4] Wang, Y., Zhao, W., Xiao, Z., et al., 2020. A risk signature with four autophagy‐related genes for predicting survival of glioblastoma multiforme. Journal of Cellular and Molecular Medicine. 24(7), 3807–3821. DOI: https://doi.org/10.1111/jcmm.14938 [5] Holland, E.C., 2000. Glioblastoma multiforme: The terminator. Proceedings of the National Academy of Sciences. 97(12), 6242–6244. DOI: https://doi.org/10.1073/pnas.97.12.6242 [6] Gomez, S.L., Shariff‐Marco, S., DeRouen, M., et al., 2015. The impact of neighborhood social and built environment factors across the cancer continuum: Current research, methodological considerations, and future directions. Cancer. 121(14), 2314–2330. DOI: https://doi.org/10.1002/cncr.29345 [7] McTiernan, A., Friedenreich, C.M., Katzmarzyk, P.T., et al., 2019. Physical activity in cancer prevention and survival: A systematic review. Medicine and Science in Sports and Exercise. 51(6), 1252–1261. DOI: https://doi.org/10.1249/MSS.0000000000001937 [8] Carrera, P.M., Kantarjian, H.M., Blinder, V.S., 2018. The financial burden and distress of patients with cancer: Understanding and stepping‐up action on the financial toxicity of cancer treatment. CA: A Cancer Journal for Clinicians. 68(2), 153–165. DOI: https://doi.org/10.3322/caac.21443 [9] Weninger, L., Haarburger, C., Merhof, D., 2019. Robustness of radiomics for survival prediction of brain tumor patients depending on resection status. Frontiers in Computational Neuroscience. 13, 73. DOI: https://doi.org/10.3389/fncom.2019.00073 [10] Jonklaas, J., Nogueras-Gonzalez, G., Munsell, M., et al., 2012. The impact of age and gender on papillary thyroid cancer survival. The Journal of Clinical Endocrinology & Metabolism. 97(6), E878–E887. DOI: https://doi.org/10.1210/jc.2011-2864 [11] Chowdhary, C.L., Acharjya, D.P., 2020. Segmentation and feature extraction in medical imaging: A systematic review. Procedia Computer Science. 167, 26–36. DOI: https://doi.org/10.1016/j.procs.2020.03.179 [12] Choi, Y., Nam, Y., Jang, J., et al., 2021. Radiomics may increase the prognostic value for survival in glioblastoma patients when combined with conventional clinical and genetic prognostic models. European Radiology. 31, 2084–2093. DOI: https://doi.org/10.1007/s00330-020-07335-1 [13] Ardakani, A.A., Bureau, N.J., Ciaccio, E.J., et al., 2022. Interpretation of radiomics features—a pictorial review. Computer Methods and Programs in Biomedicine. 215, 106609. DOI: https://doi.org/10.1016/j.cmpb.2021.106609 [14] Tomaszewski, M.R., Gillies, R.J., 2021. The biological meaning of radiomic features. Radiology. 298(3), 505–516. DOI: https://doi.org/10.1148/radiol.2021202553 [15] Hooper, G.W., Ginat, D.T., 2023. MRI radiomics and potential applications to glioblastoma. Frontiers in Oncology. 13, 1134109. DOI: https://doi.org/10.3389/fonc.2023.1134109 [16] Zhu, J., Ye, J., Dong, L., et al., 2023. Non‐invasive prediction of overall survival time for glioblastoma multiforme patients based on multimodal MRI radiomics. International Journal of Imaging Systems and Technology. 33(4), 1261–1274. DOI: https://doi.org/10.1002/ima.22869 [17] Li, Y., Bao, L., Yang, C., et al., 2023. A multiparameter radiomic model for accurate prognostic prediction of glioma. MedComm–Future Medicine. 2(2), e41. DOI: https://doi.org/10.1002/mef2.41 [18] Shboul, Z.A., Vidyaratne, L., Alam, M., et al., 2018. Glioblastoma and survival prediction. Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer International Publishing: Cham. pp. 358–368. DOI: https://doi.org/10.1007/978-3-319-75238-9_31 [19] Feng, X., Tustison, N.J., Patel, S.H., et al., 2020. Brain tumor segmentation using an ensemble of 3d u-nets and overall survival prediction using radiomic features. Frontiers in Computational Neuroscience. 14, 25. DOI: https://doi.org/10.3389/fncom.2020.00025 [20] Bakas, S., Reyes, M., Jakab, A., et al., 2018. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv preprint arXiv:1811.02629. [21] Baid, U., Talbar, S., Rane, S., et al., 2019. Deep learning radiomics algorithm for gliomas (drag) model: A novel approach using 3d unet based deep convolutional neural network for predicting survival in gliomas. Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer International Publishing: Cham. pp. 369–379. DOI: https://doi.org/10.1007/978-3-030-11726-9_33 [22] Jungo, A., McKinley, R., Meier, R., et al., 2018. Towards uncertainty-assisted brain tumor segmentation and survival prediction. Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer International Publishing: Cham. pp. 474–485. DOI: https://doi.org/10.1007/978-3-319-75238-9_40 [23] Puybareau, E., Tochon, G., Chazalon, J., et al., 2019. Segmentation of gliomas and prediction of patient overall survival: A simple and fast procedure. Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer International Publishing: Cham. pp. 199–209. DOI: https://doi.org/10.1007/978-3-030-11726-9_18 [24] Sun, L., Zhang, S., Luo, L., 2019. Tumor segmentation and survival prediction in glioma with deep learning. Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries. Springer International Publishing: Cham. pp. 83–93. DOI: https://doi.org/10.1007/978-3-030-11726-9_8 [25] Choi, Y.S., Ahn, S.S., Chang, J.H., et al., 2020. Machine learning and radiomic phenotyping of lower grade gliomas: Improving survival prediction. European Radiology. 30, 3834–3842. DOI: https://doi.org/10.1007/s00330-020-06737-5 [26] Wankhede, D.S., Selvarani, R., 2022. Dynamic architecture based deep learning approach for glioblastoma brain tumor survival prediction. Neuroscience Informatics. 2(4), 100062. DOI: https://doi.org/10.1016/j.neuri.2022.100062 [27] Hu, Z., Yang, Z., Zhang, H., et al., 2022. A deep learning model with radiomics analysis integration for glioblastoma post-resection survival prediction. arXiv preprint arXiv:2203.05891. [28] Fang, L., Wang, X., 2022. Brain tumor segmentation based on the dual-path network of multi-modal MRI images. Pattern Recognition. 124, 108434. DOI: https://doi.org/10.1016/j.patcog.2021.108434 [29] Liu, J., Li, M., Wang, J., et al., 2014. A survey of MRI-based brain tumor segmentation methods. Tsinghua Science and Technology. 19(6), 578–595. DOI: https://doi.org/10.1109/TST.2014.6961028 [30] Senders, J.T., Staples, P., Mehrtash, A., et al., 2020. An online calculator for the prediction of survival in glioblastoma patients using classical statistics and machine learning. Neurosurgery. 86(2), E184–E192. DOI: https://doi.org/10.1093/neuros/nyz403 [31] Menze, B.H., Jakab, A., Bauer, S., et al., 2014. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Transactions on Medical Imaging. 34(10), 1993–2024. DOI: https://doi.org/10.1109/TMI.2014.2377694 [32] Bakas, S., Akbari, H., Sotiras, A., et al., 2017. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Scientific Data. 4, 170117. DOI: https://doi.org/10.1038/sdata.2017.117 [33] Segmentation Labels for the Pre-operative Scans of the TCGA-GBM Collection [Internet]. The Cancer Imaging Archive. Available from: https://doi.org/10.7937/K9/TCIA.2017.KLXWJJ1Q [34] Segmentation Labels and Radiomic Features for the Pre-operative Scans of the TCGA-LGG Collection [Internet]. The Cancer Imaging Archive. Available from: https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF [35] Soltani, M., Bonakdar, A., Shakourifar, N., et al., 2021. Efficacy of location-based features for survival prediction of patients with glioblastoma depending on resection status. Frontiers in Oncology. 11, 661123. DOI: https://doi.org/10.3389/fonc.2021.661123 [36] Tustison, N.J., Avants, B.B., Cook, P.A., et al., 2010. N4ITK: Improved N3 bias correction. IEEE Transactions on Medical Imaging. 29(6), 1310–1320. DOI: https://doi.org/10.1109/TMI.2010.2046908 [37] Gaillochet, M., Tezcan, K.C., Konukoglu, E., 2020. Joint reconstruction and bias field correction for undersampled MR imaging. Medical image computing and computer-assisted intervention. Springer International Publishing: Cham. pp. 44–52. DOI: https://doi.org/10.1007/978-3-030-59713-9_5 [38] Van Griethuysen, J.J., Fedorov, A., Parmar, C., et al., 2017. Computational radiomics system to decode the radiographic phenotype. Cancer Research. 77(21), e104–e107. DOI: https://doi.org/10.1158/0008-5472.CAN-17-0339 [39] Bzdok, D., 2017. Classical statistics and statistical learning in imaging neuroscience. Frontiers in Neuroscience. 11, 543. DOI: https://doi.org/10.3389/fnins.2017.00543 [40] Gillies, R.J., Kinahan, P.E., Hricak, H., 2016. Radiomics: Images are more than pictures, they are data. Radiology. 278(2), 563–577. DOI: https://doi.org/10.1148/radiol.2015151169 [41] Abdi, H., Williams, L.J., 2010. Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics. 2(4), 433–459. DOI: http://dx.doi.org/10.1002/wics.101 [42] Kambhatla, N., Leen, T.K., 1997. Dimension reduction by local principal component analysis. Neural Computation. 9(7), 1493–1516. DOI: https://doi.org/10.1162/neco.1997.9.7.1493 [43] Benjamini, Y., Hochberg, Y., 1995. Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society: Series B (Methodological). 57(1), 289–300. DOI: https://doi.org/10.1111/j.2517-6161.1995.tb02031.x [44] Gutman, D.A., Cooper, L.A., Hwang, S.N., et al., 2013. MR imaging predictors of molecular profile and survival: Multi-institutional study of the TCGA glioblastoma data set. Radiology. 267(2), 560–569. DOI: https://doi.org/10.1148/radiol.13120118 [45] Macyszyn, L., Akbari, H., Pisapia, J.M., et al., 2015. Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques. Neuro-oncology. 18(3), 417–425. DOI: https://doi.org/10.1093/neuonc/nov127 [46] Kickingereder, P., Burth, S., Wick, A., et al., 2016. Radiomic profiling of glioblastoma: Identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models. Radiology. 280(3), 880–889. DOI: https://doi.org/10.1148/radiol.2016160845 [47] Lao, J., Chen, Y., Li, Z.C., et al., 2017. A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme. Scientific Reports. 7, 10353. DOI: https://doi.org/10.1038/s41598-017-10649-8 [48] Li, Q., Bai, H., Chen, Y., et al., 2017. A fully-automatic multiparametric radiomics model: towards reproducible and prognostic imaging signature for prediction of overall survival in glioblastoma multiforme. Scientific Reports. 7, 14331. DOI: https://doi.org/10.1038/s41598-017-14753-7 [49] Zhang, Z., Jiang, H., Chen, X., et al., 2014. Identifying the survival subtypes of glioblastoma by quantitative volumetric analysis of MRI. Journal of Neuro-oncology. 119, 207–214. DOI: https://doi.org/10.1007/s11060-014-1478-2 [50] Nie, D., Zhang, H., Adeli, E., et al., 2016. 3D deep learning for multi-modal imaging-guided survival time prediction of brain tumor patients. Medical image computing and computer-assisted intervention. Springer International Publishing: Cham. pp. 212–220. DOI: https://doi.org/10.1007/978-3-319-46723-8_25 [51] Sun, W., Jiang, M., Dang, J., et al., 2018. Effect of machine learning methods on predicting NSCLC overall survival time based on Radiomics analysis. Radiation Oncology. 13, 197. DOI: https://doi.org/10.1186/s13014-018-1140-9 [52] Wijethilake, N., Islam, M., Ren, H., 2020. Radiogenomics model for overall survival prediction of glioblastoma. Medical & Biological Engineering & Computing. 58, 1767–1777. DOI: https://doi.org/10.1007/s11517-020-02179-9 [53] Baid, U., Rane, S.U., Talbar, S., et al., 2020. Overall survival prediction in glioblastoma with radiomic features using machine learning. Frontiers in Computational Neuroscience. 14, 61. DOI: https://doi.org/10.3389/fncom.2020.00061 [54] Shaheen, A., Burigat, S., Bagci, U., et al., 2020. Overall survival prediction in gliomas using region-specific radiomic features. Machine learning in clinical neuroimaging and radiogenomics in neuro-oncology. Springer International Publishing: Cham. pp. 259–267. DOI: https://doi.org/10.1007/978-3-030-66843-3_25 [55] Ammari, S., Sallé de Chou, R., Balleyguier, C., et al., 2021. A predictive clinical-radiomics nomogram for survival prediction of glioblastoma using MRI. Diagnostics. 11(11), 2043. DOI: https://doi.org/10.3390/diagnostics11112043 [56] Calabrese, E., Rudie, J.D., Rauschecker, A.M., et al., 2022. Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma. Neuro-Oncology Advances. 4(1), vdac060. DOI: https://doi.org/10.1093/noajnl/vdac060 [57] Manjunath, M., Saravanakumar, S., Kiran, S., et al., 2023. A comparison of machine learning models for survival prediction of patients with glioma using radiomic features from MRI scans. Indian Journal of Radiology and Imaging. 33(3), 338–343. DOI: https://doi.org/10.1055/s-0043-1767786 [58] Chiesa, S., Russo, R., Beghella Bartoli, F., et al., 2023. MRI-derived radiomics to guide post-operative management of glioblastoma: Implication for personalized radiation treatment volume delineation. Frontiers in Medicine. 10, 1059712. DOI: https://doi.org/10.3389/fmed.2023.1059712 [59] Tran, M.T., Yang, H.J., Kim, S.H., et al., 2023. Prediction of survival of glioblastoma patients using local spatial relationships and global structure awareness in FLAIR MRI brain images. IEEE Access. 11, 37437–37449. DOI: https://doi.org/10.1109/ACCESS.2023.3266771 [60] Martin, P., Holloway, L., Metcalfe, P., et al., 2022. Challenges in glioblastoma radiomics and the path to clinical implementation. Cancers. 14(16), 3897. DOI: https://doi.org/10.3390/cancers14163897 [61] Khan, M.A., Ashraf, I., Alhaisoni, M., et al., 2020. Multimodal brain tumor classification using deep learning and robust feature selection: A machine learning application for radiologists. Diagnostics. 10(8), 565. DOI: https://doi.org/10.3390/diagnostics10080565