Quantitative MRI Biomarkers of Stereotactic Radiotherapy Outcome in Brain Metastasis

About 20–40% of cancer patients develop brain metastases, causing significant morbidity and mortality. Stereotactic radiation treatment is an established option that delivers high dose radiation to the target while sparing the surrounding normal tissue. However, up to 20% of metastatic brain tumours progress despite stereotactic treatment, and it can take months before it is evident on follow-up imaging. An early predictor of radiation therapy outcome in terms of tumour local failure (LF) is crucial, and can facilitate treatment adjustments or allow for early salvage treatment. In this study, an MR-based radiomics framework was proposed to derive and investigate quantitative MRI (qMRI) biomarkers for the outcome of LF in brain metastasis patients treated with hypo-fractionated stereotactic radiation therapy (SRT). The qMRI biomarkers were constructed through a multi-step feature extraction/reduction/selection framework using the conventional MR imaging data acquired from 100 patients (133 lesions), and were applied in conjunction with machine learning techniques for outcome prediction and risk assessment. The results indicated that the majority of the features in the optimal qMRI biomarkers characterize the heterogeneity in the surrounding regions of tumour including edema and tumour/lesion margins. The optimal qMRI biomarker consisted of five features that predict the outcome of LF with an area under the curve (AUC) of 0.79, and a cross-validated sensitivity and specificity of 81% and 79%, respectively. The Kaplan-Meier analyses showed a statistically significant difference in local control (p-value < 0.0001) and overall survival (p = 0.01). Findings from this study are a step towards using qMRI for early prediction of local failure in brain metastasis patients treated with SRT. This may facilitate early adjustments in treatment, such as surgical resection or salvage radiation, that can potentially improve treatment outcomes. Investigations on larger cohorts of patients are, however, required for further validation of the technique.

[1]  Daniel L. Rubin,et al.  Dynamic contrast-enhanced MRI-based biomarkers of therapeutic response in triple-negative breast cancer. , 2013, Journal of the American Medical Informatics Association : JAMIA.

[2]  P. Sooriakumaran,et al.  Tumour heterogeneity poses a significant challenge to cancer biomarker research , 2017, British Journal of Cancer.

[3]  P. Brown,et al.  Whole-Brain Radiotherapy for Brain Metastases: Evolution or Revolution? , 2017, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[4]  C. Brennan,et al.  Clinical outcomes of patients with limited brain metastases treated with hypofractionated (5×6Gy) conformal radiotherapy. , 2017, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[5]  Aaron D Ward,et al.  Detection of Local Cancer Recurrence After Stereotactic Ablative Radiation Therapy for Lung Cancer: Physician Performance Versus Radiomic Assessment. , 2016, International journal of radiation oncology, biology, physics.

[6]  M. Foote,et al.  Treatment of brain oligometastases with hypofractionated stereotactic radiotherapy utilising volumetric modulated arc therapy , 2015, Clinical & Experimental Metastasis.

[7]  Y. Yatabe,et al.  A 25-signal proteomic signature and outcome for patients with resected non-small-cell lung cancer. , 2007, Journal of the National Cancer Institute.

[8]  Martin J. Yaffe,et al.  Imaging innovations for cancer therapy response monitoring , 2012 .

[9]  D. Hill,et al.  Medical image registration , 2001, Physics in medicine and biology.

[10]  P. Lambin,et al.  Predicting outcomes in radiation oncology—multifactorial decision support systems , 2013, Nature Reviews Clinical Oncology.

[11]  John R. Mackey,et al.  Phase III Randomized Trial Comparing Doxorubicin and Cyclophosphamide Followed by Docetaxel (AC→T) with Doxorubicin and Cyclophosphamide Followed by Docetaxel and Trastuzumab (AC→TH) with Docetaxel, Carboplatin and Trastuzumab (TCH) in Her2neu Positive Early Breast Cancer Patients: BCIRG 006 Study. , 2009 .

[12]  G. Pazour,et al.  Ror2 signaling regulates Golgi structure and transport through IFT20 for tumor invasiveness , 2017, Scientific Reports.

[13]  Martin Bendszus,et al.  Response assessment criteria for brain metastases: proposal from the RANO group. , 2015, The Lancet. Oncology.

[14]  I. J. van der Klei,et al.  The Impact of Peroxisomes on Cellular Aging and Death , 2012, Front. Oncol..

[15]  Douglas C. Miller,et al.  Results of surgical resection for progression of brain metastases previously treated by gamma knife radiosurgery. , 2006, Neurosurgery.

[16]  G. Kramer-Marek,et al.  Diagnostic and Therapeutic Biomarkers in Glioblastoma: Current Status and Future Perspectives , 2017, BioMed research international.

[17]  Maciej A Mazurowski,et al.  Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging. , 2014, Radiology.

[18]  Monika Janda,et al.  Systematic Review of Interventions to Improve the Provision of Information for Adults with Primary Brain Tumors and Their Caregivers , 2014, Front. Oncol..

[19]  P. Mortensen.  EPIDEMIOLOGY , 2012, Schizophrenia Research.

[20]  Ali Sadeghi-Naini,et al.  Early detection of chemotherapy-refractory patients by monitoring textural alterations in diffuse optical spectroscopic images. , 2015, Medical physics.

[21]  Martin J. Yaffe,et al.  Early prediction of therapy responses and outcomes in breast cancer patients using quantitative ultrasound spectral texture , 2014, Oncotarget.

[22]  Erich P Huang,et al.  MR Imaging Radiomics Signatures for Predicting the Risk of Breast Cancer Recurrence as Given by Research Versions of MammaPrint, Oncotype DX, and PAM50 Gene Assays. , 2016, Radiology.

[23]  Ahmad Chaddad,et al.  Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images , 2018, Front. Oncol..

[24]  R. Labianca,et al.  Molecular markers and biological targeted therapies in metastatic colorectal cancer: expert opinion and recommendations derived from the 11th ESMO/World Congress on Gastrointestinal Cancer, Barcelona, 2009. , 2010, Annals of oncology : official journal of the European Society for Medical Oncology.

[25]  Daniel A. Braun,et al.  Inferring Visuomotor Priors for Sensorimotor Learning , 2011, PLoS Comput. Biol..

[26]  P. Lambin,et al.  CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. , 2015, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[27]  H. Murota,et al.  Usefulness of Sweat Management for Patients with Adult Atopic Dermatitis, regardless of Sweat Allergy: A Pilot Study , 2017, BioMed research international.

[28]  P. Lambin,et al.  Defining the biological basis of radiomic phenotypes in lung cancer , 2017, eLife.

[29]  Amara Lynn Graps,et al.  An introduction to wavelets , 1995 .

[30]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[31]  Dong-Chen He,et al.  Texture Unit, Texture Spectrum, And Texture Analysis , 1990 .

[32]  L. Deangelis,et al.  Overview of metastatic disease of the central nervous system. , 2018, Handbook of clinical neurology.

[33]  Tobias Gauer,et al.  Radiomics of Brain MRI: Utility in Prediction of Metastatic Tumor Type. , 2019, Radiology.

[34]  V. Staedtke,et al.  Actionable molecular biomarkers in primary brain tumors. , 2016, Trends in cancer.

[35]  Milan Sonka,et al.  3D Slicer as an image computing platform for the Quantitative Imaging Network. , 2012, Magnetic resonance imaging.

[36]  Mehrdad J. Gangeh,et al.  Computer Aided Theragnosis Using Quantitative Ultrasound Spectroscopy and Maximum Mean Discrepancy in Locally Advanced Breast Cancer , 2016, IEEE Transactions on Medical Imaging.

[37]  James S. Lawson,et al.  Oncogenic Viruses and Breast Cancer: Mouse Mammary Tumor Virus (MMTV), Bovine Leukemia Virus (BLV), Human Papilloma Virus (HPV), and Epstein–Barr Virus (EBV) , 2018, Front. Oncol..

[38]  Michael C. Kolios,et al.  Low-frequency quantitative ultrasound imaging of cell death in vivo. , 2013, Medical Physics (Lancaster).

[39]  A. Akabane,et al.  A Multi-institutional Prospective Observational Study of Stereotactic Radiosurgery for Patients With Multiple Brain Metastases (JLGK0901 Study Update): Irradiation-related Complications and Long-term Maintenance of Mini-Mental State Examination Scores. , 2017, International journal of radiation oncology, biology, physics.

[40]  M. Giger,et al.  Deciphering Genomic Underpinnings of Quantitative MRI-based Radiomic Phenotypes of Invasive Breast Carcinoma , 2015, Scientific Reports.

[41]  H. Shu,et al.  Hypofractionated radiosurgery for intact or resected brain metastases: defining the optimal dose and fractionation , 2013, Radiation oncology.

[42]  María Blanca Fernández-Viñéa.  CURRENT STATUS AND FUTURE PERSPECTIVES , 2018 .

[43]  J. Robertson,et al.  Face Dependence of Schottky Barriers Heights of Silicides and Germanides on Si and Ge , 2017, Scientific Reports.

[44]  Mehrdad J. Gangeh,et al.  A priori Prediction of Neoadjuvant Chemotherapy Response and Survival in Breast Cancer Patients using Quantitative Ultrasound , 2017, Scientific Reports.

[45]  Chris Bakal,et al.  Microenvironmental Heterogeneity Parallels Breast Cancer Progression: A Histology–Genomic Integration Analysis , 2016, PLoS medicine.

[46]  Bal Sanghera,et al.  Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? , 2012, Insights into Imaging.

[47]  G. Pond,et al.  Comparative survival in patients with brain metastases from non-small-cell lung cancer treated before and after implementation of radiosurgery. , 2017, Current oncology.

[48]  Marios Politis,et al.  Clinical application of stem cell therapy in Parkinson's disease , 2012, BMC Medicine.

[49]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[50]  M. McDermott,et al.  Adverse radiation effect after stereotactic radiosurgery for brain metastases: incidence, time course, and risk factors. , 2015, Journal of neurosurgery.

[51]  R. C. Macridis.  A review , 1963 .

[52]  Gregory J. Czarnota,et al.  Noninvasive Characterization of Locally Advanced Breast Cancer Using Textural Analysis of Quantitative Ultrasound Parametric Images , 2014, Translational oncology.

[53]  Issam El-Naqa,et al.  Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer , 2017, Scientific Reports.

[54]  A. Sahgal,et al.  A meta‐analysis evaluating stereotactic radiosurgery, whole‐brain radiotherapy, or both for patients presenting with a limited number of brain metastases , 2012, Cancer.

[55]  Kornelia Polyak,et al.  Heterogeneity in breast cancer. , 2011, The Journal of clinical investigation.

[56]  M. Taphoorn,et al.  Neurocognitive functioning and health-related quality of life in patients treated with stereotactic radiotherapy for brain metastases: a prospective study. , 2015, Neuro-oncology.

[57]  Ali Sadeghi-Naini,et al.  Predicting breast cancer response to neoadjuvant chemotherapy using pretreatment diffuse optical spectroscopic texture analysis , 2017, British Journal of Cancer.

[58]  Gregory J. Czarnota,et al.  Quantitative ultrasound assessment of breast tumor response to chemotherapy using a multi-parameter approach , 2016, Oncotarget.

[59]  E. Kohn,et al.  Proteomics as a guiding tool for more effective personalized therapy. , 2010, Annals of oncology : official journal of the European Society for Medical Oncology.

[60]  K. Yeom,et al.  Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches , 2017, American Journal of Neuroradiology.

[61]  Yuta Shibamoto,et al.  Treatment of Single or Multiple Brain Metastases by Hypofractionated Stereotactic Radiotherapy Using Helical Tomotherapy , 2014, International journal of molecular sciences.

[62]  Hassan Rivaz,et al.  Breast Ultrasound Elastography Using Full Inversion-Based Elastic Modulus Reconstruction , 2017, IEEE Transactions on Computational Imaging.

[63]  Mohamed S. Kamel,et al.  Categorizing Extent of Tumor Cell Death Response to Cancer Therapy Using Quantitative Ultrasound Spectroscopy and Maximum Mean Discrepancy , 2014, IEEE Transactions on Medical Imaging.

[64]  Gregory J. Czarnota,et al.  Quantification of Ultrasonic Scattering Properties of In Vivo Tumor Cell Death in Mouse Models of Breast Cancer1 , 2015, Translational oncology.

[65]  David A. Larson,et al.  Stereotactic radiosurgery (SRS) in the modern management of patients with brain metastases , 2016, Oncotarget.

[66]  G. Parker,et al.  Imaging Intratumor Heterogeneity: Role in Therapy Response, Resistance, and Clinical Outcome , 2014, Clinical Cancer Research.

[67]  E. Ruppin,et al.  Co-targeting the tumor endothelium and P-selectin-expressing glioblastoma cells leads to a remarkable therapeutic outcome , 2017, eLife.

[68]  P. Lambin,et al.  Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer , 2015, Front. Oncol..

[69]  Ann M. Peiffer,et al.  Radiation-induced brain injury: A review , 2012, Front. Oncol..

[70]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[71]  Sidra Nawaz,et al.  Mapping spatial heterogeneity in the tumor microenvironment: a new era for digital pathology , 2015, Laboratory Investigation.

[72]  R. Gillies,et al.  Quantitative imaging in cancer evolution and ecology. , 2013, Radiology.

[73]  Philippe Lambin,et al.  Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures , 2017, The British journal of radiology.

[74]  P. Marchetti,et al.  Brain Metastases: Surgical Treatment and Overall Survival. , 2017, World neurosurgery.

[75]  Satoshi Suzuki,et al.  Stereotactic radiosurgery for patients with multiple brain metastases (JLGK0901): a multi-institutional prospective observational study. , 2014, The Lancet. Oncology.

[76]  Charles Swanton,et al.  Translational Implications of Tumor Heterogeneity , 2015, Clinical Cancer Research.

[77]  A. Niemierko,et al.  The impact of different stereotactic radiation therapy regimens for brain metastases on local control and toxicity , 2017, Advances in radiation oncology.

[78]  Dan Theodorescu,et al.  Precision medicine for urothelial bladder cancer: update on tumour genomics and immunotherapy , 2018, Nature Reviews Urology.

[79]  David Venet,et al.  Most Random Gene Expression Signatures Are Significantly Associated with Breast Cancer Outcome , 2011, PLoS Comput. Biol..

[80]  V. Staedtke,et al.  Actionable Molecular Biomarkers in Primary Brain Tumors. , 2016, Trends in cancer.

[81]  Michael C. Kolios,et al.  Quantitative Ultrasound Spectroscopic Imaging for Characterization of Disease Extent in Prostate Cancer Patients1 , 2015, Translational oncology.

[82]  Wilfrido Gómez-Flores,et al.  Improving classification performance of breast lesions on ultrasonography , 2015, Pattern Recognit..

[83]  Dan Wang,et al.  Corrigendum: An indica rice genotype showed a similar yield enhancement to that of hybrid rice under free air carbon dioxide enrichment , 2015, Scientific Reports.

[84]  Volker W Stieber,et al.  Effect of Radiosurgery Alone vs Radiosurgery With Whole Brain Radiation Therapy on Cognitive Function in Patients With 1 to 3 Brain Metastases: A Randomized Clinical Trial. , 2016, JAMA.

[85]  Gregory J. Czarnota,et al.  Chemotherapy-Response Monitoring of Breast Cancer Patients Using Quantitative Ultrasound-Based Intra-Tumour Heterogeneities , 2017, Scientific Reports.

[86]  Kevin Brindle,et al.  New approaches for imaging tumour responses to treatment , 2008, Nature Reviews Cancer.

[87]  Jill S Barnholtz-Sloan,et al.  Brain metastases: epidemiology. , 2018, Handbook of clinical neurology.

[88]  V. Esposito,et al.  Single-Fraction Versus Multifraction (3 × 9 Gy) Stereotactic Radiosurgery for Large (>2 cm) Brain Metastases: A Comparative Analysis of Local Control and Risk of Radiation-Induced Brain Necrosis. , 2016, International journal of radiation oncology, biology, physics.

[89]  E. Diamandis,et al.  The failure of protein cancer biomarkers to reach the clinic: why, and what can be done to address the problem? , 2012, BMC Medicine.

[90]  Rajendu Srivastava,et al.  A Retrospective Analysis of Precision Medicine Outcomes in Patients With Advanced Cancer Reveals Improved Progression-Free Survival Without Increased Health Care Costs , 2016, Journal of oncology practice.

[91]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[92]  Junmin Peng,et al.  Proteomics of gliomas: initial biomarker discovery and evolution of technology. , 2011, Neuro-oncology.

[93]  Chaofeng Liang,et al.  A Fully-Automatic Multiparametric Radiomics Model: Towards Reproducible and Prognostic Imaging Signature for Prediction of Overall Survival in Glioblastoma Multiforme , 2017, Scientific Reports.

[94]  Michael C. Kolios,et al.  Conventional frequency ultrasonic biomarkers of cancer treatment response in vivo. , 2013, Translational oncology.