A pilot study using kernelled support tensor machine for distant failure prediction in lung SBRT

&NA; We developed a kernelled support tensor machine (KSTM)‐based model with tumor tensors derived from pre‐treatment PET and CT imaging as input to predict distant failure in early stage non‐small cell lung cancer (NSCLC) treated with stereotactic body radiation therapy (SBRT). The patient cohort included 110 early stage NSCLC patients treated with SBRT, 25 of whom experienced failure at distant sites. Three‐dimensional tumor tensors were constructed and used as input for the KSTM‐based classifier. A KSTM iterative algorithm with a convergent proof was developed to train the weight vectors for every mode of the tensor for the classifier. In contrast to conventional radiomics approaches that rely on handcrafted imaging features, the KSTM‐based classifier uses 3D imaging as input, taking full advantage of the imaging information. The KSTM‐based classifier preserves the intrinsic 3D geometry structure of the medical images and the correlation in the original images and trains the classification hyper‐plane in an adaptive feature tensor space. The KSTM‐based predictive algorithm was compared with three conventional machine learning models and three radiomics approaches. For PET and CT, the KSTM‐based predictive method achieved the highest prediction results among the seven methods investigated in this study based on 10‐fold cross validation and independent testing.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  L V Rubinstein,et al.  Randomized trial of lobectomy versus limited resection for T1 N0 non-small cell lung cancer. Lung Cancer Study Group. , 1995, The Annals of thoracic surgery.

[3]  J. Alison Noble,et al.  Learning-based prediction of gestational age from ultrasound images of the fetal brain , 2015, Medical Image Anal..

[4]  Vicky Goh,et al.  Radiomics in PET: principles and applications , 2014, Clinical and Translational Imaging.

[5]  Steve B. Jiang,et al.  Predicting distant failure in early stage NSCLC treated with SBRT using clinical parameters. , 2016, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[6]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[7]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[8]  Suresh Senan,et al.  Patterns of disease recurrence after stereotactic ablative radiotherapy for early stage non-small-cell lung cancer: a retrospective analysis. , 2012, The Lancet. Oncology.

[9]  Renato Martins,et al.  Non-small cell lung cancer. , 2012, Journal of the National Comprehensive Cancer Network : JNCCN.

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

[11]  I. El Naqa,et al.  A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities , 2015, Physics in medicine and biology.

[12]  Andreas Uhl,et al.  Directional wavelet based features for colonic polyp classification , 2016, Medical Image Anal..

[13]  Nico Karssemeijer,et al.  Large scale deep learning for computer aided detection of mammographic lesions , 2017, Medical Image Anal..

[14]  Shan Tan,et al.  Spatial-temporal [¹⁸F]FDG-PET features for predicting pathologic response of esophageal cancer to neoadjuvant chemoradiation therapy. , 2013, International journal of radiation oncology, biology, physics.

[15]  Thierry Denoeux,et al.  Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction , 2016, Medical Image Anal..

[16]  Ronald M. Summers,et al.  Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation , 2015, IEEE Transactions on Medical Imaging.

[17]  L. Lathauwer,et al.  Signal Processing based on Multilinear Algebra , 1997 .

[18]  Sunita Ghosh,et al.  Outcomes in stage I non-small cell lung cancer following the introduction of stereotactic body radiotherapy in Alberta - A population-based study. , 2015, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[19]  Chong Li,et al.  Existence of solutions for variational inequalities on Riemannian manifolds , 2009 .

[20]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[21]  Xuelong Li,et al.  Supervised tensor learning , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[22]  Ashek Ahmmed.  Image denoising using Gabor filter banks , 2011, 2011 IEEE Symposium on Computers & Informatics.

[23]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

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

[25]  D. Rubin,et al.  Early-Stage Non-Small Cell Lung Cancer: Quantitative Imaging Characteristics of (18)F Fluorodeoxyglucose PET/CT Allow Prediction of Distant Metastasis. , 2016, Radiology.

[26]  Bram van Ginneken,et al.  Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box , 2015, Medical Image Anal..

[27]  Wei Shen,et al.  Multi-scale Convolutional Neural Networks for Lung Nodule Classification , 2015, IPMI.

[28]  Fei Wang,et al.  Deep learning for healthcare: review, opportunities and challenges , 2018, Briefings Bioinform..

[29]  Masoom A. Haider,et al.  Discovery Radiomics for Computed Tomography Cancer Detection , 2015, ArXiv.

[30]  Zhongxing Liao,et al.  Systemic review of the patterns of failure following stereotactic body radiation therapy in early-stage non-small-cell lung cancer: clinical implications. , 2010, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[31]  Zvi Friedman,et al.  Automatic apical view classification of echocardiograms using a discriminative learning dictionary , 2017, Medical Image Anal..

[32]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[33]  Joshua D. Lawson,et al.  Locoregional and distant failure following image-guided stereotactic body radiation for early-stage primary lung cancer. , 2011, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[34]  Ninon Burgos,et al.  Voxelwise atlas rating for computer assisted diagnosis: Application to congenital heart diseases of the great arteries , 2015, Medical Image Anal..

[35]  Steve B. Jiang,et al.  Multi-objective radiomics model for predicting distant failure in lung SBRT , 2017, Physics in medicine and biology.

[36]  Andre Dekker,et al.  Radiomics: the process and the challenges. , 2012, Magnetic resonance imaging.

[37]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[38]  George Lee,et al.  Image analysis and machine learning in digital pathology: Challenges and opportunities , 2016, Medical Image Anal..

[39]  Quynh-Thu Le,et al.  Non-small cell lung cancer: Clinical practice guidelines in oncology , 2006 .

[40]  P Giraud,et al.  Chapter 44 – Non–Small Cell Lung Cancer , 2016 .

[41]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[42]  D. Aberle,et al.  Results of initial low-dose computed tomographic screening for lung cancer. , 2013, The New England journal of medicine.

[43]  Sébastien Jodogne,et al.  FDG PET/CT texture analysis for predicting the outcome of lung cancer treated by stereotactic body radiation therapy , 2016, European Journal of Nuclear Medicine and Molecular Imaging.

[44]  A. Jemal,et al.  Cancer treatment and survivorship statistics, 2016 , 2016, CA: a cancer journal for clinicians.

[45]  Dinggang Shen,et al.  View‐aligned hypergraph learning for Alzheimer's disease diagnosis with incomplete multi‐modality data , 2017, Medical Image Anal..

[46]  P. Dupont,et al.  Prognostic importance of the standardized uptake value on (18)F-fluoro-2-deoxy-glucose-positron emission tomography scan in non-small-cell lung cancer: An analysis of 125 cases. Leuven Lung Cancer Group. , 1999, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[47]  H. Abdi,et al.  Principal component analysis , 2010 .

[48]  P. Lambin,et al.  Machine Learning methods for Quantitative Radiomic Biomarkers , 2015, Scientific Reports.

[49]  H. Benali,et al.  Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI , 2009, Neuroradiology.

[50]  Amnon Shashua,et al.  Linear image coding for regression and classification using the tensor-rank principle , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[51]  Masoom A. Haider,et al.  Discovery Radiomics for Multi-Parametric MRI Prostate Cancer Detection , 2015, ArXiv.

[52]  M E Burt,et al.  Incidence of local recurrence and second primary tumors in resected stage I lung cancer. , 1995, The Journal of thoracic and cardiovascular surgery.

[53]  R. Fletcher,et al.  Clinical Epidemiology: The Essentials , 1982 .

[54]  John Cho,et al.  Stereotactic body radiotherapy (SBRT) for non-small cell lung cancer (NSCLC): is FDG-PET a predictor of outcome? , 2012, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[55]  Xi Chen,et al.  Constructing multi-modality and multi-classifier radiomics predictive models through reliable classifier fusion , 2017, ArXiv.

[56]  Xiaowei Yang,et al.  A Linear Support Higher-Order Tensor Machine for Classification , 2013, IEEE Transactions on Image Processing.

[57]  Andrea Bezjak,et al.  Stereotactic body radiation therapy for inoperable early stage lung cancer. , 2010, JAMA.

[58]  Andrew J. Saykin,et al.  Longitudinal measurement and hierarchical classification framework for the prediction of Alzheimer’s disease , 2017, Scientific Reports.

[59]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[60]  Anil K. Jain,et al.  Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[61]  C Shang,et al.  Significance of Tumor Cell Histology for Local Control of Early-Stage Non-Small Cell Lung Cancer Treated With Stereotactic Body Radiation Therapy: A Stratified Retrospective Analysis. , 2016 .

[62]  J. M. Michalski,et al.  Long-term Results of RTOG 0236: A Phase II Trial of Stereotactic Body Radiation Therapy (SBRT) in the Treatment of Patients with Medically Inoperable Stage I Non-Small Cell Lung Cancer , 2014 .

[63]  Lionel M. Raff,et al.  Quasiclassical trajectory studies using 3D spline interpolation of ab initio surfaces , 1975 .

[64]  Fang Liu,et al.  Object information based interactive segmentation for fatty tissue extraction , 2013, Comput. Biol. Medicine.

[65]  Larry S. Davis,et al.  Texture Analysis Using Generalized Co-Occurrence Matrices , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[66]  F. Turkheimer,et al.  A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities , 2015 .

[67]  Liangpei Zhang,et al.  A Multifeature Tensor for Remote-Sensing Target Recognition , 2011, IEEE Geoscience and Remote Sensing Letters.

[68]  Nenghai Yu,et al.  Camera Model Identification for JPEG Images via Tensor Analysis , 2010, 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[69]  Marko Robnik-Sikonja,et al.  Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF , 2004, Applied Intelligence.

[70]  Peyman Milanfar,et al.  Linear Support Tensor Machine With LSK Channels: Pedestrian Detection in Thermal Infrared Images , 2016, IEEE Transactions on Image Processing.