TriZ-a rotation-tolerant image feature and its application in endoscope-based disease diagnosis

Endoscopy is becoming one of the widely-used technologies to screen the gastric diseases, and it heavily relies on the experiences of the clinical endoscopists. The location, shape, and size are the typical patterns for the endoscopists to make the diagnosis decisions. The contrasting texture patterns also suggest the potential lesions. This study designed a novel rotation-tolerant image feature, TriZ, and demonstrated the effectiveness on both the rotation invariance and the lesion detection of three gastric lesion types, i.e., gastric polyp, gastric ulcer, and gastritis. TriZ achieved 87.0% in the four-class classification problem of the three gastric lesion types and the healthy controls, averaged over the twenty random runs of 10-fold cross-validations. Due to that biomedical imaging technologies may capture the lesion sites from different angles, the symmetric image feature extraction algorithm TriZ may facilitate the biomedical image based disease diagnosis modeling. Compared with the 378,434 features of the HOG algorithm, TriZ achieved a better accuracy using only 126 image features.

[1]  Miodrag Krstić,et al.  Complications of Peptic Ulcer Disease , 2011, Digestive Diseases.

[2]  Hee Seok Moon,et al.  Improving the Endoscopic Detection Rate in Patients with Early Gastric Cancer , 2015, Clinical endoscopy.

[3]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  T Banzato,et al.  Development of a deep convolutional neural network to predict grading of canine meningiomas from magnetic resonance images. , 2018, Veterinary journal.

[5]  Ying Xu,et al.  Prediction of pathogenicity islands in Enterohemorrhagic Escherichia coli O157:H7 using genomic barcodes , 2010, FEBS letters.

[6]  Yukio Yamada,et al.  Near-infrared noninvasive blood glucose prediction without using multivariate analyses: introduction of imaginary spectra due to scattering change in the skin. , 2015, Journal of biomedical optics.

[7]  Wilhelm Burger,et al.  Scale-Invariant Feature Transform (SIFT) , 2016 .

[8]  Kevin Noronha,et al.  Local configuration pattern features for age-related macular degeneration characterization and classification , 2015, Comput. Biol. Medicine.

[9]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[10]  Daniel R. Hyduke,et al.  Identifying radiation exposure biomarkers from mouse blood transcriptome , 2013, Int. J. Bioinform. Res. Appl..

[11]  Shuai Liu,et al.  RIFS: a randomly restarted incremental feature selection algorithm , 2017, Scientific Reports.

[12]  Yong Zhou,et al.  Advancing the prediction accuracy of protein-protein interactions by utilizing evolutionary information from position-specific scoring matrix and ensemble classifier. , 2017, Journal of theoretical biology.

[13]  Edward J. Ciaccio,et al.  Suggestions for automatic quantitation of endoscopic image analysis to improve detection of small intestinal pathology in celiac disease patients , 2015, Comput. Biol. Medicine.

[14]  Weixin Xie,et al.  Novel Hybrid Feature Selection Algorithms for Diagnosing Erythemato-Squamous Diseases , 2012, HIS.

[15]  Leontios J. Hadjileontiadis,et al.  Computer-aided capsule endoscopy images evaluation based on color rotation and texture features: An educational tool to physicians , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

[16]  Guoqing Wang,et al.  McTwo: a two-step feature selection algorithm based on maximal information coefficient , 2016, BMC Bioinformatics.

[17]  Anamaria Crisan,et al.  Whole-transcriptome profiling of thyroid nodules identifies expression-based signatures for accurate thyroid cancer diagnosis. , 2013, The Journal of clinical endocrinology and metabolism.

[18]  Max Q.-H. Meng,et al.  Saliency Based Ulcer Detection for Wireless Capsule Endoscopy Diagnosis , 2015, IEEE Transactions on Medical Imaging.

[19]  M. Saaiq,et al.  Marjolin's ulcers in the post-burned lesions and scars. , 2014, World journal of clinical cases.

[20]  Yi-Ping Phoebe Chen,et al.  Image based computer aided diagnosis system for cancer detection , 2015, Expert Syst. Appl..

[21]  Debjani Chakraborty,et al.  Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration. , 2017, Biomedical optics express.

[22]  Loris Nanni,et al.  Local binary patterns variants as texture descriptors for medical image analysis , 2010, Artif. Intell. Medicine.

[23]  Leontios J. Hadjileontiadis,et al.  A curvelet-based lacunarity approach for ulcer detection from Wireless Capsule Endoscopy images , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

[24]  Juanying Xie,et al.  Using support vector machines with a novel hybrid feature selection method for diagnosis of erythemato-squamous diseases , 2011, Expert Syst. Appl..

[25]  Jijun Tang,et al.  PhosPred-RF: A Novel Sequence-Based Predictor for Phosphorylation Sites Using Sequential Information Only , 2017, IEEE Transactions on NanoBioscience.

[26]  F. Zhou,et al.  Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images. , 2016, Biomedical optics express.

[27]  Jian Cheng,et al.  Visualizing deep neural network by alternately image blurring and deblurring , 2018, Neural Networks.

[28]  Carmen C. Y. Poon,et al.  Automatic Detection and Classification of Colorectal Polyps by Transferring Low-Level CNN Features From Nonmedical Domain , 2017, IEEE Journal of Biomedical and Health Informatics.

[29]  Vangelis Metsis,et al.  Heterogeneous Data Fusion to Type Brain Tumor Biopsies , 2009, AIAI.

[30]  Liujuan Cao,et al.  A novel features ranking metric with application to scalable visual and bioinformatics data classification , 2016, Neurocomputing.

[31]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[32]  Aymeric Histace,et al.  Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge , 2017, IEEE Transactions on Medical Imaging.

[33]  Seth W Perry,et al.  Second-harmonic generation scattering directionality predicts tumor cell motility in collagen gels , 2015, Journal of biomedical optics.

[34]  Ahmed S. Gado,et al.  Gastric cancer missed at endoscopy , 2013 .

[35]  P Deyhle,et al.  Results of endoscopic polypectomy in the gastrointestinal tract. , 1980, Endoscopy.

[36]  A. Jemal,et al.  Cancer statistics in China, 2015 , 2016, CA: a cancer journal for clinicians.

[37]  Qionghai Dai,et al.  Motion-corrected Fourier ptychography. , 2016, Biomedical optics express.

[38]  Matti Pietikäinen,et al.  Outex - new framework for empirical evaluation of texture analysis algorithms , 2002, Object recognition supported by user interaction for service robots.

[39]  Yukiyasu Kamitani,et al.  Sharpening of Hierarchical Visual Feature Representations of Blurred Images , 2018, eNeuro.

[40]  Tien Dat Nguyen,et al.  Enhanced Gender Recognition System Using an Improved Histogram of Oriented Gradient (HOG) Feature from Quality Assessment of Visible Light and Thermal Images of the Human Body , 2016, Sensors.

[41]  Nima Tajbakhsh,et al.  Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information , 2016, IEEE Transactions on Medical Imaging.

[42]  Ana Cristina Murillo,et al.  SURF features for efficient robot localization with omnidirectional images , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[43]  Daniel Pizarro-Perez,et al.  Computer-Aided Classification of Gastrointestinal Lesions in Regular Colonoscopy , 2016, IEEE Transactions on Medical Imaging.

[44]  D. Marsh,et al.  Tissue biomarkers of breast cancer and their association with conventional pathologic features , 2013, British Journal of Cancer.

[45]  Max Q.-H. Meng,et al.  Texture analysis for ulcer detection in capsule endoscopy images , 2009, Image Vis. Comput..

[46]  Gaotao Shi,et al.  CPPred-RF: A Sequence-based Predictor for Identifying Cell-Penetrating Peptides and Their Uptake Efficiency. , 2017, Journal of proteome research.

[47]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[48]  Quan Zou,et al.  Which statistical significance test best detects oncomiRNAs in cancer tissues? An exploratory analysis , 2016, Oncotarget.

[49]  Sina Farsiu,et al.  Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. , 2014, Biomedical optics express.

[50]  Prashant K. Kharat,et al.  Description of Rotation-Invariant Textures using Local Binary Pattern Features , 2014 .

[51]  Xin Yang,et al.  Automated Detection of Clinically Significant Prostate Cancer in mp-MRI Images Based on an End-to-End Deep Neural Network , 2018, IEEE Transactions on Medical Imaging.

[52]  Ying Xu,et al.  Large-Scale Analyses of Glycosylation in Cellulases , 2009, Genom. Proteom. Bioinform..

[53]  Jie Zheng,et al.  Identification of lesion images from gastrointestinal endoscope based on feature extraction of combinational methods with and without learning process , 2016, Medical Image Anal..

[54]  Yaonan Wang,et al.  Multiscale Bi-Gaussian Filter for Adjacent Curvilinear Structures Detection With Application to Vasculature Images , 2013, IEEE Transactions on Image Processing.

[55]  Mubashir Husain Rehmani,et al.  Computer-based classification of chromoendoscopy images using homogeneous texture descriptors , 2017, Comput. Biol. Medicine.

[56]  Xing Chen,et al.  PSPEL: In Silico Prediction of Self-Interacting Proteins from Amino Acids Sequences Using Ensemble Learning , 2017, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[57]  S. Woolf,et al.  Colorectal cancer screening and surveillance: clinical guidelines and rationale-Update based on new evidence. , 2003, Gastroenterology.

[58]  Samuel H. Hawkins,et al.  Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival Among Patients with Lung Adenocarcinoma , 2016, Tomography.

[59]  Yu Shang,et al.  Near-infrared diffuse optical monitoring of cerebral blood flow and oxygenation for the prediction of vasovagal syncope , 2014, Journal of biomedical optics.