In Silico Brain Tumor Research Center Emory University, Atlanta, GA Classification of Brain Tumor Regions S. Cholleti, *L. Cooper, J. Kong, C. Chisolm,

Slides:



Advertisements
Similar presentations
Multiclass SVM and Applications in Object Classification
Advertisements

CS4670 / 5670: Computer Vision Bag-of-words models Noah Snavely Object
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
CS771 Machine Learning : Tools, Techniques & Application Gaurav Krishna Y Harshit Maheshwari Pulkit Jain Sayantan Marik
Biased Normalized Cuts 1 Subhransu Maji and Jithndra Malik University of California, Berkeley IEEE Conference on Computer Vision and Pattern Recognition.
Bag-of-features models Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
Image segmentation. The goals of segmentation Group together similar-looking pixels for efficiency of further processing “Bottom-up” process Unsupervised.
Lecture 28: Bag-of-words models
TextonBoost : Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation J. Shotton*, J. Winn†, C. Rother†, and A.
Berkeley Vision GroupNIPS Vancouver Learning to Detect Natural Image Boundaries Using Local Brightness,
Bag-of-features models
Cliff Rhyne and Jerry Fu June 5, 2007 Parallel Image Segmenter CSE 262 Spring 2007 Project Final Presentation.
1 How do ideas from perceptual organization relate to natural scenes?
K-means Based Unsupervised Feature Learning for Image Recognition Ling Zheng.
Heather Dunlop : Advanced Perception January 25, 2006
Automatic Detection And Classification Of Microcalcifications In Digital Mammograms Institute for Brain and Neural Systems Brown University Providence.
Clinical Trials, TCGA: Deep Integrative Research RT, Imaging, Pathology, “omics” Joel Saltz MD, PhD Director Center for Comprehensive Informatics.
CaGrid, Fog and Clouds Joel Saltz MD, PhD Director Center for Comprehensive Informatics.
Review: Intro to recognition Recognition tasks Machine learning approach: training, testing, generalization Example classifiers Nearest neighbor Linear.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Gene expression profiling identifies molecular subtypes of gliomas
Integrative Analysis of Pathology, Radiology and High Throughput Molecular Data Joel Saltz MD, PhD Director Center for Comprehensive Informatics.
Integrative Analysis of Pathology, Radiology and High Throughput Molecular Data Joel Saltz MD, PhD Director Center for Comprehensive Informatics.
ENDA MOLLOY, ELECTRONIC ENG. FINAL PRESENTATION, 31/03/09. Automated Image Analysis Techniques for Screening of Mammography Images.
Unsupervised Object Segmentation with a Hybrid Graph Model (HGM) Reporter: 鄭綱 (6/14)
ASPRS Annual Conference 2005, Baltimore, March Utilizing Multi-Resolution Image data vs. Pansharpened Image data for Change Detection V. Vijayaraj,
Building local part models for category-level recognition C. Schmid, INRIA Grenoble Joint work with G. Dorko, S. Lazebnik, J. Ponce.
Department of Radiology and Imaging Sciences Division of Neuroradiology University School of Medicine.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Texture We would like to thank Amnon Drory for this deck הבהרה : החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Texture We would like to thank Amnon Drory for this deck הבהרה : החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Object Recognition in Images Slides originally created by Bernd Heisele.
Handwritten Hindi Numerals Recognition Kritika Singh Akarshan Sarkar Mentor- Prof. Amitabha Mukerjee.
Veggie Vision: A Produce Recognition System R.M. Bolle J.H. Connell N. Haas R. Mohan G. Taubin IBM T.J. Watson Resarch Center Presented by Chris McClendon.
MEDICI Project Update Jayashree Kalpathy-Cramer Karl Helmer, Artem Mamanov Massachusetts General Hospital CTIIP Coordination Call 29 July 2015.
Mammogram Analysis – Tumor classification - Geethapriya Raghavan.
A New Method for Crater Detection Heather Dunlop November 2, 2006.
CS654: Digital Image Analysis
A Statistical Approach to Texture Classification Nicholas Chan Heather Dunlop Project Dec. 14, 2005.
THIRD CLASSIFICATION OF MICROCALCIFICATION STAGES IN MAMMOGRAPHIC IMAGES THIRD REVIEW Supervisor: Mrs.P.Valarmathi HOD/CSE Project Members: M.HamsaPriya( )
Texture Analysis and Synthesis. Texture Texture: pattern that “looks the same” at all locationsTexture: pattern that “looks the same” at all locations.
TUMOR BURDEN ANALYSIS ON CT BY AUTOMATED LIVER AND TUMOR SEGMENTATION RAMSHEEJA.RR Roll : No 19 Guide SREERAJ.R ( Head Of Department, CSE)
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
Representing, Learning, and Recognizing Non-Rigid Textures and Texture Categories Svetlana LazebnikCordelia SchmidJean Ponce Beckman InstituteGravir LaboratoryBeckman.
The Contribution of caBIG and In Silico Resources to Glioblastoma Research Daniel J. Brat MD, PhD Department of Pathology and Laboratory Medicine Emory.
Face Detection 蔡宇軒.
PD: Joel Saltz, MD, PhD PI: Daniel J. Brat MD, PhD Emory University School of Medicine In Silico Center for Brain Tumor Research.
Lecture IX: Object Recognition (2)
Lecture 21: GIS Analytical Functionality (V)
Pathology Spatial Analysis February 2017
In Search of the Optimal Set of Indicators when Classifying Histopathological Images Catalin Stoean University of Craiova, Romania
CLASSIFICATION OF TUMOR HISTOPATHOLOGY VIA SPARSE FEATURE LEARNING Nandita M. Nayak1, Hang Chang1, Alexander Borowsky2, Paul Spellman3 and Bahram Parvin1.
Performance of Computer Vision
Joel Saltz MD, PhD Director Center for Comprehensive Informatics
Color-Texture Analysis for Content-Based Image Retrieval
Schizophrenia Classification Using
By Suren Manvelyan, Crocodile (nile crocodile?) By Suren Manvelyan,
Cyclin-Dependent Kinase 2 Promotes Tumor Proliferation and Induces Radio Resistance in Glioblastoma  Jia Wang, Tong Yang, Gaofeng Xu, Hao Liu, Chunying.
What is Pattern Recognition?
Finding Clusters within a Class to Improve Classification Accuracy
Texture Analysis for Pulmonary Nodules Interpretation and Retrieval
Texture Classification of Normal Tissues in Computed Tomography
Focus on central nervous system neoplasia
Cécile L. Maire, Keith L. Ligon  Cancer Cell 
Grouping/Segmentation
Earthen Mounds Recognition Using LiDAR Images
Image Processing and Multi-domain Translation
Levels of neutrophil infiltration into gliomas correlate with tumor grades and tumor progression. Levels of neutrophil infiltration into gliomas correlate.
Presentation transcript:

In Silico Brain Tumor Research Center Emory University, Atlanta, GA Classification of Brain Tumor Regions S. Cholleti, *L. Cooper, J. Kong, C. Chisolm, D. Brat, D. Gutman, T. Pan, A. Sharma, C. Moreno, T. Kurc, J. Saltz

In Silico Brain Tumor Research Datasets: histologyneuroimaging clincal\pathology Integrated Analysis molecular In Silico Research Centers of Excellence

Morphometry of the Gliomas Oligodendroglioma Astrocytoma Nuclear Morphology: Vessel Morphology: Necrosis:

Morphometric Analysis PAIS Database Parallel Matlab Scientific Queries ? (90+ Million Nuclei)

Morphological Correlates of Genomic Analysis Nuclear Characterization Region Filtering Nuclear Classification Nuclear priors Class Summary Statistics ? Proneural Neural Classical Mesenchymal (Neoplastic Oligodendroglia, Neoplastic Astrocytes, Reactive Endothelial,...)

Morphological Correlates of Genomic Analysis Nuclear Characterization Tissue Classification Nuclear Classification Nuclear Priors Class Summary Statistics ? Proneural Neural Classical Mesenchymal (Neoplastic Oligodendroglia, Neoplastic Astrocytes, Reactive Endothelial,...)

Region Classification Classify regions as normal or tumor –exclude nuclei in normal tissue regions –conditional probabilities for nuclear classification texton approach –Multiple layers of classification add robustness –Combines supervised and unsupervised classifiers References –Malik, J., Belongie, S., Shi, J., and Leung, T Textons, contours and regions: Cue integration in image segmentation. In Proceedings IEEE 7th International Conference on Computer Vision, Corfu, Greece, pp. 918–925. –O. Tuzel, L. Yang, P. Meer, and D. J. Foran. Classification of hematologic malignancies using texton signatures. Pattern Anal. Appl., 10(4): ,2007. –M. Varma and A. Zisserman. Texture classification: Are filter banks necessary? In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages , 2003.

Tissue Classifier: Training Train Region Classifier SVM For each training region: Extract “Textures” Training Regions Texton Library For each class (texture classification): Region “Textures” Texton Histogram

Tissue Classifier: Testing Texton Library SVM Region “Textures” Texton Histogram Test Region Region Classification

Dataset Human Annotated regions –18 whole-slide images –Normal, GBM (IV), Astrocytoma (II & III), Oligodendroglioma (II & III), Oligoastrocytoma (II & III) Region type# Normal45 Astrocytoma20 Oligodendroglioma54 Oligoastrocytoma29 Glioblastoma18 Total166

Experiment and Results ExperimentClassification accuracy (%) Normal vs Tumor98 Oligodendroglioma vs Oligoastrocytoma86 Oligodendroglioma vs Astrocytoma92 Olgiodendroglioma vs Glioblastoma91 Oligoastrocytoma vs Astrocytoma80 Oligoastrocytoma vs Gligoblastoma76 Astrocytoma vs Glioblastoma70 30 x 2 cross-validation Randomly pick 50% data for training and 50% for testing. Classification accuracy: Average(correct regions / total regions)

Extension: Region Masking

Questions