The problem State of the art Proposed approach Achieved results Combined Radiology and Pathology Classification of Brain Tumors Rozpoznanie guza mózgu na podstawie obrazu radiologicznego i patologicznego Piotr Giedziun Supervisor: dr hab. in˙ z. Henryk Maciejewski 4 March 2016 Piotr Giedziun Wrocław University of Technology 4 March 2016 1 / 25
The problem State of the art Proposed approach Achieved results Outline The problem 1 State of the art 2 Proposed approach 3 Achieved results 4 Piotr Giedziun Wrocław University of Technology 4 March 2016 2 / 25
The problem State of the art Proposed approach Achieved results Definitions Cancer Cancer occurs when abnormal cells grow out of control Brain tumor Benign or Malignant Over time, a low-grade tumor can become a high-grade tumor Brain tumors are classified as grade I, grade II, or grade III, or grade IV Piotr Giedziun Wrocław University of Technology 4 March 2016 3 / 25
The problem State of the art Proposed approach Achieved results Brain tumor - Survival rate (5 years or more) F IGURE – Based on data from SEER 18 2005-2011, cancer.gov Piotr Giedziun Wrocław University of Technology 4 March 2016 4 / 25
The problem State of the art Proposed approach Achieved results Brain tumor - Survival by stage F IGURE – Ovarian cancer, Five-year stage-specific relative survival rates, adults (ages 15-99), Anglia Cancer Net- work, 1987-2008 Piotr Giedziun Wrocław University of Technology 4 March 2016 5 / 25
The problem State of the art Proposed approach Achieved results Brain tumor - Diagnosis process General Practitioner Neurologist MR or CT - Radiologists (tumor confirmed) (clear image) Neurosurgeon Benign Malignant Pathologist 2 Pathologists (final diagnosis) (final diagnosis) Piotr Giedziun Wrocław University of Technology 4 March 2016 6 / 25
The problem State of the art Proposed approach Achieved results Diagnosis problems Problems Diverse shapes, sizes and appearances of tumors Relies on histopathologic examination (biopsy examination) Waiting for tests and to start treatment F IGURE – Glioblastoma cells Radiology imaging is used only to establish location, size and whether it is benign and malignant tumor F IGURE – Oligodendroglioma cells Piotr Giedziun Wrocław University of Technology 4 March 2016 7 / 25
The problem State of the art Proposed approach Achieved results Diagnosis problems Problems Diverse shapes, sizes and appearances of tumors Relies on histopathologic examination (biopsy examination) Waiting for tests and to start treatment F IGURE – Glioblastoma cells Radiology imaging is used only to establish location, size and whether it is benign and malignant tumor Targets in the UK No more than 2 months wait between the date the hospital receives an urgent GP F IGURE – Oligodendroglioma cells referral for suspected cancer and starting treatment Piotr Giedziun Wrocław University of Technology 4 March 2016 7 / 25
The problem State of the art Proposed approach Achieved results Aims & Limitations Aims Research & build a segmentation mechanism for the MRI scans (ROI selection) Research & build a classifier based on the segmented radiological images (if possible) Combine the Pathology-based classification with radiology-based classifier Limitations Limited access to the MRI samples with the diadnosis provided by the doctor Conservative environment - only non-black box models Piotr Giedziun Wrocław University of Technology 4 March 2016 8 / 25
The problem State of the art Proposed approach Achieved results Related work Brain tumor segmentation The topic of brain segmentation is relatively popular thanks to BraTS challenge Several supervised and unsupervised algorithms were proposed Random Decision Forest that classifies voxels Fuzzy C-means clustering Mean Shift and K-means clustering Brain tumor classification Slightly less popular subject (current diagnosis fully rely on histopathology imaging) Feature extraction Extraction of structure information Feature selection GLCM (Gray-Level Co-occurrence Matrix) Piotr Giedziun Wrocław University of Technology 4 March 2016 9 / 25
The problem State of the art Proposed approach Achieved results Influential articles Joana Festa and Sérgio Pereira and José António Mariz and Nuno Sousa and Carlos A. Silva Automatic Brain Tumor Segmentation of Multi-sequence MR images using Random Decision Forests Proceedings of NCI-MICCAI BRATS 2013 , Nagoya, Japan, 2013 Nitish Zulpe and Vrushsen Pawar GLCM Textural Features for Brain Tumor International Journal of Computer Science , 2012 Hassan Khotanlou, Olivier Colliot, and Isabelle Bloch Automatic brain tumor segmentation using symmetry analysis and deformable models Nationale Superieure des Telecommunications , 2007 Piotr Giedziun Wrocław University of Technology 4 March 2016 10 / 25
The problem State of the art Proposed approach Achieved results Brain tumor - Modified diagnosis process General Practitioner Neurologist MR or CT - Radiologists & piece of software (tumor confirmed & partial diagnosis ) (clear image) Neurosurgeon Benign Malignant Pathologist 2 Pathologists (final diagnosis) (final diagnosis) Piotr Giedziun Wrocław University of Technology 4 March 2016 11 / 25
The problem State of the art Proposed approach Achieved results Data set 900 7000 550 800 6000 500 700 Average intensity 5000 450 Max intensity 600 4000 400 Width 500 3000 350 400 2000 300 300 200 1000 250 100 0 200 0 5 10 15 20 25 30 35 0 5 10 15 20 25 30 35 0 5 10 15 20 25 30 35 Sample No. Sample No. Sample No. F IGURE – Plots of different attributes of the data set Angle 1 Angle 2 Angle 3 F IGURE – Viewing angles of MRI scan Piotr Giedziun Wrocław University of Technology 4 March 2016 12 / 25
The problem State of the art Proposed approach Achieved results Data set Summary 27 cases with lower grade glioma tumors 13 of them with Oligodendroglioma and 14 with Astrocytoma Each case has 3 or 4 MRI scans (T1, T1C, FLAIR, and T2) Provided samples were taken using different hardware 900 7000 550 Angle 1 Angle 2 Angle 3 800 6000 500 700 Average intensity 5000 450 Max intensity 600 4000 Width 400 500 3000 350 400 2000 300 300 200 1000 250 100 0 200 0 5 10 15 20 25 30 35 0 5 10 15 20 25 30 35 0 5 10 15 20 25 30 35 Sample No. Sample No. Sample No. F IGURE – Plots of different attributes of the data set F IGURE – Viewing angles of MRI scan Piotr Giedziun Wrocław University of Technology 4 March 2016 13 / 25
The problem State of the art Proposed approach Achieved results Pre-processing Histogram 5000 Tresholded binary map Extracted skull binary map 4000 Numer of pixels 3000 2000 1000 0 0 50 100 150 200 250 Intensity level F IGURE – Process of skull extraction FLAIR skull figure T2 skull figure F IGURE – Skulls properties in FLAIR and T2 Piotr Giedziun Wrocław University of Technology 4 March 2016 14 / 25
The problem State of the art Proposed approach Achieved results Pre-processing Histogram before FLAIR before 6000 5000 Numer of pixels 4000 3000 2000 1000 0 0 20 40 60 80 100 120 140 160 180 Intensity level Histogram after FLAIR after 8000 7000 Numer of pixels 6000 5000 4000 3000 2000 1000 0 0 20 40 60 80 100 120 140 160 180 Intensity level F IGURE – Median filter effect on image histogram Piotr Giedziun Wrocław University of Technology 4 March 2016 15 / 25
The problem State of the art Proposed approach Achieved results Segmentation - K-Means The silhouette plot for the various clusters. The visualization of the clustered data. 3 Feature space for the Intensity 14 12 10 2 Cluster label 8 6 4 2 0 2 1 1.2 Feature space for the Y 1.0 0.8 0 0.0 0.6 0.2 0.4 0.4 Feature space for the X 0.6 0.1 0.0 0.2 0.4 0.6 0.8 1.0 0.8 0.2 1.0 The silhouette coefficient values 0.0 1.2 F IGURE – Silhouette analysis for K-Means(k=5) Piotr Giedziun Wrocław University of Technology 4 March 2016 16 / 25
The problem State of the art Proposed approach Achieved results Segmentation - Combined K-Means segmentation Symetry analysis segmentation Result K-Means segmentation Symetry analysis segmentation Result K-Means segmentation Symetry analysis segmentation Result F IGURE – Segmentation with results Piotr Giedziun Wrocław University of Technology 4 March 2016 17 / 25
The problem State of the art Proposed approach Achieved results Segmentation - Alternatives Agglomerative Clustering vs K-Means 120 Agglomerative Modified K-Means vs K-Means Modified K-Means vs K-Means 120 K-Means 120 Modified K-Means Mini Batch K-Means 100 K-Means K-Means 100 100 80 80 80 Scores 60 Scores Scores 60 60 40 40 40 20 20 20 0 3 4 5 6 7 8 0 0 3 4 5 6 7 8 Number of clusters 3 4 5 6 7 8 Number of clusters Number of clusters F IGURE – Agglomerative cluste- F IGURE – Mini K-Means F IGURE – K-Means with position ring Piotr Giedziun Wrocław University of Technology 4 March 2016 18 / 25
Recommend
More recommend
