Translational health research
Download as PPT, PDF
1 like265 views
Cervical cancer rates have dramatically declined in the United States due to widespread Pap smear screening and the ability to treat precancerous lesions before they develop into cancer. The introduction of the Pap test in the 1940s allowed early detection and helped reduce cervical cancer incidence and mortality rates by over 60% between 1955 and 1992. New automated screening systems using digital imaging and computational analysis now further aid in screening and may help expand screening to rural areas through remote image analysis.
Translational health research
- 1. Translational Health Research Cervical cancer
- 4. YESTERDAY In 1940s, cervical cancer was a major cause of death among women of childbearing age in the United States. TODAY Cervical cancer once one of the most common cancers affecting U.S. women now ranks 14th in frequency. Because precancerous lesions found by Pap smears can be treated and cured before they develop into cancer, and because cervical cancer is often detected before it becomes advanced, the incidence and death rates for this disease are relatively low. HOW? Better visualization:- Introduction Papanicolaou (Pap) smear test in which a sample of cervical cells is examined under a microscope to detect cellular abnormalities. The incidence of invasive cervical cancer declined dramatically. Between 1955 and 1992, U.S. cervical cancer incidence and death rates declined by more than 60%. and automation Automation:- Introduction of ThinPrep速, FocalPoint速 (FDA approved) systems which screens and suggest potential cases to cytopathologists http://report.nih.gov/NIHfactsheets/ViewFactSheet.aspx?csid=76 http://report.nih.gov/NIHfactsheets/ViewFactSheet.aspx?csid=76
- 5. Cancer Facts and Figures 2012 America cancer society
- 6. Why cant I just mimic the existing technology?
- 7. Experinced Cytopathologists COST Accuracy (False neg.) Massive screening OUR CONCERN Automated imaging Computational Facility Extension to rural areas Business Model Awareness . .
- 9. Monolayer Preparation Collection of cervical smears from transformation zone and endo cervix by Ayers spatula and endo-cervical brush respectively into polysol solution. Centrifugation at 2000-4000 rpm for 5 mins, supernatant discarded and re-suspension of pallet in fresh polysol solution Preparation of cervical monolayer smear using cyto-centrifuge with appropriate funnel and filter cards. Fixation of the smear with 95% ethanol for 10 mins. Pap staining of the monolayer cervical smear using hematoxylin (stains nucleus blue), orange G (stains cytoplasm of superficial cells pink) and eosine-azure (stains cytoplasm of intermediate cells blue to green) 9
- 10. Feature Identification & Significance No. Nuclear Feature Significance 1 Brightness of Nucleus Most Significant 2 Area of Nucleus Significant 3 Irregularity of the Nuclear Significant Membrane 4 Nucleus Roundness Significant 5 Size of Chromatin Granule Significant Table shows the importance of feature significance in 40 X magnification 12
- 11. Presence of Variations in Normal Nuclei A set of normal nuclei cropped from images of size 2048 x 1536. Magnification 40X. 13
- 12. Presence of Variations in Abnormal Nuclei A set of abnormal nuclei. Image size 404 x 270. Courtesy by International Agency for Research on Cancer cervical cells image database. Magnification 40X 14
- 13. Ambiguity in Nuclear Features a b c d a.Malignant Intermediate Cell Nucleus. b.Normal Parabasal Cell Nucleus c.Malignant Superficial Cell Nucleus. d.Normal Parabasal Cell Nucleus 15
- 14. Implementating out of box Features and Classification Classification Classification Feature Feature Quantification Quantification Feature Feature Identification Identification 16
- 15. Nucleus Localization & Segmentation A three phase technique is adopted for segmentation of nucleus. 17
- 16. Color Imbalance As we are intend to implement color image processing , there should be no disruptions in color cue Sources of description a) Light source (temperature dependent) b) Digital camera (biasing of any one channel of R,G,B) CIE standard Color gamut provided and limitation of screen display 18
- 17. White Balancing Cont. Pap stained image of a Normal Pap stained image of a Abnormal smear under microscope at 40x smear under microscope at 40x White Balancing Step White Balanced Images 19
- 18. Image Enhancement Top two images are white balanced. Bottom two are enhanced with CLAHE 20
- 20. Segmentaion performance Level set Method Morphological filtering Bilateral Initial Color Original L Plane Saturation Filtered Mask Deconv image of Lab + Color Intensity image output space 22 https://www.dropbox.com/sh/p2kt9e181mdx9eh/NfHrVzhrTC
- 21. Results of Active Contour(Level Sets) 23
- 24. Target Features of the nucleus for computer assisted diagnosis 1. Area 1. Mean value of Blue color value on 2. Perimeter nucleus 2. Entropy of red color values of nucleus 3. ConvexArea 3. Entropy of Green color values of 4. Filled area nucleus 5. Eccentricity 4. Entropy of Blue color values of 6. MajorAxisLength nucleus 7. MinorAxisLength 5. contrast of gray values of nucleus 8. EquivDiameter 6. correlation of gray values of nucleus 9. MinorAxisLength 7. energy homogeneity of gray values of nucleus 10. Standard deviation of Red color values on nucleus 8. standard deviation of Laws mask response 11. Mean value of Red color value on nucleus 9. mean of Laws mask response 12. Standard deviation of Green color values 10. standard deviation of LBP(local on nucleus binary pattern) response 13. Mean value of Green color value on 11. mean of LBP response nucleus 14. Standard deviation of Blue color values on nucleus 26
- 25. SVM based classification for 25 nuclear features 28
Editor's Notes
- #17: Microsoft Engineering Excellence Microsoft Confidential