Improving the breast cancer diagnosis using digital repositories

Transcript

1. breast cancer diagnosis using digital repositories improving the César Suárez Ortega uaa@ceta-ciemat.es 18-20 March 2013 International Work-Conference on Bioinformatics and Biomedical Engineering
2. The IMED project
3. introduction » IMED is a collaboration among: » CETA-CIEMAT (Trujillo, Spain) » INEGI (Porto, Portugal) » FMUP-HSJ (Porto, Portugal) » Since 2008 » Created to ease the cancer diagnosis. » Focused on breast cancer.
4. Breast cancer is most common cancer for women. According to World Health Organization: http://www.who.int/cancer/events/breast_cancer_month/en/ 1 1 1
5. Early detection is the cornerstone of its control.
6. Double checking of cases reduces the ratio of missed cancer R. Ramos-Pollan, et al., Discovering Mammography-based Machine Learning Classifiers for Breast Cancer Diagnosis. Journal of Medical Systems (9 April 2011), pp. 1-11. 1 1
7. But this is expensive!
8. But this is expensive! Solutions?
9. But this is expensive! Solutions? Computer-aided diagnosis
10. But this is expensive! Solutions? Computer-aided diagnosis CAD Systems 1 1
11. what are CAD systems? » Assistance in the diagnosis of medical images » Multiple disciplines are combined: » Artificial intelligence » Digital image processing » Radiology
12. what are CAD systems? » Assistance in the diagnosis of medical images » Multiple disciplines are combined: » Artificial intelligence » Digital image processing » Radiology They don't replace doctors, they support them.
13. MIWAD BCDR MLCs three pillars Breast Cancer Digital Repository Machine Learning Classifiers Mammography Image Workstation for Analysis and Diagnosis
14. MIWAD BCDR MLCs three pillars BCDR – A repository of annotated breast cancer cases. MLCs Machine learning classifiers for breast cancer diagnosis MIWAD – A workstation prototype with a CAD system.
15. MIWAD BCDR MLCs
16. MLCs » Artificial intelligent systems. » They learn from data.
17. benign malign Examples MLC info + classification info + classification
18. benign malign Examples MLC – benign? malign? benign classification info + classification info + classification info
19. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them!
20. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree
21. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule
22. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks
23. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks Genetic Programming
24. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks Genetic Programming Support Vector Machines
25. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks Genetic Programming Support Vector Machines Clustering
26. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks Genetic Programming Support Vector Machines Clustering Bayesian Networks
27. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks Genetic Programming Support Vector Machines Clustering Bayesian Networks Inductive Logic
28. MLCs » Artificial intelligent systems. » They learn from data. » Lot of them! Decision Tree Association Rule Neural Networks Genetic Programming Support Vector Machines Clustering Bayesian Networks Inductive Logic Sparse Dictionary
29. What is the best one for breast cancer?
30. We are working on it :)
31. current results » GRID and HPC to speed up the research. » Metrics » ROC → True positives VS. False positives » AUC → Probability of a true positive » Our classifiers?
32. current results » GRID and HPC to speed up the research. » Metrics » ROC → True positives VS. False positives » AUC → Probability of a true positive » Our classifiers? AUC = 85%
33. What data we use to train our MLCs?
34. MIWAD BCDR MLCs
35. BCDR is a wide-ranging annotated repository of anonymous breast cancer studies
36. BCDR » Our reference dataset for MLCs. » It contains a custom subset of DICOM and: » Reviewed by specialists and biopsy proven » Cases classified using BI-RADS » Useful for researchers. 23 17 per lesion region intesity, texture and shape features clinical features per case
37. data model patients images lesions segmentations classifications studies * * * * * *
38. data model patients images lesions segmentations classifications studies * * * * * * ?
39. segmentation of a lesion
40. two flavours BCDR-FMR 1010 cases 795 segmented lesions 3073 mammographies 720x1168 TIFF images (8bpp)
41. two flavours BCDR-DMR 600 cases 828 segmented lesions 2837 mammographies 3328x4084 TIFF images (14bpp)
42. two flavours BCDR-DMR 600 cases 828 segmented lesions 2837 mammographies 3328x4084 TIFF images (14bpp) + 2073 ultrasound images 800x600 (8bpp)
45. http://bcdr.inegi.up.pt
46. http://bcdr.inegi.up.pt
47. http://bcdr.inegi.up.pt
48. http://bcdr.inegi.up.pt
49. MIWAD BCDR MLCs
50. MIWAD » A workstation for analysing and diagnosing. » It's multiplatform (Windows, Linux & Mac) » Composed by two connected apps: MIWAD-DB MIWAD-CAD
51. MIWAD-DB » It manages... » ...the clinical data » ...the mammographies » BCDR as data source. » It operates over BCDR data. » Executes MLCs with a 1-click process.
53. patients studies lesions segmentations classifications
54. mammographies
55. classifiers
56. results
57. MIWAD-CAD » Screening tool (based on TUDOR Viewer) » It includes image processing tools. » Tools to help in the segmentation process. » Three functions: 1 It stores the segmentations in BCDR. 2 It calculates image features. 3 It helps doctors to find lessions.
58. CAPTURAS CAD
61. this is real
63. CAD DB Bruno São João Hospital
64. summarizing...
65. MIWAD BCDR MLCs BCDR – A repository of annotated breast cancer cases. MLC Machine learning classifiers for breast cancer diagnosis MIWAD – A workstation prototype with a CAD system.
66. MIWAD BCDR MLCs BCDR is used to train MLCs
67. MIWAD BCDR MLCs BCDR is the data source of MIWAD...
68. MIWAD BCDR MLCs ...and MIWAD feeds the BCDR
69. MIWAD BCDR MLCs So, MIWAD helps to improve the MLCs
70. MIWAD BCDR MLCs The MLCs are integrated in MIWAD
71. future work » IMED goes educational! » MIWAD as a training app for radiologists: » Web architecture & responsive design. » Auto-evaluation using MLCs. » BCDR as a formative resource. » Continuation of the improvement of MLCs. (+90% AUC) » Certification for MLCs » Continuation of the BCDR growth (searching new sources)
72. conclusions » CAD systems can achieve great results in: » Improving the breast cancer diagnosis » Training specialists » Specialists demand better educational apps (difficult to find) » All is about data! » It's difficult to get reliable data. » BCDR is the most complete open breast cancer repository. » MLCs data
73. CETA-CIEMAT acknowledges the support received from the European Regional Development Fund through its Operational Programme Knowledge-based Economy.
74. any questions? thanks for your attention! :)