1. Automatic determination of cardiovascular risk from thoracic CT scans using a coronary calcium atlas I. Išgum, M. Prokop, P.C. Jacobs, M.J. Gondrie, W.P.Th.M. Mali, M.A. Viergever, B. van Ginneken Image Sciences Institute University Medical Center Utrecht NFBI, 10. 09. 2009.

2. Cardiovascular disease Class of diseases that involve the heart or blood vessels Usually used to refer to diseases related to atherosclerosis Condition in which an arterial wall thickens

3. Atherosclerosis Arterial calcifications High density lesions inside arteries visible in CT scans Calcium score Value representing amount of arterial calcifications Independent marker of cardiovascular disease

4. Calcium scoring in clinical practice Possible calcifications extracted by thresholding Calcifications are Identified manually Subsequently automatically quantified

6. Goal Automatic detection and quantification of coronary calcifications in thoracic CT scans from lung cancer screening to determine cardiovascular risk status

8. Dutch-Belgian lung cancer screening trial (NELSON):

9. ~1% subjects - detected lung cancer (baseline)

11. ECG- synchronized Not ECG- synchronized

12. Challenges for automatic coronary calcium scoring Thoracic CT scans from screening Non-ECG synchronization Cardiac motion Non-contrast enhancement Coronaries not visible

13. Non contrast enhanced Contrast enhanced

14. Challenges for automatic coronary calcium scoring Thoracic CT scans from screening Non-ECG synchronization Cardiac motion Non-contrast enhancement Coronaries not visible Low-dose Noise with same intensity as calcium

15. Pattern recognition system Candidate extraction Thresholding (130 HU) 3D connected-component labeling Discarding too small (noise) and too large (bony structures) candidates Feature computation Position (6 features) Texture and size (41 features) Classification Two stage classification (kNN with feature selection)

16. Position features For accurate calcium detection Location of the coronaries very important Coronaries not visible Segmentation not feasible Alternative Segmentation other anatomical structures to estimate location of the coronaries* Time consuming, less accurate * Isgum et al; Med Phys 2007; 34:1450-1461

17. Position Features Calcifications in the coronaries are visible Design coronary calcium atlas Estimate location of the coronaries using calcifications in them Estimate probability for spatial appearance of calcifications

18. Data 121 thoracic CT scans 16 x 0.75 mm collimation 0.7 mm section thickness 1 mm increment

19. 121 scans 51 for creating coronary calcium atlas 70 for designing pattern recognition system 35 training 35 testing 1 atlas 50 references elastically registered* (coronary calcium atlas) elastically registeredto compute position features * http://elastix.isi.uu.nl/

20. Coronary calcium atlas Probabilistic segmentation Atlas with segmentation

21. Automatic system Reference standard 72% sensitivity; 0.9 false positives/scan

22. Risk categories based on the coronary score 5 standard risk categories based on theAgatston score in the coronary arteries* * Rumberger et al; AJR 2003; 181(3):743-74

23. Reference standard Automaticresult

24. Reference standard Automaticresult 83% - agreement

25. Reference standard Automaticresult 83% - agreement 14% - one category off

26. Reference standard Automaticresult 83% - agreement 3% - two categories off 14% - one category off

27. Conclusion Automatic calcium scoring from low-dose, non-ECG synchronized thoracic CT scans appears feasible In lung cancer screening cardiovascular risk can be estimated automatically