POS0256 AUTOMATED CAPILLARY DETECTION AND IMAGE ANALYSIS SOFTWARE IN CAPILLAROSCOPY: CAPILLARY.IO

Abstract

Background: A nailfold capillaroscopy procedure is a non-invasive, low-cost, and well-established examination that can be used to diagnose several rheumatic autoimmune diseases and support the necessary follow-up of patients. There are two main elements to nailfold capillaroscopy: image acquisition and image interpretation. Both of these can present challenges: we need to ensure that the best possible images are captured, and we need to define the enlarged capillaries, capillary loss and pericapillary hemorrhages objectively. We introduce Capillary.io, an automatic image reading system able to recognize capillaries in images obtained with any microscope, generate automatic measurements of each capillary and take advantage of this information to report capillary morphology. Together it allows a comprehensive analysis that is capable of producing detailed reports for each patient. Objectives: The primary outcome was general sensitivity and specificity, using images assessed by expert capillaroscopists as the gold standard. Methods: 6500 images previously analyzed by capillaroscopists from GREC were compared with Capillary.io. Capillary morphology (enlarged capillaries, tortuosities, ramifications, megacapillaries, hemorrhages) of each of the capillaries contained in each of the images was analyzed manually by at least one expert capillaroscopist. Subsequently, the automatic image interpretation system was used to fully automatically analyze each of the capillaries contained in each image and the results obtained were compared. Results: Overall, a total of 78.347 capillaries were compared, of which 47.734 were normal capillaries, 21.991 enlarged capillaries, 2672 megacapillaries, 8512 tortuosities, 1322 ramifications and 5149 hemorrhages. Capillary.io was able to detect 38.101 normal capillaries, 19.126 enlarged capillaries, 2389 megacapillaries, 5698 tortuosities, 718 ramifications and 3706 hemorraghes. Capillary.io presented a sensitivity (S) of 79.82% and a specificity (E) of 82% in the recognition of normal capillaries. The automatized system was able to recognize enlarged capillaries with a sensitivity of 86.97% and a specificity of 81.38%. Megacapillaries were detected with 89.41% sensitivity and 78.75% specificity. Similarly, the system was able to detect tortuosities (S 66.94%; E 67.71%), ramifications (S 54.34%; E 58.61%) and hemorrhages (S 71.36; E 73.97%). Conclusion: Capillary.io is a simple, easy-learning web-based system to get interpretation of nailfold capillaroscopic images. It may be a very useful tool to standardize the interpretation of capillaroscopic pictures and could provide great research in that field.