Color Detection in Dermoscopy Images Based on Scarce Annotations
Dermatologists often prefer clinically oriented Computer Aided Diagnosis (CAD) Systems. However, the development of such systems is not straightforward due to lack of detailed image annotations (medical labels and segmentation of their corresponding regions). Most of the times we only have access to medical labels that are not sufficient to learn proper models. In this study, we address this issue using the Correspondence-LDA algorithm. The algorithm is applied with success to the identification identification of relevant colors in dermoscopy images, obtaining a precision of 82.1 % and a recall of 90.4 %.
KeywordsMelanoma diagnosis Correspondence-LDA Image annotation Color detection
This work was funded by grant SFRH/BD/84658/2012 and by the FCT project FCT [UID/EEA/50009/2013].
- 3.Argenziano, G., Soyer, H.P., De Giorgi, V., et al.: Interactive atlas of dermoscopy. In: EDRA (2000)Google Scholar
- 6.Barata, C., Figueiredo, M.A.T., Celebi, M.E., Marques, J.S.: Color identification in dermoscopy images using gaussian mixture models. In: ICASSP 2014, pp. 3611–3615 (2014)Google Scholar
- 7.Blei, D., Jordan, M.: Modeling annotated data. In: 26th ACM SIGIR, pp. 127–134. ACM (2003)Google Scholar
- 8.Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR 2005, vol. 2, pp. 524–531. IEEE (2005)Google Scholar