S Seidenari1, G Pellacani, C Grana. 1. Departments of Dermatology and Computer Engineering, University of Modena and Reggio Emilia, 41100 Modena, Italy. sedenar@unimo.it
Abstract
BACKGROUND: The assessment of colours is essential for the diagnosis of malignant melanoma (MM), both for pattern analysis on dermoscopic images, and when employing semiquantitative methods. OBJECTIVES: To develop a computer program for colour assessment in MM images mimicking the human perception of lesion colours, and to compare the automatic colour evaluation with one performed by human observers. METHODS: A colour palette comprising six colour groups (black, dark brown, light brown, blue-grey, red and white) was created by selecting single colour components inside melanocytic lesion images acquired by means of a digital videomicroscope, and was implemented in the image analysis program. Subsequently, colours were assessed by the computer program on 331 melanocytic lesion images composing our image database, and the results were compared with the evaluation of lesion colours performed by the clinician. RESULTS: The black, white and blue-grey colours were more frequently found in MMs than in naevi, both by the clinicians and by the computer. In MM images we observed 4.27 +/- 1.14 colours (mean + or - SD) per lesion, as opposed to 3.22 +/- 0.68 in naevi. The correlation between clinical and computer evaluation of the colours was very good, with a value of 0.781 for overall assessment. CONCLUSIONS: This innovative method for automatic colour evaluation, reproducing clinical assessment of melanocytic lesion colours, may provide numerical parameters to be employed for computer-aided diagnosis of MM.
BACKGROUND: The assessment of colours is essential for the diagnosis of malignant melanoma (MM), both for pattern analysis on dermoscopic images, and when employing semiquantitative methods. OBJECTIVES: To develop a computer program for colour assessment in MM images mimicking the human perception of lesion colours, and to compare the automatic colour evaluation with one performed by human observers. METHODS: A colour palette comprising six colour groups (black, dark brown, light brown, blue-grey, red and white) was created by selecting single colour components inside melanocytic lesion images acquired by means of a digital videomicroscope, and was implemented in the image analysis program. Subsequently, colours were assessed by the computer program on 331 melanocytic lesion images composing our image database, and the results were compared with the evaluation of lesion colours performed by the clinician. RESULTS: The black, white and blue-grey colours were more frequently found in MMs than in naevi, both by the clinicians and by the computer. In MM images we observed 4.27 +/- 1.14 colours (mean + or - SD) per lesion, as opposed to 3.22 +/- 0.68 in naevi. The correlation between clinical and computer evaluation of the colours was very good, with a value of 0.781 for overall assessment. CONCLUSIONS: This innovative method for automatic colour evaluation, reproducing clinical assessment of melanocytic lesion colours, may provide numerical parameters to be employed for computer-aided diagnosis of MM.