Automated Diagnosis Of Cutaneous Malignant Melanoma in Histological Slides Using Spectral Imaging Technology


Abstract in English

Inasmuch as for incrimination of occurrence dermal malignant melanoma and difficulties of the clinical and histological diagnosis, so it is needed to search about method, giving fast diagnosis and self of high credibility, so the automatic spectral imaging was for the histological slides of dermal melanoma, where use of the morphological information is complete with the local information in establishing of the tissue print, through education of the machine (machine learning). 31 Cutaneous biopsies have been studied, of their 11 malignant melanomas, 16 benign lesions, and 4 normal skin. It has done spectral imaging for Histological sections stained routinely during the evaluation in digital camera pick up (CCD Camera) on luminous spectroscope, his luminous wavelengths ranges from 390-700 nanometer. the automated classifying results showed in the acquaintance on the malignant cells in tumor tissues in a ratio of ranged between 65-82%, these are very promising results. method of the non-supported classification revealed better results. in the future, we must complete classification of all types of other tissues, and build data base characterized each type of disease in various tissues. in order to use it as supportive factor in the accurate diagnosis and correct.

References used

ROSAI, J. Rosai and Ackerman's Surgical Pathology. 8th ed., Mosby, USA & London, 2004, 2977
RUBIN, E. Essential Pathology. 3rd ed., Lippincott Williams& Wilkins, USA, London, & Tokyo, 2001, 786
DE VRIES, E. S. ; VISSER, L. V. RISING Trends In The Incidence And Mortality From Cutaneous Melanoma In The Netherland, A Northwest Gradient. EurJ Cancer, 39, 1439-1446, 2003

Download