Development of a novel border detection method for melanocytic and non-melanocytic dermoscopy images.
ABSTRACT Computer aided diagnosis of dermoscopy images has shown great promise in developing a quantitative, objective way of classifying skin lesions. An important step in the classification process is the lesion segmentation. Many papers have been successful at segmenting melanocytic skin lesions (MSLs) but few have focused on non-melanocytic skin lesions (NoMSLs), since the wide variety of lesions makes accurate segmentation difficult. We developed an automatic segmentation program for the border detection of skin lesions. We tested our method on a set of 107 non-melanocytic lesions and on a set of 319 melanocytic lesions. Our method achieved precision/recall scores of 84.5% and 88.5% for NoMSLs, achieving higher scores than two previously published methods. Our method also achieved precision/recall scores of 93.9% and 93.8% for MSLs which was competitive or better than the two other methods. Therefore, we conclude that our approach is an accurate segmentation method for both melanocytic and non-melanocytic lesions.
- [show abstract] [hide abstract]
ABSTRACT: The aims of this study were to provide a quantitative assessment of the tumour area extracted by dermatologists and to evaluate computer-based methods from dermoscopy images for refining a computer-based melanoma diagnostic system. Dermoscopic images of 188 Clark naevi, 56 Reed naevi and 75 melanomas were examined. Five dermatologists manually drew the border of each lesion with a tablet computer. The inter-observer variability was evaluated and the standard tumour area (STA) for each dermoscopy image was defined. Manual extractions by 10 non-medical individuals and by two computer-based methods were evaluated with STA-based assessment criteria: precision and recall. Our new computer-based method introduced the region-growing approach in order to yield results close to those obtained by dermatologists. The effectiveness of our extraction method with regard to diagnostic accuracy was evaluated. Two linear classifiers were built using the results of conventional and new computer-based tumour area extraction methods. The final diagnostic accuracy was evaluated by drawing the receiver operating curve (ROC) of each classifier, and the area under each ROC was evaluated. The standard deviations of the tumour area extracted by five dermatologists and 10 non-medical individuals were 8.9% and 10.7%, respectively. After assessment of the extraction results by dermatologists, the STA was defined as the area that was selected by more than two dermatologists. Dermatologists selected the melanoma area with statistically smaller divergence than that of Clark naevus or Reed naevus (P = 0.05). By contrast, non-medical individuals did not show this difference. Our new computer-based extraction algorithm showed superior performance (precision, 94.1%; recall, 95.3%) to the conventional thresholding method (precision, 99.5%; recall, 87.6%). These results indicate that our new algorithm extracted a tumour area close to that obtained by dermatologists and, in particular, the border part of the tumour was adequately extracted. With this refinement, the area under the ROC increased from 0.795 to 0.875 and the diagnostic accuracy showed an increase of approximately 20% in specificity when the sensitivity was 80%. It can be concluded that our computer-based tumour extraction algorithm extracted almost the same area as that obtained by dermatologists and provided improved computer-based diagnostic accuracy.Melanoma Research 05/2006; 16(2):183-90. · 2.52 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: Background The occurrence of non-melanoma skin cancer (NMSC), including actinic keratosis (AK) is increasing all over the world. The detection and diagnosis of NMSC is not optimal in clinical practice. Complementary methods for detection and accurate demarcation of NMSC at an early stage are needed in order to limit the damage caused by tumours.Objective The purpose of the present study was to use a large area skin fluorescence detection system to detect early NMSCs (clinical visible as well as non-visible lesions) in the face, neck, chest, back and hands of patients treated with UV and outdoor workers.Methods Fluorescence detection with a purpose-made digital camera and software (Dyaderm®) combined with 5-aminolevulinic acid (5-ALA) encapsulated in liposomes.ResultsIn 93 consecutively referred patients positive skin fluorescence was detected in 61 patients. After histological examination the positive fluorescence appeared to be correlated to benign lesions in 28 patients (sebaceous gland hyperplasia in 22 patients) and to (pre-) malignant lesions in 33 patients (actinic keratosis in 29, BCC in 3 and SCC in 1 patient). False negative fluorescence was found in only one lesion. In five patients the FD technique used in this study appeared to be more sensitive for the identification of (pre-) malignant lesions than the clinical examination. This is in contrast with FD techniques used in previous studies.Conclusion Diagnostic skin fluorescence using liposomal encapsulated 5-ALA and a specialised computerised detection and visualisation system offers the possibility for detection of NMSC at an early, pre-clinical stage. The technique is well suited to examine large areas of skin. It also identifies areas of most interest for performing confirmatory skin biopsies, as well as pre-operative assessment of boundaries of skin malignancies, and finally, the technique is applicable in the control and follow-up of skin cancer treatment. Lasers Surg. Med. 41:96–103, 2009. © 2009 Wiley-Liss, Inc.Lasers in Surgery and Medicine 02/2009; 41(2):96 - 103. · 2.46 Impact Factor