Computer-aided epiluminescence microscopy of pigmented skin lesions: the value of clinical data for the classification process

Abstract

Early melanoma is often difficult to differentiate from benign pigmented skin lesions (PSLs). Digital epiluminescence microscopy (DELM) and automated image analysis could represent possible aids for inexperienced clinicians. We designed an automated computerized image analysis system that has the potential for use as an additional tool for the differentiation of melanoma from dysplastic naevi and common naevi. The PC-based pilot system was attached to a common DELM system as the image source. Digital images of PSLs were automatically segmented and a panel of 107 morphological parameters were measured. Additionally, seven clinical parameters were evaluated and used as an additional source of information. Neural networks were then trained to distinguish melanoma from benign PSLs. One class of networks was trained solely based on the morphometric features, whereas the second class of networks was trained on the combination of morphometric and clinical features. The automatic segmentation algorithm was correct in 96% of cases. Using three-way receiver operating characteristic (ROC) analysis, for networks trained solely on morphometric features the volume under surface (VUS) was 0.617 (SD 0.036). The performance was significantly better for networks trained on the combination of both morphometric and clinical features (VUS = 0.682, SD 0.035). In a dichotomous model, distinguishing benign lesion (common naevi + dysplastic naevi) from melanoma, the area under the curve (AUC) from two-way ROC analysis was 0.942 (SD 0.018) for networks trained solely on morphometric features and 0.968 (SD 0.012) for those trained on the combination of clinical and morphometric data (P= NS). Automated feature extraction from PSLs and the training of neural networks as classifiers has thus shown satisfactory performance in a large scale experiment. The addition of clinical data significantly increases the diagnostic performance for distinguishing three classes of lesions (i.e. common naevi, dysplastic naevi and melanoma). Such integrated systems hold promise as a decision aid for the diagnosis of PSLs.

Dermoscopy of pigmented skin lesions

“…48,[75][76][77][78] Some systems even offer the potential of ''computerassisted diagnosis.'' [79][80][81][82][83][84][85][86][87][88][89][90][91][92][93][94] Because diagnostic accuracy with dermoscopy has been shown to depend on the experience of the dermatologist, such objective systems might help less-experienced dermatologists in the future.…”

Current and emerging technologies in melanoma diagnosis: the state of the art

“…35,36 Since that time, advances in computer technology, digital imaging, and software programming have made computers figure more prominently as potential aids in the evaluation of melanocytic lesions. 37,38 A recent trial comparing three commercially available systems for diagnostic accuracy found that each one tended to overdiagnose suspect melanocytic lesions as melanoma and questioned whether they were ready to be used in clinical practice. 39 Nonetheless, logic dictates that with proficient training and programming, automated systems will eventually match, if not exceed, clinical diagnostic accuracy.…”

“…40-45 Some have achieved a degree of sensitivity and specificity approaching expert dermoscopists. 37,43,45-48 On the basis of these encouraging results, scientists are working to develop fully automated diagnosis systems. 38,43,49 …”

Investigation of the relationship between dermoscopic features and histopathological prognostic indicators in patients with cutaneous melanoma

“…Yapılan araştırmalarda dermoskopinin melanom tanısındaki sensitiviteyi %92, spesifiteyi ise %99 oranlarına kadar arttırabildiği belirtilmektedir 2 . Çeşitli çalışmalarda melanomların Breslow kalınlığı ve invazyon düzeylerine göre farklı dermoskopik bulgular sergilediği ve böylece dermoskopi aracılığıyla bu histopatolojik prognostik faktörlerin tanı anında öngörülebildiği bildirilmiştir 1,[3][4][5] .…”