Related Experiment Video
Updated: Mar 19, 2026
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
Published on: August 18, 2022
Diagnosis of cutaneous melanoma: accuracy of a computerized image analysis system (Skin View)
M Cristofolini1, P Bauer1, S Boi1
1Departments of Dermatology, Santa Chiara Hospital, Trento, ItalyDepartments of Histopathology, Santa Chiara Hospital, Trento, ItalyDepartment of Statistics, University of Trento, Trento, Italy.
Background/Aims:
Early diagnosis is essential for reducing the high mortality of CM (cutaneous melanoma). An expert dermatologist has a diagnostic accuracy of 85% but, in performing mass screening, the problem is to transfer the experience of a specialized centre to peripheral health clinics. Therefore, some computerized analysis systems were made. The aim of this paper is to compare the diagnostic accuracy of one such system, the Skin View System (SVS), to the accuracy of a well trained dermatologist in order to establish the real usefulness of the instrument and to verify how much it can help the diagnostic accuracy of the clinician in a dermatology setting.
Method:
During a campaign for the early diagnosis of CM, 176 patients with small and flat pigmentary lesions underwent clinical diagnosis, computerized analysis with SVS and skin biopsy. For clinical and computerized diagnosis, we evaluated sensitivity, specificity, true and negative predictive value.
Results:
The statistical evaluation, in our study, reveals that the computerized system has a diagnostic accuracy lower than that of a trained dermatologist.
Conclusions:
This computerized system does not help the clinician in the diagnosis of pigmented lesions.
