BACKGROUND AND OBJECTIVE: Several systems for the diagnosis of melanoma from images of naevi obtained under controlled conditions have demonstrated comparable efficiency with dermatologists. However, their robustness to analyze daily routine images was sometimes questionable. The purpose of this work is to investigate to what extent the automatic melanoma diagnosis may be achieved from the analysis of uncontrolled images of pigmented skin lesions. MATERIALS AND METHODS: Images were acquired during regular practice by two dermatologists using Reflex 24 x 36 cameras combined with Heine Delta 10 dermascopes. The images were then digitalized using a scanner. In addition, five senior dermatologists were asked to give the diagnosis and therapeutic decision (exeresis) for 227 images of naevi, together with an opinion about the existence of malignancy-predictive features. Meanwhile, a learning by sample classifier for the diagnosis of melanoma was constructed, which combines image-processing with machine-learning techniques. After an automatic segmentation, geometric and colorimetric parameters were extracted from images and selected according to their efficiency in predicting malignancy features. A diagnosis was subsequently provided based on selected parameters. An extensive comparison of dermatologists' and computer results was subsequently performed. RESULTS AND CONCLUSION: The KL-PLS-based classifier shows comparable performances with respect to dermatologists (sensitivity: 95% and specificity: 60%). The algorithm provides an original insight into the clinical knowledge of pigmented skin lesions.
BACKGROUND AND OBJECTIVE: Several systems for the diagnosis of melanoma from images of naevi obtained under controlled conditions have demonstrated comparable efficiency with dermatologists. However, their robustness to analyze daily routine images was sometimes questionable. The purpose of this work is to investigate to what extent the automatic melanoma diagnosis may be achieved from the analysis of uncontrolled images of pigmented skin lesions. MATERIALS AND METHODS: Images were acquired during regular practice by two dermatologists using Reflex 24 x 36 cameras combined with Heine Delta 10 dermascopes. The images were then digitalized using a scanner. In addition, five senior dermatologists were asked to give the diagnosis and therapeutic decision (exeresis) for 227 images of naevi, together with an opinion about the existence of malignancy-predictive features. Meanwhile, a learning by sample classifier for the diagnosis of melanoma was constructed, which combines image-processing with machine-learning techniques. After an automatic segmentation, geometric and colorimetric parameters were extracted from images and selected according to their efficiency in predicting malignancy features. A diagnosis was subsequently provided based on selected parameters. An extensive comparison of dermatologists' and computer results was subsequently performed. RESULTS AND CONCLUSION: The KL-PLS-based classifier shows comparable performances with respect to dermatologists (sensitivity: 95% and specificity: 60%). The algorithm provides an original insight into the clinical knowledge of pigmented skin lesions.
Authors: Jacqueline Dinnes; Jonathan J Deeks; Naomi Chuchu; Rubeta N Matin; Kai Yuen Wong; Roger Benjamin Aldridge; Alana Durack; Abha Gulati; Sue Ann Chan; Louise Johnston; Susan E Bayliss; Jo Leonardi-Bee; Yemisi Takwoingi; Clare Davenport; Colette O'Sullivan; Hamid Tehrani; Hywel C Williams Journal: Cochrane Database Syst Rev Date: 2018-12-04
Authors: Jacqueline Dinnes; Jonathan J Deeks; Naomi Chuchu; Lavinia Ferrante di Ruffano; Rubeta N Matin; David R Thomson; Kai Yuen Wong; Roger Benjamin Aldridge; Rachel Abbott; Monica Fawzy; Susan E Bayliss; Matthew J Grainge; Yemisi Takwoingi; Clare Davenport; Kathie Godfrey; Fiona M Walter; Hywel C Williams Journal: Cochrane Database Syst Rev Date: 2018-12-04