Linda Tognetti1, Simone Bonechi2, Paolo Andreini3, Monica Bianchini3, Franco Scarselli3, Gabriele Cevenini4, Elvira Moscarella5, Francesca Farnetani6, Caterina Longo7, Aimilios Lallas8, Cristina Carrera9, Susana Puig10, Danica Tiodorovic11, Jean Luc Perrot12, Giovanni Pellacani6, Giuseppe Argenziano5, Elisa Cinotti13, Gennaro Cataldo4, Alberto Balistreri4, Alessandro Mecocci3, Marco Gori3, Pietro Rubegni13, Alessandra Cartocci14. 1. Dermatology Unit, Department of Medical, Surgical and Neurosciences, University of Siena, Italy. Electronic address: linda.tognetti@dbm.unisi.it. 2. Department of Information Engineering and Mathematics, University of Siena, Siena, Italy; Department of Economy Engineering Society and Buisiness, Tuscia University, Viterbo, Italy. 3. Department of Information Engineering and Mathematics, University of Siena, Siena, Italy. 4. Bioengineering Unit, Department of Medical Biotechnology, University of Siena, Italy. 5. Dermatology Unit, University of Campania Luigi Vanvitelli, Naples, Italy. 6. Department of Dermatology, University of Modena and Reggio Emilia, Modena, Italy. 7. Centro Oncologico ad Alta Tecnologia Diagnostica, Azienda Unità Sanitaria Locale, IRCCS di Reggio Emilia, Reggio Emilia, Italy. 8. First Department of Dermatology, Aristotle University, Thessaloniki, Greece. 9. Melanoma Unit, Department of Dermatology, University of Barcelona, Barcelona, Spain; Centro de Investigación Biomédica en Red de Enfermedades Raras (CIBERER), Instituto de Salud Carlos III, University of Barcelona, Barcelona, Spain. 10. Melanoma Unit, Department of Dermatology, University of Barcelona, Barcelona, Spain. 11. Dermatology Clinic, Medical Faculty, Nis University, Nis, Serbia. 12. Dermatology Unit, University Hospital of St-Etienne, Saint Etienne, France. 13. Dermatology Unit, Department of Medical, Surgical and Neurosciences, University of Siena, Italy. 14. Dermatology Unit, Department of Medical, Surgical and Neurosciences, University of Siena, Italy; Bioengineering Unit, Department of Medical Biotechnology, University of Siena, Italy.
Abstract
BACKGROUND: Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists' experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM). OBJECTIVE: We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL). METHODS: A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated "iDCNN_aMSL" model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models. RESULTS: In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %). CONCLUSIONS: The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions.
BACKGROUND: Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists' experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM). OBJECTIVE: We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL). METHODS: A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated "iDCNN_aMSL" model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models. RESULTS: In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %). CONCLUSIONS: The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions.