Expert-Level Diagnosis of Nonpigmented Skin Cancer by Combined Convolutional Neural Networks
| Autor: | Bengü Nisa Akay, Christoph Rinner, Harold S. Rabinovitz, Iris Zalaudek, Philipp Tschandl, Horacio Cabo, Jean-Yves Gourhant, Giuseppe Argenziano, Jan Lapins, Christoph Sinz, Ashfaq A. Marghoob, Nina Maria Neuber, Andreas Blum, Scott W. Menzies, H. Peter Soyer, Aimilios Lallas, Alon Scope, John Paoli, J. Kreusch, Ralph P. Braun, Harald Kittler, Cliff Rosendahl, Luc Thomas |
|---|---|
| Přispěvatelé: | Tschandl, P, Rosendahl, C, Akay, Bn, Argenziano, G, Blum, A, Braun, Rp, Cabo, H, Gourhant, Jy, Kreusch, J, Lallas, A, Lapins, J, Marghoob, A, Menzies, S, Neuber, Nm, Paoli, J, Rabinovitz, H, Rinner, C, Scope, A, Soyer, Hp, Sinz, C, Thomas, L, Zalaudek, I, Kittler, H., University of Zurich, Tschandl, Philipp, Rosendahl, Cliff, Akay, Bengu Nisa, Argenziano, Giuseppe, Blum, Andrea, Braun, Ralph P, Cabo, Horacio, Gourhant, Jean-Yve, Kreusch, Jürgen, Lallas, Aimilio, Lapins, Jan, Marghoob, Ashfaq, Menzies, Scott, Neuber, Nina Maria, Paoli, John, Rabinovitz, Harold S, Rinner, Christoph, Scope, Alon, Soyer, H Peter, Sinz, Christoph, Thomas, Luc, Zalaudek, Iri, Kittler, Harald |
| Rok vydání: | 2018 |
| Předmět: |
Adult
Male medicine.medical_specialty Skin Neoplasms 610 Medicine & health Dermoscopy Dermatology Convolutional neural network melanocytic lesions skin cancer cnns 2708 Dermatology Diagnosis Differential 030207 dermatology & venereal diseases 03 medical and health sciences 0302 clinical medicine medicine Humans Medical diagnosis Original Investigation Retrospective Studies Skin Receiver operating characteristic business.industry Follow up studies Outcome measures 10177 Dermatology Clinic Reproducibility of Results Mean age Retrospective cohort study Middle Aged medicine.disease ROC Curve 030220 oncology & carcinogenesis Female Radiology Neural Networks Computer melanocytic lesion Skin cancer business Algorithms Follow-Up Studies |
| Zdroj: | JAMA dermatology. 155(1) |
| ISSN: | 2168-6084 |
| Popis: | Importance: Convolutional neural networks (CNNs) achieve expert-level accuracy in the diagnosis of pigmented melanocytic lesions. However, the most common types of skin cancer are nonpigmented and nonmelanocytic, and are more difficult to diagnose. Objective: To compare the accuracy of a CNN-based classifier with that of physicians with different levels of experience. Design, Setting, and Participants: A CNN-based classification model was trained on 7895 dermoscopic and 5829 close-up images of lesions excised at a primary skin cancer clinic between January 1, 2008, and July 13, 2017, for a combined evaluation of both imaging methods. The combined CNN (cCNN) was tested on a set of 2072 unknown cases and compared with results from 95 human raters who were medical personnel, including 62 board-certified dermatologists, with different experience in dermoscopy. Main Outcomes and Measures: The proportions of correct specific diagnoses and the accuracy to differentiate between benign and malignant lesions measured as an area under the receiver operating characteristic curve served as main outcome measures. Results: Among 95 human raters (51.6% female; mean age, 43.4 years; 95% CI, 41.0-45.7 years), the participants were divided into 3 groups (according to years of experience with dermoscopy): beginner raters (10 years). The area under the receiver operating characteristic curve of the trained cCNN was higher than human ratings (0.742; 95% CI, 0.729-0.755 vs 0.695; 95% CI, 0.676-0.713; P |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|