Artificial intelligence algorithm for the histopatological diagnosis of skin cancer
Clin. biomed. res
;
40(4): 218-222, 2020. ilus, tab
Artículo
en Inglés
| LILACS
| ID: biblio-1252678
ABSTRACT
Introduction:
Cutaneous neoplasms are the most common cancers in the world, and have high morbidity rates. A definitive diagnosis can only be obtained after histopathological evaluation of the lesions. To develop an artificial intelligence program to establish the histopathological diagnosis of cutaneous lesions.Methods:
A deep learning program was built using three neural network architectures MobileNet, Inception and convolutional networks. A database was constructed using 2732 images of melanomas, basal and squamous cell carcinomas, and normal skin. The validation set consisted of 284 images from all 4 categories, allowing for the calculation of sensitivity and specificity. All images were provided by the Path Presenter website.Results:
The sensitivity and specificity of the MobileNet model were 92% (95%CI, 83-100%) and 97% (95%CI, 90-100%), respectively; corresponding figures for the Inception model were 98.3% (95%CI, 86-100%) and 98.8% (95%CI, 98.2-100%); lastly, the sensitivity and specificity of the convolutional network model were 91.6% (95%CI, 73.8-100%) and 95.7% (95%CI, 94.4-97.2%). The maximum sensitivity for the differentiation of malignant conditions was 91%, and specificity was 95.4%.Conclusion:
The program developed in the present study can efficiently distinguish between the main types of skin cancer with high sensitivity and specificity. (AU)
Texto completo:
Disponible
Índice:
LILACS (Américas)
Asunto principal:
Neoplasias Cutáneas
/
Algoritmos
/
Inteligencia Artificial
Tipo de estudio:
Estudio diagnóstico
/
Estudio pronóstico
Idioma:
Inglés
Revista:
Clin. biomed. res
Asunto de la revista:
Medicina
Año:
2020
Tipo del documento:
Artículo
País de afiliación:
Brasil
Institución/País de afiliación:
Hospital de Clínicas de Passo Fundo/BR
/
Universidade Internacional/BR
/
Universidade de Passo Fundo/BR
/
Universidade do Oeste de Santa Catarina/BR
Similares
MEDLINE
...
LILACS
LIS