Artificial intelligence algorithm for the histopathological diagnosis of skin cancer

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.

Diagnostic and Prognostic Deep Learning Applications for Histological Assessment of Cutaneous Melanoma

“…Most deep-learning diagnostic applications for histological images are for the differentiation between melanoma and nevi [ 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 ]. However, multiple studies show applications in the differentiation between melanoma, nevi, and normal skin [ 34 , 35 ]; and differentiation between melanoma and nonmelanoma skin cancers [ 36 , 37 , 38 ]. Several studies showed deep-learning applications for the segmentation of whole tumor regions [ 39 , 40 , 41 , 42 ] or individual diagnostic markers such as mitotic cells [ 43 , 44 ], melanocytes [ 45 , 46 ], and melanocytic nests [ 47 ].…”

Currículo e Curadoria: programas de filmes como procedimento metodológico de pesquisa entre o cinema e a educação

“…Pelo contrário, parafraseando a citação, essa individuação 'aumenta desmensuradamente' a potência do coletivo, as histórias aumentam 'desmensuradamente' a potência da História. Aliás, não há História, não há o que possamos qualificar de histórico sem que pulsem aí as histórias de si (Kuiava;Wiacek, 2009, p. 171).…”

Curriculum and Curation: film programs as a methodological research procedure between cinema and education

“…On the contrary, to paraphrase the quote, this individuation 'increases immeasurably' the power of the collective, stories increase 'immeasurably' the power of History. In fact, there is no History, there is nothing that we can describe as historical without the stories of the self-pulsating there (Kuiava;Sierra;Wiacek, 2009, p. 171).…”