Machine learning in identifying skin tumor images

Introduction: The technology has undergone many advances over the years, as an example, we have Machine Learning, which uses programming structure to solve a problem after data analysis. With the use of this technology it is possible to organize and analyze the data, interpreting them and detecting standards to generate solutions without human intervention. It is a learning that never stops and can be used to identify various tumor types, including skin tumors. Objective: in the present study we proceed with the use of Machine Learning in the identification of melanoma skin tumor images and normal skin. Methods: The detection and validation analyzes of Machine Learning algorithms, using Python programming language along with Tensorflow, were performed in histopathological images of melanoma skin cancer (n=10) from Pathological Atlas online and Padre Albino University Center (Unifipa) of Catanduva. Normal tissue samples (n=10) were obtained in histological Atlas. Results: The results obtained indicate that the training and accuracy validation tests, performed in the tumor and normal images, have low accuracy to find the patterns related to the ductal in situ carcinoma. In addition, it is important to note that, despite the promising results, the tests of this scenario show that more training is needed to reduce the loss of accuracy. Conclusion: The set of our data widespread that Machine Learning offers advantages in the medical field, such as improving the accuracy of pathological diagnoses. Validation of the algorithms presented underfitting standards, where it was not able to learn enough about the data. These results stimulate the continuity of studies increasing the number of samples.
Keyword: machine learning, artificial intelligence, cance