A Convolutional Neural Network Application for Predicting the Locating of Squamous Cell Carcinoma in the Lung

Abstract

Squamous cell carcinoma, one of the most commontypes of lung cancer types, usually occurs in the middle, right orleft bronchi. Squamous cell carcinoma can be easily detected byimaging methods to determine the location within the lung.However, rarely the location of some tumor types cannot bedetermined. In this case, it may be delayed to obtain the results ofthe assay such as biopsy. This possible delay also means delayeddiagnosis and delayed start of treatment. In order to solve thisproblem, it is possible to perform applications with machinelearning methods. In this study, convolutional neural networksmethod was used to determine the location of cancerous tumor insquamous cell carcinoma of lung. With the designed convolutionalneural network model, squamous cell carcinoma tumor location inlung cancer was estimated with an accuracy rate close to 100%.