Home // ALLSENSORS 2022, The Seventh International Conference on Advances in Sensors, Actuators, Metering and Sensing // View article

Development of a Lung Cancer Diagnosis Support System

Authors:
Nélson Faria
Vítor Carvalho
Sofia Campelos

Keywords: lung cancer; digital pathology; artificial intelligence; convolutional neural networks; whole slide images

Abstract:
Lung cancer is the leading type of cancer death worldwide, and a correct diagnosis in an early stage gives more possibilities for treatment. Whole Slide Images generated from glass slides can be analysed using Artificial Intelligence technologies to help pathologists. In this study, an overview of lung cancer is made, exploring the methodologies used to improve the histopathological diagnosis of lung cancer. These methods are composed of Detection and Classification phases. To detect the neoplastic cells, the Whole Slide Image is split into patches, and a convolutional neural network is applied to identify the tumour regions and generate a heatmap to highlight them. Then, the features are extracted from the cancerous regions and submitted in a classifier to determine the histologic type of tumour present in each patch. In addition, it is proposed a possible solution based on the literature review that could be used as an aid in the pathological diagnosis of lung cancer.

Pages: 30 to 32

Copyright: Copyright (c) IARIA, 2022

Publication date: June 26, 2022

Published in: conference

ISSN: 2519-836X

ISBN: ISBN: 978-1-61208-987-4

Location: Porto, Portugal

Dates: from June 26, 2022 to June 30, 2022