Lung Nodule Segmentation Based on Convolutional Neural Networks Using Multi-orientation and Patchwise Mechanisms

Abstract

Image segmentation is used in several knowledge domains, such as medicine, biology, remote sensing, industrial automation, surveillance and security. More specifically, image segmentation plays a crucial role in various medical imaging applications, as an important part of clinical diagnosis. Deep learning techniques have recently benefited medical image segmentation and classification tasks. In this work, we have explored the use of Convolutional Neural Networks (CNN) for lung nodule segmentation using multi-orientation and patchwise mechanisms. Experiments conducted on the public LIDC-IRI dataset demonstrate that our results were able to reduce the number of false negatives, which is important in this task. High segmentation rates were achieved when compared to medical specialists.