%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2021/09.15.19.59
%2 sid.inpe.br/sibgrapi/2021/09.15.19.59.11
%T Methods for segmentation of spinal cord and esophagus in radiotherapy planning computed tomography
%D 2021
%A Diniz, João Otávio Bandeira,
%A Silva, Aristófanes Corrêa,
%A Paiva, Anselmo Cardoso de,
%@affiliation Instituto Federal de Educação, Ciência e Tecnologia do Maranhão
%@affiliation Universidade Federal do Maranhão
%@affiliation Universidade Federal do Maranhão
%E Paiva, Afonso,
%E Menotti, David,
%E Baranoski, Gladimir V. G.,
%E Proença, Hugo Pedro,
%E Junior, Antonio Lopes Apolinario,
%E Papa, João Paulo,
%E Pagliosa, Paulo,
%E dos Santos, Thiago Oliveira,
%E e Sá, Asla Medeiros,
%E da Silveira, Thiago Lopes Trugillo,
%E Brazil, Emilio Vital,
%E Ponti, Moacir A.,
%E Fernandes, Leandro A. F.,
%E Avila, Sandra,
%B Conference on Graphics, Patterns and Images, 34 (SIBGRAPI)
%C Gramado, RS, Brazil (virtual)
%8 18-22 Oct. 2021
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Computed Tomography, Esophagus, Spinal Cord, OAR, Deep Learning.
%X Organs at Risk (OARs) are healthy tissues around cancer that must be preserved in radiotherapy (RT). The spinal cord and esophagus are crucial OARs. In this work, we proposed methods for the segmentation of these OARs from the CT using image processing techniques and deep convolutional neural network (CNN). For spinal cord segmentation, two methods are proposed, the first using techniques such as template matching, superpixel, and CNN. The second method, use adaptive template matching and CNN. In the esophagus segmentation, we proposed a method composed of registration techniques, atlas, pre-processing, U-Net, and post-processing. The methods were applied to 36 planning CT images provided by The Cancer Imaging Archive. The first method for spinal cord segmentation obtained 78.20\% Dice. The second method for spinal cord segmentation obtained 81.69\% Dice. The esophagus segmentation method obtained an accuracy of 82.15\% Dice.
%@language en
%3 paper.pdf