João Otávio Bandeira Diniz1, Pedro Henrique Bandeira Diniz2, Thales Levi Azevedo Valente3, Aristófanes Corrêa Silva4, Anselmo Cardoso Paiva4. 1. Federal University of Maranhão - UFMA Applied Computing Group - NCA Av. dos Portugueses, SN, Bacanga, São Luís, 65085-580, MA, Brazil. Electronic address: joao.obd@gmail.com. 2. Pontifical Catholic University of Rio de Janeiro - PUC - Rio R. São Vicente, 225, Gávea, Rio de Janeiro, 22453-900, RJ, Brazil. Electronic address: pedro_hbd@hotmail.com. 3. Pontifical Catholic University of Rio de Janeiro - PUC - Rio R. São Vicente, 225, Gávea, Rio de Janeiro, 22453-900, RJ, Brazil. Electronic address: selaht7@gmail.com. 4. Federal University of Maranhão - UFMA Applied Computing Group - NCA Av. dos Portugueses, SN, Bacanga, São Luís, 65085-580, MA, Brazil. Electronic address: aricsilva@gmail.com.
Abstract
BACKGROUND AND OBJECTIVE: The spinal cord is a very important organ that must be protected in treatments of radiotherapy (RT), considered an organ at risk (OAR). Excess rays associated with the spinal cord can cause irreversible diseases in patients who are undergoing radiotherapy. For the planning of treatments with RT, computed tomography (CT) scans are commonly used to delimit the OARs and to analyze the impact of rays in these organs. Delimiting these OARs take a lot of time from medical specialists, plus the fact that involves a large team of professionals. Moreover, this task made slice-by-slice becomes an exhaustive and consequently subject to errors, especially in organs such as the spinal cord, which extend through several slices of the CT and requires precise segmentation. Thus, we propose, in this work, a computational methodology capable of detecting spinal cord in planning CT images. METHODS: The techniques highlighted in this methodology are adaptive template matching for initial segmentation, intrinsic manifold simple linear iterative clustering (IMSLIC) for candidate segmentation and convolutional neural networks (CNN) for candidate classification, that consists of four steps: (1) images acquisition, (2) initial segmentation, (3) candidates segmentation and (4) candidates classification. RESULTS: The methodology was applied on 36 planning CT images provided by The Cancer Imaging Archive, and achieved an accuracy of 92.55%, specificity of 92.87% and sensitivity of 89.23% with 0.065 of false positives per images, without any false positives reduction technique, in detection of spinal cord. CONCLUSIONS: It is demonstrated the feasibility of the analysis of planning CT images using IMSLIC and convolutional neural network techniques to achieve success in detection of spinal cord regions.
BACKGROUND AND OBJECTIVE: The spinal cord is a very important organ that must be protected in treatments of radiotherapy (RT), considered an organ at risk (OAR). Excess rays associated with the spinal cord can cause irreversible diseases in patients who are undergoing radiotherapy. For the planning of treatments with RT, computed tomography (CT) scans are commonly used to delimit the OARs and to analyze the impact of rays in these organs. Delimiting these OARs take a lot of time from medical specialists, plus the fact that involves a large team of professionals. Moreover, this task made slice-by-slice becomes an exhaustive and consequently subject to errors, especially in organs such as the spinal cord, which extend through several slices of the CT and requires precise segmentation. Thus, we propose, in this work, a computational methodology capable of detecting spinal cord in planning CT images. METHODS: The techniques highlighted in this methodology are adaptive template matching for initial segmentation, intrinsic manifold simple linear iterative clustering (IMSLIC) for candidate segmentation and convolutional neural networks (CNN) for candidate classification, that consists of four steps: (1) images acquisition, (2) initial segmentation, (3) candidates segmentation and (4) candidates classification. RESULTS: The methodology was applied on 36 planning CT images provided by The Cancer Imaging Archive, and achieved an accuracy of 92.55%, specificity of 92.87% and sensitivity of 89.23% with 0.065 of false positives per images, without any false positives reduction technique, in detection of spinal cord. CONCLUSIONS: It is demonstrated the feasibility of the analysis of planning CT images using IMSLIC and convolutional neural network techniques to achieve success in detection of spinal cord regions.
Authors: João O B Diniz; Darlan B P Quintanilha; Antonino C Santos Neto; Giovanni L F da Silva; Jonnison L Ferreira; Stelmo M B Netto; José D L Araújo; Luana B Da Cruz; Thamila F B Silva; Caio M da S Martins; Marcos M Ferreira; Venicius G Rego; José M C Boaro; Carolina L S Cipriano; Aristófanes C Silva; Anselmo C de Paiva; Geraldo Braz Junior; João D S de Almeida; Rodolfo A Nunes; Roberto Mogami; M Gattass Journal: Multimed Tools Appl Date: 2021-06-24 Impact factor: 2.757