Giovanni Lucca França da Silva1, Thales Levi Azevedo Valente2, Aristófanes Corrêa Silva3, Anselmo Cardoso de Paiva4, Marcelo Gattass5. 1. Federal University of Maranhão - UFMA, Applied Computing Group - NCA Av. dos Portugueses, SN, Bacanga, São Luís, MA 65085-580, Brazil. Electronic address: giovannilucca@nca.ufma.br. 2. Pontifical Catholic University of Rio de Janeiro - PUC - Rio R. São Vicente, 225, Gávea, Rio de Janeiro, RJ 22453-900, Brazil. Electronic address: selaht7@gmail.com. 3. Federal University of Maranhão - UFMA, Applied Computing Group - NCA Av. dos Portugueses, SN, Bacanga, São Luís, MA 65085-580, Brazil. Electronic address: ari@nca.ufma.br. 4. Federal University of Maranhão - UFMA, Applied Computing Group - NCA Av. dos Portugueses, SN, Bacanga, São Luís, MA 65085-580, Brazil. Electronic address: paiva@nca.ufma.br. 5. Pontifical Catholic University of Rio de Janeiro - PUC - Rio R. São Vicente, 225, Gávea, Rio de Janeiro, RJ 22453-900, Brazil. Electronic address: mgattass@tecgraf.puc-rio.br.
Abstract
BACKGROUND AND OBJECTIVE: Detection of lung nodules is critical in CAD systems; this is because of their similar contrast with other structures and low density, which result in the generation of numerous false positives (FPs). Therefore, this study proposes a methodology to reduce the FP number using a deep learning technique in conjunction with an evolutionary technique. METHOD: The particle swarm optimization (PSO) algorithm was used to optimize the network hyperparameters in the convolutional neural network (CNN) in order to enhance the network performance and eliminate the requirement of manual search. RESULTS: The methodology was tested on computed tomography (CT) scans from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) with the highest accuracy of 97.62%, sensitivity of 92.20%, specificity of 98.64%, and area under the receiver operating characteristic (ROC) curve of 0.955. CONCLUSION: The results demonstrate the high performance-potential of the PSO algorithm in the identification of optimal CNN hyperparameters for lung nodule candidate classification into nodules and non-nodules, increasing the sensitivity rates in the FP reduction step of CAD systems.
BACKGROUND AND OBJECTIVE: Detection of lung nodules is critical in CAD systems; this is because of their similar contrast with other structures and low density, which result in the generation of numerous false positives (FPs). Therefore, this study proposes a methodology to reduce the FP number using a deep learning technique in conjunction with an evolutionary technique. METHOD: The particle swarm optimization (PSO) algorithm was used to optimize the network hyperparameters in the convolutional neural network (CNN) in order to enhance the network performance and eliminate the requirement of manual search. RESULTS: The methodology was tested on computed tomography (CT) scans from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) with the highest accuracy of 97.62%, sensitivity of 92.20%, specificity of 98.64%, and area under the receiver operating characteristic (ROC) curve of 0.955. CONCLUSION: The results demonstrate the high performance-potential of the PSO algorithm in the identification of optimal CNN hyperparameters for lung nodule candidate classification into nodules and non-nodules, increasing the sensitivity rates in the FP reduction step of CAD systems.
Authors: Ke Nie; Hania Al-Hallaq; X Allen Li; Stanley H Benedict; Jason W Sohn; Jean M Moran; Yong Fan; Mi Huang; Michael V Knopp; Jeff M Michalski; James Monroe; Ceferino Obcemea; Christina I Tsien; Timothy Solberg; Jackie Wu; Ping Xia; Ying Xiao; Issam El Naqa Journal: Int J Radiat Oncol Biol Phys Date: 2019-01-31 Impact factor: 7.038
Authors: Radouane El Ayachy; Nicolas Giraud; Paul Giraud; Catherine Durdux; Philippe Giraud; Anita Burgun; Jean Emmanuel Bibault Journal: Front Oncol Date: 2021-05-05 Impact factor: 6.244
Authors: Kun-Hsing Yu; Tsung-Lu Michael Lee; Ming-Hsuan Yen; S C Kou; Bruce Rosen; Jung-Hsien Chiang; Isaac S Kohane Journal: J Med Internet Res Date: 2020-08-05 Impact factor: 5.428