José Raniery Ferreira1, Paulo Mazzoncini de Azevedo-Marques2, Marcelo Costa Oliveira3. 1. Center of Imaging Sciences and Medical Physics, Internal Medicine Department, Ribeirao Preto Medical School, University of Sao Paulo (USP), Av. dos Bandeirantes, 3900, Campus USP, Monte Alegre, Ribeirão Preto, São Paulo, 14049-900, Brazil. jose.raniery@usp.br. 2. Center of Imaging Sciences and Medical Physics, Internal Medicine Department, Ribeirao Preto Medical School, University of Sao Paulo (USP), Av. dos Bandeirantes, 3900, Campus USP, Monte Alegre, Ribeirão Preto, São Paulo, 14049-900, Brazil. 3. Lab of Telemedicine and Medical Informatics, University Hospital Prof. Alberto Antunes, Institute of Computing, Federal University of Alagoas (UFAL), Av. Lourival Melo Mota, s/n, Campus A. C. Simões, Cidade Universitária, Maceió, Alagoas, 57072-900, Brazil.
Abstract
PURPOSE: Lung cancer is the leading cause of cancer-related deaths in the world. Its diagnosis is a challenge task to specialists due to several aspects on the classification of lung nodules. Therefore, it is important to integrate content-based image retrieval methods on the lung nodule classification process, since they are capable of retrieving similar cases from databases that were previously diagnosed. However, this mechanism depends on extracting relevant image features in order to obtain high efficiency. The goal of this paper is to perform the selection of 3D image features of margin sharpness and texture that can be relevant on the retrieval of similar cancerous and benign lung nodules. METHODS: A total of 48 3D image attributes were extracted from the nodule volume. Border sharpness features were extracted from perpendicular lines drawn over the lesion boundary. Second-order texture features were extracted from a cooccurrence matrix. Relevant features were selected by a correlation-based method and a statistical significance analysis. Retrieval performance was assessed according to the nodule's potential malignancy on the 10 most similar cases and by the parameters of precision and recall. RESULTS: Statistical significant features reduced retrieval performance. Correlation-based method selected 2 margin sharpness attributes and 6 texture attributes and obtained higher precision compared to all 48 extracted features on similar nodule retrieval. CONCLUSION: Feature space dimensionality reduction of 83 % obtained higher retrieval performance and presented to be a computationaly low cost method of retrieving similar nodules for the diagnosis of lung cancer.
PURPOSE:Lung cancer is the leading cause of cancer-related deaths in the world. Its diagnosis is a challenge task to specialists due to several aspects on the classification of lung nodules. Therefore, it is important to integrate content-based image retrieval methods on the lung nodule classification process, since they are capable of retrieving similar cases from databases that were previously diagnosed. However, this mechanism depends on extracting relevant image features in order to obtain high efficiency. The goal of this paper is to perform the selection of 3D image features of margin sharpness and texture that can be relevant on the retrieval of similar cancerous and benign lung nodules. METHODS: A total of 48 3D image attributes were extracted from the nodule volume. Border sharpness features were extracted from perpendicular lines drawn over the lesion boundary. Second-order texture features were extracted from a cooccurrence matrix. Relevant features were selected by a correlation-based method and a statistical significance analysis. Retrieval performance was assessed according to the nodule's potential malignancy on the 10 most similar cases and by the parameters of precision and recall. RESULTS: Statistical significant features reduced retrieval performance. Correlation-based method selected 2 margin sharpness attributes and 6 texture attributes and obtained higher precision compared to all 48 extracted features on similar nodule retrieval. CONCLUSION: Feature space dimensionality reduction of 83 % obtained higher retrieval performance and presented to be a computationaly low cost method of retrieving similar nodules for the diagnosis of lung cancer.
Authors: Marcos Vinicius Naves Bedo; Davi Pereira Dos Santos; Marcelo Ponciano-Silva; Paulo Mazzoncini de Azevedo-Marques; André Ponce de León Ferreira de Carvalho; Caetano Traina Journal: J Digit Imaging Date: 2016-02 Impact factor: 4.056
Authors: Mylene T Truong; Jane P Ko; Santiago E Rossi; Ignacio Rossi; Chitra Viswanathan; John F Bruzzi; Edith M Marom; Jeremy J Erasmus Journal: Radiographics Date: 2014-10 Impact factor: 5.333
Authors: Samuel G Armato; Geoffrey McLennan; Luc Bidaut; Michael F McNitt-Gray; Charles R Meyer; Anthony P Reeves; Binsheng Zhao; Denise R Aberle; Claudia I Henschke; Eric A Hoffman; Ella A Kazerooni; Heber MacMahon; Edwin J R Van Beeke; David Yankelevitz; Alberto M Biancardi; Peyton H Bland; Matthew S Brown; Roger M Engelmann; Gary E Laderach; Daniel Max; Richard C Pais; David P Y Qing; Rachael Y Roberts; Amanda R Smith; Adam Starkey; Poonam Batrah; Philip Caligiuri; Ali Farooqi; Gregory W Gladish; C Matilda Jude; Reginald F Munden; Iva Petkovska; Leslie E Quint; Lawrence H Schwartz; Baskaran Sundaram; Lori E Dodd; Charles Fenimore; David Gur; Nicholas Petrick; John Freymann; Justin Kirby; Brian Hughes; Alessi Vande Casteele; Sangeeta Gupte; Maha Sallamm; Michael D Heath; Michael H Kuhn; Ekta Dharaiya; Richard Burns; David S Fryd; Marcos Salganicoff; Vikram Anand; Uri Shreter; Stephen Vastagh; Barbara Y Croft Journal: Med Phys Date: 2011-02 Impact factor: 4.071
Authors: Emmanuel Rios Velazquez; Chintan Parmar; Mohammed Jermoumi; Raymond H Mak; Angela van Baardwijk; Fiona M Fennessy; John H Lewis; Dirk De Ruysscher; Ron Kikinis; Philippe Lambin; Hugo J W L Aerts Journal: Sci Rep Date: 2013-12-18 Impact factor: 4.379