E Lopez Torres1, E Fiorina2, F Pennazio2, C Peroni2, M Saletta3, N Camarlinghi4, M E Fantacci4, P Cerello3. 1. CEADEN, Havana 11300, Cuba and INFN, Sezione di Torino, Torino 10125, Italy. 2. Department of Physics, University of Torino, Torino 10125, Italy and INFN, Sezione di Torino, Torino 10125, Italy. 3. INFN, Sezione di Torino, Torino 10125, Italy. 4. Department of Physics, University of Pisa, Pisa 56127, Italy and INFN, Sezione di Pisa, Pisa 56127, Italy.
Abstract
PURPOSE: M5L, a fully automated computer-aided detection (CAD) system for the detection and segmentation of lung nodules in thoracic computed tomography (CT), is presented and validated on several image datasets. METHODS: M5L is the combination of two independent subsystems, based on the Channeler Ant Model as a segmentation tool [lung channeler ant model (lungCAM)] and on the voxel-based neural approach. The lungCAM was upgraded with a scan equalization module and a new procedure to recover the nodules connected to other lung structures; its classification module, which makes use of a feed-forward neural network, is based of a small number of features (13), so as to minimize the risk of lacking generalization, which could be possible given the large difference between the size of the training and testing datasets, which contain 94 and 1019 CTs, respectively. The lungCAM (standalone) and M5L (combined) performance was extensively tested on 1043 CT scans from three independent datasets, including a detailed analysis of the full Lung Image Database Consortium/Image Database Resource Initiative database, which is not yet found in literature. RESULTS: The lungCAM and M5L performance is consistent across the databases, with a sensitivity of about 70% and 80%, respectively, at eight false positive findings per scan, despite the variable annotation criteria and acquisition and reconstruction conditions. A reduced sensitivity is found for subtle nodules and ground glass opacities (GGO) structures. A comparison with other CAD systems is also presented. CONCLUSIONS: The M5L performance on a large and heterogeneous dataset is stable and satisfactory, although the development of a dedicated module for GGOs detection could further improve it, as well as an iterative optimization of the training procedure. The main aim of the present study was accomplished: M5L results do not deteriorate when increasing the dataset size, making it a candidate for supporting radiologists on large scale screenings and clinical programs.
PURPOSE: M5L, a fully automated computer-aided detection (CAD) system for the detection and segmentation of lung nodules in thoracic computed tomography (CT), is presented and validated on several image datasets. METHODS: M5L is the combination of two independent subsystems, based on the Channeler Ant Model as a segmentation tool [lung channeler ant model (lungCAM)] and on the voxel-based neural approach. The lungCAM was upgraded with a scan equalization module and a new procedure to recover the nodules connected to other lung structures; its classification module, which makes use of a feed-forward neural network, is based of a small number of features (13), so as to minimize the risk of lacking generalization, which could be possible given the large difference between the size of the training and testing datasets, which contain 94 and 1019 CTs, respectively. The lungCAM (standalone) and M5L (combined) performance was extensively tested on 1043 CT scans from three independent datasets, including a detailed analysis of the full Lung Image Database Consortium/Image Database Resource Initiative database, which is not yet found in literature. RESULTS: The lungCAM and M5L performance is consistent across the databases, with a sensitivity of about 70% and 80%, respectively, at eight false positive findings per scan, despite the variable annotation criteria and acquisition and reconstruction conditions. A reduced sensitivity is found for subtle nodules and ground glass opacities (GGO) structures. A comparison with other CAD systems is also presented. CONCLUSIONS: The M5L performance on a large and heterogeneous dataset is stable and satisfactory, although the development of a dedicated module for GGOs detection could further improve it, as well as an iterative optimization of the training procedure. The main aim of the present study was accomplished: M5L results do not deteriorate when increasing the dataset size, making it a candidate for supporting radiologists on large scale screenings and clinical programs.
Authors: Marco Das; Georg Mühlenbruch; Andreas H Mahnken; Thomas G Flohr; Lutz Gündel; Sven Stanzel; Thomas Kraus; Rolf W Günther; Joachim E Wildberger Journal: Radiology Date: 2006-11 Impact factor: 11.105
Authors: Matthew S Brown; Pechin Lo; Jonathan G Goldin; Eran Barnoy; Grace Hyun J Kim; Michael F McNitt-Gray; Denise R Aberle Journal: Eur Radiol Date: 2014-07-24 Impact factor: 5.315
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: Myrna C B Godoy; Peter L Cooperberg; Zeev V Maizlin; Ren Yuan; Annette McWilliams; Stephen Lam; John R Mayo Journal: J Thorac Imaging Date: 2008-02 Impact factor: 3.000
Authors: Alan A Peters; Adrian T Huber; Verena C Obmann; Johannes T Heverhagen; Andreas Christe; Lukas Ebner Journal: Eur Radiol Date: 2022-01-21 Impact factor: 5.315
Authors: Giang Son Tran; Thi Phuong Nghiem; Van Thi Nguyen; Chi Mai Luong; Jean-Christophe Burie Journal: J Healthc Eng Date: 2019-02-04 Impact factor: 2.682