Combination of computer-aided detection algorithms for automatic lung nodule identification
- 516 Downloads
The aim of this work is to evaluate the potential of combining different computer-aided detection (CADe) methods to increase the actual support for radiologists of automated systems in the identification of pulmonary nodules in CT scans.
The outputs of three different CADe systems developed by researchers of the Italian MAGIC-5 collaboration were combined. The systems are: the CAMCADe (based on a Channeler-Ant-Model which segments vessel tree and nodule candidates and a neural classifier), the RGVPCADe (a Region-Growing- Volume-Plateau algorithm detects nodule candidates and a neural network reduces false positives); the VBNACADe (two dedicated procedures, based respectively on a 3D dot-enhancement algorithm and on intersections of pleura surface normals, identifies internal and juxtapleural nodules, and a Voxel-Based-Neural-Approach reduces false positives. A dedicated OsiriX plugin implemented with the Cocoa environments of MacOSX allows annotating nodules and visualizing singles and combined CADe findings.
The combined CADe has been tested on thin slice (lower than 2 mm) CTs of the LIDC public research database and the results have been compared with those obtained by the single systems. The FROC (Free Receiver Operating Characteristic) curves show better results than the best of the single approaches.
Has been demonstrated that the combination of different approaches offers better results than each single CADe system. A clinical validation of the combined CADe as second reader is being addressed by means of the dedicated OsiriX plugin.
KeywordsComputer-aided detection Computed tomography Lung cancer Medical image analysis Pattern recognition
Unable to display preview. Download preview PDF.
- 1.Online document. American Cancer Society (2009) http://www.cancer.org/Research/CancerFactsFigures. Accessed 16 December 2010
- 5.Online document U.S. National Cancer Institute November (2010) http://www.cancer.gov/clinicaltrials/noteworthy-trials/nlst. Accessed 16 December 2010
- 6.Roberts HC, Patsios D, Kucharczyk DM, Paul N, Roberts TP (2005) The utility of computer-aided detection (CAD) for lung cancer screening using low-dose CT, Computer Assisted Radiology and Surgery, Proceedings of the 19th International Congress and Exhibition, Berlin, June 22–25, 2005, International Congress Series 1281, pp 1137–1142Google Scholar
- 10.van Ginneken B, Armato SG 3rd, de Hoop B, Amelsvoort-van Vorst S, Duindam T, Niemeijer M, Murphy K, Schilham A, Retico A, Fantacci ME, Camarlinghi N, Bagagli F, Gori I, Hara T, Fujita H, Gargano G, Bellotti R, Tangaro S, Bolaños L, De Carlo F, Cerello P, Cristian Cheran S, Lopez Torres E, Prokop M (2010) Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: the ANODE09 study. Med Image Anal 14(6): 707–722PubMedCrossRefGoogle Scholar
- 14.De Nunzio G et al (2009) Automatic lung segmentation in CT images with accurate handling of the Hilar region. J Digit Imaging, Online FirstGoogle Scholar
- 15.Cerello P, Cheran SC, Bagagli F, Bagnasco S, Bellotti R, Bolanos L, Catanzariti E, De Nunzio G, Fiorina E, Gargano G, Gemme G, Lopez Torres E, Masala G, Peroni C and Santoro M (2008) The Channeler Ant Model: object segmentation with virtual ant colonies. In: IEEE nuclear science symposium conference records, 2008, 3147–3152Google Scholar
- 17.Fantacci ME et al Computer aided detection of nodules in low dose and thin slice lung CT. doi: 10.1594/ecr2010/C-1053
- 20.Gori I, Bagagli F, Fantacci ME, Preite Martinez A, Retico A, De Mitri I, Donadio S, Fulcheri C, Gargano G, Magro R, Santoro M, Stumbo S (2007) Multi-scale analysis of lung computed tomography images. J Instrum 2(09):P09007Google Scholar
- 22.Retico A et al (2009) A voxel-based neural approach (VBNA) to identify lung nodules in the ANODE09 study. Proc SPIE, vol. 7260, 72601S-72601S-8Google Scholar
- 23.McNitt-Gray MF, Armato SG 3rd, Meyer CR, Reeves AP, McLennan G, Pais RC, Freymann J, Brown MS, Engelmann RM, Bland PH, Laderach GE, Piker C, Guo J, Towfic Z, Qing DP, Yankelevitz DF, Aberle DR, van Beek EJ, MacMahon H, Kazerooni EA, Croft BY, Clarke LP (2007) The lung image database consortium (LIDC) data collection process for nodule detection and annotation. Acad Radiol 14(12): 1464–1474PubMedCrossRefGoogle Scholar
- 24.https://wiki.nci.nih.gov/display/cip/lidc. Accessed 16 december 2010
- 25.Fukunaga K (1990) Introduction to statistical pattern recognition. Academic Press, New YorkGoogle Scholar
- 26.Stone M (1974) Cross-validatory choice and assessment of statistical predictions. J R Stat Soc B 36(1): 111–147Google Scholar
- 27.Retico A, Bagagli F, Camarlinghi N, Carpentieri C, Fantacci ME, Gori I (2009) A voxel-based neural approach (VBNA) to identify lung nodules in the ANODE09 study. In: Medical Imaging 2009: Computer-Aided Diagnosis, 7260, 72601S–8, SPIE, Lake Buena Vista, FL, USAGoogle Scholar
- 30.http://www.osirix-viewer.com/. Accessed 16 december 2010