Development and Application in Clinical Routine of Computer Aided Detection (CAD) Algorithms for the Identification of Pulmonary Nodules

Alberto Traverso

Abstract

Lung Cancer is one of the main public health issues in developed countries, accounting for about 19% and 28% of cancer-related deaths in Europe and the United States of America, respectively, with a five-year survival rate of only 10-16%. Computed Tomography (CT) has been shown to be the most sensitive imaging modality for the detection of small pulmonary nodules. The identification of early stage pathological Regions of Interests (ROIs) in low dose high resolution CT scans is a very difficult and time consuming task for radiologists, because of the large number (300/500) of noisy 2D slices to be analyzed. In order to support radiologists, researchers have started developing Computer Aided Detection (CAD) algorithms to be applied to CT scans. Several studies reported an improvement in the sensitivity of radiologists when assisted by CAD systems. So far, the most common way to make CAD algorithms available in the clinical routine of health facilities is thedeployment of standalone workstations, usually equipped with a vendor-dependent Graphic User Interface (GUI). This approach presents several drawbacks, such as the high fixed cost of the software licenses, hardware and the obsolescence of both. In this paper we present a PHD project aiming at: developing and improving CADs for automatic detection of pulmonary nodules and their features, spreading the usage of CADs inside clinical practice, investigating the impact of CAD algorithms on the performance of radiodioligsts when assisted by CADs during clinical practice. In relation to the first goal we present some of the recent challenges related to the improvement of CADs, like for example the possiblity to predict the maglignancy of a nodule starting from some computed feature of the nodule itself. In the second part we analyze the big issues that have been limitating the diffusion of CADs in clinical practice and we propose a possible solution to tackle them. In the third part we propose some observer studies in order, not only to investigate the impact of CAD on the performance of radioligsts, but also to determine the most to insert CADs in clinical practice.

References

  1. Awai, K., Murao, K., Ozawa, A., Komi, M., Hayakawa, H., Hori, S., and Nishimura, Y. (2004). Pulmonary nodules at chest ct: Effect of computer-aided diagnosis on radiologists detection performance 1. Radiology, 230(2):347-352.
  2. B., V. G. et al. (2013). Cirrus lung: an optimized workflow for quantitative image analysis of thoracic computed tomography and chest radiography for major pulmonary diseases: chronic obstructive pulmonary disease, lung cancer and tuberculosis. In RSNA.
  3. Bellotti, R. et al. (2007). Distributed medical images analysis on a grid infrastructure. Future Generation Computer Systems, 23(3):475-484.
  4. Berzano, D. (2014). Elastiq,github.com/dberzano/elastiq.
  5. Beyer, F., Zierott, L., Fallenberg, E., Juergens, K., Stoeckel, J., Heindel, W., and Wormanns, D. (2007). Comparison of sensitivity and reading time for the use of computer-aided detection (cad) of pulmonary nodules at mdct as concurrent or second reader. European Radiology, 17(11):2941-2947.
  6. Brochu, B., Beigelman-Aubry, C., Goldmard, J., Raffy, P., Grenier, P., and Lucidarme, O. (2007). Evaluation de limpact dun systeme cad sur la performance des radiologues pour la d├ętection des nodules pulmonaires sur des examens scanographiques multicoupes du thorax. Journal de Radiologie, 88(4):573-578.
  7. Brown, M. et al. (2005). Computer-aided lung nodule detection in ct: Results of large-scale observer test1. Academic Radiology, 12(6):681-686.
  8. Buncic, P., Sanchez, C. A., Blomer, J., Franco, L., Harutyunian, A., Mato, P., and Yao, Y. (2010). Cernvma virtual software appliance for lhc applications. In Journal of Physics: Conference Series, volume 219, page 042003. IOP Publishing.
  9. Cerello, P. et al. (2008). The channeler ant model: object segmentation with virtual ant colonies. In Nuclear Science Symposium Conference Record, 2008. NSS'08. IEEE, pages 3147-3152. IEEE.
  10. Coombs, K. (2009). Drupal done right. Library journal, 134(19):30-32.
  11. Das, M., Muhlenbruch, G., Mahnken, A. H., Flohr, T. G., Gundel, L., Stanzel, S., Kraus, T., Gunther, R. W., and Wildberger, J. (2006). Small pulmonary nodules: Effect of two computer-aided detection systems on radiologist performance 1. Radiology, 241(2):564-571.
  12. De Nunzio, G. et al. (2011). Automatic lung segmentation in ct images with accurate handling of the hilar region. Journal of digital imaging, 24(1):11-27.
  13. Ferlay, J., Parkin, D., and Steliarova-Foucher, E. (2010). Estimates of cancer incidence and mortality in europe in 2008. European Journal of Cancer, 46(4):765-781.
  14. Ibanez, L., Schroeder, W., Ng, L., and Cates, J. (2003). The itk software guide.
  15. Jemal, A., Siegel, R., Ward, E., Hao, Y., Xu, J., and Thun, M. (2009). Cancer statistics, 2009. CA: a cancer journal for clinicians, 59(4):225-249.
  16. Jemal, A., Siegel, R., Xu, J., and Ward, E. (2010). Cancer statistics, 2010. CA: a cancer journal for clinicians, 60(5):277-300.
  17. Klein, S. et al. (2010). Elastix: a toolbox for intensity-based medical image registration. Medical Imaging, IEEE Transactions on, 29(1):196-205.
  18. Lamanna, M. (2004). The lhc computing grid project at cern. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 534(1):1-6.
  19. Lassen, B., Jacobs, C., Kuhnigk, J., van Ginneken, B., and van Rikxoort, E. (2015). Robust semi-automatic segmentation of pulmonary subsolid nodules in chest computed tomography scans. Physics in medicine and biology, 60(3):1307.
  20. Li, Q., Sone, S., and Doi, K. (2003). Selective enhancement filters for nodules, vessels, and airway walls in two-and three-dimensional ct scans. Medical physics, 30(8):2040-2051.
  21. MacMahon, H., Austin, J. H., Gamsu, G., Herold, C. J., Jett, J., Naidich, D., Patz Jr, E. F., and Swensen, S. (2005). Guidelines for management of small pulmonary nodules detected on ct scans: a statement from the fleischner society 1. Radiology, 237(2):395-400.
  22. Matsumoto, S., Ohno, Y., Aoki, T., Yamagata, H., Nogami, ., Matsumoto, K., Yamashita, Y., and Sugimura, K. (2013). Computer-aided detection of lung nodules on multidetector ct in concurrent-reader and secondreader modes: A comparative study. European Journal of Radiology, 82(8):1332-1337.
  23. Matsumoto, S., Ohno, Y., Yamagata, H., T., D., and Sugimura, K. (2008). Computer-aided detection of lung nodules on multidetector row computed tomography using three-dimensional analysis of nodule candidates and their surroundings. Radiation medicine, 26(9):562-569.
  24. Mell, P. and Grance, T. (2011). The nist definition of cloud computing.
  25. Milojic?ic, D., Llorente, I. M., and Montero, R. S. (2011). Opennebula: A cloud management tool. IEEE Internet Computing, (2):11-14.
  26. Morse, B. S., Yoo, T. S., Rheingans, P., Chen, D. T., and Subramanian, K. R. (2005). Interpolating implicit surfaces from scattered surface data using compactly supported radial basis functions. In ACM SIGGRAPH 2005 Courses, page 78. ACM.
  27. Nakayama, R., Nakako, N., Namba, K., Hizukuri, A., Nagasawa, N., Kobayashi, S., and Takeda, K. (2012). 14th international workshop on computer-aided diagnosis. Int J CARS, 7(1):S485-S496.
  28. Retico, A., Delogu, P., Fantacci, M., Gori, I., and Martinez, A. (2008). Lung nodule detection in low-dose and thin-slice computed tomography. Computers in biology and medicine, 38(4):525-534.
  29. Retico, A., Fantacci, M., Gori, I., Kasae, P., Golosio, B., Piccioli, A., Cerello, P., De Nunzio, G., and Tangaro, S. (2009). Pleural nodule identification in low-dose and thin-slice lung computed tomography. Computers in biology and medicine, 39(12):1137-1144.
  30. Tannenbaum, T., Wright, D., Miller, K., and Livny, M. (2001). Condor: a distributed job scheduler. In Beowulf cluster computing with Linux, pages 307-350. MIT press.
  31. Team, N. L. S. T. R. et al. (2011). Reduced lungcancer mortality with low-dose computed tomographic screening. The New England journal of medicine, 365(5):395.
  32. Torres, E. L., Fiorina, E., Pennazio, F., Peroni, C., Saletta, M., Camarlinghi, N., Fantacci, M., and Cerello, P. (2015). Large scale validation of the m5l lung cad on heterogeneous ct datasets. Medical Physics, 42(4):1477-1489.
  33. Turner IV, W. P., PE, J., Seader, P., and Brill, K. (2006). Tier classification define site infrastructure performance. Uptime Institute, 17.
  34. van Ginneken, B. et al. (2010). Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: the anode09 study. Medical Image Analysis, 14(6):707-722.
Download


Paper Citation


in Harvard Style

Traverso A. (2016). Development and Application in Clinical Routine of Computer Aided Detection (CAD) Algorithms for the Identification of Pulmonary Nodules . In Doctoral Consortium - DCBIOSTEC, ISBN , pages 24-34


in Bibtex Style

@conference{dcbiostec16,
author={Alberto Traverso},
title={Development and Application in Clinical Routine of Computer Aided Detection (CAD) Algorithms for the Identification of Pulmonary Nodules},
booktitle={Doctoral Consortium - DCBIOSTEC,},
year={2016},
pages={24-34},
publisher={SciTePress},
organization={INSTICC},
doi={},
isbn={},
}


in EndNote Style

TY - CONF
JO - Doctoral Consortium - DCBIOSTEC,
TI - Development and Application in Clinical Routine of Computer Aided Detection (CAD) Algorithms for the Identification of Pulmonary Nodules
SN -
AU - Traverso A.
PY - 2016
SP - 24
EP - 34
DO -