Download PDF
Rofo 2005; 177(2): 188-196
DOI: 10.1055/s-2004-813887
Übersicht

© Georg Thieme Verlag KG Stuttgart · New York

Computerassistierter Nachweis und automatisierte Volumetrie pulmonaler Rundherde in der Multislice-CT: Aktueller Stand und Perspektiven

Computer-aided Diagnosis and Volumetry of Pulmonary Nodules: Current Concepts and Future PerspectivesK. Marten1 , E. J. Rummeny1 , C. Engelke1
  • 1Institut für Röntgendiagnostik, Klinikum rechts der Isar der TU München, München
Further Information

Publication History

Publication Date:
24 January 2005 (online)

Also available at
    Permissions and Reprints

Zusammenfassung

Die Entwicklung von Algorithmen für die computerassistierte Detektion (CAD) und Volumenbestimmung kleiner Lungenrundherde in der Multislice-CT dient einer verbesserten Diagnostik und Verlaufsbeurteilung dieser Befunde. Aktuelle Daten zeigen eine verbesserte Detektion vor allem kleiner Herde durch die Verwendung von CAD-Systemen und legen einen Nutzen der computerassistierten Detektion besonders durch erfahrene Radiologen nahe, so dass der routinemäßig eingesetzte Zweitbefunder durch das CAD-System ersetzt werden kann. Darüber hinaus präzisiert der Einsatz automatisierter Volumetrieprogramme die Wachstumsratenbestimmung von Lungenrundherden und bietet somit die Voraussetzung für eine verbesserte Einschätzung der Dignität eines Herdes. In dieser Übersicht werden aktuelle Entwicklungen auf dem Gebiet der computerassistierten Detektion und Volumetrie von Lungenrundherden vorgestellt und offene Fragen hinsichtlich ihres sinnvollen klinischen Einsatzes beleuchtet.

Abstract

For computer-aided detection (CAD) and volumetry of small pulmonary nodules, a number of algorithms have been developed for multislice CT data sets in recent years, with the goal of improving the diagnostic work-up and the follow-up of findings. Recent data show that the detection of small lesions may improve with CAD, suggesting that especially experienced readers may benefit from using CAD systems. This has lead to the recommendation of CAD as a replacement of the second reader in clinical practice. Furthermore, computer-aided volumetry of pulmonary nodules allows a precise determination of nodular growth rates as a prerequisite for a better classification of nodules as benign or malignant. In this article, we review recent developments of CAD and volumetry tools for pulmonary nodules, and address open questions regarding the use of these software tools in clinical routine.

Key words

Computers - computed tomography - lung - lung neoplasms - software reviews

Literatur

  • 1 Diederich S, Wormanns D, Semik M. et al . Screening for early lung cancer with low-dose spiral CT: prevalence in 817 asymptomatic smokers.  Radiology. 2002;  222 773-781
    CrossrefPubMedGoogle Scholar
  • 2 Henschke C I, McCauley D I, Yankelevitz D F. et al . Early lung cancer action project: overall design and findings from baseline screening.  Lancet. 1999;  354 99-104
    CrossrefPubMedGoogle Scholar
  • 3 Pastorino U, Bellomi M, Landoni C. et al . Early lung-cancer detection with spiral CT and positron emission tomography in heavy smokers: 2-year results.  Lancet. 2003;  362 593-597
    CrossrefPubMedGoogle Scholar
  • 4 Nawa T, Nakagawa T, Kusano S. et al . Lung cancer screening using low-dose spiral CT: results of baseline and 1-year follow-up studies.  Chest. 2002;  122 15-20
    CrossrefPubMedGoogle Scholar
  • 5 Sobue T, Moriyama N, Kaneko M. et al . Screening for lung cancer with low-dose helical computed tomography: anti-lung cancer association project.  J Clin Oncol. 2002;  20 911-920
    CrossrefPubMedGoogle Scholar
  • 6 Sone S, Takashima S, Li F. et al . Mass screening for lung cancer with mobile spiral computed tomography scanner.  Lancet. 1998;  351 1242-1245
    CrossrefPubMedGoogle Scholar
  • 7 Sone S, Li F, Yang Z G. et al . Characteristics of small lung cancers invisible on conventional chest radiography and detected by population based screening using spiral CT.  Br J Radiol. 2000;  73 137-145
    PubMedGoogle Scholar
  • 8 Swensen S J, Jett J R, Sloan J A. et al . Screening for lung cancer with low-dose spiral computed tomography.  Am J Respir Crit Care Med. 2002;  165 508-513
    CrossrefPubMedGoogle Scholar
  • 9 Swensen S J. CT screening for lung cancer.  Am J Roentgenol. 2002;  179 833-836
    PubMedGoogle Scholar
  • 10 Ko J P, Betke M. Automated nodule detection and assessment of change over time - preliminary experience.  Radiology. 2001;  218 267-273
    PubMedGoogle Scholar
  • 11 Giger M L, Bae K T, MacMahon H. Computerized detection of pulmonary nodules in computed tomography images.  Invest Radiol. 1994;  29 459-465
    PubMedGoogle Scholar
  • 12 Armato S G, Giger M L, MacMahon H. Automated detection of lung nodules in CT scans: Preliminary results.  Med Phys. 2001;  28 1552-1561
    CrossrefPubMedGoogle Scholar
  • 13 Fiebich M, Wietholt C, Renger B C. et al . Automatic detection of pulmonary nodules in low-dose screening thoracic CT examinations.  Proc SPIE. 1999;  3661 1434
    PubMedGoogle Scholar
  • 14 Fan L, Novak C L, Quian J. et al . Automatic detection of lung nodules from multi-slice low-dose CT images.  Proc SPIE. 2001;  4322 1828-1835
    PubMedGoogle Scholar
  • 15 Satoh H, Ukai Y, Niki N. et al . Computer aided diagnosis system for lung cancer based on retrospective helical CT images.  Proc SPIE. 1999;  3661 1324-1335
    PubMedGoogle Scholar
  • 16 Okomura T, Miwa T, Kako J. et al . Image processing for computer-aided diagnosis of lung cancer screening system by CT (LSCT).  Proc SPIE. 1998;  3338 1314-1322
    PubMedGoogle Scholar
  • 17 Lee Y, Hara T, Fujita H. et al . Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique.  IEEE Trans Med Imaging. 2001;  20 595-604
    CrossrefPubMedGoogle Scholar
  • 18 Lou S, Chang C, Lin K. et al . Object-based deformation technique for 3-D CT lung nodule detection.  Proc SPIE. 1999;  3661 1544-1552
    PubMedGoogle Scholar
  • 19 Brown M S, McNitt-Gray M F, Goldin J G. et al . Patient-specific models for lung nodule detection and surveillance in CT images.  IEEE Trans Med Imaging. 2001;  20 1242-1250
    CrossrefPubMedGoogle Scholar
  • 20 Taguchi H, Kawata Y, Niki N. et al . Lung cancer detection based on helical CT images using curved surface morphology analysis.  Proc SPIE. 1999;  3661 1307-1314
    PubMedGoogle Scholar
  • 21 Croisille P, Souto M, Cova M. et al . Pulmonary nodules: improved detection with vascular segmentation and extraction with spiral CT.  Radiology. 1995;  197 397-401
    PubMedGoogle Scholar
  • 22 Beyer F, Wormanns D, Novak C. et al . [Clinical evaluation of a software for automated localization of lung nodules at follow-up CT examinations].  Fortschr Röntgenstr. 2004;  176 829-836
    Article in Thieme ConnectPubMedGoogle Scholar
  • 23 Ko J P, Naidich D P. Computer-aided diagnosis and the evaluation of lung disease.  J Thorac Imaging. 2004;  19 136-155
    PubMedGoogle Scholar
  • 24 Armato S G, Giger M L, Moran C J. et al . Computerized detection of pulmonary nodules on CT scans.  Radiographics. 1999;  19 1303-1311
    PubMedGoogle Scholar
  • 25 Wormanns D, Fiebich M, Saidi M. et al . Automatic detection of pulmonary nodules at spiral CT: clinical application of a computer-aided diagnosis system.  Eur Radiol. 2002;  12 1052-1057
    CrossrefPubMedGoogle Scholar
  • 26 Giger M L, Bae K T, MacMahon H. Computerized detection of pulmonary nodules in computed tomography images.  Invest Radiol. 1994;  29 459-465
    PubMedGoogle Scholar
  • 27 Zhao B, Gamsu G, Ginsberg M S. et al . Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm.  J Appl Clin Med Phys. 2003;  4 248-260
    CrossrefPubMedGoogle Scholar
  • 28 Kanazawa K, Kawata Y, Niki N. et al . Computer-aided diagnosis for pulmonary nodules based on helical CT images.  Comput Med Imaging Graph. 1998;  22 157-167
    PubMedGoogle Scholar
  • 29 Awai K, Murao K, Ozawa A. et al . Pulmonary nodules at chest CT: effect of computer-aided diagnosis on radiologists’ detection performance.  Radiology. 2004;  230 347-352
    PubMedGoogle Scholar
  • 30 Novak C L, Quian J, Fan L. et al . Interobserver variations on interpretation of multislice CT lung cancer screening studies, and the implications for computer aided diagnosis.  SPIE. 2002;  4686 68-69
    PubMedGoogle Scholar
  • 31 Marten K, Engelke C, Seyfarth T. et al . Computer-aided detection of pulmonary nodules: influence of nodule characteristics on detection performance.  Clin Radiol. 2004; im Druck; 
    PubMedGoogle Scholar
  • 32 Armato S G, Li F, Giger M L. et al . Lung cancer: performance of automated lung nodule detection applied to cancers missed in a CT screening program.  Radiology. 2002;  225 685-692
    PubMedGoogle Scholar
  • 33 Marten K, Seyfarth T, Auer F. et al . Computer-assisted detection of pulmonary nodules: Performance evaluation of an expert knowledge-based detection system in consensus reading with experienced and inexperienced chest radiologists.  Eur Radiol. 2004;  14 1930-1938
    PubMedGoogle Scholar
  • 34 Wormanns D, Beyer F, Diederich S. et al . Diagnostic performance of a commercially available computer-aided diagnosis system for automatic detection of pulmonary nodules: comparison with single and double reading.  Fortschr Röntgenstr. 2004;  176 953-958
    Article in Thieme ConnectPubMedGoogle Scholar
  • 35 Chakraborty D P, Winter L. Free-response methodology: alternate analysis and a new observer-performance experiment.  Radiology. 1990;  174 873-881
    PubMedGoogle Scholar
  • 36 Obuchowski N A. Multireader receiver operating characteristic studies: a comparison of study designs.  Acad Radiol. 1995;  2 709-716
    PubMedGoogle Scholar
  • 37 Novak C L, Fan L, Quian J. et al . Identification of missed pulmonary nodules on low-dose CT lung cancer screening studies using an automatic detection system.  SPIE. 2003;  5034 439-447
    PubMedGoogle Scholar
  • 38 Rubin G, Lyo J, Paik D. et al . Impact of computer-assisted detection (CAD) algorithm vs a second radiologist on reader sensitivity for detecting pulmonary nodules in MDCT scans.  Radiology. 2003;  S293
    PubMedGoogle Scholar
  • 39 Peldschus K, Martensen J, Cheema J. et al . Computer-aided diagnosis of focal lung disease with dedicated visualization tools and automated lesion detection: influence on reader effectiveness.  Radiology. 2003;  S293
    PubMedGoogle Scholar
  • 40 Herzog P, Seyfarth T, Novak C. et al . Performance of a computer-aided diagnosis tool for the detection of pulmonary nodules at multidetector-row CT.  Radiology. 2003;  S292
    PubMedGoogle Scholar
  • 41 Marten K, Seyfarth T, Grillhösl A. et al . Computer-assisted detection of pulmonary nodules: evaluation of diagnostic performance using an expert knowledge-based detection system with variable reconstruction slice thickness settings.  Eur Radiol. 2004;  DOI: DOI: 10.1007/s0030-004-2544-5
    PubMedGoogle Scholar
  • 42 Fischbach F, Knollmann F, Griesshaber V. et al . Detection of pulmonary nodules by multislice computed tomography: improved detection rate with reduced slice thickness.  Eur Radiol. 2003;  13 2378-2383
    CrossrefPubMedGoogle Scholar
  • 43 Kim J, Cho G S, Bae K. Automated detection of pulmonary nodules from multi-slice CT images of varying slice thickness and reconstruction interval.  Radiology. 2003;  S617
    PubMedGoogle Scholar
  • 44 Enquobahrie A, Reeves A P, Yankelevitz D F. et al . Automated detection of solid pulmonary nodules from low dose helical CT scans.  Radiology. 2003;  S618
    PubMedGoogle Scholar
  • 45 Henschke C I, Yankelevitz D F, Mirtcheva R. et al . CT screening for lung cancer: frequency and significance of part-solid and nonsolid nodules.  AJR Am J Roentgenol. 2002;  178 1053-1057
    CrossrefPubMedGoogle Scholar
  • 46 Yankelevitz D F, Gupta R, Zhao B. et al . Small pulmonary nodules: evaluation with repeat CT - preliminary experience.  Radiology. 1999;  212 561-566
    PubMedGoogle Scholar
  • 47 Wormanns D, Kohl G, Klotz E. et al . Volumetric measurements of pulmonary nodules at multi-row detector CT: in vivo reproducibility.  Eur Radiol. 2004;  14 86-92
    CrossrefPubMedGoogle Scholar
  • 48 Gulsun M, Goodman L R, Washington L. et al . CT determination of pulmonary nodule volumes: Interobserver repeatability.  Radiology. 2003;  S440
    PubMedGoogle Scholar
  • 49 Yankelevitz D F, Reeves A P, Kostis W J. et al . Small pulmonary nodules: volumetrically determined growth rates based on CT evaluation.  Radiology. 2000;  217 251-256
    CrossrefPubMedGoogle Scholar
  • 50 Kostis W J, Yankelevitz D F, Reeves A P. et al . Small pulmonary nodules: reproducibility of three-dimensional volumetric measurement and estimation of time to follow-up.  Radiology. 2004;  231 446-452
    CrossrefPubMedGoogle Scholar
  • 51 Marten K, Engelke C, Grabbe E. et al . Flat-panel detector based computed tomography: accuracy of experimental growth rate assessment in pulmonary nodules.  Fortschr Röntgenstr. 2004;  176 752-757
    PubMedGoogle Scholar
  • 52 Marten K, Funke M, Engelke C. Flat panel detector-based volumetric CT: Prototype evaluation with volumetry of small artificial nodules in a pulmonary phantom.  J Thoracic Imaging. 2004;  19 156-163
    PubMedGoogle Scholar

Dr. Katharina Marten

Institut für Röntgendiagnostik, Klinikum rechts der Isar der TU München

Ismaningerstr. 22

81675 München

Phone: 0 89/41 40 26 21

Fax: 0 89/41 40 48 34

Email: Katharina.Marten@roe.med.tum.de

      >