Korean J Radiol.  2014 Jun;15(3):386-396. 10.3348/kjr.2014.15.3.386.

Computer-Aided Classification of Visual Ventilation Patterns in Patients with Chronic Obstructive Pulmonary Disease at Two-Phase Xenon-Enhanced CT

• Yoon SH
• Goo JM
• Jung J
• Hong H
• Park EA
• Lee CH
• Lee Y
• Jin KN
• Choo JY
• Lee NK

• KMID: 2078650
• DOI: http://doi.org/10.3348/kjr.2014.15.3.386

Abstract

OBJECTIVE
To evaluate the technical feasibility, performance, and interobserver agreement of a computer-aided classification (CAC) system for regional ventilation at two-phase xenon-enhanced CT in patients with chronic obstructive pulmonary disease (COPD).
MATERIALS AND METHODS
Thirty-eight patients with COPD underwent two-phase xenon ventilation CT with resulting wash-in (WI) and wash-out (WO) xenon images. The regional ventilation in structural abnormalities was visually categorized into four patterns by consensus of two experienced radiologists who compared the xenon attenuation of structural abnormalities with that of adjacent normal parenchyma in the WI and WO images, and it served as the reference. Two series of image datasets of structural abnormalities were randomly extracted for optimization and validation. The proportion of agreement on a per-lesion basis and receiver operating characteristics on a per-pixel basis between CAC and reference were analyzed for optimization. Thereafter, six readers independently categorized the regional ventilation in structural abnormalities in the validation set without and with a CAC map. Interobserver agreement was also compared between assessments without and with CAC maps using multirater kappa statistics.
RESULTS
Computer-aided classification maps were successfully generated in 31 patients (81.5%). The proportion of agreement and the average area under the curve of optimized CAC maps were 94% (75/80) and 0.994, respectively. Multirater kappa value was improved from moderate (kappa = 0.59; 95% confidence interval [CI], 0.56-0.62) at the initial assessment to excellent (kappa = 0.82; 95% CI, 0.79-0.85) with the CAC map.
CONCLUSION
Our proposed CAC system demonstrated the potential for regional ventilation pattern analysis and enhanced interobserver agreement on visual classification of regional ventilation.

Keyword

Computer-aided classification; Computed tomography; Chronic obstructive pulmonary disease; Regional ventilation; Xenon CT

MeSH Terms

Aged
Area Under Curve
Feasibility Studies
Female
Humans
Male
Middle Aged
Observer Variation
Pulmonary Disease, Chronic Obstructive/physiopathology/*radiography
Pulmonary Emphysema/physiopathology/radiography
*Respiration
Retrospective Studies
Tomography, X-Ray Computed/*methods
Xenon/*diagnostic use
Xenon

Figure

• 

  Fig. 1 Overall strategy of CAC system with multi-step post-processing procedures. CAC = computer-aided classification, WI = wash-in, WO = wash-out

• 

  Fig. 2 Determination of xenon attenuation in CAC system. A. Estimation of thresholds in xenon attenuation histogram. Two thresholds (Tlow, Thigh) are estimated by calculating mean and standard deviation of xenon attenuation histogram. t(x) is attenuation type of pixel x, A(x) is xenon attenuation of pixel x, µ is mean value of xenon attenuation histogram, σ is standard deviation of xenon attenuation histogram, w is weight, and, α, β are coefficients for weight. B. Representative image of automatic estimation of weight for thresholds using ratio of normal area to whole area using sigma function. Yellow represents abnormal low-attenuating parenchyma with attenuation values less than -950 HU. Weight w is automatically estimated by calculating ratio of normal area to whole lung. CAC = computer-aided classification, HU = Hounsfield units

• 

  Fig. 3 Decision rule of CAC system in classifying regional ventilation patterns. CAC = computer-aided classification, WI = wash-in, WO = wash-out

• 

  Fig. 4 Flowchart of optimization and validation of CAC system. CAC = computer-aided classification

• 

  Fig. 5 Representative images of patterns A and C for structural abnormalities in 64-year-old male with Gold stage I emphysema. Large subpleural bulla in right basal lung on CT (A; arrows) shows high attenuation on wash-in xenon-enhanced image (B) and iso-attenuation on wash-out xenon-enhanced image (C). This ventilation pattern is compatible with pattern A shown on CAC map in blue (D). Small subpleural bulla anterior to large bulla on CT (A; arrowhead) shows low attenuation on wash-in (B) and wash-out xenon-enhanced images (C). This ventilation pattern is in agreement with pattern C and is correctly visualized on CAC map in red (D). CAC = computer-aided classification

• 

  Fig. 6 Representative image of patterns B and D for structural abnormalities in 72-year-old male with Gold stage II emphysema. Small subpleural bulla in right upper lobe on CT (A; arrowheads) shows high attenuation on wash-in (B) and wash-out xenon-enhanced images (C), which is compatible with pattern B shown in CAC map in sky blue (D). Large subpleural bulla in right lower lobe on CT (A; arrows) shows low attenuation on wash-in (B) and wash-out xenon-enhanced images (C). This ventilation pattern is in agreement with pattern D and is correctly visualized on CAC map in yellow (D). CAC = computer-aided classification

Reference

1. Rabe KF, Hurd S, Anzueto A, Barnes PJ, Buist SA, Calverley P, et al. Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary. Am J Respir Crit Care Med. 2007; 176:532–555.

2. Murray CJ, Lopez AD. Alternative projections of mortality and disability by cause 1990-2020: Global Burden of Disease Study. Lancet. 1997; 349:1498–1504.

3. Matsuoka S, Yamashiro T, Washko GR, Kurihara Y, Nakajima Y, Hatabu H. Quantitative CT assessment of chronic obstructive pulmonary disease. Radiographics. 2010; 30:55–66.

4. Yoon SH, Goo JM, Goo HW. Quantitative thoracic CT techniques in adults: can they be applied in the pediatric population? Pediatr Radiol. 2013; 43:308–314.

5. Driehuys B, Martinez-Jimenez S, Cleveland ZI, Metz GM, Beaver DM, Nouls JC, et al. Chronic obstructive pulmonary disease: safety and tolerability of hyperpolarized 129Xe MR imaging in healthy volunteers and patients. Radiology. 2012; 262:279–289.

6. Kirby M, Mathew L, Heydarian M, Etemad-Rezai R, McCormack DG, Parraga G. Chronic obstructive pulmonary disease: quantification of bronchodilator effects by using hyperpolarized ³He MR imaging. Radiology. 2011; 261:283–292.

7. Park EA, Goo JM, Park SJ, Lee HJ, Lee CH, Park CM, et al. Chronic obstructive pulmonary disease: quantitative and visual ventilation pattern analysis at xenon ventilation CT performed by using a dual-energy technique. Radiology. 2010; 256:985–997.

8. Kim WW, Lee CH, Goo JM, Park SJ, Kim JH, Park EA, et al. Xenon-enhanced dual-energy CT of patients with asthma: dynamic ventilation changes after methacholine and salbutamol inhalation. AJR Am J Roentgenol. 2012; 199:975–981.

9. Chae EJ, Seo JB, Kim N, Song KS, Shin JH, Kim TH, et al. Collateral ventilation in a canine model with bronchial obstruction: assessment with xenon-enhanced dual-energy CT. Radiology. 2010; 255:790–798.

10. Goo HW, Yang DH, Kim N, Park SI, Kim DK, Kim EA. Collateral ventilation to congenital hyperlucent lung lesions assessed on xenon-enhanced dynamic dual-energy CT: an initial experience. Korean J Radiol. 2011; 12:25–33.

11. Hersh CP, Washko GR, Jacobson FL, Gill R, Estepar RS, Reilly JJ, et al. Interobserver variability in the determination of upper lobe-predominant emphysema. Chest. 2007; 131:424–431.

12. Mets OM, Smit EJ, Mohamed Hoesein FA, Gietema HA, Bokkers RP, Attrach M, et al. Visual versus automated evaluation of chest computed tomography for the presence of chronic obstructive pulmonary disease. PLoS One. 2012; 7:e42227.

13. Gierada DS, Pilgram TK, Ford M, Fagerstrom RM, Church TR, Nath H, et al. Lung cancer: interobserver agreement on interpretation of pulmonary findings at low-dose CT screening. Radiology. 2008; 246:265–272.

14. Watadani T, Sakai F, Johkoh T, Noma S, Akira M, Fujimoto K, et al. Interobserver variability in the CT assessment of honeycombing in the lungs. Radiology. 2013; 266:936–944.

15. Park SO, Seo JB, Kim N, Park SH, Lee YK, Park BW, et al. Feasibility of automated quantification of regional disease patterns depicted on high-resolution computed tomography in patients with various diffuse lung diseases. Korean J Radiol. 2009; 10:455–463.

16. Sluimer IC, van Waes PF, Viergever MA, van Ginneken B. Computer-aided diagnosis in high resolution CT of the lungs. Med Phys. 2003; 30:3081–3090.

17. Uppaluri R, Hoffman EA, Sonka M, Hartley PG, Hunninghake GW, McLennan G. Computer recognition of regional lung disease patterns. Am J Respir Crit Care Med. 1999; 160:648–654.

18. Jeon KN, Goo JM, Lee CH, Lee Y, Choo JY, Lee NK, et al. Computer-aided nodule detection and volumetry to reduce variability between radiologists in the interpretation of lung nodules at low-dose screening computed tomography. Invest Radiol. 2012; 47:457–461.

19. Chae EJ, Seo JB, Goo HW, Kim N, Song KS, Lee SD, et al. Xenon ventilation CT with a dual-energy technique of dual-source CT: initial experience. Radiology. 2008; 248:615–624.

20. Yim Y, Hong H. Correction of segmented lung boundary for inclusion of pleural nodules and pulmonary vessels in chest CT images. Comput Biol Med. 2008; 38:845–857.

21. Yim Y, Hong H, Shin YG. Deformable lung registration between exhale and inhale CT scans using active cells in a combined gradient force approach. Med Phys. 2010; 37:4307–4317.

22. Crewson PE. Reader agreement studies. AJR Am J Roentgenol. 2005; 184:1391–1397.

23. Han MK, Agusti A, Calverley PM, Celli BR, Criner G, Curtis JL, et al. Chronic obstructive pulmonary disease phenotypes: the future of COPD. Am J Respir Crit Care Med. 2010; 182:598–604.

24. Shah PL, Hopkinson NS. Bronchoscopic lung volume reduction for emphysema: where next? Eur Respir J. 2012; 39:1287–1289.

25. Shah PL, Geddes DM. Collateral ventilation and selection of techniques for bronchoscopic lung volume reduction. Thorax. 2012; 67:285–286.