TY - JOUR
T1 - Automated CT Scoring of Airway Diseases. Preliminary Results
AU - Odry, Benjamin L.
AU - Kiraly, Atilla P.
AU - Godoy, Myrna C.B.
AU - Ko, Jane
AU - Naidich, David P.
AU - Novak, Carol L.
AU - Lerallut, Jean Francois
PY - 2010/9
Y1 - 2010/9
N2 - Rationale and Objectives: The aim of this study was to retrospectively evaluate an automated global scoring system for evaluating the extent and severity of disease in a known cohort of patients with documented bronchiectasis. On the basis of a combination of validated three-dimensional automated algorithms for bronchial tree extraction and quantitative airway measurements, global scoring combines the evaluation of bronchial lumen-to-artery ratios and bronchial wall-to-artery ratios, as well as the detection of mucoid-impacted airways. The result is an automatically generated global computed tomographic (CT) score designed to simplify and standardize the interpretation of scans in patients with chronic airway infections. Materials and Methods: Twenty high-resolution CT data sets were used to evaluate an automated CT scoring method that combines algorithms for airway quantitative analysis that have been individually tested and validated. Patients with clinically documented atypical mycobacterial infections with visually assessed CT evidence of bronchiectasis varying from mild to severe were retrospectively selected. These data sets were evaluated by two independent experienced radiologists and by computer scoring, with the results compared statistically, including Spearman's rank correlation. Results: Computer evaluation required 3 to 5 minutes per data set, compared to 12 to 15 minutes for manual scoring. Initial Spearman's rank tests showed positive correlations between automated and readers' global scores (r = 0.609, P = .01), extent of bronchiectasis (r = 0.69, P = 0004), and severity of bronchiectasis (r = 0.61, P = 01), while mucus plug detection showed a lesser extent of positive correlation between the scoring methods (r = 0.42, P = 07) and wall thickness a negative weak correlation (r = -0.10, P = 40). Further retrospective review of 24 lobes in which wall thickness scores showed the highest discrepancy between manual and automated methods was then performed, using electronic calipers and perpendicular cross-sections to reassess airway measurements. This resulted in an improved Spearman's rank correlation to r = 0.62 (P = 009), for a global score of r = 0.67 (P = 001). Conclusion: Automated computerized scoring shows considerable promise for providing a standardized, quantitative method, demonstrating overall good correlation with the results of experienced readers' evaluation of the extent and severity of bronchiectasis. It is speculated that this technique may also be applicable to a wide range of other conditions associated with chronic bronchial inflammation, as well as of potential value for monitoring response to therapy in these same populations.
AB - Rationale and Objectives: The aim of this study was to retrospectively evaluate an automated global scoring system for evaluating the extent and severity of disease in a known cohort of patients with documented bronchiectasis. On the basis of a combination of validated three-dimensional automated algorithms for bronchial tree extraction and quantitative airway measurements, global scoring combines the evaluation of bronchial lumen-to-artery ratios and bronchial wall-to-artery ratios, as well as the detection of mucoid-impacted airways. The result is an automatically generated global computed tomographic (CT) score designed to simplify and standardize the interpretation of scans in patients with chronic airway infections. Materials and Methods: Twenty high-resolution CT data sets were used to evaluate an automated CT scoring method that combines algorithms for airway quantitative analysis that have been individually tested and validated. Patients with clinically documented atypical mycobacterial infections with visually assessed CT evidence of bronchiectasis varying from mild to severe were retrospectively selected. These data sets were evaluated by two independent experienced radiologists and by computer scoring, with the results compared statistically, including Spearman's rank correlation. Results: Computer evaluation required 3 to 5 minutes per data set, compared to 12 to 15 minutes for manual scoring. Initial Spearman's rank tests showed positive correlations between automated and readers' global scores (r = 0.609, P = .01), extent of bronchiectasis (r = 0.69, P = 0004), and severity of bronchiectasis (r = 0.61, P = 01), while mucus plug detection showed a lesser extent of positive correlation between the scoring methods (r = 0.42, P = 07) and wall thickness a negative weak correlation (r = -0.10, P = 40). Further retrospective review of 24 lobes in which wall thickness scores showed the highest discrepancy between manual and automated methods was then performed, using electronic calipers and perpendicular cross-sections to reassess airway measurements. This resulted in an improved Spearman's rank correlation to r = 0.62 (P = 009), for a global score of r = 0.67 (P = 001). Conclusion: Automated computerized scoring shows considerable promise for providing a standardized, quantitative method, demonstrating overall good correlation with the results of experienced readers' evaluation of the extent and severity of bronchiectasis. It is speculated that this technique may also be applicable to a wide range of other conditions associated with chronic bronchial inflammation, as well as of potential value for monitoring response to therapy in these same populations.
KW - CT scoring for airway diseases
KW - Computer-aided diagnosis
UR - http://www.scopus.com/inward/record.url?scp=77955414949&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77955414949&partnerID=8YFLogxK
U2 - 10.1016/j.acra.2010.04.019
DO - 10.1016/j.acra.2010.04.019
M3 - Article
C2 - 20576450
AN - SCOPUS:77955414949
SN - 1076-6332
VL - 17
SP - 1136
EP - 1145
JO - Academic radiology
JF - Academic radiology
IS - 9
ER -