Comparison of Artificial Intelligence-Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function Testing
| Autor: | Andreas Fischer, L. Parkwood Griffith, Marly van Assen, Akos Varga-Szemes, Jonathan I. Sperl, Pooyan Sahbaee, U. Joseph Schoepf, John W. Nance |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Adult
Male Spirometry Vital capacity Respiratory physiology DIAGNOSIS Spearman's rank correlation coefficient DISEASE 030218 nuclear medicine & medical imaging Pulmonary function testing chronic obstructive pulmonary disease 03 medical and health sciences 0302 clinical medicine FUTURE MANAGEMENT Humans Medicine OBJECTIVE QUANTIFICATION Radiology Nuclear Medicine and imaging emphysema quantification MACROSCOPIC MORPHOMETRY Aged Retrospective Studies Aged 80 and over Lung medicine.diagnostic_test COMPUTED DENSITY business.industry LUNG DENSITY MORTALITY General Medicine DENSITOMETRY Middle Aged Airway obstruction medicine.disease artificial intelligence Respiratory Function Tests medicine.anatomical_structure Pulmonary Emphysema 030220 oncology & carcinogenesis Radiographic Image Interpretation Computer-Assisted Female Artificial intelligence Tomography X-Ray Computed Densitometry business lung function values CT |
| Zdroj: | American Journal of Roentgenology, 214(5), 1065-1071. AMER ROENTGEN RAY SOC |
| ISSN: | 0361-803X |
| DOI: | 10.2214/ajr.19.21572 |
| Popis: | OBJECTIVE. The purpose of this study was to evaluate an artificial intelligence (AI)based prototype algorithm for fully automated quantification of emphysema on chest CT compared with pulmonary function testing (spirometry).MATERIALS AND METHODS. A total of 141 patients (72 women, mean age +/- SD of 66.46 +/- 9.7 years [range, 23-86 years]; 69 men, mean age of 66.72 +/- 11.4 years [range, 27-91 years]) who underwent both chest CT acquisition and spirometry within 6 months were retrospectively included. The spirometry-based Tiffeneau index (TI; calculated as the ratio of forced expiratory volume in the first second to forced vital capacity) was used to measure emphysema severity; a value less than 0.7 was considered to indicate airway obstruction. Segmentation of the lung based on two different reconstruction methods was carried out by using a deep convolution image-to-image network. This multilayer convolutional neural network was combined with multilevel feature chaining and depth monitoring. To discriminate the output of the network from ground truth, an adversarial network was used during training. Emphysema was quantified using spatial filtering and attenuation-based thresholds. Emphysema quantification and TI were compared using the Spearman correlation coefficient.RESULTS. The mean TI for all patients was 0.57 +/- 0.13. The mean percentages of emphysema using reconstruction methods 1 and 2 were 9.96% +/- 11.87% and 8.04% +/- 10.32%, respectively. AI-based emphysema quantification showed very strong correlation with TI (reconstruction method 1, rho = -0.86; reconstruction method 2, rho = -0.85; both p CONCLUSION. AI-based, fully automated emphysema quantification shows good correlation with TI, potentially contributing to an image-based diagnosis and quantification of emphysema severity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|