Search

Rationale and Objectives The aims of this study were to assess the influence of slice thickness on the ability of radiologists to detect or not detect nodules and to agree or disagree on the diagnosis and also to investigate the potential dependence of these relations on the sizes, average computed tomographic (CT) values, and locations of the nodules. Materials and Methods Six radiologists performed qualitative diagnostic readings of multislice CT images with a slice thickness of 2 or 10 mm obtained from 360 subjects. The nodules were diagnosed as nodules for further examination (NFEs), inactive nodules for no further examination (INNFEs), or no abnormality. The results of the diagnoses were cross-tabulated and quantitatively analyzed using the average CT values, sizes, and locations of the nodules with reference to the 2-mm slices. Multivariate logistic regression analyses were used to estimate the significant associations of these parameters with the ability of radiologists to detect or not detect nodules and to agree or disagree on the diagnosis. Results Totals of 130 NFEs and 403 INNFEs for 2-mm slice thickness and 142 NFEs and 338 INNFEs for 10-mm slice thickness were diagnosed. Nodule classifications were as follows: the same diagnosis on both slice thickness images (67.6%), different diagnoses on two slice thickness images (21%), missed on 10-mm slice thickness images (10.6%), and misinterpreted on 10-mm slice thickness images (0.7%). Regarding detection and nondetection, NFE diagnoses were influenced by size (odds ratio [OR], 132.50; 95% confidence interval [CI], 4.77–4711) and the average CT value (OR, 27.20; 95% CI, 3.21–645.3), and INNFE diagnoses were influenced by size (OR, 16.10; 95% CI, 6.18–55.19) and the average CT value (OR, 7.67; 95% CI, 2.19–30.91). Regarding diagnostic agreement and disagreement, the NFE diagnoses were influenced by size (OR, 3.60; 95% CI, 1.29–11.04), nodule distance from the lung border (OR, 2.85; 95% CI, 1.27–6.65), and nodule location in the right upper lobe (OR, 0.07; 95% CI, 0.003–0.477), while the INNFE diagnoses were influenced by the average CT value (OR, 11.84; 95% CI, 3.33–55.86), size (OR, 0.42; 95% CI, 0.25–0.70), and nodule distance from the lung border (OR, 0.41; 95% CI, 0.25–0.66). Conclusions The influence of slice thickness on the ability of radiologists to detect or not detect nodules and to agree or disagree on the diagnosis was quantitatively evaluated. Detection and nondetection of NFEs and INNFEs are influenced by size and average CT value. Agreement and disagreement on NFE and INNFE diagnoses are influenced not only by size and average CT value but also, importantly, by the locations of nodules.

Rationale and Objectives. An example-based assisting approach that supports decision making in classifying pulmonary nodules in 3-dimensional (3D) thoracic computed tomography images has been developed. Materials and Methods. The example-based assisting approach retrieves and displays nodules that exhibit morphologic and internal profiles consistent to the nodule in question. It uses a 3D computed tomography image database containing 143 pulmonary nodules for which diagnosis is known. The central module makes possible analysis of the query nodule image and extraction of the features of interest: shape, surrounding structure, and internal structure of the nodules. The principal axes and the compactness characterize the nodule shape. The surrounding and internal structures are represented by the distribution pattern of computed tomography density value and 3D curvature indexes. The nodule representation is then used for computing a similarity measure such as a correlation coefficient and a malignant likelihood of the query nodule. The malignant likelihood is estimated by the difference between the representation patterns of the query case and the retrieved lesions. The Mahalanobis distance was adopted as the difference measure. The approach performance was assessed through leave-one-out method by the false-positive rate. Results. Given a query nodule image, the proposed method retrieved benign and malignant images similar to the query case and provided its malignant likelihood. The number of cases that obtained enough number of the retrieved cases for estimating the malignant likelihood was 107 cases (malignant, 70; benign, 37) in our database. Sensitivity was 91.4% (64 of 70 malignant nodules), specificity was 51.4% (19 of 37 benign nodules), and accuracy values were 77.6% (83 of 107 nodules). Conclusion. Preliminary assessment of this approach showed that an example-based assisting approach is an effective tool for making the diagnostic decision in the classification of pulmonary nodules using the nodule image database.

This paper presents a prospective evaluation of lung cancer screening based on low-dose single helical 3D CT images. This CT screening uses a computer-aided diagnosis (CAD) system to efficiently detect lung nodules from 3D images. The performance of this screening is evaluated by over 5,000 cases for 5 years. The effectiveness of the screening using the CAD system is certified from a large data test.

Our objective is to develop a new computer-aided diagnosis (CAD) system to support effectively the comparative reading using serial helical CT images for lung cancer screening without using the film display. This system can detect the changed size and shape of lung affected by the difference of an inspired air. This algorithm consists of the extraction process of region of interest and the comparison process of each region in serial CT images. We validated the efficiency of this algorithm by application to images of 60 subjects.