Pulmonary nodules: estimation of malignancy at thin-section helical CT--effect of computer-aided diagnosis on performance of radiologists

[Automatic detection of pulmonary nodules on computed tomography: a preliminary study]

OBJECTIVES

Recent years have seen growing interest in the development of algorithms for computer-assisted diagnosis (CAD) for the detection of pulmonary nodules on both plain-film radiographs and computed tomography (CT) studies. The purpose of CAD algorithms in this context is to alert radiologists to suspicious radioopacities that might represent cancer in the images. We are developing a CAD system for the detection of pulmonary nodules on helical CT images.

MATERIAL AND METHODS

We collected cases of patients with pulmonary nodules examined with helical CT. A total of 64 nodules, including both calcified and noncalcified lesions, ranging from 3 to 30 mm in diameter were included in the study. Studies were acquired on one 4-slice and one 64-slice CT scanners. Three chest radiologists at two institutions interpreted the studies to determine whether pulmonary nodules were present. We calculated the sensitivity and the number of false positives per image to evaluate the CAD system.

RESULTS

We have developed and evaluated an algorithm for the automatic detection of pulmonary nodules on CT images. For a sensitivity of 76%, the false-positive rate was 1.3 per image.

CONCLUSIONS

Our preliminary results suggest that the system might be useful for radiologists in the detection of pulmonary nodules on helical CT images.

Differentiation of urinary stone and vascular calcifications on non-contrast CT images: an initial experience using computer aided diagnosis

The purpose of this study was to develop methods for the differentiation of urinary stones and vascular calcifications using computer-aided diagnosis (CAD) of non-contrast computed tomography (CT) images. From May 2003 to February 2004, 56 patients that underwent a pre-contrast CT examination and subsequently diagnosed as ureter stones were included in the study. Fifty-nine ureter stones and 53 vascular calcifications on pre-contrast CT images of the patients were evaluated. The shapes of the lesions including disperseness, convex hull depth, and lobulation count were analyzed for patients with ureter stones and vascular calcifications. In addition, the internal textures including edge density, skewness, difference histogram variation (DHV), and the gray-level co-occurrence matrix moment were also evaluated for the patients. For evaluation of the diagnostic accuracy of the shape and texture features, an artificial neural network (ANN) and receiver operating characteristics curve (ROC) analyses were performed. Of the several shape factors, disperseness showed a statistical difference between ureter stones and vascular calcifications (p < 0.05). For the internal texture features, skewness and DHV showed statistical differences between ureter stones and vascular calcifications (p < 0.05). The performance of the ANN was evaluated by examining the area under the ROC curves (AUC, A (z)). The A (z) value was 0.85 for the shape parameters and 0.88 for the texture parameters. In this study, several parameters regarding shape and internal texture were statistically different between ureter stones and vascular calcifications. The use of CAD would make it possible to differentiate ureter stones from vascular calcifications by a comparison of these parameters.

Binary and multi-category ratings in a laboratory observer performance study: a comparison

The authors investigated radiologists, performances during retrospective interpretation of screening mammograms when using a binary decision whether to recall a woman for additional procedures or not and compared it with their receiver operating characteristic (ROC) type performance curves using a semi-continuous rating scale. Under an Institutional Review Board approved protocol nine experienced radiologists independently rated an enriched set of 155 examinations that they had not personally read in the clinic, mixed with other enriched sets of examinations that they had individually read in the clinic, using both a screening BI-RADS rating scale (recall/not recall) and a semi-continuous ROC type rating scale (0 to 100). The vertical distance, namely the difference in sensitivity levels at the same specificity levels, between the empirical ROC curve and the binary operating point were computed for each reader. The vertical distance averaged over all readers was used to assess the proximity of the performance levels under the binary and ROC-type rating scale. There does not appear to be any systematic tendency of the readers towards a better performance when using either of the two rating approaches, namely four readers performed better using the semi-continuous rating scale, four readers performed better with the binary scale, and one reader had the point exactly on the empirical ROC curve. Only one of the nine readers had a binary "operating point" that was statistically distant from the same reader's empirical ROC curve. Reader-specific differences ranged from -0.046 to 0.128 with an average width of the corresponding 95% confidence intervals of 0.2 and p-values ranging for individual readers from 0.050 to 0.966. On average, radiologists performed similarly when using the two rating scales in that the average distance between the run in individual reader's binary operating point and their ROC curve was close to zero. The 95% confidence interval for the fixed-reader average (0.016) was (-0.0206, 0.0631) (two-sided p-value 0.35). In conclusion the authors found that in retrospective observer performance studies the use of a binary response or a semi-continuous rating scale led to consistent results in terms of performance as measured by sensitivity-specificity operating points.

Is the computer-aided detection scheme for lung nodule also useful in detecting lung cancer?

OBJECTIVE

To evaluate the impact of a computer-aided diagnosis (CAD) system on the performance of observers for the detection of both lung nodules and lung cancers.

MATERIALS AND METHODS

One hundred fifty computed tomographic scans were evaluated. Database included 23 lung cancers (long diameter <20 mm), nodules stable for at least 2 years, and normal cases. Five chest radiologists and 5 radiology residents each independently recorded the locus of each nodule candidate and assigned a confidence score for the likelihood of nodule and malignancy without CAD; then, the interpretation was repeated with the use of CAD. A consensus panel of 2 chest radiologists served as a reference standard for the nodules. Histological confirmation was a reference standard for the cancers. The performances of the observers for the detection of nodules and cancer with and without CAD were compared using jackknife free-response receiver operating characteristic analysis.

RESULTS

The performance of detecting lung nodules was increased significantly with CAD for all radiologists and subgroups (P < 0.01). Although the overall performance of detecting lung cancers was not affected significantly with the use of CAD (P > 0.05), 4 lung cancers missed by 3 residents on their initial observation were additionally detected with CAD. Eighteen of 23 lung cancers were detected by CAD itself.

CONCLUSIONS

The overall radiologists' performance of detecting lung nodules was improved significantly with the use of CAD, whereas no statistical significance was observed for the detection of lung cancers. The use of CAD, however, contributed to the detection of additional lung cancers for less experienced readers.

Computer-aided diagnosis of lung cancer and pulmonary embolism in computed tomography-a review

Computer-aided detection (CADe) and computer-aided diagnosis (CADx) have been important areas of research in the last two decades. Significant progress has been made in the area of breast cancer detection, and CAD techniques are being developed in many other areas. Recent advances in multidetector row computed tomography have made it an increasingly common modality for imaging of lung diseases. A thoracic examination using thin-section computed tomography contains hundreds of images. Detection of lung cancer and pulmonary embolism on computed tomographic (CT) examinations are demanding tasks for radiologists because they have to search for abnormalities in a large number of images, and the lesions can be subtle. If successfully developed, CAD can be a useful second opinion to radiologists in thoracic CT interpretation. In this review, we summarize the studies that have been reported in these areas, discuss some challenges in the development of CAD, and identify areas that deserve particular attention in future research.

Volume CT: State-of-the-Art Reporting

OBJECTIVE

CT has undergone generational change that has led to true volume imaging. Interpretation of volume images requires interaction between the radiologist and the volume data sets. The aim of this review is to examine postprocessing options and the evidence in the literature for changing the process of reporting to digital volume reporting.

CONCLUSION

Diagnostic confidence and the accuracy of interpretation of volume CT images have increased with improvements in postprocessing techniques.

Differential diagnosis of ground-glass opacity nodules: CT number analysis by three-dimensional computerized quantification

OBJECTIVES

To differentiate among atypical adenomatous hyperplasia (AAH), bronchioloalveolar carcinoma (BAC), and adenocarcinoma showing ground-glass opacity (GGO) on CT scans, we conducted a study to determine the optimal parameter on CT number analysis using three-dimensional (3D) computerized quantification.

METHODS

From the CT numbers of GGO lesions obtained by 3D computerized quantification, CT number histogram pattern, peak CT number on the histogram, mean CT number, and the 5th to 95th percentile CT numbers were analyzed to determine the optimal parameter for differentiation among AAH (n = 10), BAC (n = 21), and adenocarcinoma (n = 12).

RESULTS

While the CT number histogram showed one peak in all 10 of the AAH lesions (100%), it showed two peaks in 8 of 21 BAC lesions (38%), and in 5 of 12 adenocarcinoma lesions (42%). For differentiation between AAH and BAC, the 75th percentile CT number with a cutoff value of -584 Hounsfield units (HU) was optimal, with a sensitivity of 0.90 and a specificity of 0.81. For differentiation between BAC and adenocarcinoma, a mean CT number with a cutoff value of -472 HU was optimal, with a sensitivity of 0.75 and a specificity of 0.81.

CONCLUSIONS

From the analysis of CT numbers of GGO lesions obtained by 3D computerized quantification, we conclude the following: (1) two peaks on the CT number histogram can rule out AAH; (2) the 75th percentile is the optimal CT number for differentiating between AAH and BAC; and (3) the mean CT number is the optimal CT number for differentiating between BAC and adenocarcinoma.

Nodular Ground-Glass Opacity at Thin-Section CT: Histologic Correlation and Evaluation of Change at Follow-up

The popularization of computed tomography (CT) in clinical practice and the introduction of mass screening for early lung cancer with the use of CT have increased the frequency of findings of subtle nodules or nodular ground-glass opacity. Nodular ground-glass opacity may be observed in malignancies such as bronchioloalveolar carcinoma and adenocarcinoma, as well as in their putative precursors, such as atypical adenomatous hyperplasia. Nodular ground-glass opacity also may be seen in the presence of benign conditions, including focal interstitial fibrosis, inflammation, and hemorrhage. The persistence of nodular ground-glass opacity over time may be strongly suggestive of an early-stage malignancy, especially if the lesion increases in size or includes a solid component that increases in its extent. Persistent nodular ground-glass opacity also may remain stable in size but show increased attenuation. The more extensive the solid portions of the lesion, the higher the probability of malignancy and the poorer the prognosis. An awareness of the clinical setting, in addition to familiarity with the thin-section CT features of nodular ground-glass opacity at initial and follow-up imaging over several months, can help identify malignancy and achieve an accurate diagnosis. A meticulous evaluation of those CT features, and their correlation with specific histopathologic characteristics, also may enable a more accurate prognosis in cases of neoplastic disease.