Characteristics of regions suspicious for pulmonary nodules at chest radiography

Deep Convolutional Neural Network-based Software Improves Radiologist Detection of Malignant Lung Nodules on Chest Radiographs

Background Multicenter studies are required to validate the added benefit of using deep convolutional neural network (DCNN) software for detecting malignant pulmonary nodules on chest radiographs. Purpose To compare the performance of radiologists in detecting malignant pulmonary nodules on chest radiographs when assisted by deep learning-based DCNN software with that of radiologists or DCNN software alone in a multicenter setting. Materials and Methods Investigators at four medical centers retrospectively identified 600 lung cancer-containing chest radiographs and 200 normal chest radiographs. Each radiograph with a lung cancer had at least one malignant nodule confirmed by CT and pathologic examination. Twelve radiologists from the four centers independently analyzed the chest radiographs and marked regions of interest. Commercially available deep learning-based computer-aided detection software separately trained, tested, and validated with 19 330 radiographs was used to find suspicious nodules. The radiologists then reviewed the images with the assistance of DCNN software. The sensitivity and number of false-positive findings per image of DCNN software, radiologists alone, and radiologists with the use of DCNN software were analyzed by using logistic regression and Poisson regression. Results The average sensitivity of radiologists improved (from 65.1% [1375 of 2112; 95% confidence interval {CI}: 62.0%, 68.1%] to 70.3% [1484 of 2112; 95% CI: 67.2%, 73.1%], P < .001) and the number of false-positive findings per radiograph declined (from 0.2 [488 of 2400; 95% CI: 0.18, 0.22] to 0.18 [422 of 2400; 95% CI: 0.16, 0.2], P < .001) when the radiologists re-reviewed radiographs with the DCNN software. For the 12 radiologists in this study, 104 of 2400 radiographs were positively changed (from false-negative to true-positive or from false-positive to true-negative) using the DCNN, while 56 of 2400 radiographs were changed negatively. Conclusion Radiologists had better performance with deep convolutional network software for the detection of malignant pulmonary nodules on chest radiographs than without. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Jacobson in this issue.

The effects of ambient lighting in chest radiology reading rooms

Under typical dark chest radiography reading room conditions, a radiologist's pupils contract and dilate as their visual focus intermittently shifts between the high luminance monitor and the darker background wall, resulting in increased visual fatigue and degradation of diagnostic performance. A controlled increase of ambient lighting may minimize these visual adjustments and potentially improve comfort and accuracy. This study was designed to determine the effect of a controlled increase of ambient lighting on chest radiologist nodule detection performance. Four chest radiologists read 100 radiographs (50 normal and 50 containing a subtle nodule) under low (E=1 lx) and elevated (E=50 lx) ambient lighting levels on a DICOM-calibrated, medical-grade liquid crystal display. Radiologists were asked to identify nodule locations and rate their detection confidence. A receiver operating characteristic (ROC) analysis of radiologist results was performed and area under ROC curve (AUC) values calculated for each ambient lighting level. Additionally, radiologist selection times under both illuminance conditions were determined. Average AUC values did not significantly differ (p>0.05) between ambient lighting levels (estimated mean difference=-0.03; 95% CI, (-0.08, 0.03)). Average selection times decreased or remained constant with increased illuminance. The most considerable decreases occurred for false positive identification times (35.4±18.8 to 26.2±14.9 s) and true positive identification times (29.7±18.3 to 24.5±15.5 s). No performance differences were statistically significant. Study findings suggest that a controlled increase of ambient lighting within darkly lit chest radiology reading rooms, to a level more suitable for performance of common radiological tasks, does not appear to have a statistically significant effect on nodule detection performance.

Quantitative MDCT analysis of pulmonary solid nodules using three parameters

PURPOSE

The purpose of this prospective study was to perform quantitative multidetector computed tomography (MDCT) analysis of pulmonary solid nodules using three parameters (long-short ratio, compactness, and intranodular CT number) and to evaluate the usefulness of each parameter in the differentiation of the nodules.

MATERIALS AND METHODS

Seventy solitary pulmonary nodules with a long axis length of 5-30 mm were examined using one multidetector CT (MDCT) system and one three-dimensional (3D) system, and the findings regarding the three parameters were statistically analyzed among five diseases (hamartoma, organizing pneumonia, adenocarcinoma, squamous cell carcinoma, and metastasis).

RESULTS

The long-short ratio of the pulmonary nodule showed no significant differences among five diseases. The compactness showed significant differences (P < 0.05) in five pairs of diseases. Intranodular CT number showed significant differences (P < 0.05) in three pairs of diseases.

CONCLUSION

Our results are insufficient for the complete differentiation of pulmonary solid nodules. However, among the three parameters, compactness and intranodular CT number contribute somewhat to the differentiation of pulmonary nodules.

Multiprojection correlation imaging for improved detection of pulmonary nodules

OBJECTIVE

The purpose of this study was the development and preliminary evaluation of multiprojection correlation imaging with 3D computer-aided detection (CAD) on chest radiographs for cost- and dose-effective improvement of early detection of pulmonary nodules.

SUBJECTS AND METHODS

Digital chest radiographs of 10 configurations of a chest phantom and of seven human subjects were acquired in multiple angular projections with an acquisition time of 11 seconds (single breath-hold) and total exposure comparable with that of a posteroanterior chest radiograph. An initial 2D CAD algorithm with two difference-of-gaussians filters and multilevel thresholds was developed with an independent database of 44 single-view chest radiographs with confirmed lesions. This 2D CAD algorithm was used on each projection image to find likely suspect nodules. The CAD outputs were reconstructed in 3D, reinforcing signals associated with true nodules while simultaneously decreasing false-positive findings produced by overlapping anatomic features. The performance of correlation imaging was tested on two to 15 projection images.

RESULTS

Optimum performance of correlation imaging was attained when nine projection images were used. Compared with conventional, single-view CAD, correlation imaging decreased as much as 79% the frequency of false-positive findings in phantom cases at a sensitivity level of 65%. The corresponding reduction in false-positive findings in the cases of human subjects was 78%.

CONCLUSION

Although limited by a relatively simple CAD implementation and a small number of cases, the findings suggest that correlation imaging performs substantially better than single-view CAD and may greatly enhance identification of subtle solitary pulmonary nodules on chest radiographs.

Computerized classification of suspicious regions in chest radiographs using subregion Hotelling observers

We propose to investigate the use of subregion Hotelling observers (SRHOs) in conjunction with perceptrons for the computerized classification of suspicious regions in chest radiographs for being nodules requiring follow up. Previously, 239 regions of interest (ROIs), each containing a suspicious lesion with proven classification, were collected. We chose to investigate the use of SRHOs as part of a multilayer classifier to determine the presence of a nodule. Each SRHO incorporates information about signal, background, and noise correlation for classification. For this study, 225 separate Hotelling observers were set up in a grid across each ROI. Each separate observer discriminates an 8 by 8 pixel area. A round robin sampling scheme was used to generate the 225 features, where each feature is the output of the individual observers. These features were then rank ordered by the magnitude of the weights of a perceptron. Once rank ordered, subsets of increasing number of features were selected to be used in another perceptron. This perceptron was trained to minimize mean squared error and the output was a continuous variable representing the likelihood of the region being a nodule. Performance was evaluated by receiver operating characteristic (ROC) analysis and reported as the area under the curve (Az). The classifier was optimized by adding additional features until the Az declined. The optimized subset of observers then were combined using a third perceptron. A subset of 80 features was selected which gave an Az of 0.972. Additionally, at 98.6% sensitivity, the classifier had a specificity of 71.3% and increased the positive predictive value from 60.7% to 84.1 %. Preliminary results suggest that using SRHOs in combination with perceptrons can provide a successful classification scheme for pulmonary nodules. This approach could be incorporated into a larger computer aided detection system for decreasing false positives.