Search

Purpose : To determine the quantitative relationship between image quality and radiologist performance in detecting small lung nodules in pediatric CT. Methods : The study included clinical chest CTimages of 30 pediatric patients (0–16 years) scanned at tube currents of 55–180 mA. Calibrated noise addition software was used to simulate cases at three nominal mA settings: 70, 35, and 17.5 mA, resulting in quantum noise of 7–32 Hounsfield Unit (HU). Using a validated nodule simulation technique, lung nodules with diameters of 3–5 mm and peak contrasts of 200–500 HU were inserted into the cases, which were then randomized and rated independently by four experienced pediatric radiologists for nodule presence on a continuous scale from 0 (definitely absent) to 100 (definitely present). The receiver operating characteristic (ROC) data were analyzed to quantify the relationship between diagnostic accuracy (area under the ROC curve, AUC) and image quality (the product of nodule peak contrast and displayed diameter to noise ratio, CDNR display ). Results : AUC increased rapidly from 0.70 to 0.87 when CDNR display increased from 60 to 130 mm, followed by a slow increase to 0.94 when CDNR display further increased to 257 mm. For the average nodule diameter (4 mm) and contrast (350 HU), AUC decreased from 0.93 to 0.71 with noise increased from 7 to 28 HU. Conclusions : We quantified the relationship between image quality and the performance of radiologists in detecting lung nodules in pediatric CT. The relationship can guide CT protocol design to achieve the desired diagnostic performance at the lowest radiationdose.]

Purpose: The authors propose the framework for an individualized adaptive computer-aided educational system in mammography that is based on user modeling. The underlying hypothesis is that user models can be developed to capture the individual error making patterns of radiologists-in-training. In this pilot study, the authors test the above hypothesis for the task of breast cancer diagnosis in mammograms. Methods: The concept of a user model was formalized as the function that relates image features to the likelihood/extent of the diagnostic error made by a radiologist-in-training and therefore to the level of difficulty that a case will pose to the radiologist-in-training (or “user”). Then, machine learning algorithms were implemented to build such user models. Specifically, the authors explored k -nearest neighbor, artificial neural networks, and multiple regression for the task of building the model using observer data collected from ten Radiology residents at Duke University Medical Center for the problem of breast mass diagnosis in mammograms. For each resident, a user-specific model was constructed that predicts the user’s expected level of difficulty for each presented case based on two BI-RADS image features. In the experiments, leave-one-out data handling scheme was applied to assign each case to a low-predicted-difficulty or a high-predicted-difficulty group for each resident based on each of the three user models. To evaluate whether the user model is useful in predicting difficulty, the authors performed statistical tests using the generalized estimating equations approach to determine whether the mean actual error is the same or not between the low-predicted-difficulty group and the high-predicted-difficulty group. Results: When the results for all observers were pulled together, the actual errors made by residents were statistically significantly higher for cases in the high-predicted-difficulty group than for cases in the low-predicted-difficulty group for all modeling algorithms ( p ≤ 0.002 for all methods). This indicates that the user models were able to accurately predict difficulty level of the analyzed cases. Furthermore, the authors determined that among the two BI-RADS features that were used in this study, mass margin was the most useful in predicting individual user errors. Conclusions: The pilot study shows promise for developing individual user models that can accurately predict the level of difficulty that each case will pose to the radiologist-in-training. These models could allow for constructing adaptive computer-aided educational systems in mammography.

To determine the quantitative relationship between image quality and radiologist performance in detecting small lung nodules in pediatric CT.The study included clinical chest CT images of 30 pediatric patients (0-16 years) scanned at tube currents of 55-180 mA. Calibrated noise addition software was used to simulate cases at three nominal mA settings: 70, 35, and 17.5 mA, resulting in quantum noise of 7-32 Hounsfield Unit (HU). Using a validated nodule simulation technique, lung nodules with diameters of 3-5 mm and peak contrasts of 200-500 HU were inserted into the cases, which were then randomized and rated independently by four experienced pediatric radiologists for nodule presence on a continuous scale from 0 (definitely absent) to 100 (definitely present). The receiver operating characteristic (ROC) data were analyzed to quantify the relationship between diagnostic accuracy (area under the ROC curve, AUC) and image quality (the product of nodule peak contrast and displayed diameter to noise ratio, CDNR display).AUC increased rapidly from 0.70 to 0.87 when CDNR display increased from 60 to 130 mm, followed by a slow increase to 0.94 when CDNR display further increased to 257 mm. For the average nodule diameter (4 mm) and contrast (350 HU), AUC decreased from 0.93 to 0.71 with noise increased from 7 to 28 HU.We quantified the relationship between image quality and the performance of radiologists in detecting lung nodules in pediatric CT. The relationship can guide CT protocol design to achieve the desired diagnostic performance at the lowest radiation dose.]

The authors propose the framework for an individualized adaptive computer-aided educational system in mammography that is based on user modeling. The underlying hypothesis is that user models can be developed to capture the individual error making patterns of radiologists-in-training. In this pilot study, the authors test the above hypothesis for the task of breast cancer diagnosis in mammograms.The concept of a user model was formalized as the function that relates image features to the likelihood/extent of the diagnostic error made by a radiologist-in-training and therefore to the level of difficulty that a case will pose to the radiologist-in-training (or "user"). Then, machine learning algorithms were implemented to build such user models. Specifically, the authors explored k-nearest neighbor, artificial neural networks, and multiple regression for the task of building the model using observer data collected from ten Radiology residents at Duke University Medical Center for the problem of breast mass diagnosis in mammograms. For each resident, a user-specific model was constructed that predicts the user's expected level of difficulty for each presented case based on two BI-RADS image features. In the experiments, leave-one-out data handling scheme was applied to assign each case to a low-predicted-difficulty or a high-predicted-difficulty group for each resident based on each of the three user models. To evaluate whether the user model is useful in predicting difficulty, the authors performed statistical tests using the generalized estimating equations approach to determine whether the mean actual error is the same or not between the low-predicted-difficulty group and the high-predicted-difficulty group.When the results for all observers were pulled together, the actual errors made by residents were statistically significantly higher for cases in the high-predicted-difficulty group than for cases in the low-predicted-difficulty group for all modeling algorithms (por = 0.002 for all methods). This indicates that the user models were able to accurately predict difficulty level of the analyzed cases. Furthermore, the authors determined that among the two BI-RADS features that were used in this study, mass margin was the most useful in predicting individual user errors.The pilot study shows promise for developing individual user models that can accurately predict the level of difficulty that each case will pose to the radiologist-in-training. These models could allow for constructing adaptive computer-aided educational systems in mammography.

Purpose: Volume quantifications of lung nodules with multidetector computed tomography (CT) images provide useful information for monitoring nodule developments. The accuracy and precision of the volume quantification, however, can be impacted by imaging and reconstruction parameters. This study aimed to investigate the impact of iterative reconstruction algorithms on the accuracy and precision of volume quantification with dose and slice thickness as additional variables. Methods: Repeated CT images were acquired from an anthropomorphic chest phantom with synthetic nodules (9.5 and 4.8 mm) at six dose levels, and reconstructed with three reconstruction algorithms [filtered backprojection (FBP), adaptive statistical iterative reconstruction (ASiR), and model based iterative reconstruction (MBIR)] into three slice thicknesses. The nodule volumes were measured with two clinical software (A: Lung VCAR, B: iNtuition), and analyzed for accuracy and precision. Results: Precision was found to be generally comparable between FBP and iterative reconstruction with no statistically significant difference noted for different dose levels, slice thickness, and segmentation software. Accuracy was found to be more variable. For large nodules, the accuracy was significantly different between ASiR and FBP for all slice thicknesses with both software, and significantly different between MBIR and FBP for 0.625 mm slice thickness with Software A and for all slice thicknesses with Software B. For small nodules, the accuracy was more similar between FBP and iterative reconstruction, with the exception of ASIR vs FBP at 1.25 mm with Software A and MBIR vs FBP at 0.625 mm with Software A. Conclusions: The systematic difference between the accuracy of FBP and iterative reconstructions highlights the importance of extending current segmentation software to accommodate the image characteristics of iterative reconstructions. In addition, a calibration process may help reduce the dependency of accuracy on reconstruction algorithms, such that volumes quantified from scans of different reconstruction algorithms can be compared. The little difference found between the precision of FBP and iterative reconstructions could be a result of both iterative reconstruction's diminished noise reduction at the edge of the nodules as well as the loss of resolution at high noise levels with iterative reconstruction. The findings do not rule out potential advantage of IR that might be evident in a study that uses a larger number of nodules or repeated scans.