Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?

OBJECTIVES: Post-imaging mathematical prediction models (MPMs) provide guidance for the management of solid pulmonary nodules by providing a lung cancer risk score from demographic and radiologists-indicated imaging characteristics. We hypothesized calibrating the MPM risk score threshold to a local study cohort would result in improved performance over the original recommended MPM thresholds. We compared the pre- and post-calibration performance of four MPM models and determined if improvement in MPM prediction occurs as nodules are imaged longitudinally. MATERIALS AND METHODS: A common cohort of 317 individuals with computed tomography-detected, solid nodules (80 malignant, 237 benign) were used to evaluate the MPM performance. We created a web-based application for this study that allows others to easily calibrate thresholds and analyze the performance of MPMs on their local cohort. Thirty patients with repeated imaging were tested for improved performance longitudinally. RESULTS: Using calibrated thresholds, Mayo Clinic and Brock University (BU) MPMs performed the best (AUC = 0.63, 0.61) compared to the Veteran's Affairs (0.51) and Peking University (0.55). Only BU had consensus with the original MPM threshold; the other calibrated thresholds improved MPM accuracy. No significant improvements in accuracy were found longitudinally between time points. CONCLUSIONS: Calibration to a common cohort can select the best-performing MPM for your institution. Without calibration, BU has the most stable performance in solid nodules ≥ 8 mm but has only moderate potential to refine subjects into appropriate workup. Application of MPM is recommended only at initial evaluation as no increase in accuracy was achieved over time. KEY POINTS: • Post-imaging lung cancer risk mathematical predication models (MPMs) perform poorly on local populations without calibration. • An application is provided to facilitate calibration to new study cohorts: the Mayo Clinic model, the U.S. Department of Veteran's Affairs model, the Brock University model, and the Peking University model. • No significant improvement in risk prediction occurred in nodules with repeated imaging sessions, indicating the potential value of risk prediction application is limited to the initial evaluation.

Computed Tomography and Magnetic Resonance Imaging for Longitudinal Characterization of Lung Structure Changes in a Yucatan Miniature Pig Silicosis Model.

Medical imaging is a rapidly advancing field enabling the repeated, noninvasive assessment of physiological structure and function. These beneficial characteristics can supplement studies in swine by mirroring the clinical functions of detection, diagnosis, and monitoring in humans. In addition, swine may serve as a human surrogate, facilitating the development and comparison of new imaging protocols for translation to humans. This study presents methods for pulmonary imaging developed for monitoring pulmonary disease initiation and progression in a pig exposure model with computed tomography and magnetic resonance imaging. In particular, a focus was placed on systematic processes, including positioning, image acquisition, and structured reporting to monitor longitudinal change. The image-based monitoring procedure was applied to 6 Yucatan miniature pigs. A subset of animals (n= 3) were injected with crystalline silica into the apical bronchial tree to induce silicosis. The methodology provided longitudinal monitoring and evidence of progressive lung disease while simultaneously allowing for a cross-modality comparative study highlighting the practical application of medical image data collection in swine. The integration of multimodality imaging with structured reporting allows for cross comparison of modalities, refinement of CT and MRI protocols, and consistently monitors potential areas of interest for guided biopsy and/or necropsy.

Localization of liver lesions in abdominal CT imaging: I. Correlation of human observer performance between anatomical and uniform backgrounds.

The purpose of this study was to determine the correlation between human observer performance for localization of small low contrast lesions within uniform water background versus an anatomical liver background, under the conditions of varying dose, lesion size, and reconstruction algorithm. Liver lesions (5 mm, 7 mm, and 9 mm, contrast: -21 HU) were digitally inserted into CT projection data of ten normal patients in vessel-free liver regions. Noise was inserted into the projection data to create three image sets: full dose and simulated half and quarter doses. Images were reconstructed with a standard filtered back projection (FBP) and an iterative reconstruction (IR) algorithm. Lesion and noise insertion procedures were repeated with water phantom data. Two-dimensional regions of interest (66 lesion-present, 34 lesion-absent) were selected, randomized, and independently reviewed by three medical physicists to identify the most likely location of the lesion and provide a confidence score. Locations and confidence scores were assessed using the area under the localization receiver operating characteristic curve (AzLROC). We examined the correlation between human performance for the liver and uniform water backgrounds as dose, lesion size, and reconstruction algorithm varied. As lesion size or dose increased, reader localization performance improved. For full dose IR images, the AzLROC for 5, 7, and 9 mm lesions were 0.53, 0.91, and 0.97 (liver) and 0.51, 0.96, and 0.99 (uniform water), respectively. Similar trends were seen with other parameters. Performance values for liver and uniform backgrounds were highly correlated for both reconstruction algorithms, with a Spearman correlation of ρ = 0.97, and an average difference in AzLROC of 0.05 ± 0.04. For the task of localizing low contrast liver lesions, human observer performance was highly correlated between anatomical and uniform backgrounds, suggesting that lesion localization studies emulating a clinical test of liver lesion detection can be performed using a uniform background.

Localization of liver lesions in abdominal CT imaging: II. Mathematical model observer performance correlates with human observer performance for localization of liver lesions in abdominal CT imaging.

Determination of the effect of protocol modifications on diagnostic performance in CT with human observers is extremely time-consuming, limiting the applicability of such methods in routine clinical practice. In this work, we sought to determine whether a channelized Hotelling observer (CHO) could predict human observer performance for the task of liver lesion localization as background, reconstruction algorithm, dose, and lesion size were varied. Liver lesions (5 mm, 7 mm, and 9 mm) were digitally inserted into the CT projection data of patients with normal livers and water phantoms. The projection data were reconstructed with filtered back projection (FBP) and iterative reconstruction (IR) algorithms for three dose levels: full dose (liver CTDIvol = 10.5 ± 8.5 mGy, water phantom CTDIvol = 9.6 ± 0.1 mGy) and simulated half and quarter doses. For each of 36 datasets (3 dose levels × 2 reconstruction algorithms × 2 backgrounds × 3 sizes), 66 signal-present and 34 signal-absent 2D images were extracted from the reconstructed volumes. Three medical physicists independently reviewed each dataset and noted the lesion location and a confidence score for each image. A CHO with Gabor channels was calculated to estimate the performance for each of the 36 localization tasks. The CHO performances, quantified using localization receiver operating characteristic (LROC) analysis, were compared to the human observer performances. Performance values between human and model observers were highly correlated for equivalent parameters (same lesion size, dose, background, and reconstruction), with a Spearman's correlation coefficient of 0.93 (95% CI: 0.82-0.98). CHO performance values for the uniform background were strongly correlated (ρ = 0.94, CI: 0.80-1.0) with the human observer performance values for the liver background. Performance values between human observers and CHO were highly correlated as dose, reconstruction type and object size were varied for the task of localization of patient liver lesions in both uniform and liver backgrounds.

Computed Tomography Cholangiography Using the Magnetic Resonance Contrast Agent Gadoxetate Disodium: A Phantom Study.

OBJECTIVE: The purpose of this work is to determine whether low doses of gadoxetate disodium (Eovist; Bayer Healthcare LLC, Whippany, NJ), a gadolinium-based contrast agent used for magnetic resonance liver imaging, can be visualized for computed tomography (CT) cholangiography using a phantom setup. MATERIALS AND METHODS: Vials containing 4 concentrations of gadoxetate disodium (1.9, 3.4, 4.8, and 9.6 mg Gd/mL) were placed in a 35 × 26-cm water phantom and imaged on 2 CT scanners: Siemens Somatom Flash and Force (Siemens Healthcare, Erlangen, Germany). These concentrations correspond to the estimated concentration in the bile duct for a 40-, 70-, or 100-kg patient, and twice the concentration of a 100-kg patient, respectively. Single-energy (SE) scans were acquired at 70, 80, 90, 100, 120, and 140 kVp, and dual-energy scans were acquired at 90/150Sn (Force) and 100/150 (Flash) for 2 dose levels (CTDIvol 13 and 23 mGy). Virtual monoenergetic images at 50 keV were created (Mono+; Siemens Healthcare, Erlangen, Germany). The mean intensity and standard deviation for each concentration of gadoxetate disodium and the water background were extracted from each image set and used to compute the contrast and contrast-to-noise ratio (CNR). To determine whether the signal provided by gadoxetate disodium was clinically sufficient, the measures were compared with those acquired from 12 clinical CT cholangiography examinations performed with iodine-containing iodipamide meglumine. RESULTS: From the retrospective clinical cohort, mean contrast (± standard deviation) of 239 ± 107 HU and CNR of 12.8 ± 4.2 were found in the bile duct relative to the liver. Comparing these metrics to the gadoxetate disodium samples, the highest concentration (9.6 mg Gd/mL) surpassed these thresholds at all energy levels. The 4.8 mg Gd/mL had sufficient CNR in the Force, but not in the Flash. The 3.4 mg Gd/mL had clinically relevant CNR at low kV of SE (<100 kVp) and 50 keV of dual energy in the Force but was insufficient in the Flash. Images acquired by the Force had a lower noise level and greater CNR compared with the Flash. Similar trends were seen at both dose levels. CONCLUSIONS: Gadoxetate disodium shows promise as a viable contrast agent for CT cholangiography, with CNR similar to those seen clinically with an iodine-based contrast agent. Dual-energy CT or low kV SE-CT is helpful to enhance the signal.

Radiomics of Lung Nodules: A Multi-Institutional Study of Robustness and Agreement of Quantitative Imaging Features.

Radiomics is to provide quantitative descriptors of normal and abnormal tissues during classification and prediction tasks in radiology and oncology. Quantitative Imaging Network members are developing radiomic "feature" sets to characterize tumors, in general, the size, shape, texture, intensity, margin, and other aspects of the imaging features of nodules and lesions. Efforts are ongoing for developing an ontology to describe radiomic features for lung nodules, with the main classes consisting of size, local and global shape descriptors, margin, intensity, and texture-based features, which are based on wavelets, Laplacian of Gaussians, Law's features, gray-level co-occurrence matrices, and run-length features. The purpose of this study is to investigate the sensitivity of quantitative descriptors of pulmonary nodules to segmentations and to illustrate comparisons across different feature types and features computed by different implementations of feature extraction algorithms. We calculated the concordance correlation coefficients of the features as a measure of their stability with the underlying segmentation; 68% of the 830 features in this study had a concordance CC of ≥0.75. Pairwise correlation coefficients between pairs of features were used to uncover associations between features, particularly as measured by different participants. A graphical model approach was used to enumerate the number of uncorrelated feature groups at given thresholds of correlation. At a threshold of 0.75 and 0.95, there were 75 and 246 subgroups, respectively, providing a measure for the features' redundancy.

Improved pulmonary nodule classification utilizing quantitative lung parenchyma features.

Current computer-aided diagnosis (CAD) models for determining pulmonary nodule malignancy characterize nodule shape, density, and border in computed tomography (CT) data. Analyzing the lung parenchyma surrounding the nodule has been minimally explored. We hypothesize that improved nodule classification is achievable by including features quantified from the surrounding lung tissue. To explore this hypothesis, we have developed expanded quantitative CT feature extraction techniques, including volumetric Laws texture energy measures for the parenchyma and nodule, border descriptors using ray-casting and rubber-band straightening, histogram features characterizing densities, and global lung measurements. Using stepwise forward selection and leave-one-case-out cross-validation, a neural network was used for classification. When applied to 50 nodules (22 malignant and 28 benign) from high-resolution CT scans, 52 features (8 nodule, 39 parenchymal, and 5 global) were statistically significant. Nodule-only features yielded an area under the ROC curve of 0.918 (including nodule size) and 0.872 (excluding nodule size). Performance was improved through inclusion of parenchymal (0.938) and global features (0.932). These results show a trend toward increased performance when the parenchyma is included, coupled with the large number of significant parenchymal features that support our hypothesis: the pulmonary parenchyma is influenced differentially by malignant versus benign nodules, assisting CAD-based nodule characterizations.