Search

Objective: Progressive pulmonary fibrosis (PPF) is the leading cause of death in systemic sclerosis (SSc). This study aimed to develop a clinical prediction nomogram using clinical and biological data to assess risk of PPF among patients receiving treatment of SSc‐related interstitial lung disease (SSc‐ILD). Methods: Patients with SSc‐ILD who participated in the Scleroderma Lung Study II (SLS II) were randomized to treatment with either mycophenolate mofetil (MMF) or cyclophosphamide (CYC). Clinical and biological parameters were analyzed using univariable and multivariable logistic regression, and a nomogram was created to assess the risk of PPF and validated by bootstrap resampling. Results: Among 112 participants with follow‐up data, 22 (19.6%) met criteria for PPF between 12 and 24 months. An equal proportion of patients randomized to CYC (n = 11 of 56) and mycophenolate mofetil (n = 11 of 56) developed PPF. The baseline severity of ILD was similar for patients who did, compared to those who did not, experience PPF in terms of their baseline forced vital capacity percent predicted, diffusing capacity for carbon monoxide percent predicted, and quantitative radiological extent of ILD. Predictors in the nomogram included sex, baseline CXCL4 level, and baseline gastrointestinal reflux score. The nomogram demonstrated moderate discrimination in estimating the risk of PPF, with a C‐index of 0.72 (95% confidence interval 0.60‐0.84). Conclusion: The SLS II data set provided a unique opportunity to investigate predictors of PPF and develop a nomogram to help clinicians identify patients with SSc‐ILD who require closer monitoring while on therapy and potentially an alternative treatment approach. This nomogram warrants external validation in other SSc‐ILD cohorts to confirm its predictive power. [ABSTRACT FROM AUTHOR]

Objective: To investigate whether symptoms of gastroesophageal reflux disease and radiographic measures of esophageal dilation are associated with radiographic progression of systemic sclerosis–related interstitial lung disease (SSc‐ILD). Methods: Participants of the Scleroderma Lung Study II, which compared mycophenolate versus cyclophosphamide for SSc‐ILD, completed the reflux domain of the University of California Los Angeles Scleroderma Clinical Trials Consortium Gastrointestinal Tract 2.0 at baseline. The diameter and area of the esophagus in the region of maximum dilation was measured by quantitative image analysis. Univariate and multivariable linear regression analyses were created to evaluate the relationship between these measures of esophageal involvement and progression of SSc‐ILD over 2 years, based on the radiologic quantitative interstitial lung disease (QILD) and quantitative lung fibrosis (QLF) in the lobe of maximum involvement (LM). All multivariable models controlled for the treatment arm, baseline ILD severity, and proton‐pump inhibitor use. Results: The baseline mean patient‐reported reflux score was 0.57, indicating moderate reflux (n = 141). Baseline mean maximal esophageal diameter and area were 22 mm and 242 mm2, respectively. Baseline reflux scores were significantly associated with the change in QLF‐LM and QILD‐LM in the univariate and multivariable models. Neither radiographic measure of esophageal dilation was associated with the change in radiographic measures of lung involvement. Conclusion: Severity of reflux symptoms as measured by an SSc‐specific questionnaire was independently associated with the change in the radiographic extent of ILD and fibrosis over 2 years in patients with SSc‐ILD. Two objective measures of esophageal dilation were not associated with radiographic progression of ILD, highlighting the need for improved objective measures of esophageal dysfunction in SSc. [ABSTRACT FROM AUTHOR]

Background: Idiopathic pulmonary fibrosis (IPF) is a progressive, irreversible, and usually fatal lung disease of unknown reasons, generally affecting the elderly population. Early diagnosis of IPF is crucial for triaging patients' treatment planning into anti-fibrotic treatment or treatments for other causes of pulmonary fibrosis. However, current IPF diagnosis workflow is complicated and time-consuming, which involves collaborative efforts from radiologists, pathologists, and clinicians and it is largely subject to inter-observer variability. Purpose: The purpose of this work is to develop a deep learning-based automated system that can diagnose subjects with IPF among subjects with interstitial lung disease (ILD) using an axial chest computed tomography (CT) scan. This work can potentially enable timely diagnosis decisions and reduce inter-observer variability. Methods: Our dataset contains CT scans from 349 IPF patients and 529 non-IPF ILD patients. We used 80% of the dataset for training and validation purposes and 20% as the holdout test set. We proposed a two-stage model:at stage one, we built a multi-scale, domain knowledge-guided attention model (MSGA) that encouraged the model to focus on specific areas of interest to enhance model explainability, including both high- and medium-resolution attentions; at stage two, we collected the output from MSGA and constructed a random forest (RF) classifier for patient-level diagnosis, to further boost model accuracy. RF classifier is utilized as a final decision stage since it is interpretable, computationally fast, and can handle correlated variables. Model utility was examined by (1) accuracy, represented by the area under the receiver operating characteristic curve (AUC) with standard deviation (SD), and (2) explainability, illustrated by the visual examination of the estimated attention maps which showed the important areas for model diagnostics. Results: During the training and validation stage, we observe that when we provide no guidance from domain knowledge, the IPF diagnosis model reaches acceptable performance (AUC±SD = 0.93±0.07), but lacks explainability; when including only guided high- or medium-resolution attention, the learned attentionmaps are not satisfactory;when including both high- and medium-resolution attention, under certain hyperparameter settings, the model reaches the highest AUC among all experiments (AUC±SD = 0.99±0.01) and the estimated attention maps concentrate on the regions of interests for this task. Three bestperforming hyperparameter selections according to MSGA were applied to the holdout test set and reached comparable model performance to that of the validation set. Conclusions: Our results suggest that, for a task with only scan-level labels available, MSGA+RF can utilize the population-level domain knowledge to guide the training of the network, which increases both model accuracy and explainability. [ABSTRACT FROM AUTHOR]

Metaheuristics is a powerful optimization tool that is increasingly used across disciplines to tackle general purpose optimization problems. Nature‐inspired metaheuristic algorithms is a subclass of metaheuristic algorithms and have been shown to be particularly flexible and useful in solving complicated optimization problems in computer science and engineering. A common practice with metaheuristics is to hybridize it with another suitably chosen algorithm for enhanced performance. This paper reviews metaheuristic algorithms and demonstrates some of its utility in tackling pharmacometric problems. Specifically, we provide three applications using one of its most celebrated members, particle swarm optimization (PSO), and show that PSO can effectively estimate parameters in complicated nonlinear mixed‐effects models and to gain insights into statistical identifiability issues in a complex compartment model. In the third application, we demonstrate how to hybridize PSO with sparse grid, which is an often‐used technique to evaluate high dimensional integrals, to search for D‐efficient designs for estimating parameters in nonlinear mixed‐effects models with a count outcome. We also show the proposed hybrid algorithm outperforms its competitors when sparse grid is replaced by its competitor, adaptive gaussian quadrature to approximate the integral, or when PSO is replaced by three notable nature‐inspired metaheuristic algorithms. [ABSTRACT FROM AUTHOR]

Purpose: Size‐specific dose estimate (SSDE) is a metric that adjusts CTDIvol to account for patient size. While not intended to be an estimate of organ dose, AAPM Report 204 notes the difference between the patient organ dose and SSDE is expected to be 10–20%. The purpose of this work was therefore to evaluate SSDE against estimates of organ dose obtained using Monte Carlo (MC) simulation techniques applied to routine exams across a wide range of patient sizes. Materials and Methods: Size‐specific dose estimate was evaluated with respect to organ dose based on three routine protocols taken from Siemens scanners: (a) brain parenchyma dose in routine head exams, (b) lung and breast dose in routine chest exams, and (c) liver, kidney, and spleen dose in routine abdomen/pelvis exams. For each exam, voxelized phantom models were created from existing models or derived from clinical patient scans. For routine head exams, 15 patient models were used which consisted of 10 GSF/ICRP voxelized phantom models and five pediatric voxelized patient models created from CT image data. For all exams, the size metric used was water equivalent diameter (Dw). For the routine chest exams, data from 161 patients were collected with a Dw range of ~16–44 cm. For the routine abdomen/pelvis exams, data from 107 patients were collected with a range of Dw from ~16 to 44 cm. Image data from these patients were segmented to generate voxelized patient models. For routine head exams, fixed tube current (FTC) was used while tube current modulation (TCM) data for body exams were extracted from raw projection data. The voxelized patient models and tube current information were used in detailed MC simulations for organ dose estimation. Organ doses from MC simulation were normalized by CTDIvol and parameterized as a function of Dw. For each patient scan, the SSDE was obtained using Dw and CTDIvol values of each scan, according to AAPM Report 220 for body scans and Report 293 for head scans. For each protocol and each patient, normalized organ doses were compared with SSDE. A one‐sided tolerance limit covering 95% (P = 0.95) of the population with 95% confidence (α = 0.05) was used to assess the upper tolerance limit (TU) between SSDE and normalized organ dose. Results: For head exams, the TU between SSDE and brain parenchyma dose was observed to be 12.5%. For routine chest exams, the TU between SSDE and lung and breast dose was observed to be 35.6% and 68.3%, respectively. For routine abdomen/pelvis exams, the TU between SSDE and liver, spleen, and kidney dose was observed to be 30.7%, 33.2%, and 33.0%, respectively. Conclusions: The TU of 20% between SSDE and organ dose was found to be insufficient to cover 95% of the sampled population with 95% confidence for all of the organs and protocols investigated, except for brain parenchyma dose. For the routine body exams, excluding the breasts, a wider threshold difference of ~30–36% would be needed. These results are, however, specific to Siemens scanners. [ABSTRACT FROM AUTHOR]

Purpose: Recent studies have demonstrated a lack of reproducibility of radiomic features in response to variations in CT parameters. In addition, reproducibility of radiomic features has not been well established in clinical datasets. We aimed to investigate the effects of a wide range of CT acquisition and reconstruction parameters on radiomic features in a realistic setting using clinical low dose lung cancer screening cases. We performed univariable and multivariable explorations to consider the effects of individual parameters and the simultaneous interactions between three different acquisition/reconstruction parameters of radiation dose level, reconstructed slice thickness, and kernel. Method: A cohort of 89 lung cancer screening patients were collected that each had a solid lung nodule >4mm diameter. A computational pipeline was used to perform a simulation of dose reduction of the raw projection data, collected from patient scans. This was followed by reconstruction of raw data with weighted filter back projection (wFBP) algorithm and automatic lung nodule detection and segmentation using a computer‐aided detection tool. For each patient, 36 different image datasets were created corresponding to dose levels of 100%, 50%, 25%, and 10% of the original dose level, three slice thicknesses of 0.6 mm, 1 mm, and 2 mm, as well as three reconstruction kernels of smooth, medium, and sharp. For each nodule, 226 well‐known radiomic features were calculated at each image condition. The reproducibility of radiomic features was first evaluated by measuring the intercondition agreement of the feature values among the 36 image conditions. Then in a series of univariable analyses, the impact of individual CT parameters was assessed by selecting subsets of conditions with one varying and two constant CT parameters. In each subset, intraparameter agreements were assessed. Overall concordance correlation coefficient (OCCC) served as the measure of agreement. An OCCC ≥ 0.9 implied strong agreement and reproducibility of radiomic features in intercondition or intraparameter comparisons. Furthermore, the interaction of CT parameters in impacting radiomic feature values was investigated via ANOVA. Results: All included radiomic features lacked intercondition reproducibility (OCCC < 0.9) among all the 36 conditions. Out of 226 radiomic features analyzed, only 17 and 18 features were considered reproducible (OCCC ≥ 0.9) to dose and kernel variation, respectively, within the corresponding condition subsets. Slice thickness demonstrated the largest impact on radiomic feature values where only one to five features were reproducible at a few condition subsets. ANOVA revealed significant interactions (P < 0.05) between CT parameters affecting the variability of >50% of radiomic features. Conclusion: We systematically explored the multidimensional space of CT parameters in affecting lung nodule radiomic features. Univariable and multivariable analyses of this study not only showed the lack of reproducibility of the majority of radiomic features but also revealed existing interactions among CT parameters, meaning that the effect of individual CT parameters on radiomic features can be conditional upon other CT acquisition and reconstruction parameters. Our findings advise on careful radiomic feature selection and attention to the inclusion criteria for CT image acquisition protocols within the datasets of radiomic studies. [ABSTRACT FROM AUTHOR]

Purpose: Domain knowledge (DK) acquired from prior studies is important for medical diagnosis. This paper leverages the population‐level DK using an optimality design criterion to train a deep learning model in an end‐to‐end manner. In this study, the problem of interest is at the patient level to diagnose a subject with idiopathic pulmonary fibrosis (IPF) among subjects with interstitial lung disease (ILD) using a computed tomography (CT). IPF diagnosis is a complicated process with multidisciplinary discussion with experts and is subject to interobserver variability, even for experienced radiologists. To this end, we propose a new statistical method to construct a time/memory‐efficient IPF diagnosis model using axial chest CT and DK, along with an optimality design criterion via a DK‐enhanced loss function of deep learning. Methods: Four state‐of‐the‐art two‐dimensional convolutional neural network (2D‐CNN) architectures (MobileNet, VGG16, ResNet‐50, and DenseNet‐121) and one baseline 2D‐CNN are implemented to automatically diagnose IPF among ILD patients. Axial lung CT images are retrospectively acquired from 389 IPF patients and 700 non‐IPF ILD patients in five multicenter clinical trials. To enrich the sample size and boost model performance, we sample 20 three‐slice samples (triplets) from each CT scan, where these three slices are randomly selected from the top, middle, and bottom of both lungs respectively. Model performance is evaluated using a fivefold cross‐validation, where each fold was stratified using a fixed proportion of IPF vs non‐IPF. Results: Using DK‐enhanced loss function increases the model performance of the baseline CNN model from 0.77 to 0.89 in terms of study‐wise accuracy. Four other well‐developed models reach satisfactory model performance with an overall accuracy >0.95 but the benefits brought on by the DK‐enhanced loss function is not noticeable. Conclusions: We believe this is the first attempt that (a) uses population‐level DK with an optimal design criterion to train deep learning‐based diagnostic models in an end‐to‐end manner and (b) focuses on patient‐level IPF diagnosis. Further evaluation of using population‐level DK on prospective studies is warranted and is underway. [ABSTRACT FROM AUTHOR]

Objective: To evaluate short‐ and long‐term outcomes of African American (AA) participants of Scleroderma Lung Studies (SLS) I and II. Methods: SLS I randomized 158 participants with systemic sclerosis‐interstitial lung disease (SSc‐ILD) to 1 year of oral cyclophosphamide (CYC) versus placebo. SLS II randomized 142 participants with SSc‐ILD to 1 year of oral CYC followed by 1 year of placebo versus 2 years of mycophenolate (MMF). Joint models compared the course of forced vital capacity (FVC) and diffusing capacity for carbon monoxide (DLCO) between AA and non‐AA, and Cox proportional hazard models assessed long‐term morbidity and mortality outcomes. Results: In SLS I, there was no difference in the course of the FVC or DLCO between AA and non‐AA in either treatment arm. In SLS II, AA had an improved course of the FVC compared with non‐AA in the CYC arm; in the MMF arm, there was no difference in FVC course. There was no difference in DLCO course in either arm. Time to death and respiratory failure were similar for AA and non‐AA in SLS I. There was a trend for improved survival and time to respiratory failure in AA compared with non‐AA in SLS II. AA race was not independently associated with mortality in the SLS I or II in the Cox models. Conclusion: Data from two randomized controlled trials demonstrated that AA patients with SSc‐ILD have similar morbidity and mortality outcomes compared with non‐AA patients. These findings contrast with the racial disparities described in prior observational studies and warrant further investigation. [ABSTRACT FROM AUTHOR]

Objective: To examine changes in the extent of specific patterns of interstitial lung disease (ILD) as they transition from one pattern to another in response to immunosuppressive therapy in systemic sclerosis–related ILD (SSc‐ILD). Methods: We evaluated changes in the quantitative extent of specific lung patterns of ILD using volumetric high‐resolution computed tomography (HRCT) scans obtained at baseline and after 2 years of therapy in patients treated with either cyclophosphamide (CYC) for 1 year or mycophenolate mofetil (MMF) for 2 years in Scleroderma Lung Study II. ILD patterns included lung fibrosis, ground glass, honeycombing, and normal lung. Net change was calculated as the difference in the probability of change from one ILD pattern to another. Wilcoxon's signed rank test was used to compare the changes. Results: Forty‐seven and 50 patients had baseline and follow‐up scans in the CYC and MMF groups, respectively. Mean net improvements reflecting favorable changes from one ILD pattern to another in the whole lung in the CYC and MMF groups, respectively, were as follows: from lung fibrosis to a normal lung pattern, 21% and 19%; from a ground‐glass pattern to a normal lung pattern, 30% and 28%; and from lung fibrosis to a ground‐glass pattern, 5% and 0.5%. The mean overall improvement in transitioning from a ground‐glass pattern or lung fibrosis to a normal lung pattern was significant for both treatments (all P < 0.001). Conclusion: Significantly favorable transitions from both ground‐glass and lung fibrosis ILD patterns to a normal lung pattern were observed in patients undergoing immunosuppressive treatment for SSc‐ILD, suggesting the usefulness of examining these transitions for insights into the underlying pathobiology of treatment response. [ABSTRACT FROM AUTHOR]

Purpose Currently, available Computed Tomography dose metrics are mostly based on fixed tube current Monte Carlo ( MC) simulations and/or physical measurements such as the size specific dose estimate ( SSDE). In addition to not being able to account for Tube Current Modulation ( TCM), these dose metrics do not represent actual patient dose. The purpose of this study was to generate and evaluate a dose estimation model based on the Generalized Linear Model ( GLM), which extends the ability to estimate organ dose from tube current modulated examinations by incorporating regional descriptors of patient size, scanner output, and other scan-specific variables as needed. Methods The collection of a total of 332 patient CT scans at four different institutions was approved by each institution's IRB and used to generate and test organ dose estimation models. The patient population consisted of pediatric and adult patients and included thoracic and abdomen/pelvis scans. The scans were performed on three different CT scanner systems. Manual segmentation of organs, depending on the examined anatomy, was performed on each patient's image series. In addition to the collected images, detailed TCM data were collected for all patients scanned on Siemens CT scanners, while for all GE and Toshiba patients, data representing z-axis-only TCM, extracted from the DICOM header of the images, were used for TCM simulations. A validated MC dosimetry package was used to perform detailed simulation of CT examinations on all 332 patient models to estimate dose to each segmented organ (lungs, breasts, liver, spleen, and kidneys), denoted as reference organ dose values. Approximately 60% of the data were used to train a dose estimation model, while the remaining 40% was used to evaluate performance. Two different methodologies were explored using GLM to generate a dose estimation model: (a) using the conventional exponential relationship between normalized organ dose and size with regional water equivalent diameter ( WED) and regional CTDIvol as variables and (b) using the same exponential relationship with the addition of categorical variables such as scanner model and organ to provide a more complete estimate of factors that may affect organ dose. Finally, estimates from generated models were compared to those obtained from SSDE and Im PACT. Results The Generalized Linear Model yielded organ dose estimates that were significantly closer to the MC reference organ dose values than were organ doses estimated via SSDE or Im PACT. Moreover, the GLM estimates were better than those of SSDE or Im PACT irrespective of whether or not categorical variables were used in the model. While the improvement associated with a categorical variable was substantial in estimating breast dose, the improvement was minor for other organs. Conclusions The GLM approach extends the current CT dose estimation methods by allowing the use of additional variables to more accurately estimate organ dose from TCM scans. Thus, this approach may be able to overcome the limitations of current CT dose metrics to provide more accurate estimates of patient dose, in particular, dose to organs with considerable variability across the population. [ABSTRACT FROM AUTHOR]

The purpose of this work was to validate a parallel imaging (PI) and compressed sensing (CS) combined reconstruction method for a recently proposed 4D non-breath-held, multiphase, steady-state imaging technique (MUSIC) cardiovascular MRI in a cohort of pediatric congenital heart disease patients. We implemented a graphics processing unit accelerated CS-PI combined reconstruction method and applied it in 13 pediatric patients who underwent cardiovascular MRI after ferumoxytol administration. Conventional breath-held contrast-enhanced magnetic resonance angiography (CE-MRA) was first performed during the first pass of ferumoxytol injection, followed by the original MUSIC and the proposed CS-PI MUSIC during the steady-state distribution phase of ferumoxytol. Qualities of acquired images were then evaluated using a four-point scale. Left ventricular volumes and ejection fractions calculated from the original MUSIC and the CS-PI MUSIC were also compared with conventional multi-slice 2D cardiac cine MRI. The proposed CS-PI MUSIC reduced the imaging time of the MUSIC acquisition to 4.6 ± 0.4 min from 8.9 ± 1.2 min. Computationally intensive image reconstruction was completed within 5 min without interruption of sequential clinical scans. The proposed method (mean 3.3-4.0) provided image quality comparable to that of the original MUSIC (3.2-4.0) (all P ≥ 0.42), and better than conventional breath-held first-pass CE-MRA (1.1-3.3) for 13 anatomical structures (all P ≤ 0.0014) with good inter-observer agreement ( κ > 0.46). The calculated ventricular volumes and ejection fractions from both original MUSIC ( r > 0.90) and CS-PI MUSIC ( r > 0.85) correlated well with 2D cine imaging. In conclusion, PI and CS were successfully incorporated into the 4D MUSIC acquisition to further reduce scan time by approximately 50% while maintaining highly comparable image quality in a clinically practical reconstruction time. [ABSTRACT FROM AUTHOR]

The cover image, by PENG HU et al., is based on the Research Article Accelerated ferumoxytol‐enhanced 4D multiphase, steady‐state imaging with contrast enhancement (MUSIC) cardiovascular MRI: validation in pediatric congenital heart disease, DOI: 10.1002/nbm.3663. [ABSTRACT FROM AUTHOR]