Pseudomonas aeruginosa (Pa) infection is an important contributor to the progression of cystic fibrosis (CF) lung disease. The cornerstone treatment for Pa infection is the use of inhaled ...antibiotics. However, there is substantial lung disease heterogeneity within and between patients that likely impacts deposition patterns of inhaled antibiotics. Therefore, this may result in airways below the minimal inhibitory concentration of the inhaled agent. Very little is known about antibiotic concentrations in small airways, in particular the effect of structural lung abnormalities. We therefore aimed to develop a patient-specific airway model to predict concentrations of inhaled antibiotics and to study the impact of structural lung changes and breathing profile on local concentrations in airways of patients with CF.
In- and expiratory CT-scans of children with CF (5-17 years) were scored (CF-CT score), segmented and reconstructed into 3D airway models. Computational fluid dynamic (CFD) simulations were performed on 40 airway models to predict local Aztreonam lysine for inhalation (AZLI) concentrations. Patient-specific lobar flow distribution and nebulization of 75 mg AZLI through a digital Pari eFlow model with mass median aerodynamic diameter range were used at the inlet of the airway model. AZLI concentrations for central and small airways were computed for different breathing patterns and airway surface liquid thicknesses.
In most simulated conditions, concentrations in both central and small airways were well above the minimal inhibitory concentration. However, small airways in more diseased lobes were likely to receive suboptimal AZLI. Structural lung disease and increased tidal volumes, respiratory rates and larger particle sizes greatly reduced small airway concentrations.
CFD modeling showed that concentrations of inhaled antibiotic delivered to the small airways are highly patient specific and vary throughout the bronchial tree. These results suggest that anti-Pa treatment of especially the small airways can be improved.
To compare the results obtained by using numerical flow simulations with the results of combined single photon emission computed tomography (SPECT) and computed tomography (CT) and to demonstrate the ...importance of correct boundary conditions for the numerical methods to account for the large amount of interpatient variability in airway geometry.
This study was approved by all relevant institutional review boards. All patients gave their signed informed consent. In this study, six patients with mild asthma (three men; three women; overall mean age, 46 years ± 17 standard deviation) underwent CT at functional residual capacity and total lung capacity, as well as SPECT/CT. CT data were used for segmentation and computational fluid dynamics (CFD) simulations. A comparison was made between airflow distribution, as derived with (a) SPECT/CT through tracer concentration analysis, (b) CT through lobar expansion measurement, and (c) CFD through flow computer simulation. Also, the heterogeneity of the ventilation was examined.
Good agreement was found between SPECT/CT, CT, and CFD in terms of airflow distribution and hot spot detection. The average difference for the internal airflow distribution was less than 3% for CFD and CT versus SPECT/CT. Heterogeneity in ventilation patterns could be detected with SPECT/CT and CFD.
This results of this study show that patient-specific computer simulations with appropriate boundary conditions yield information that is similar to that obtained with functional imaging tools, such as SPECT/CT.
http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.10100322/-/DC1.
Upper airway stimulation has been shown to be an effective treatment for some patients with obstructive sleep apnea. However, the mechanism by which hypoglossal nerve stimulation increases upper ...airway caliber is not clear. Therefore, the objective of this study was to identify the mechanism of action of upper airway stimulation. We hypothesized that, with upper airway stimulation, responders would show greater airway opening in the retroglossal (base of the tongue) region, greater hyoid movement toward the mandible, and greater anterior motion in the posterior, inferior region of the tongue compared with nonresponders.
Seven participants with obstructive sleep apnea who had been successfully treated with upper airway stimulation (responders) and six participants who were not successfully treated (nonresponders) underwent computed tomography imaging during wakefulness with and without hypoglossal nerve stimulation. Responders reduced their apnea-hypopnea index (AHI) by 22.63 ± 6.54 events per hour, whereas nonresponders had no change in their AHI (0.17 ± 14.04 events per hour). We examined differences in upper airway caliber, the volume of the upper airway soft tissue structures, craniofacial relationships, and centroid tongue and soft palate movement between responders and nonresponders with and without hypoglossal nerve stimulation.
Our data indicate that compared with nonresponders, responders had a smaller baseline soft palate volume and, with stimulation, had (1) a greater increase in retroglossal airway size; (2) increased shortening of the mandible-hyoid distance; and (3) greater anterior displacement of the tongue.
These results suggest that smaller soft palate volumes at baseline and greater tongue movement anteriorly with stimulation improve the response to upper airway stimulation.
Summary Obstructive sleep apnea syndrome in children is a manifestation of sleep-disordered breathing and associated with a number of complications. Structural narrowing of the upper airway in ...combination with inadequate compensation for a decrease in neuromuscular tone is an important factor in the pathogenesis. Adenotonsillar hypertrophy is the most important predisposing factor. However, many other causes of craniofacial defects may coexist. Additionally, the pathogenesis of narrowing is more complex in certain subgroups such as children with obesity, craniofacial malformations, Down syndrome or neuromuscular disorders. The diagnosis of obstructive sleep apnea is based on an overnight polysomnography. This investigation is expensive, time consuming and not widely available. In view of the major role of structural narrowing, upper airway imaging could be a useful tool for investigating obstructive sleep apnea and in establishing the site(s) of obstruction. Several radiological techniques (lateral neck radiography, cephalometry, computerized tomography, magnetic resonance imaging and post-processing of these images using computational fluid dynamics) have been used to investigate the role of structural alterations in the pathogenesis. We reviewed the literature to examine if upper airway imaging could replace polysomnography in making the diagnosis and if imaging could predict the effect of treatment with a focus on adenotonsillectomy. There is a limited number of high quality studies of imaging predicting the effect of treatment. To avoid unnecessary risks and ineffective surgeries, it seems crucial to couple the exact individual anatomical risk factor with the most appropriate treatment. We conclude that imaging could be a non-invasive tool that could assist in selection of treatment.
Purpose
To develop machine learning models to predict para-aortic lymph node (PALN) involvement in patients with locally advanced cervical cancer (LACC) before chemoradiotherapy (CRT) using
18
F-FDG ...PET/CT and MRI radiomics combined with clinical parameters.
Methods
We retrospectively collected 178 patients (60% for training and 40% for testing) in 2 centers and 61 patients corresponding to 2 further external testing cohorts with LACC between 2010 to 2022 and who had undergone pretreatment analog or digital
18
F-FDG PET/CT, pelvic MRI and surgical PALN staging. Only primary tumor volumes were delineated. Radiomics features were extracted using the Radiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Different prediction models were trained using a neural network approach with either clinical, radiomics or combined models. They were then evaluated on the testing and external validation sets and compared.
Results
In the training set (
n
= 102), the clinical model achieved a good prediction of the risk of PALN involvement with a C-statistic of 0.80 (95% CI 0.71, 0.87). However, it performed in the testing (
n
= 76) and external testing sets (
n
= 30 and
n
= 31) with C-statistics of only 0.57 to 0.67 (95% CI 0.36, 0.83). The ComBat-radiomic (GLDZM_HISDE_PET_FBN64 and Shape_maxDiameter2D3_PET_FBW0.25) and ComBat-combined (FIGO 2018 and same radiomics features) models achieved very high predictive ability in the training set and both models kept the same performance in the testing sets, with C-statistics from 0.88 to 0.96 (95% CI 0.76, 1.00) and 0.85 to 0.92 (95% CI 0.75, 0.99), respectively.
Conclusions
Radiomic features extracted from pre-CRT analog and digital
18
F-FDG PET/CT outperform clinical parameters in the decision to perform a para-aortic node staging or an extended field irradiation to PALN. Prospective validation of our models should now be carried out.
The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) ...status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 95% CI (0.32-1.00) with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.
Artificial intelligence (AI) has increasingly been serving the field of radiology over the last 50 years. As modern medicine is evolving towards precision medicine, offering personalized patient care ...and treatment, the requirement for robust imaging biomarkers has gradually increased. Radiomics, a specific method generating high-throughput extraction of a tremendous amount of quantitative imaging data using data-characterization algorithms, has shown great potential in individuating imaging biomarkers. Radiomic analysis can be implemented through the following two methods: hand-crafted radiomic features extraction or deep learning algorithm. Its application in lung diseases can be used in clinical decision support systems, regarding its ability to develop descriptive and predictive models in many respiratory pathologies. The aim of this article is to review the recent literature on the topic, and briefly summarize the interest of radiomics in chest Computed Tomography (CT) and its pertinence in the field of pulmonary diseases, from a clinician’s perspective.
Long-term survival after lung transplantation (LTx) is limited by bronchiolitis obliterans syndrome (BOS), defined as a sustained decline in forced expiratory volume in the first second (FEV
) not ...explained by other causes. We assessed whether machine learning (ML) utilizing quantitative computed tomography (qCT) metrics can predict eventual development of BOS.
Paired inspiratory-expiratory CT scans of 71 patients who underwent LTx were analyzed retrospectively (BOS n = 41 versus non-BOS n = 30), using at least two different time points. The BOS cohort experienced a reduction in FEV
of >10% compared to baseline FEV
post LTx. Multifactor analysis correlated declining FEV
with qCT features linked to acute inflammation or BOS onset. Student t test and ML were applied on baseline qCT features to identify lung transplant patients at baseline that eventually developed BOS.
The FEV
decline in the BOS cohort correlated with an increase in the lung volume (P = .027) and in the central airway volume at functional residual capacity (P = .018), not observed in non-BOS patients, whereas the non-BOS cohort experienced a decrease in the central airway volume at total lung capacity with declining FEV
(P = .039). Twenty-three baseline qCT parameters could significantly distinguish between non-BOS patients and eventual BOS developers (P < .05), whereas no pulmonary function testing parameters could. Using ML methods (support vector machine), we could identify BOS developers at baseline with an accuracy of 85%, using only three qCT parameters.
ML utilizing qCT could discern distinct mechanisms driving FEV
decline in BOS and non-BOS LTx patients and predict eventual onset of BOS. This approach may become useful to optimize management of LTx patients.
The aim of our study was to determine the potential role of CT-based radiomics in predicting treatment response and survival in patients with advanced NSCLC treated with immune checkpoint inhibitors. ...We retrospectively included 188 patients with NSCLC treated with PD-1/PD-L1 inhibitors from two independent centers. Radiomics analysis was performed on pre-treatment contrast-enhanced CT. A delta-radiomics analysis was also conducted on a subset of 160 patients who underwent a follow-up contrast-enhanced CT after 2 to 4 treatment cycles. Linear and random forest (RF) models were tested to predict response at 6 months and overall survival. Models based on clinical parameters only and combined clinical and radiomics models were also tested and compared to the radiomics and delta-radiomics models. The RF delta-radiomics model showed the best performance for response prediction with an AUC of 0.8 (95% CI: 0.65-0.95) on the external test dataset. The Cox regression delta-radiomics model was the most accurate at predicting survival with a concordance index of 0.68 (95% CI: 0.56-0.80) (
= 0.02). The baseline CT radiomics signatures did not show any significant results for treatment response prediction or survival. In conclusion, our results demonstrated the ability of a CT-based delta-radiomics signature to identify early on patients with NSCLC who were more likely to benefit from immunotherapy.
Acute chronic obstructive pulmonary disease exacerbations (AECOPD) have a significant negative impact on the quality of life and accelerate progression of the disease. Functional respiratory imaging ...(FRI) has the potential to better characterize this disease. The purpose of this study was to identify FRI parameters specific to AECOPD and assess their ability to predict future AECOPD, by use of machine learning algorithms, enabling a better understanding and quantification of disease manifestation and progression.
A multicenter cohort of 62 patients with COPD was analyzed. FRI obtained from baseline high resolution CT data (unenhanced and volume gated), clinical, and pulmonary function test were analyzed and incorporated into machine learning algorithms.
A total of 11 baseline FRI parameters could significantly distinguish ( p < 0.05) the development of AECOPD from a stable period. In contrast, no baseline clinical or pulmonary function test parameters allowed significant classification. Furthermore, using Support Vector Machines, an accuracy of 80.65% and positive predictive value of 82.35% could be obtained by combining baseline FRI features such as total specific image-based airway volume and total specific image-based airway resistance, measured at functional residual capacity. Patients who developed an AECOPD, showed significantly smaller airway volumes and (hence) significantly higher airway resistances at baseline.
This study indicates that FRI is a sensitive tool (PPV 82.35%) for predicting future AECOPD on a patient specific level in contrast to classical clinical parameters.