Improved detection of air trapping on expiratory computed tomography using deep learning

BACKGROUND

Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in limited efficacy for monitoring disease progression.

OBJECTIVE

To investigate the effectiveness of a convolutional neural network (CNN) model for quantifying and monitoring AT, and to compare it with other quantitative AT measures obtained from threshold-based techniques.

MATERIALS AND METHODS

Paired volumetric whole lung inspiratory and expiratory CT scans were obtained at four time points (0, 3, 12 and 24 months) on 36 subjects with mild CF lung disease. A densely connected CNN (DN) was trained using AT segmentation maps generated from a personalized threshold-based method (PTM). Quantitative AT (QAT) values, presented as the relative volume of AT over the lungs, from the DN approach were compared to QAT values from the PTM method. Radiographic assessment, spirometric measures, and clinical scores were correlated to the DN QAT values using a linear mixed effects model.

RESULTS

QAT values from the DN were found to increase from 8.65% ± 1.38% to 21.38% ± 1.82%, respectively, over a two-year period. Comparison of CNN model results to intensity-based measures demonstrated a systematic drop in the Dice coefficient over time (decreased from 0.86 ± 0.03 to 0.45 ± 0.04). The trends observed in DN QAT values were consistent with clinical scores for AT, bronchiectasis, and mucus plugging. In addition, the DN approach was found to be less susceptible to variations in expiratory deflation levels than the threshold-based approach.

CONCLUSION

The CNN model effectively delineated AT on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring AT in CF patients.

Multicenter evaluation of parametric response mapping as an indicator of bronchiolitis obliterans syndrome after hematopoietic stem cell transplantation

Parametric response mapping (PRM) is a novel computed tomography (CT) technology that has shown potential for assessment of bronchiolitis obliterans syndrome (BOS) after hematopoietic stem cell transplantation (HCT). The primary aim of this study was to evaluate whether variations in image acquisition under real-world conditions affect the PRM measurements of clinically diagnosed BOS. CT scans were obtained retrospectively from 72 HCT recipients with BOS and graft-versus-host disease from Fred Hutchinson Cancer Research Center, Karolinska Institute, and the University of Michigan. Whole lung volumetric scans were performed at inspiration and expiration using site-specific acquisition and reconstruction protocols. PRM and pulmonary function measurements were assessed. Patients with moderately severe BOS at diagnosis (median forced expiratory volume at 1 second [FEV1] 53.5% predicted) had similar characteristics between sites. Variations in site-specific CT acquisition protocols had a negligible effect on the PRM-derived small airways disease (SAD), that is, BOS measurements. PRM-derived SAD was found to correlate with FEV1% predicted and FEV1/ forced vital capacity (R = -0.236, P = .046; and R = -0.689, P < .0001, respectively), which suggests that elevated levels in the PRM measurements are primarily affected by BOS airflow obstruction and not CT scan acquisition parameters. Based on these results, PRM may be applied broadly for post-HCT diagnosis and monitoring of BOS.

Assessing small airways dysfunction in asthma, asthma remission and healthy controls using particles in exhaled air

Asthma is a chronic disease, characterised by variable airflow obstruction and airway inflammation [1]. Small airways are thought to be a major site of pathology in asthma [2, 3]. There are different tools to assess small airways dysfunction (SAD), such as spirometry, body plethysmography, impulse oscillometry (IOS), multiple-breath nitrogen washout (MBNW), alveolar fraction of exhaled nitric oxide (F_ENO) and gas trapping assessed by high-resolution computed tomography (CT). However, there is no golden standard and some tests are difficult to perform [2, 3].

PExA mass can distinguish asthmatics from healthy individuals. Subjects with complete, but not clinical, asthma remission exhale more PExA mass compared to asthma. Higher PExA mass was associated with better function of both the small and large airways.http://bit.ly/2znHABg

Influence of Inspiratory/Expiratory CT Registration on Quantitative Air Trapping

RATIONALE AND OBJECTIVES

The aim of this study was to assess variability in quantitative air trapping (QAT) measurements derived from spatially aligned expiration CT scans.

MATERIALS AND METHODS

Sixty-four paired CT examinations, from 16 school-age cystic fibrosis subjects examined at four separate time intervals, were used in this study. For each pair, visually inspected lobe segmentation maps were generated and expiration CT data were registered to the inspiration CT frame. Measurements of QAT, the percentage of voxels on the expiration CT scan below a set threshold were calculated for each lobe and whole-lung from the registered expiration CT and compared to the true values from the unregistered data.

RESULTS

A mathematical model, which simulates the effect of variable regions of lung deformation on QAT values calculated from aligned to those from unaligned data, showed the potential for large bias. Assessment of experimental QAT measurements using Bland-Altman plots corroborated the model simulations, demonstrating biases greater than 5% when QAT was approximately 40% of lung volume. These biases were removed when calculating QAT from aligned expiration CT data using the determinant of the Jacobian matrix. We found, by Dice coefficient analysis, good agreement between aligned expiration and inspiration segmentation maps for the whole-lung and all but one lobe (Dice coefficient > 0.9), with only the lingula generating a value below 0.9 (mean and standard deviation of 0.85 ± 0.06).

CONCLUSION

The subtle and predictable variability in corrected QAT observed in this study suggests that image registration is reliable in preserving the accuracy of the quantitative metrics.

[Ambulatory electrocardiographic monitoring: a comparison of ischemic changes of the ST-segment and coronary cineangiography]

PURPOSE

To determine the usefulness of an ambulatory electrocardiographic monitoring system, in identifying atherosclerotic coronary artery disease among symptomatic and asymptomatic patients, through a comparison of ST-segment depression with angiographic findings.

METHODS

Fifty patients, 48 men, with the mean age 49 +/- 13 years (range 20 to 73), presenting ST-segment depression, were submitted to coronary angiography, complemented by echocardiogram and exercise testing, when the angiography was considered normal. According to the symptoms patients were divided into three groups: I--asymptomatic (16-32%); II--atypical chest pain (15-30%); and III--angina (19-38%). The Cardiac Care Units (Compass TM) system was used for the ambulatory electrocardiographic monitoring.

RESULTS

Twenty-four patients (48%) had significant atherosclerotic coronary artery disease documented angiographically. Twenty-six patients (52%) had normal coronary arteries by angiography: 18 (36%), presented some pathology demonstrated by echocardiographic studies (left ventricle hypertrophy, mitral valve prolapse, non-obstructive septal hypertrophy, dilated cardiomyopathy). Eight patients (16%) had normal echocardiograms, and in (6%) the exercise test was positive and in the other 5 (6%) negative. One of those patients (2%), with negative exercise test, had a myocardial bridge over the anterior descending branch of the left coronary artery, 2 patients (4%) presented symptomatic episodes of ST depression, and 2 other patients (4%) were asymptomatic.

CONCLUSION

A comparison of the ST depression analysed in real time during ambulatory electrocardiographic monitoring with the cinecoronarographic findings showed a poor correlation of the two methods in identifying atherosclerotic coronary disease. The ischemic depressions of ST-segment were associated to obstructive lesions or slow flow in the coronary arteries in only 48% of the cases studied.

[The mitral valve apparatus: an anatomo-echocardiographic approach]

The shape of the mitral valve ring, the position of its chordae and of its leaflets were studied in 34 normal hearts fixed through intra-ventricular injection of tamponate formalin. As the authors have assumed that the post-rigor left ventricle has an architecture very similar to that seen at to the end of ventricular systole, comparisons were made between the anatomical and the echocardiographic features usually seen at the end of the phase of the cardiac cycle. The mitral ring has the shape of a hyperbolic paraboloid, and this peculiar geometry explains why the "apical-four chambers" view, which explores the most superficial ring segments, is the more appropriate view for detecting mitral valve prolapses. In that incidence the valvar diameter is longer (2.43 +/- 0.45 cm) that in the "parasternal view" (1.99 +/- 0.45 cm) and the angle made by the leaflets is comparatively less acute ("four chambers" = 127.41 +/- 16.45 degrees; "parasternal" = 102.05 +/- 0.17 degrees). In the "four chamber" view the point of coaptation (which represents the vertex of the referred angle) is 0.45 +/- 0.17 cm far from the echographic line usually taken as the valvar plane (EVPL-echocardiographic valvar plane line) whereas in the other view, it is more distant from this line (0.59 +/- 0.16 cm). These two last factors make both leaflets closer to the left atrium and explains why mitral valve prolapse, when present, is more easily seen in that incidence.(ABSTRACT TRUNCATED AT 250 WORDS)