Dataset Information

Validation of automated lobe segmentation on paired inspiratory-expiratory chest CT in 8-14 year-old children with cystic fibrosis.

ABSTRACT:

Objectives

Densitometry on paired inspiratory and expiratory multidetector computed tomography (MDCT) for the quantification of air trapping is an important approach to assess functional changes in airways diseases such as cystic fibrosis (CF). For a regional analysis of functional deficits, an accurate lobe segmentation algorithm applicable to inspiratory and expiratory scans is beneficial.

Materials and methods

We developed a fully automated lobe segmentation algorithm, and subsequently validated automatically generated lobe masks (ALM) against manually corrected lobe masks (MLM). Paired inspiratory and expiratory CTs from 16 children with CF (mean age 11.1±2.4) acquired at 4 time-points (baseline, 3mon, 12mon, 24mon) with 2 kernels (B30f, B60f) were segmented, resulting in 256 ALM. After manual correction spatial overlap (Dice index) and mean differences in lung volume and air trapping were calculated for ALM vs. MLM.

Results

The mean overlap calculated with Dice index between ALM and MLM was 0.98±0.02 on inspiratory, and 0.86±0.07 on expiratory CT. If 6 lobes were segmented (lingula treated as separate lobe), the mean overlap was 0.97±0.02 on inspiratory, and 0.83±0.08 on expiratory CT. The mean differences in lobar volumes calculated in accordance with the approach of Bland and Altman were generally low, ranging on inspiratory CT from 5.7±52.23cm3 for the right upper lobe to 17.41±14.92cm3 for the right lower lobe. Higher differences were noted on expiratory CT. The mean differences for air trapping were even lower, ranging from 0±0.01 for the right upper lobe to 0.03±0.03 for the left lower lobe.

Conclusions

Automatic lobe segmentation delivers excellent results for inspiratory and good results for expiratory CT. It may become an important component for lobe-based quantification of functional deficits in cystic fibrosis lung disease, reducing necessity for user-interaction in CT post-processing.

SUBMITTER: Konietzke P

PROVIDER: S-EPMC5890971 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Validation of automated lobe segmentation on paired inspiratory-expiratory chest CT in 8-14 year-old children with cystic fibrosis.

Konietzke Philip P Weinheimer Oliver O Wielpütz Mark O MO Savage Dasha D Ziyeh Tiglath T Tu Christin C Newman Beverly B Galbán Craig J CJ Mall Marcus A MA Kauczor Hans-Ulrich HU Robinson Terry E TE

PloS one 20180409 4

<h4>Objectives</h4>Densitometry on paired inspiratory and expiratory multidetector computed tomography (MDCT) for the quantification of air trapping is an important approach to assess functional changes in airways diseases such as cystic fibrosis (CF). For a regional analysis of functional deficits, an accurate lobe segmentation algorithm applicable to inspiratory and expiratory scans is beneficial.<h4>Materials and methods</h4>We developed a fully automated lobe segmentation algorithm, and subs ...[more]

PMID: 29630630

Similar Datasets

Project description:IntroductionCurrently, high-resolution computed tomography (HRCT) is the imaging of choice for the differential diagnosis of various cystic lung lesions, including true cystic lung diseases (CLD) and lesions that may mimic them. However, the traditionally used inspiratory scan still presents a significant spectrum of overlapping radiological features. Recent studies have demonstrated variation in lesion size between inspiratory and expiratory phases, probably due to cyst-airway communication. In this study, we aimed to conduct a systematic review of paired inspiratory and expiratory HRCT in the assessment of cystic lesions as an additional tool to narrow the differential diagnosis.MethodsA systematic search was performed in PubMed, Scopus, EMBASE, BVS, and Cochrane through August 2023. Full-text articles that performed paired inspiratory and expiratory CT scans in adult patients with cystic lung lesions were included, with the outcome measured as the reduction in lesion size according to the respiratory phase. Diagnoses were confirmed through histopathological or radiological features.ResultsOut of the 96 records, three studies met the criteria for inclusion and were analyzed, comprising a total of 149 participants and 513 cystic lesions. Pulmonary Langerhans Cell Histiocytosis (PLCH), Lymphangioleiomyomatosis (LAM) honeycombing and cystic bronchiectasis became considerably smaller during expiratory CT scans, while the size of emphysema tended to remain constant during respiratory cycles.ConclusionsThis study has suggested that paired inspiratory and expiratory CT scans can be valuable for helping differentiate between emphysema and other diseases with a cystic pattern due to their ability to reveal dynamic properties of the lesions. However, the average reduction in cyst size as a single parameter is not sufficient for further refining diagnostics. Studies exploring advanced metrics to assess the reduction in lesion diameter emerge as potential opportunities to investigate the cyst-airway communication hypothesis and further enhance the diagnostic accuracy of paired methods.

Project description:PurposeTo establish a method for quantitatively estimating the extent of the communication between the cyst and the airway in cystic lung diseases (CLDs) and evaluate its diagnostic utility in differentiating among CLDs.Materials and methodsSeventy-one patients (mean age, 49.9 years; age range, 25-79 years) with CLDs who underwent paired inspiratory and expiratory CT between July 2015 and July 2018 were enrolled in this prospective study. Participants were divided into three groups based on their diagnosis: Birt-Hogg-Dubé syndrome (BHDS) group (15 participants), lymphangioleiomyomatosis (LAM) group (43 participants), and other diseases (OT) group (13 participants). Total lung volume (TLV) and low-attenuation area volume (LAAV) were calculated at inspiration and expiration. The collapsibility of the LAAV was determined as the expiration-to-inspiration (E/I) ratio of LAAV (E/I ratio LAAV). The cyst-airway communicating index (CACI), the ratio of the LAAV change between inspiration and expiration to the TLV change between inspiration and expiration, was also determined. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic utility for differentiating diseases.ResultsThe E/I ratio LAAV was significantly higher in the BHDS group (0.69; 95% confidence interval [CI]: 0.61, 0.78) than in the LAM (0.33; 95% CI: 0.28, 0.38) (P < .001) and the OT (0.51; 95% CI: 0.38, 0.64) (P = .038) groups. The CACI was significantly lower in the BHDS group (0.89; 95% CI: 0.61, 1.17) than in the LAM (1.89; 95% CI: 1.76, 2.0) (P < .001) and the OT (1.539; 95% CI: 1.21, 1.86) (P = .003) groups. There was no significant difference in the area under the ROC curve of the CACI (0.881; 95% CI: 0.7749, 0.987) and the E/I ratio LAAV (0.877; 95% CI: 0.791, 0.963) for differentiating BHDS from other diseases.ConclusionQuantitative analysis using paired inspiratory and expiratory CT for estimating the extent of cyst-airway communication in CLDs is useful when distinguishing BHDS from other diseases.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Chung in this issue.

Project description:PurposeFunctional radiotherapy avoids the delivery of high-radiation dosages to high-ventilated lung areas. Methods to determine CT-ventilation imaging (CTVI) typically rely on deformable image registration (DIR) to calculate volume changes within inhale/exhale CT image pairs. Since DIR is a non-trivial task that can bias CTVI, we hypothesize that lung volume changes needed to calculate CTVI can be computed from AI-driven lobe segmentations in inhale/exhale phases, without DIR. We utilize a novel lobe segmentation pipeline (TriSwinUNETR), and the resulting inhale/exhale lobe volumes are used to calculate CTVI.MethodsOur pipeline involves three SwinUNETR networks, each trained on 6,501 CT image pairs from the COPDGene study. An initial network provides right/left lung segmentations used to define bounding boxes for each lung. Bounding boxes are resized to focus on lung volumes and then lobes are segmented with dedicated right and left SwinUNETR networks. Fine-tuning was conducted on CTs from 11 patients treated with radiotherapy for non-small cell lung cancer. Five-fold cross-validation was then performed on 51 LUNA16 cases with manually delineated ground truth. Breathing-induced volume change was calculated for each lobe using AI-defined lobe volumes from inhale/exhale phases, without DIR. Resulting lobar CTVI values were validated with 4DCT and positron emission tomography (PET)-Galligas ventilation imaging for 19 lung cancer patients. Spatial Spearman correlation between TriSwinUNETR lobe ventilation and ground-truth PET-Galligas ventilation was calculated for each patient.ResultsTriSwinUNETR achieved a state-of-the-art mean Dice score of 93.72% (RUL: 93.49%, RML: 85.78%, RLL: 95.65%, LUL: 97.12%, LLL: 96.58%), outperforming best-reported accuracy of 92.81% for the lobe segmentation task. CTVI calculations yielded a median Spearman correlation coefficient of 0.9 across 19 cases, with 13 cases exhibiting correlations of at least 0.5, indicating strong agreement with PET-Galligas ventilation.ConclusionOur TriSwinUNETR pipeline demonstrated superior performance in the lobe segmentation task, while our segmentation-based CTVI exhibited strong agreement with PET-Galligas ventilation. Moreover, as our approach leverages deep-learning for segmentation, it provides interpretable ventilation results and facilitates quality assurance, thereby reducing reliance on DIR.

Project description:IntroductionSegmentation of lung structures in medical imaging is crucial for the application of automated post-processing steps on lung diseases like cystic fibrosis (CF). Recently, machine learning methods, particularly neural networks, have demonstrated remarkable improvements, often outperforming conventional segmentation methods. Nonetheless, challenges still remain when attempting to segment various imaging modalities and diseases, especially when the visual characteristics of pathologic findings significantly deviate from healthy tissue.MethodsOur study focuses on imaging of pediatric CF patients [mean age, standard deviation (7.50 ± 4.6)], utilizing deep learning-based methods for automated lung segmentation from chest magnetic resonance imaging (MRI). A total of 165 standardized annual surveillance MRI scans from 84 patients with CF were segmented using the nnU-Net framework. Patient cases represented a range of disease severities and ages. The nnU-Net was trained and evaluated on three MRI sequences (BLADE, VIBE, and HASTE), which are highly relevant for the evaluation of CF induced lung changes. We utilized 40 cases for training per sequence, and tested with 15 cases per sequence, using the Sørensen-Dice-Score, Pearson's correlation coefficient (r), a segmentation questionnaire, and slice-based analysis.ResultsThe results demonstrated a high level of segmentation performance across all sequences, with only minor differences observed in the mean Dice coefficient: BLADE (0.96 ± 0.05), VIBE (0.96 ± 0.04), and HASTE (0.95 ± 0.05). Additionally, the segmentation quality was consistent across different disease severities, patient ages, and sizes. Manual evaluation identified specific challenges, such as incomplete segmentations near the diaphragm and dorsal regions. Validation on a separate, external dataset of nine toddlers (2-24 months) demonstrated generalizability of the trained model achieving a Dice coefficient of 0.85 ± 0.03.Discussion and conclusionOverall, our study demonstrates the feasibility and effectiveness of using nnU-Net for automated segmentation of lung halves in pediatric CF patients, showing promising directions for advanced image analysis techniques to assist in clinical decision-making and monitoring of CF lung disease progression. Despite these achievements, further improvements are needed to address specific segmentation challenges and enhance generalizability.

Dataset Information

Validation of automated lobe segmentation on paired inspiratory-expiratory chest CT in 8-14 year-old children with cystic fibrosis.

Objectives

Materials and methods

Results

Conclusions

Publications

Validation of automated lobe segmentation on paired inspiratory-expiratory chest CT in 8-14 year-old children with cystic fibrosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets