scholarly journals Improved Detection of Air Trapping on Expiratory Computed Tomography Using Deep Learning

2020 ◽  
Author(s):  
Sundaresh Ram ◽  
Benjamin A. Hoff ◽  
Alexander J. Bell ◽  
Stefanie Galban ◽  
Aleksa B. Fortuna ◽  
...  
Keyword(s):  
Relative Volume ◽  
Ct Scans ◽  
Radiographic Assessment ◽  
Dice Coefficient ◽  
Air Trapping ◽  
Linear Mixed Effects ◽  
Limited Efficacy ◽  
Clinical Scores ◽  
Standard Techniques ◽  
Radiologic Evidence

ABSTRACTBackgroundRadiologic evidence of air trapping (AT) on expiratory 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.ObjectiveTo 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 MethodsPaired 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.ResultsQAT 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.ConclusionThe CNN model effectively delineated air trapping on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring air trapping in CF patients.

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

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248902
Author(s):  
Sundaresh Ram ◽  
Benjamin A. Hoff ◽  
Alexander J. Bell ◽  
Stefanie Galban ◽  
Aleksa B. Fortuna ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Relative Volume ◽  
Ct Scans ◽  
Dice Coefficient ◽  
Air Trapping ◽  
Linear Mixed Effects ◽  
Limited Efficacy ◽  
Clinical Scores ◽  
Standard Techniques ◽  
Radiologic Evidence

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.

scholarly journals Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
C. A. Neves ◽  
E. D. Tran ◽  
I. M. Kessler ◽  
N. H. Blevins
Keyword(s):  
Facial Nerve ◽  
Inner Ear ◽  
Temporal Bone ◽  
Hausdorff Distance ◽  
Sigmoid Sinus ◽  
Ct Scans ◽  
Automated Segmentation ◽  
Dice Coefficient ◽  
Lateral Skull Base ◽  
End To End

AbstractMiddle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.

scholarly journals CT densitovolumetry in children with obliterative bronchiolitis: correlation with clinical scores and pulmonary function test results

2013 ◽  
Vol 39 (6) ◽  
pp. 701-710 ◽  
Author(s):  
Helena Mocelin ◽  
Gilberto Bueno ◽  
Klaus Irion ◽  
Edson Marchiori ◽  
Edgar Sarria ◽  
...  
Keyword(s):  
Pulmonary Function ◽  
Pulmonary Function Test ◽  
Clinical Score ◽  
Obliterative Bronchiolitis ◽  
Normal Lung ◽  
Test Results ◽  
Air Trapping ◽  
Clinical Scores ◽  
Function Test ◽  
Minute Walk

OBJECTIVE: To determine whether air trapping (expressed as the percentage of air trapping relative to total lung volume [AT%]) correlates with clinical and functional parameters in children with obliterative bronchiolitis (OB).METHODS: CT scans of 19 children with OB were post-processed for AT% quantification with the use of a fixed threshold of −950 HU (AT%950) and of thresholds selected with the aid of density masks (AT%DM). Patients were divided into three groups by AT% severity. We examined AT% correlations with oxygen saturation (SO2) at rest, six-minute walk distance (6MWD), minimum SO2 during the six-minute walk test (6MWT_SO2), FVC, FEV1, FEV1/FVC, and clinical parameters.RESULTS: The 6MWD was longer in the patients with larger normal lung volumes (r = 0.53). We found that AT%950 showed significant correlations (before and after the exclusion of outliers, respectively) with the clinical score (r = 0.72; 0.80), FVC (r = 0.24; 0.59), FEV1 (r = −0.58; −0.67), and FEV1/FVC (r = −0.53; r = −0.62), as did AT%DM with the clinical score (r = 0.58; r = 0.63), SO2 at rest (r = −0.40; r = −0.61), 6MWT_SO2 (r = −0.24; r = −0.55), FVC (r = −0.44; r = −0.80), FEV1 (r = −0.65; r = −0.71), and FEV1/FVC (r = −0.41; r = −0.52).CONCLUSIONS: Our results show that AT% correlates significantly with clinical scores and pulmonary function test results in children with OB.

The Anatomic Relevance of the Haller Cell in Sinusitis

1997 ◽  
Vol 11 (3) ◽  
pp. 219-224 ◽  
Author(s):  
Sarah A. Stackpole ◽  
David R. Edelstein
Keyword(s):  
Maxillary Antrum ◽  
Causative Factor ◽  
Small Cells ◽  
Ct Scans ◽  
Etiologic Factor ◽  
Mucosal Disease ◽  
Ostiomeatal Complex ◽  
Mucosal Thickening ◽  
Radiologic Evidence

In current theories of sinusitis, obstruction at the ostiomeatal complex leads to localized inflammation and infection. Haller cells, an extension of ethmoid pneumatization along the maxillary antrum roof, have also been suggested as a causative factor in sinusitis because of their ability to cause narrowing of the infundibulum. Coronal CT scans were reviewed in 154 patients to evaluate the role of Haller cells in sinusitis. Haller cells were present in 34% of patients. The cells were graded as small, medium, or large, and correlated with radiologic evidence of sinusitis (e.g., mucosal thickening or opacification). A statistically significant increase in maxillary sinus mucosal disease was noted in patients with medium or large Haller cells (45.8%) versus those with small cells (28.9%, p < 0.05). Thus obstructive medium and large Haller cells may be an etiologic factor in sinusitis.

scholarly journals Laryngotracheobronchial papillomatosis: chest CT findings

2017 ◽  
Vol 43 (4) ◽  
pp. 259-263 ◽  
Author(s):  
Helena Ribeiro Fortes ◽  
Felipe Mussi von Ranke ◽  
Dante Luiz Escuissato ◽  
Cesar Augusto Araujo Neto ◽  
Gláucia Zanetti ◽  
...  
Keyword(s):  
Respiratory Infections ◽  
Lung Parenchyma ◽  
Pulmonary Involvement ◽  
Chest Ct ◽  
Ct Scans ◽  
Lung Nodules ◽  
Inclusion Criteria ◽  
Air Trapping ◽  
Recurrent Respiratory Infections ◽  
Ct Findings

ABSTRACT To evaluate the findings on chest CTs in 16 patients (8 men and 8 women) with laryngotracheobronchial papillomatosis. Methods: This was a retrospective study involving patients ranging from 2 to 72 years of age. The evaluation of the CT scans was independently performed by two observers, and discordant results were resolved by consensus. The inclusion criteria were presence of abnormalities on the CT scans, and the diagnosis was confirmed by anatomopathological examination of the papillomatous lesions. Results: The most common symptoms were hoarseness, cough, dyspnea, and recurrent respiratory infections. The major CT findings were nodular formations in the trachea, solid or cavitated nodules in the lung parenchyma, air trapping, masses, and consolidation. Nodular formations in the trachea were observed in 14 patients (87.5%). Only 2 patients had lesions in lung parenchyma without tracheal involvement. Only 1 patient had no pulmonary dissemination of the disease, showing airway involvement only. Solid and cavitated lung nodules were observed in 14 patients (87.5%) and 13 (81.2%), respectively. Masses were observed in 6 patients (37.5%); air trapping, in 3 (18.7%); consolidation in 3 (18.7%); and pleural effusion, in 1 (6.3%). Pulmonary involvement was bilateral in all cases. Conclusions: The most common tomography findings were nodular formations in the trachea, as well as solid or cavitated nodules and masses in the lung parenchyma. Malignant transformation of the lesions was observed in 5 cases.

scholarly journals Risk Stratification for ECMO Requirement in COVID-19 ICU Patients Using Quantitative Imaging Features in CT Scans on Admission

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1029
Author(s):  
Eva Gresser ◽  
Jakob Reich ◽  
Bastian O. Sabel ◽  
Wolfgang G. Kunz ◽  
Matthias P. Fabritius ◽  
...  
Keyword(s):  
Resource Management ◽  
Risk Stratification ◽  
Sofa Score ◽  
Ct Scans ◽  
Imaging Features ◽  
Lung Involvement ◽  
Icu Admission ◽  
Clinical Scores ◽  
Diagnostic Potential ◽  
Ecmo Therapy

(1) Background: Extracorporeal membrane oxygenation (ECMO) therapy in intensive care units (ICUs) remains the last treatment option for Coronavirus disease 2019 (COVID-19) patients with severely affected lungs but is highly resource demanding. Early risk stratification for the need of ECMO therapy upon admission to the hospital using artificial intelligence (AI)-based computed tomography (CT) assessment and clinical scores is beneficial for patient assessment and resource management; (2) Methods: Retrospective single-center study with 95 confirmed COVID-19 patients admitted to the participating ICUs. Patients requiring ECMO therapy (n = 14) during ICU stay versus patients without ECMO treatment (n = 81) were evaluated for discriminative clinical prediction parameters and AI-based CT imaging features and their diagnostic potential to predict ECMO therapy. Reported patient data include clinical scores, AI-based CT findings and patient outcomes; (3) Results: Patients subsequently allocated to ECMO therapy had significantly higher sequential organ failure (SOFA) scores (p < 0.001) and significantly lower oxygenation indices on admission (p = 0.009) than patients with standard ICU therapy. The median time from hospital admission to ECMO placement was 1.4 days (IQR 0.2–4.0). The percentage of lung involvement on AI-based CT assessment on admission to the hospital was significantly higher in ECMO patients (p < 0.001). In binary logistic regression analyses for ECMO prediction including age, sex, body mass index (BMI), SOFA score on admission, lactate on admission and percentage of lung involvement on admission CTs, only SOFA score (OR 1.32, 95% CI 1.08–1.62) and lung involvement (OR 1.06, 95% CI 1.01–1.11) were significantly associated with subsequent ECMO allocation. Receiver operating characteristic (ROC) curves showed an area under the curve (AUC) of 0.83 (95% CI 0.73–0.94) for lung involvement on admission CT and 0.82 (95% CI 0.72–0.91) for SOFA scores on ICU admission. A combined parameter of SOFA on ICU admission and lung involvement on admission CT yielded an AUC of 0.91 (0.84–0.97) with a sensitivity of 0.93 and a specificity of 0.84 for ECMO prediction; (4) Conclusions: AI-based assessment of lung involvement on CT scans on admission to the hospital and SOFA scoring, especially if combined, can be used as risk stratification tools for subsequent requirement for ECMO therapy in patients with severe COVID-19 disease to improve resource management in ICU settings.

scholarly journals A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

Diagnostics ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. 131 ◽  
Author(s):  
Shimaa EL-Bana ◽  
Ahmad Al-Kabbany ◽  
Maha Sharkas
Keyword(s):  
Pulmonary Nodule ◽  
Semantic Segmentation ◽  
Ct Scans ◽  
Computational Time ◽  
Dice Coefficient ◽  
Two Stage ◽  
Second Stage ◽  
Nodule Detection ◽  
Pulmonary Nodule Detection ◽  
The Impact

This research is concerned with malignant pulmonary nodule detection (PND) in low-dose CT scans. Due to its crucial role in the early diagnosis of lung cancer, PND has considerable potential in improving the survival rate of patients. We propose a two-stage framework that exploits the ever-growing advances in deep neural network models, and that is comprised of a semantic segmentation stage followed by localization and classification. We employ the recently published DeepLab model for semantic segmentation, and we show that it significantly improves the accuracy of nodule detection compared to the classical U-Net model and its most recent variants. Using the widely adopted Lung Nodule Analysis dataset (LUNA16), we evaluate the performance of the semantic segmentation stage by adopting two network backbones, namely, MobileNet-V2 and Xception. We present the impact of various model training parameters and the computational time on the detection accuracy, featuring a 79.1% mean intersection-over-union (mIoU) and an 88.34% dice coefficient. This represents a mIoU increase of 60% and a dice coefficient increase of 30% compared to U-Net. The second stage involves feeding the output of the DeepLab-based semantic segmentation to a localization-then-classification stage. The second stage is realized using Faster RCNN and SSD, with an Inception-V2 as a backbone. On LUNA16, the two-stage framework attained a sensitivity of 96.4%, outperforming other recent models in the literature, including deep models. Finally, we show that adopting a transfer learning approach, particularly, the DeepLab model weights of the first stage of the framework, to infer binary (malignant-benign) labels on the Kaggle dataset for pulmonary nodules achieves a classification accuracy of 95.66%, which represents approximately 4% improvement over the recent literature.

scholarly journals Asthma-Like Features and Anti-Asthmatic Drug Prescription in Children with Non-CF Bronchiectasis

2020 ◽  
Vol 9 (12) ◽  
pp. 4009
Author(s):  
Konstantinos Douros ◽  
Olympia Sardeli ◽  
Spyridon Prountzos ◽  
Angeliki Galani ◽  
Dafni Moriki ◽  
...  
Keyword(s):  
Inhaled Corticosteroids ◽  
Drug Prescription ◽  
Ct Scans ◽  
Total Serum ◽  
Blood Eosinophil ◽  
Mosaic Pattern ◽  
Air Trapping ◽  
Serum Ige ◽  
Skin Prick Tests ◽  
Eosinophil Counts

Bronchiectasis and asthma may share some characteristics and some patients may have both conditions. The present study aimed to examine the rationale of prophylactic inhaled corticosteroids (ICS) prescription in children with bronchiectasis. Data of children with radiologically established bronchiectasis were retrospectively reviewed. Episodes of dyspnea and wheezing, spirometric indices, total serum IgE, blood eosinophil counts, sensitization to aeroallergens, and air-trapping on expiratory CT scans, were recorded. The study included 65 children 1.5–16 years old, with non-CF bronchiectasis. Episodes of dyspnea or wheezing were reported by 22 (33.8%) and 23 (35.4%), respectively. Skin prick tests to aeroallergens (SPTs) were positive in 15 (23.0%) patients. Mosaic pattern on CT scans was observed in 37 (56.9%) patients. Dyspnea, presence of mosaic pattern, positive reversibility test, and positive SPTs were significantly correlated with the prescription of ICS. The prescription of ICS in children with bronchiectasis is more likely when there are certain asthma-like characteristics. The difficulty to set the diagnosis of real asthma in cases of bronchiectasis may justify the decision of clinicians to start an empirical trial with ICS in certain cases.

scholarly journals Segmentation and Identification of Vertebrae in CT Scans Using CNN, k-Means Clustering and k-NN

Informatics ◽  
2021 ◽  
Vol 8 (2) ◽  
pp. 40
Author(s):  
Nicola Altini ◽  
Giuseppe De Giosa ◽  
Nicola Fragasso ◽  
Claudia Coscia ◽  
Elena Sibilano ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Machine Learning Algorithms ◽  
Ct Scans ◽  
Computer Assisted ◽  
Dice Coefficient ◽  
Labeling Algorithms ◽  
Two Phases ◽  
Vertebrae Segmentation ◽  
Whole Spine

The accurate segmentation and identification of vertebrae presents the foundations for spine analysis including fractures, malfunctions and other visual insights. The large-scale vertebrae segmentation challenge (VerSe), organized as a competition at the Medical Image Computing and Computer Assisted Intervention (MICCAI), is aimed at vertebrae segmentation and labeling. In this paper, we propose a framework that addresses the tasks of vertebrae segmentation and identification by exploiting both deep learning and classical machine learning methodologies. The proposed solution comprises two phases: a binary fully automated segmentation of the whole spine, which exploits a 3D convolutional neural network, and a semi-automated procedure that allows locating vertebrae centroids using traditional machine learning algorithms. Unlike other approaches, the proposed method comes with the added advantage of no requirement for single vertebrae-level annotations to be trained. A dataset of 214 CT scans has been extracted from VerSe’20 challenge data, for training, validating and testing the proposed approach. In addition, to evaluate the robustness of the segmentation and labeling algorithms, 12 CT scans from subjects affected by severe, moderate and mild scoliosis have been collected from a local medical clinic. On the designated test set from Verse’20 data, the binary spine segmentation stage allowed to obtain a binary Dice coefficient of 89.17%, whilst the vertebrae identification one reached an average multi-class Dice coefficient of 90.09%. In order to ensure the reproducibility of the algorithms hereby developed, the code has been made publicly available.

Sign in / Sign up

Export Citation Format

Share Document