COPD Classification in CT Images Using a 3D Convolutional Neural Network

Ahmed, Jalil; Vesal, Sulaiman; Durlak, Felix; Kaergel, Rainer; Ravikumar, Nishant; Rémy‐Jardin, Martine; Maier, Andreas

doi:10.1007/978-3-658-29267-6_8

Cited by 17 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The identified subset of features is then used for a simple multiple logistic regression for the training data and the model is used to predict the presence of the phenotype for the test data. In addition to these feature‐based approaches, a specifically developed 3D DL algorithm 39 is used to automate the detection of emphysema based on the segmentation of the entire lung (more information can be found in the Section S2). This 3D DL algorithm was pretrained on COPDGene 30 where it achieved an AUC of 81% for COPD detection based on GOLD stage criteria, comparable to the state‐of‐the‐art 2D DL method of Gonzalez et al that achieved 86% 17 …”

Section: Methodsmentioning

confidence: 99%

Unraveling the interplay of image formation, data representation and learning in CT‐based COPD phenotyping automation: The need for a meta‐strategy

et al. 2021

Self Cite

View full text Add to dashboard Cite

Purpose In the literature on automated phenotyping of chronic obstructive pulmonary disease (COPD), there is a multitude of isolated classical machine learning and deep learning techniques, mostly investigating individual phenotypes, with small study cohorts and heterogeneous meta‐parameters, e.g., different scan protocols or segmented regions. The objective is to compare the impact of different experimental setups, i.e., varying meta‐parameters related to image formation and data representation, with the impact of the learning technique for subtyping automation for a variety of phenotypes. The identified associations of these parameters with automation performance and their interactions might be a first step towards a determination of optimal meta‐parameters, i.e., a meta‐strategy. Methods A clinical cohort of 981 patients (53.8 ± 15.1 years, 554 male) was examined. The inspiratory CT images were analyzed to automate the diagnosis of 13 COPD phenotypes given by two radiologists. A benchmark feature set that integrates many quantitative criteria was extracted from the lung and trained a variety of learning algorithms on the first 654 patients (two thirds) and the respective algorithm retrospectively assessed the remaining 327 patients (one third). The automation performance was evaluated by the area under the receiver operating characteristic curve (AUC). 1717 experiments were conducted with varying meta‐parameters such as reconstruction kernel, segmented regions and input dimensionality, i.e., number of extracted features. The association of the meta‐parameters with the automation performance was analyzed by multivariable general linear model decomposition of the automation performance in the contributions of meta‐parameters and the learning technique. Results The automation performance varied strongly for varying meta‐parameters. For emphysema‐predominant phenotypes, an AUC of 93%–95% could be achieved for the best meta‐configuration. The airways‐predominant phenotypes led to a lower performance of 65%–85%, while smooth kernel configurations on average were unexpectedly superior to those with sharp kernels. The performance impact of meta‐parameters, even that of often neglected ones like the missing‐data imputation, was in general larger than that of the learning technique. Advanced learning techniques like 3D deep learning or automated machine learning yielded inferior automation performance for non‐optimal meta‐configurations in comparison to simple techniques with suitable meta‐configurations. The best automation performance was achieved by a combination of modern learning techniques and a suitable meta‐configuration. Conclusions Our results indicate that for COPD phenotype automation, study design parameters such as reconstruction kernel and the model input dimensionality should be adapted to the learning technique and may be more important than the technique itself. To achieve optimal automation and prediction results, the interaction between input those meta‐parameters and the learning technique ...

show abstract

Section: Methodsmentioning

confidence: 99%

Unraveling the interplay of image formation, data representation and learning in CT‐based COPD phenotyping automation: The need for a meta‐strategy

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Experimental results showed that the recognition method based on CNN is before the method based on SVM. MFCC features are utilized to identify the lung sounds by a 5-Layer CNN (5L-CNN), and better recognition results are obtained in [1]. They used a variant of 3D VoxResNet for COPD emphysema classification.…”

Section: Related Workmentioning

confidence: 99%

“…5 Spectrogram of input after denoising spectrum line energy of the lung sounds is filtered by using a Mel filter bank. The function of filters is expressed using (1).…”

Section: Input Processing Of the Lung Sound Datamentioning

confidence: 99%

A lung sound recognition model to diagnoses the respiratory diseases by using transfer learning

Lal

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Respiratory disease is one of the leading causes of death in the world. Through advances in Artificial Intelligence, it appears possible for the days of misdiagnosis and treatment of respiratory disease symptoms rather than their root cause to move behind us. The traditional convolutional neural network cannot extract the temporal features of lung sounds. To solve the problem, a lung sounds recognition algorithm based on VGGish- stacked BiGRU is proposed which combines the VGGish network with the stacked bidirectional gated recurrent unit neural network. A lung Sound Recognition Algorithm Based on VGGish-Stacked BiGRU is used as a feature extractor which is a pre-trained model used for transfer learning. The target model is built with the same structure as the source model which is the VGGish model and parameter transfer is done from the source model to the target model. The multi-layer BiGRU stack is used to enhance the feature value and retain the model. While fine-tuning of the parameter of VGGish is frozen which successfully improves the model. The experimental results show that the proposed algorithm improves the recognition accuracy of lung sounds and the recognition accuracy of respiratory diseases.

show abstract

“…These models evaluate the local intensity distribution or use texture-based information to discern emphysema in CT [19,20]. Deep learning models, such as 3D convolutional neural networks (CNNs), deep-CNNs with long short-term memory and transfer learning models like 3D ResNet have been found to detect emphysema with acceptable performance [21,22,23]. However, all these approaches primarily make use of HRCT and there is a dearth of studies on low-dose CT for automatic detection of emphysema.…”

Section: Related Workmentioning

confidence: 99%

An unsupervised anomaly detection model to identify emphysema in low-dose computed tomography

Nagaraj¹,

Cornelissen²,

Cai³

et al. 2021

Preprint

View full text Add to dashboard Cite

<p>Challenges such as class imbalance, time intensive visual scoring, and limited amounts of labeled data are often encountered while accessing lung cancer screening low-dose computed tomography (LDCT) data for automated emphysema detection. To tackle these issues, we propose a generative adversarial network (GAN) based on unsupervised anomaly detection (UAD) to identify emphysema in LDCT. And to initiate disease specific feature learning, we introduce data augmentation based on minimum intensity projection (minIP) for the adversarial framework. The generator of the UAD model resembles an image latent-image configuration consisting of fully convolutional encoder-decoder architecture with skip connections. The discriminator is an encoder, which acts as a feature extractor and a classifier. We tested the robustness of the minIP based UAD model by adding anomalies to the training set. Furthermore to illustrate the usefulness of minIP and to serve as a comparison methodology for emphysema detection in LDCT, the proposed model was compared to the 2.5D transfer learning model. Visualization techniques like post processed residual images and Grad-cam maps were used to explain the UAD model inference. Our proposed minIP based UAD model showed an area under the curve of 0.91 0.02 for emphysema detection in LDCT. The UAD model was robust to inclusion of anomalies up to 3%. The augmentation improved the sensitivity of the transfer learning model by 2% however the UAD model outperformed the transfer learning model. The UAD model with minIP is a potential computer-aided tool for early detection of emphysema in lung cancer screening data.</p>

show abstract

COPD Classification in CT Images Using a 3D Convolutional Neural Network

Cited by 17 publications

References 8 publications

Unraveling the interplay of image formation, data representation and learning in CT‐based COPD phenotyping automation: The need for a meta‐strategy

Unraveling the interplay of image formation, data representation and learning in CT‐based COPD phenotyping automation: The need for a meta‐strategy

A lung sound recognition model to diagnoses the respiratory diseases by using transfer learning

An unsupervised anomaly detection model to identify emphysema in low-dose computed tomography

Contact Info

Product

Resources

About