Emphysema discrimination from raw HRCT images by convolutional neural networks

Karabulut, Esra; İbrikçi, Turgay

doi:10.1109/eleco.2015.7394441

Cited by 17 publications

(9 citation statements)

References 14 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bullae index method [42] was also gone through for emphysema classification. The simulation results are also compared with other existing methods like LBP [45],LRM [46], Feature ensemble [47], SFS [48], CNN [49], LBP [50], Fuzzy Decision Tree [51], CNN [52],JWRIULTP [53], and FFO+ELM [22] in terms of several positive or Type I measures like, "accuracy, sensitivity, specificity, precision, NPV, F1 Score, and MCC", and negative or Type II measures like, "FPR, FNR, and FDR".…”

Section: A Simulation Set-upmentioning

confidence: 99%

Adaptive Local Ternary Pattern on Parameter Optimized-Faster Region Convolutional Neural Network for Pulmonary Emphysema Diagnosis

2021

View full text Add to dashboard Cite

Emphysema is a lung disease that occurs due to abnormal alveoli expansion. This chronic disease causes difficulty in breathing which can lead to lung cancer. The progressive destruction of emphysema can be assessed by Computed Tomography (CT) scans and pulmonary function tests. The severity of the disease may extend to a stage where one can risk their life emphasizing the early detection of emphysema. Primary diagnosis can be done using spirometry and CT for early detection of the disease reducing the mortality rates. Difficulties associated with different diagnostic procedures and inter and intraobserver variations have made blooming researches on more computer-aided techniques. This paper intends to develop a computer-aided technique using the improved deep learning strategy. The initial process is image pre-processing, which is performed by histogram equalization and median filtering. Further, the Fuzzy C Means (FCM) clustering is used for segmentation. After segmentation, a new Adaptive Local Ternary Pattern (ALTP) is used for extracting the pattern descriptor, which is further utilized for classification. As a new contribution, the Parameter Optimized-Faster Region Convolutional Neural Network (PO-FRCNN) is developed for performing the diagnosis. The enhancement of pattern formation and deep classification is accomplished by the Improved Red Deer Algorithm (IRDA), which helps to tune the significant parameters that have a positive influence on the accurateness. The benchmark and real-time dataset are used for performing the experimentation. The results show that the proposed method yields the best result and can effectively diagnose emphysema when compared to state-of-the-art techniques.INDEX TERMS Adaptive local ternary pattern, fuzzy C means clustering, modified deep learning, parameter optimized-faster region convolutional neural network, pulmonary emphysema.

show abstract

Section: A Simulation Set-upmentioning

confidence: 99%

Adaptive Local Ternary Pattern on Parameter Optimized-Faster Region Convolutional Neural Network for Pulmonary Emphysema Diagnosis

2021

View full text Add to dashboard Cite

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

“…The existing supervised machine learning algorithms [12,13] or DL algorithms for automatic emphysema detection like 3D convolutional neural networks (CNNs) [14], deep-CNNs with long short-term memory [15], and transfer learning models like 3D ResNet [16] require disease localized annotations, which are difficult to obtain for large datasets, or they are primarily developed using HRCT [17,18]. This motivated us to develop an unsupervised model for emphysema in screening studies.…”

Section: Introductionmentioning

confidence: 99%

AI-Driven Model for Automatic Emphysema Detection in Low-Dose Computed Tomography Using Disease-Specific Augmentation

et al. 2022

View full text Add to dashboard Cite

The objective of this study is to evaluate the feasibility of a disease-specific deep learning (DL) model based on minimum intensity projection (minIP) for automated emphysema detection in low-dose computed tomography (LDCT) scans. LDCT scans of 240 individuals from a population-based cohort in the Netherlands (ImaLife study, mean age ± SD = 57 ± 6 years) were retrospectively chosen for training and internal validation of the DL model. For independent testing, LDCT scans of 125 individuals from a lung cancer screening cohort in the USA (NLST study, mean age ± SD = 64 ± 5 years) were used. Dichotomous emphysema diagnosis based on radiologists’ annotation was used to develop the model. The automated model included minIP processing (slab thickness range: 1 mm to 11 mm), classification, and detection maps generation. The data-split for the pipeline evaluation involved class-balanced and imbalanced settings. The proposed DL pipeline showed the highest performance (area under receiver operating characteristics curve) for 11 mm slab thickness in both the balanced (ImaLife = 0.90 ± 0.05) and the imbalanced dataset (NLST = 0.77 ± 0.06). For ImaLife subcohort, the variation in minIP slab thickness from 1 to 11 mm increased the DL model’s sensitivity from 75 to 88% and decreased the number of false-negative predictions from 10 to 5. The minIP-based DL model can automatically detect emphysema in LDCTs. The performance of thicker minIP slabs was better than that of thinner slabs. LDCT can be leveraged for emphysema detection by applying disease specific augmentation.

show abstract

Emphysema discrimination from raw HRCT images by convolutional neural networks

Cited by 17 publications

References 14 publications

Adaptive Local Ternary Pattern on Parameter Optimized-Faster Region Convolutional Neural Network for Pulmonary Emphysema Diagnosis

Adaptive Local Ternary Pattern on Parameter Optimized-Faster Region Convolutional Neural Network for Pulmonary Emphysema Diagnosis

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

AI-Driven Model for Automatic Emphysema Detection in Low-Dose Computed Tomography Using Disease-Specific Augmentation

Contact Info

Product

Resources

About