Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance

Kale, Mandar; Mukhopadhyay, Sudipta; Dash, Jatindra Kumar; Garg, Mandeep; Khandelwal, Niranjan

doi:10.1117/12.2216743

Cited by 8 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Here, PM2 and PM1 achieved an overall accuracy of 0.9028 and 0.9007 at feature subset size 90 and 233, respectively. The accuracy of the proposed methodologies is higher than the (Depeursinge et al, 2011) and (Kale et al, 2016) as shown in Table 8.…”

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 90%

See 1 more Smart Citation

Evaluation of feature selection methods utilizing random forest and logistic regression for lung tissue categorization using HRCT images

2023

View full text Add to dashboard Cite

Categorization of lung tissue patterns with interstitial lung diseases (ILD) utilize high‐resolution computed tomography (HRCT) lung images of the TALISMAN dataset which is challenging due to high intra‐class variation and inter‐class ambiguity. To tackle this, major contributions are made in three aspects. First, a novel shape‐based feature is proposed to quantify the amount of fibrotic and nodular components in a lung tissue pattern which helps to minimize intra‐class variation and inter‐class ambiguity. Second, we address the curse of dimensionality which often arises due to huge feature space. Third, to prevent an overfitting issue, the Grid Search optimization algorithm is utilized by tuning the Random Forest hyper‐parameters. In this manuscript, a framework is proposed to categorize lung tissue patterns by integrating four types of feature domains (a) intensity‐based, (b) texture‐based, (c) wavelet‐based, and (d) shape‐based along with the novel shape‐based feature. As a result, we encounter a large feature space (i.e., ), which leads to high dimensionality. To address this issue, we reduce the feature space using filter‐based f‐statistic, reliefF, minimum Redundancy Maximum Relevance (mRMR), and embedded‐based decision trees, regularization models. We found that the regularization model shrinks the feature space by 2.5 times in just 90 s whereas mRMR methods reduce the feature space by 10 times in 13 min. Using the proposed feature set, we employ Random Forest and Logistic Regression as potential classifiers to classify lung tissue patterns. Experiential results reveal that the proposed framework categorizes lung tissue patterns more effectively than state‐of‐the‐art hand‐crafted and deep learning‐based approaches.

show abstract

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 90%

“…Neural Networks (ANN) and Support Vector Machine (SVM) classifiers (Kale et al, 2016). Sodhi et al (2018) utilized 3-Tesla MRI for ILD detection in kids.…”

Section: Grayscale and Colormentioning

confidence: 99%

Evaluation of feature selection methods utilizing random forest and logistic regression for lung tissue categorization using HRCT images

2023

View full text Add to dashboard Cite

show abstract

“…Para obter uma avaliação mais precisa de padrões radiológicos, a Tomografia Computadorizada de Alta Resolução (TCAR) [Zhao et al 2013] vem sendo aceita como o padrão-ouro para fins de diagnóstico [Alemzadeh et al 2015]. Ademais, imagens de TCAR conseguem exibir combinações de padrões teciduais distintas para diferentes DPDs [Song et al 2013], trazendo informações detalhadas que permitem uma melhor visualização do tecido [Kale et al 2016].…”

Section: Introductionunclassified

Classificação de Blocos de Imagens de Padrões Radiológicos Pulmonares com Resampling SMOTE

Rogalsky¹,

Alves²,

Oliveira³

2018

Anais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS)

View full text Add to dashboard Cite

Diffuse Pulmonary Diseases can affect the lung parenchyma, causing respiratory deficiencies and even cause almost complete loss of function, requiring a more accurate evaluation for a concrete diagnosis. Using computational techniques, the purpose of this work is to use feature descriptors (LBP, CLBP, gray-level histogram and GLCM) for classification of lung patterns, assisting radiologists in the diagnosis of these diseases. Using a patch-based approach, SMOTE resampling and the SVM classifier, accuracy of 87.41% and sensitivity of 88.31% were achieved.Resumo. Doenças Pulmonares Difusas podem afetar o parênquima pulmonar, causando deficiências respiratórias até a quase completa perda de função, sendo necessária uma avaliação mais precisa para um diagnóstico concreto. Utilizando-se de técnicas computacionais, a proposta deste trabalho é utilizar descritores de características (LBP, CLBP, histograma de níveis de cinza e GLCM) para a classificação de padrões pulmonares, auxiliando radiologistas no diagnóstico dessas doenças. Utilizando uma abordagem baseada em blocos, resampling SMOTE e o classificador SVM, uma taxa de acerto de 87,41% e sensibilidade de 88,31% foram alcançadas.

show abstract

“…Many classifiers have shown to be fit for the image classification task in the literature. Example of recent works are (BEDO et al, 2015;KALE et al, 2016;KARARGYRIS et al, 2016;CHINO et al, 2018). Usually, they rely on color, texture, and other available features to perform classification.…”

Section: Classification Algorithmsmentioning

confidence: 99%

“…Still regarding the ILD classification problem, the work (KALE et al, 2016) analyzes the discriminatory performance of artificial neural networks and SVM classifiers. Such approaches are based on wavelet features, which were extracted from high-resolution CT images in two datasets, MedGIFT, and a private one.…”

Section: Related Workmentioning

confidence: 99%

Conquering knowledge from images: improving image mining with region-based analysis and associated information

Cazzolato¹

View full text Add to dashboard Cite

show abstract

Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance

Cited by 8 publications

References 9 publications

Evaluation of feature selection methods utilizing random forest and logistic regression for lung tissue categorization using HRCT images

Evaluation of feature selection methods utilizing random forest and logistic regression for lung tissue categorization using HRCT images

Classificação de Blocos de Imagens de Padrões Radiológicos Pulmonares com Resampling SMOTE

Conquering knowledge from images: improving image mining with region-based analysis and associated information

Contact Info

Product

Resources

About