Computerized Texture Analysis of Persistent Part-Solid Ground-Glass Nodules: Differentiation of Preinvasive Lesions from Invasive Pulmonary Adenocarcinomas

Chae, Hee‐Dong; Park, Chang Min; Park, Sang Joon; Lee, Sang Min; Kim, Kwang Gi; Goo, Jin Mo

doi:10.1148/radiol.14132187

Cited by 203 publications

(156 citation statements)

References 29 publications

Supporting

Mentioning

148

Contrasting

Order By: Relevance

“…Nevertheless, texture analysis on radiological data has nowadays become an integral part of an emerging field call radiomics, a high-throughput process in which large amounts of advanced quantitative imaging features are extracted and integrated for predictive or prognostic purpose (6)(7)(8). Some research groups have developed texture analysis methods to quantify lesion heterogeneity on lung CT (9)(10)(11).…”

Section: Introductionmentioning

confidence: 99%

“…Higher entropy indicates increased lesion heterogeneity (12). Several studies have shown that entropy extracted from medical images may add value in assessment of tissue morphologic changes induced by various diseases, including adnexal neoplasms (13,14), liver cirrhosis (15), and lung diseases (10,16). Grove et al (17) and Gatenby et al (18) first introduced a new heterogeneity metric by using entropy difference of CT attenuation across the tumor core to boundary regions and found it could predict patient survival in lung adenocarcinoma.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of Heterogeneity Difference Between Edge and Core by Using Texture Analysis

et al. 2016

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Assessment of Heterogeneity Difference Between Edge and Core by Using Texture Analysis

et al. 2016

View full text Add to dashboard Cite

“…to compute the size of solid part in a part-solid GGO nodule by EM algorithm if the GGO nodules are part-solid one. (5). to calculate the size of GGO nodules.…”

Section: Algorithm Of the Feature Extractionmentioning

confidence: 99%

“…In lung nodules, there are two types. One is solid nodules, and the other is Ground-Glass Opacity (GGO) nodules [5]. Currently, some approaches [6], [7] have been proposed to detect lung cancer based on some features of solid nodules [8] by image processing methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Extraction of Ground-Glass Opacity Nodules using Active Contour Model for Lung Cancer Detection

Miao¹,

Wang²,

Du³

et al. 2016

Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications

View full text Add to dashboard Cite

Abstract. The proportion of the solid part portion in a GGO nodule is one of features to detect lung cancer. It is difficult to segment the solid part in a GGO nodule completely because tissues surrounding GGO nodules include some impurities like noises in image processing technology. This paper proposes Active Contour Model (ACM) to find the boundary of a GGO nodule because ACM algorithm can remove noises. The size of a GGO nodule can be computed based on the boundary of the GGO nodule. Expectation-Maximization (EM) algorithm can segment the no solid part in GGO nodules because no solid part and solid part have different densities. Experiments show ACM algorithm is more effective than EM algorithm to find the boundary of a GGO nodule. Moreover, our proposal also can reduce the burden of doctors because it can find the boundary of GGO nodules automatically.

show abstract

Applying a CT texture analysis model trained with deep‐learning reconstruction images to iterative reconstruction images in pulmonary nodule diagnosis

Wang

Zhang

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Objective To investigate the feasibility and accuracy of applying a computed tomography (CT) texture analysis model trained with deep‐learning reconstruction images to iterative reconstruction images for classifying pulmonary nodules. Materials and methods CT images of 102 patients, with a total of 118 pulmonary nodules (52 benign, 66 malignant) were retrospectively reconstructed with a deep‐learning reconstruction (artificial intelligence iterative reconstruction [AIIR]) and a hybrid iterative reconstruction (HIR) technique. The AIIR data were divided into a training (n = 96) and a validation set (n = 22), and the HIR data were set as the test set (n = 118). Extracted texture features were compared using the Mann‐Whitney U test and t‐test. The diagnostic performance of the classification model was analyzed with the receiver operating characteristic curve (ROC), the area under ROC (AUC), sensitivity, specificity, and accuracy. Results Among the obtained 68 texture features, 51 (75.0%) were not influenced by the change of reconstruction algorithm (p > 0.05). Forty‐four features were significantly different between benign and malignant nodules (p < 0.05) for the AIIR dataset, which were selected to build the classification model. The accuracy and AUC of the classification model were 92.3% and 0.91 (95% confidence interval [CI], 0.74−0.90) with the validation set, which were 80.0% and 0.80 (95% CI, 0.68−0.86) with the test set. Conclusion With the CT texture analysis model trained with deep‐learning reconstruction (AIIR) images showing favorable diagnostic accuracy in discriminating benign and malignant pulmonary nodules, it also has certain applicability to the iterative reconstruction (HIR) images.

show abstract

Computerized Texture Analysis of Persistent Part-Solid Ground-Glass Nodules: Differentiation of Preinvasive Lesions from Invasive Pulmonary Adenocarcinomas

Abstract: In part-solid GGNs, higher kurtosis and smaller mass are significant differentiators of preinvasive lesions from IPAs, and preinvasive lesions can be accurately differentiated from IPAs by using computerized texture analysis. Online supplemental material is available for this article.

Cited by 203 publications

References 29 publications

Assessment of Heterogeneity Difference Between Edge and Core by Using Texture Analysis

Assessment of Heterogeneity Difference Between Edge and Core by Using Texture Analysis

Feature Extraction of Ground-Glass Opacity Nodules using Active Contour Model for Lung Cancer Detection

Applying a CT texture analysis model trained with deep‐learning reconstruction images to iterative reconstruction images in pulmonary nodule diagnosis

Contact Info

Product

Resources

About