Literature DB >> 30476456

Effect of CT Reconstruction Algorithm on the Diagnostic Performance of Radiomics Models: A Task-Based Approach for Pulmonary Subsolid Nodules.

Hyungjin Kim1, Chang Min Park1,2, Jeonghwan Gwak1, Eui Jin Hwang1, Seon Young Lee3, Julip Jung3, Helen Hong3, Jin Mo Goo1,2.   

Abstract

OBJECTIVE: We investigated whether the diagnostic performance of machine learning-based radiomics models for the discrimination of invasive pulmonary adenocarcinomas (IPAs) among subsolid nodules (SSNs) was affected by the proportion of images reconstructed with filtered back projection (FBP) and model-based iterative reconstruction (MBIR) in datasets used for feature extraction.
MATERIALS AND METHODS: This retrospective study included 60 patients (23 men and 37 women; mean age, 61.4 years) with 69 SSNs (54 part-solid and 15 pure ground-glass nodules). Preoperative CT scans were reconstructed with both FBP and MBIR. A total of 860 radiomics features were obtained from the entire nodule volume, and 70 resampled nodule datasets with an increasing proportion of nodules with MBIR-derived features (from 0/69 to 69/69) were prepared. After feature selection using neighborhood component analysis, support vector machines (SVMs) and an ensemble model were used as classifiers for the differentiation of IPAs. The diagnostic performances of all blending proportions of reconstruction algorithms were calculated and analyzed.
RESULTS: The ROC AUC and the diagnostic accuracy of the radiomics models decreased significantly as the number of nodules with MBIR-derived features increased, and this relationship followed cubic functions (R2 = 0.993 and 0.926 for SVM; R2 = 0.993 and 0.975 for the ensemble model; p < 0.001). The magnitude of variation in AUC due to the reconstruction algorithm heterogeneity was 0.39 for SVM and 0.39 for the ensemble model.
CONCLUSION: Inclusion of CT scans reconstructed with MBIR for radiomics modeling can significantly decrease diagnostic performance for the identification of IPAs.

Entities:  

Keywords:  MDCT; computer-assisted diagnosis; computer-assisted image processing; machine learning; non–small cell lung carcinoma

Year:  2018        PMID: 30476456     DOI: 10.2214/AJR.18.20018

Source DB:  PubMed          Journal:  AJR Am J Roentgenol        ISSN: 0361-803X            Impact factor:   3.959


  10 in total

1.  Integrating manual diagnosis into radiomics for reducing the false positive rate of 18F-FDG PET/CT diagnosis in patients with suspected lung cancer.

Authors:  Fei Kang; Wei Mu; Jie Gong; Shengjun Wang; Guoquan Li; Guiyu Li; Wei Qin; Jie Tian; Jing Wang
Journal:  Eur J Nucl Med Mol Imaging       Date:  2019-07-18       Impact factor: 9.236

2.  Technical note: Evaluation of a V-Net autosegmentation algorithm for pediatric CT scans: Performance, generalizability, and application to patient-specific CT dosimetry.

Authors:  Philip M Adamson; Vrunda Bhattbhatt; Sara Principi; Surabhi Beriwal; Linda S Strain; Michael Offe; Adam S Wang; Nghia-Jack Vo; Taly Gilat Schmidt; Petr Jordan
Journal:  Med Phys       Date:  2022-02-22       Impact factor: 4.071

3.  Effect of adaptive statistical iterative reconstruction-V (ASiR-V) levels on ultra-low-dose CT radiomics quantification in pulmonary nodules.

Authors:  Kai Ye; Min Chen; Qiao Zhu; Yuliu Lu; Huishu Yuan
Journal:  Quant Imaging Med Surg       Date:  2021-06

4.  Standardization of histogram- and GLCM-based radiomics in the presence of blur and noise.

Authors:  Grace Jianan Gang; Radhika Deshpande; Joseph Webster Stayman
Journal:  Phys Med Biol       Date:  2021-03-15       Impact factor: 4.174

5.  Reproducibility of lung nodule radiomic features: Multivariable and univariable investigations that account for interactions between CT acquisition and reconstruction parameters.

Authors:  Nastaran Emaminejad; Muhammad Wasil Wahi-Anwar; Grace Hyun J Kim; William Hsu; Matthew Brown; Michael McNitt-Gray
Journal:  Med Phys       Date:  2021-04-13       Impact factor: 4.506

Review 6.  Putting artificial intelligence (AI) on the spot: machine learning evaluation of pulmonary nodules.

Authors:  Yasmeen K Tandon; Brian J Bartholmai; Chi Wan Koo
Journal:  J Thorac Dis       Date:  2020-11       Impact factor: 2.895

7.  Maximum Standardized Uptake Value of 18F-deoxyglucose PET Imaging Increases the Effectiveness of CT Radiomics in Differentiating Benign and Malignant Pulmonary Ground-Glass Nodules.

Authors:  Rong Niu; Jianxiong Gao; Xiaoliang Shao; Jianfeng Wang; Zhenxing Jiang; Yunmei Shi; Feifei Zhang; Yuetao Wang; Xiaonan Shao
Journal:  Front Oncol       Date:  2021-12-17       Impact factor: 6.244

8.  A wavelet features derived radiomics nomogram for prediction of malignant and benign early-stage lung nodules.

Authors:  Rui Jing; Jingtao Wang; Jiangbing Li; Xiaojuan Wang; Baijie Li; Fuzhong Xue; Guangrui Shao; Hao Xue
Journal:  Sci Rep       Date:  2021-11-16       Impact factor: 4.379

9.  Validation of a deep learning computer aided system for CT based lung nodule detection, classification, and growth rate estimation in a routine clinical population.

Authors:  John T Murchison; Gillian Ritchie; David Senyszak; Jeroen H Nijwening; Gerben van Veenendaal; Joris Wakkie; Edwin J R van Beek
Journal:  PLoS One       Date:  2022-05-05       Impact factor: 3.752

10.  Deep learning-based reconstruction on cardiac CT yields distinct radiomic features compared to iterative and filtered back projection reconstructions.

Authors:  Sei Hyun Chun; Young Joo Suh; Kyunghwa Han; Yonghan Kwon; Aaron Youngjae Kim; Byoung Wook Choi
Journal:  Sci Rep       Date:  2022-09-07       Impact factor: 4.996

  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.