Literature DB >> 29520429

Robustness versus disease differentiation when varying parameter settings in radiomics features: application to nasopharyngeal PET/CT.

Wenbing Lv1, Qingyu Yuan2, Quanshi Wang2, Jianhua Ma3, Jun Jiang1, Wei Yang1, Qianjin Feng1, Wufan Chen1, Arman Rahmim4,5, Lijun Lu6.   

Abstract

OBJECTIVES: To investigate the impact of parameter settings as used for the generation of radiomics features on their robustness and disease differentiation (nasopharyngeal carcinoma (NPC) versus chronic nasopharyngitis (CN) in FDG PET/CT imaging).
METHODS: We studied 106 patients (69/37 NPC/CN, pathology confirmed), and extracted 57 radiomics features under different parameter settings. Robustness was assessed by the intra-class correlation coefficient (ICC). Logistic regression with leave-one-out cross validation was used to generate classification probabilities, and diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC).
RESULTS: Varying averaging strategies and symmetry, 4/26 GLCM features showed poor range of pairwise ICCs of 0.02-0.98, while depicting good AUCs of 0.82-0.91. Varying distances, 5/26 GLCM features showed ICCs of 0.82-0.99 while corresponding AUCs were 0.52-0.91. 6/13 GLRLM features showed both high AUC (0.81-0.89) and high ICC (0.85-0.99) regarding to averaging strategies. 7/13 GLSZM features showed AUCs of 0.81-0.90 while having ICCs of 0.01-0.99 under different neighbourhoods. 2/5 NGTDM features showed AUCs of 0.81-0.85 while having ICCs of 0.19-0.89 for different window sizes. Differentiating a subset of NPC (stages I-II) form CN, both SumEntropy and SZLGE achieved significantly higher AUCs than metabolically active tumour volume (AUC: 0.91 vs. 0.72, p<0.01).
CONCLUSIONS: Radiomics features depicting poor absolute-scale robustness regarding to parameter settings can still lead to good diagnostic performance. As such, robustness of radiomics features should not be overemphasized for removal of features towards assessment of clinical tasks. For differentiating NPC from CN, some radiomics features (e.g. SumEntropy, SZLGE, LGZE) outperformed conventional metrics. KEY POINTS: • Poor robustness did not necessarily translate into poor differentiation performance. • Absolute-scale robustness of radiomics features should not be overemphasized. • Radiomics features SumEntropy, SZLGE and LGZE outperformed conventional metrics.

Entities:  

Keywords:  Fluorodeoxyglucose F18; Nasopharyngeal carcinoma; Nasopharyngitis; Positron emission tomography computed tomography; Radiomics

Mesh:

Substances:

Year:  2018        PMID: 29520429     DOI: 10.1007/s00330-018-5343-0

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  45 in total

1.  Zone-size nonuniformity of 18F-FDG PET regional textural features predicts survival in patients with oropharyngeal cancer.

Authors:  Nai-Ming Cheng; Yu-Hua Dean Fang; Li-yu Lee; Joseph Tung-Chieh Chang; Din-Li Tsan; Shu-Hang Ng; Hung-Ming Wang; Chun-Ta Liao; Lan-Yan Yang; Ching-Han Hsu; Tzu-Chen Yen
Journal:  Eur J Nucl Med Mol Imaging       Date:  2014-10-23       Impact factor: 9.236

2.  Preliminary study of 11C-choline PET/CT for T staging of locally advanced nasopharyngeal carcinoma: comparison with 18F-FDG PET/CT.

Authors:  Hu-bing Wu; Quan-shi Wang; Ming-fang Wang; Xiaokang Zhen; Wen-lan Zhou; Hong-sheng Li
Journal:  J Nucl Med       Date:  2011-02-14       Impact factor: 10.057

3.  Staging of cervical cancer based on tumor heterogeneity characterized by texture features on (18)F-FDG PET images.

Authors:  Wei Mu; Zhe Chen; Ying Liang; Wei Shen; Feng Yang; Ruwei Dai; Ning Wu; Jie Tian
Journal:  Phys Med Biol       Date:  2015-06-17       Impact factor: 3.609

4.  18F-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort.

Authors:  Mathieu Hatt; Mohamed Majdoub; Martin Vallières; Florent Tixier; Catherine Cheze Le Rest; David Groheux; Elif Hindié; Antoine Martineau; Olivier Pradier; Roland Hustinx; Remy Perdrisot; Remy Guillevin; Issam El Naqa; Dimitris Visvikis
Journal:  J Nucl Med       Date:  2014-12-11       Impact factor: 10.057

Review 5.  Applications and limitations of radiomics.

Authors:  Stephen S F Yip; Hugo J W L Aerts
Journal:  Phys Med Biol       Date:  2016-06-08       Impact factor: 3.609

6.  Coregistered FDG PET/CT-based textural characterization of head and neck cancer for radiation treatment planning.

Authors:  Huan Yu; Curtis Caldwell; Katherine Mah; Daniel Mozeg
Journal:  IEEE Trans Med Imaging       Date:  2009-03       Impact factor: 10.048

7.  Intratumor heterogeneity and branched evolution revealed by multiregion sequencing.

Authors:  Marco Gerlinger; Andrew J Rowan; Stuart Horswell; James Larkin; David Endesfelder; Eva Gronroos; Pierre Martinez; Nicholas Matthews; Aengus Stewart; Charles Swanton; M Math; Patrick Tarpey; Ignacio Varela; Benjamin Phillimore; Sharmin Begum; Neil Q McDonald; Adam Butler; David Jones; Keiran Raine; Calli Latimer; Claudio R Santos; Mahrokh Nohadani; Aron C Eklund; Bradley Spencer-Dene; Graham Clark; Lisa Pickering; Gordon Stamp; Martin Gore; Zoltan Szallasi; Julian Downward; P Andrew Futreal
Journal:  N Engl J Med       Date:  2012-03-08       Impact factor: 91.245

8.  The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis.

Authors:  Ralph T H Leijenaar; Georgi Nalbantov; Sara Carvalho; Wouter J C van Elmpt; Esther G C Troost; Ronald Boellaard; Hugo J W L Aerts; Robert J Gillies; Philippe Lambin
Journal:  Sci Rep       Date:  2015-08-05       Impact factor: 4.379

9.  Revisiting the Robustness of PET-Based Textural Features in the Context of Multi-Centric Trials.

Authors:  Clément Bailly; Caroline Bodet-Milin; Solène Couespel; Hatem Necib; Françoise Kraeber-Bodéré; Catherine Ansquer; Thomas Carlier
Journal:  PLoS One       Date:  2016-07-28       Impact factor: 3.240

10.  Radiomics: Images Are More than Pictures, They Are Data.

Authors:  Robert J Gillies; Paul E Kinahan; Hedvig Hricak
Journal:  Radiology       Date:  2015-11-18       Impact factor: 11.105

View more
  21 in total

1.  Radiomics in nuclear medicine: robustness, reproducibility, standardization, and how to avoid data analysis traps and replication crisis.

Authors:  Alex Zwanenburg
Journal:  Eur J Nucl Med Mol Imaging       Date:  2019-06-25       Impact factor: 9.236

2.  Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement.

Authors:  Ji Eun Park; Donghyun Kim; Ho Sung Kim; Seo Young Park; Jung Youn Kim; Se Jin Cho; Jae Ho Shin; Jeong Hoon Kim
Journal:  Eur Radiol       Date:  2019-07-26       Impact factor: 5.315

3.  Prediction of local recurrence and distant metastasis using radiomics analysis of pretreatment nasopharyngeal [18F]FDG PET/CT images.

Authors:  Lihong Peng; Xiaotong Hong; Qingyu Yuan; Lijun Lu; Quanshi Wang; Wufan Chen
Journal:  Ann Nucl Med       Date:  2021-02-04       Impact factor: 2.668

4.  Radiomics Analysis of PET and CT Components of PET/CT Imaging Integrated with Clinical Parameters: Application to Prognosis for Nasopharyngeal Carcinoma.

Authors:  Wenbing Lv; Qingyu Yuan; Quanshi Wang; Jianhua Ma; Qianjin Feng; Wufan Chen; Arman Rahmim; Lijun Lu
Journal:  Mol Imaging Biol       Date:  2019-10       Impact factor: 3.488

5.  Radiomics on multi-modalities MR sequences can subtype patients with non-metastatic nasopharyngeal carcinoma (NPC) into distinct survival subgroups.

Authors:  En-Hong Zhuo; Wei-Jing Zhang; Hao-Jiang Li; Guo-Yi Zhang; Bing-Zhong Jing; Jian Zhou; Chun-Yan Cui; Ming-Yuan Chen; Ying Sun; Li-Zhi Liu; Hong-Min Cai
Journal:  Eur Radiol       Date:  2019-03-14       Impact factor: 5.315

6.  Machine Learning Methods for Optimal Radiomics-Based Differentiation Between Recurrence and Inflammation: Application to Nasopharyngeal Carcinoma Post-therapy PET/CT Images.

Authors:  Dongyang Du; Hui Feng; Wenbing Lv; Saeed Ashrafinia; Qingyu Yuan; Quanshi Wang; Wei Yang; Qianjin Feng; Wufan Chen; Arman Rahmim; Lijun Lu
Journal:  Mol Imaging Biol       Date:  2020-06       Impact factor: 3.488

Review 7.  Radiomics in Oncological PET Imaging: A Systematic Review-Part 1, Supradiaphragmatic Cancers.

Authors:  David Morland; Elizabeth Katherine Anna Triumbari; Luca Boldrini; Roberto Gatta; Daniele Pizzuto; Salvatore Annunziata
Journal:  Diagnostics (Basel)       Date:  2022-05-27

8.  Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET/CT to Predict Prognosis of Patients with Endometrial Cancer.

Authors:  Masatoyo Nakajo; Megumi Jinguji; Atsushi Tani; Hidehiko Kikuno; Daisuke Hirahara; Shinichi Togami; Hiroaki Kobayashi; Takashi Yoshiura
Journal:  Mol Imaging Biol       Date:  2021-03-24       Impact factor: 3.488

9.  Radiomics side experiments and DAFIT approach in identifying pulmonary hypertension using Cardiac MRI derived radiomics based machine learning models.

Authors:  Sarv Priya; Tanya Aggarwal; Caitlin Ward; Girish Bathla; Mathews Jacob; Alicia Gerke; Eric A Hoffman; Prashant Nagpal
Journal:  Sci Rep       Date:  2021-06-16       Impact factor: 4.996

10.  Assessment of MRI-Based Radiomics in Preoperative T Staging of Rectal Cancer: Comparison between Minimum and Maximum Delineation Methods.

Authors:  Haidi Lu; Yuan Yuan; Zhen Zhou; Xiaolu Ma; Fu Shen; Yuwei Xia; Jianping Lu
Journal:  Biomed Res Int       Date:  2021-07-10       Impact factor: 3.411

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.