Literature DB >> 33763816

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.

Masatoyo Nakajo1, Megumi Jinguji2, Atsushi Tani2, Hidehiko Kikuno2, Daisuke Hirahara3, Shinichi Togami4, Hiroaki Kobayashi4, Takashi Yoshiura2.   

Abstract

PURPOSE: To examine the prognostic significance of pretreatment 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG) positron emission tomography (PET)-based radiomic features using a machine learning approach in patients with endometrial cancers. PROCEDURES: Included in this retrospective study were 53 patients with endometrial cancers who underwent [18F]-FDG PET/X-ray computed tomography (CT) before treatment. Since two different PET scanners were used, post-reconstruction harmonization was performed for all PET parameters using the ComBat harmonization method. Four clinical (age, histological type, stage, and treatment method) and 40 [18F]-FDG PET-based radiomic features were ranked, and a subset of useful features was selected based on the decrease in the Gini impurity in terms of associations with disease progression. The machine learning algorithms (random forest, neural network, k-nearest neighbors (kNN), naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method. Progression-free survival (PFS) and overall survival (OS) were assessed by the Cox regression analysis.
RESULTS: The five best predictors of disease progression were coarseness, gray-level run length nonuniformity, stage, treatment method, and gray-level zone length nonuniformity. The kNN model obtained the best performance classifier for predicting the disease progression (AUC =0.890, accuracy =0.849, F1 score =0.848, precision =0.857, and recall =0.849). Coarseness which was the first ranked radiomic feature was selected for survival analyses, and only coarseness remained as a significant and independent factor for both PFS (hazard ratios (HR), 0.65; 95 % confidence interval [CI], 0.49-0.86; p=0.003) and OS (HR, 0.52; 95 % CI, 0.36-0.76; p<0.001) at multivariate Cox regression analysis.
CONCLUSIONS: [18F]-FDG PET-based radiomic analysis using a machine learning approach may be useful for predicting tumor progression and prognosis in patients with endometrial cancers.
© 2021. World Molecular Imaging Society.

Entities:  

Keywords:  Endometrial neoplasms, [18F]-FDG; Machine learning, Prognosis; PET/CT

Mesh:

Substances:

Year:  2021        PMID: 33763816     DOI: 10.1007/s11307-021-01599-9

Source DB:  PubMed          Journal:  Mol Imaging Biol        ISSN: 1536-1632            Impact factor:   3.488


  38 in total

1.  Prediction of outcome using pretreatment 18F-FDG PET/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy.

Authors:  François Lucia; Dimitris Visvikis; Marie-Charlotte Desseroit; Omar Miranda; Jean-Pierre Malhaire; Philippe Robin; Olivier Pradier; Mathieu Hatt; Ulrike Schick
Journal:  Eur J Nucl Med Mol Imaging       Date:  2017-12-09       Impact factor: 9.236

2.  Global cancer statistics.

Authors:  Ahmedin Jemal; Freddie Bray; Melissa M Center; Jacques Ferlay; Elizabeth Ward; David Forman
Journal:  CA Cancer J Clin       Date:  2011-02-04       Impact factor: 508.702

3.  Prognostic significance of gross myometrial invasion with endometrial cancer.

Authors:  D M Larson; G P Connor; S K Broste; B R Krawisz; K K Johnson
Journal:  Obstet Gynecol       Date:  1996-09       Impact factor: 7.661

4.  Surgical staging in endometrial cancer: clinical-pathologic findings of a prospective study.

Authors:  R C Boronow; C P Morrow; W T Creasman; P J Disaia; S G Silverberg; A Miller; J A Blessing
Journal:  Obstet Gynecol       Date:  1984-06       Impact factor: 7.661

5.  Temporal analysis of intratumoral metabolic heterogeneity characterized by textural features in cervical cancer.

Authors:  Fei Yang; Maria A Thomas; Farrokh Dehdashti; Perry W Grigsby
Journal:  Eur J Nucl Med Mol Imaging       Date:  2013-01-23       Impact factor: 9.236

6.  A preliminary investigation into textural features of intratumoral metabolic heterogeneity in (18)F-FDG PET for overall survival prognosis in patients with bulky cervical cancer treated with definitive concurrent chemoradiotherapy.

Authors:  Kung-Chu Ho; Yu-Hua Dean Fang; Hsiao-Wen Chung; Tzu-Chen Yen; Tsung-Ying Ho; Hung-Hsueh Chou; Ji-Hong Hong; Yi-Ting Huang; Chun-Chieh Wang; Chyong-Huey Lai
Journal:  Am J Nucl Med Mol Imaging       Date:  2016-07-06

7.  Prognosis and treatment of endometrial cancer.

Authors:  M L Berman; S C Ballon; L D Lagasse; W G Watring
Journal:  Am J Obstet Gynecol       Date:  1980-03-01       Impact factor: 8.661

8.  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

9.  Prediction of cervical cancer recurrence using textural features extracted from 18F-FDG PET images acquired with different scanners.

Authors:  Sylvain Reuzé; Fanny Orlhac; Cyrus Chargari; Christophe Nioche; Elaine Limkin; François Riet; Alexandre Escande; Christine Haie-Meder; Laurent Dercle; Sébastien Gouy; Irène Buvat; Eric Deutsch; Charlotte Robert
Journal:  Oncotarget       Date:  2017-06-27

10.  Textural features of cervical cancers on FDG-PET/CT associate with survival and local relapse in patients treated with definitive chemoradiotherapy.

Authors:  Shang-Wen Chen; Wei-Chih Shen; Te-Chun Hsieh; Ji-An Liang; Yao-Ching Hung; Lian-Shung Yeh; Wei-Chun Chang; Wu-Chou Lin; Kuo-Yang Yen; Chia-Hung Kao
Journal:  Sci Rep       Date:  2018-08-08       Impact factor: 4.379

View more
  7 in total

Review 1.  Radiomics in Oncological PET Imaging: A Systematic Review-Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers.

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

2.  Clinical parameters combined with radiomics features of PET/CT can predict recurrence in patients with high-risk pediatric neuroblastoma.

Authors:  Lijuan Feng; Luodan Qian; Shen Yang; Qinghua Ren; Shuxin Zhang; Hong Qin; Wei Wang; Chao Wang; Hui Zhang; Jigang Yang
Journal:  BMC Med Imaging       Date:  2022-05-28       Impact factor: 2.795

3.  An Applicable Machine Learning Model Based on Preoperative Examinations Predicts Histology, Stage, and Grade for Endometrial Cancer.

Authors:  Ying Feng; Zhixiang Wang; Meizhu Xiao; Jinfeng Li; Yuan Su; Bert Delvoux; Zhen Zhang; Andre Dekker; Sofia Xanthoulea; Zhiqiang Zhang; Alberto Traverso; Andrea Romano; Zhenyu Zhang; Chongdong Liu; Huiqiao Gao; Shuzhen Wang; Linxue Qian
Journal:  Front Oncol       Date:  2022-05-30       Impact factor: 5.738

4.  FDG PET biomarkers for prediction of survival in metastatic melanoma prior to anti-PD1 immunotherapy.

Authors:  A Flaus; V Habouzit; N De Leiris; J P Vuillez; M T Leccia; J L Perrot; N Prevot; F Cachin
Journal:  Sci Rep       Date:  2021-09-22       Impact factor: 4.379

5.  Radiomic Phenotypes for Improving Early Prediction of Survival in Stage III Non-Small Cell Lung Cancer Adenocarcinoma after Chemoradiation.

Authors:  José Marcio Luna; Andrew R Barsky; Russell T Shinohara; Leonid Roshkovan; Michelle Hershman; Alexandra D Dreyfuss; Hannah Horng; Carolyn Lou; Peter B Noël; Keith A Cengel; Sharyn Katz; Eric S Diffenderfer; Despina Kontos
Journal:  Cancers (Basel)       Date:  2022-01-29       Impact factor: 6.639

6.  Outcome Prediction at Patient Level Derived from Pre-Treatment 18F-FDG PET Due to Machine Learning in Metastatic Melanoma Treated with Anti-PD1 Treatment.

Authors:  Anthime Flaus; Vincent Habouzit; Nicolas de Leiris; Jean-Philippe Vuillez; Marie-Thérèse Leccia; Mathilde Simonson; Jean-Luc Perrot; Florent Cachin; Nathalie Prevot
Journal:  Diagnostics (Basel)       Date:  2022-02-02

Review 7.  Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential.

Authors:  Xingping Zhang; Yanchun Zhang; Guijuan Zhang; Xingting Qiu; Wenjun Tan; Xiaoxia Yin; Liefa Liao
Journal:  Front Oncol       Date:  2022-02-17       Impact factor: 6.244

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.