Literature DB >> 33936969

Considerable effects of imaging sequences, feature extraction, feature selection, and classifiers on radiomics-based prediction of microvascular invasion in hepatocellular carcinoma using magnetic resonance imaging.

Houjiao Dai1,2, Minhua Lu3, Bingsheng Huang1,2, Mimi Tang4, Tiantian Pang5, Bing Liao6, Huasong Cai4, Mengqi Huang4, Yongjin Zhou3,7, Xin Chen3, Huijun Ding3, Shi-Ting Feng4.   

Abstract

BACKGROUND: Microvascular invasion (MVI) has a significant effect on the prognosis of hepatocellular carcinoma (HCC), but its preoperative identification is challenging. Radiomics features extracted from medical images, such as magnetic resonance (MR) images, can be used to predict MVI. In this study, we explored the effects of different imaging sequences, feature extraction and selection methods, and classifiers on the performance of HCC MVI predictive models.
METHODS: After screening against the inclusion criteria, 69 patients with HCC and preoperative gadoxetic acid-enhanced MR images were enrolled. In total, 167 features were extracted from the MR images of each sequence for each patient. Experiments were designed to investigate the effects of imaging sequence, number of gray levels (Ng), quantization algorithm, feature selection method, and classifiers on the performance of radiomics biomarkers in the prediction of HCC MVI. We trained and tested these models using leave-one-out cross-validation (LOOCV).
RESULTS: The radiomics model based on the images of the hepatobiliary phase (HBP) had better predictive performance than those based on the arterial phase (AP), portal venous phase (PVP), and pre-enhanced T1-weighted images [area under the receiver operating characteristic (ROC) curve (AUC) =0.792 vs. 0.641/0.634/0.620, P=0.041/0.021/0.010, respectively]. Compared with the equal-probability and Lloyd-Max algorithms, the radiomics features obtained using the Uniform quantization algorithm had a better performance (AUC =0.643/0.666 vs. 0.792, P=0.002/0.003, respectively). Among the values of 8, 16, 32, 64, and 128, the best predictive performance was achieved when the Ng was 64 (AUC =0.792 vs. 0.584/0.697/0.677/0.734, P<0.001/P=0.039/0.001/0.137, respectively). We used a two-stage feature selection method which combined the least absolute shrinkage and selection operator (LASSO) and recursive feature elimination (RFE) gradient boosting decision tree (GBDT), which achieved better stability than and outperformed LASSO, minimum redundancy maximum relevance (mRMR), and support vector machine (SVM)-RFE (stability =0.967 vs. 0.837/0.623/0.390, respectively; AUC =0.850 vs. 0.792/0.713/0.699, P=0.142/0.007/0.003, respectively). The model based on the radiomics features of HBP images using the GBDT classifier showed a better performance for the preoperative prediction of MVI compared with logistic regression (LR), SVM, and random forest (RF) classifiers (AUC =0.895 vs. 0.850/0.834/0.884, P=0.558/0.229/0.058, respectively). With the optimal combination of these factors, we established the best model, which had an AUC of 0.895, accuracy of 87.0%, specificity of 82.5%, and sensitivity of 93.1%.
CONCLUSIONS: Imaging sequences, feature extraction and selection methods, and classifiers can have a considerable effect on the predictive performance of radiomics models for HCC MVI. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Hepatocellular carcinoma (HCC); magnetic resonance imaging (MRI); microvascular invasion (MVI); radiomics

Year:  2021        PMID: 33936969      PMCID: PMC8047362          DOI: 10.21037/qims-20-218

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  54 in total

1.  Can Current Preoperative Imaging Be Used to Detect Microvascular Invasion of Hepatocellular Carcinoma?

Authors:  Matteo Renzulli; Stefano Brocchi; Alessandro Cucchetti; Federico Mazzotti; Cristina Mosconi; Camilla Sportoletti; Giovanni Brandi; Antonio Daniele Pinna; Rita Golfieri
Journal:  Radiology       Date:  2015-12-10       Impact factor: 11.105

2.  Noninvasive radiomics signature based on quantitative analysis of computed tomography images as a surrogate for microvascular invasion in hepatocellular carcinoma: a pilot study.

Authors:  Shaimaa Bakr; Sebastian Echegaray; Rajesh Shah; Aya Kamaya; John Louie; Sandy Napel; Nishita Kothary; Olivier Gevaert
Journal:  J Med Imaging (Bellingham)       Date:  2017-08-21

3.  Reproducibility of tumor uptake heterogeneity characterization through textural feature analysis in 18F-FDG PET.

Authors:  Florent Tixier; Mathieu Hatt; Catherine Cheze Le Rest; Adrien Le Pogam; Laurent Corcos; Dimitris Visvikis
Journal:  J Nucl Med       Date:  2012-03-27       Impact factor: 10.057

4.  Factors associated with early recurrence after resection for hepatocellular carcinoma and outcomes.

Authors:  Shimul A Shah; Paul D Greig; Steven Gallinger; Mark S Cattral; Elijah Dixon; Robin D Kim; Bryce R Taylor; David R Grant; Charles M Vollmer
Journal:  J Am Coll Surg       Date:  2005-12-19       Impact factor: 6.113

5.  Improved results of liver resection for hepatocellular carcinoma on cirrhosis give the procedure added value.

Authors:  G L Grazi; G Ercolani; F Pierangeli; M Del Gaudio; M Cescon; A Cavallari; A Mazziotti
Journal:  Ann Surg       Date:  2001-07       Impact factor: 12.969

6.  Microvascular invasion is a better predictor of tumor recurrence and overall survival following surgical resection for hepatocellular carcinoma compared to the Milan criteria.

Authors:  Kheng-Choon Lim; Pierce Kah-Hoe Chow; John C Allen; Ghim-Song Chia; Miaoshan Lim; Peng-Chung Cheow; Alexander Y F Chung; London L P Ooi; Say-Beng Tan
Journal:  Ann Surg       Date:  2011-07       Impact factor: 12.969

Review 7.  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

8.  Hyperintense HCC on hepatobiliary phase images of gadoxetic acid-enhanced MRI: correlation with clinical and pathological features.

Authors:  Ja Young Kim; Myeong-Jin Kim; Kyung Ah Kim; Hyeon Tae Jeong; Young Nyun Park
Journal:  Eur J Radiol       Date:  2012-09-03       Impact factor: 3.528

9.  Microvascular invasion in patients with hepatocellular carcinoma and its predictable clinicopathological factors.

Authors:  Shuji Sumie; Ryoko Kuromatsu; Koji Okuda; Eiji Ando; Akio Takata; Nobuyoshi Fukushima; Yasutomo Watanabe; Masamichi Kojiro; Michio Sata
Journal:  Ann Surg Oncol       Date:  2008-03-07       Impact factor: 5.344

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
  8 in total

1.  Deep learning radiomics for focal liver lesions diagnosis on long-range contrast-enhanced ultrasound and clinical factors.

Authors:  Li Liu; Chunlin Tang; Lu Li; Ping Chen; Ying Tan; Xiaofei Hu; Kaixuan Chen; Yongning Shang; Deng Liu; He Liu; Hongjun Liu; Fang Nie; Jiawei Tian; Mingchang Zhao; Wen He; Yanli Guo
Journal:  Quant Imaging Med Surg       Date:  2022-06

2.  Developing and validating a deep learning and radiomic model for glioma grading using multiplanar reconstructed magnetic resonance contrast-enhanced T1-weighted imaging: a robust, multi-institutional study.

Authors:  Jialin Ding; Rubin Zhao; Qingtao Qiu; Jinhu Chen; Jinghao Duan; Xiujuan Cao; Yong Yin
Journal:  Quant Imaging Med Surg       Date:  2022-02

3.  Histogram peritumoral enhanced features on MRI arterial phase with extracellular contrast agent can improve prediction of microvascular invasion of hepatocellular carcinoma.

Authors:  Xinxin Wang; Yunfeng Sun; Xueyan Zhou; Zhiwei Shen; Hongxia Zhang; Jiqing Xing; Yang Zhou
Journal:  Quant Imaging Med Surg       Date:  2022-02

Review 4.  Long Noncoding RNA 00472: A Novel Biomarker in Human Diseases.

Authors:  Dan-Yang Ren; Xin-Rong Yuan; Cai-Xia Tu; Jian-Ling Shen; Yun-Wei Li; Ai-Hua Yan; Yi Ru; Hui-Yun Han; Yan-Ming Yang; Yan Liu; Hui-Ying Li
Journal:  Front Pharmacol       Date:  2021-12-20       Impact factor: 5.810

Review 5.  Progress of MRI Radiomics in Hepatocellular Carcinoma.

Authors:  Xue-Qin Gong; Yun-Yun Tao; Yao-Kun Wu; Ning Liu; Xi Yu; Ran Wang; Jing Zheng; Nian Liu; Xiao-Hua Huang; Jing-Dong Li; Gang Yang; Xiao-Qin Wei; Lin Yang; Xiao-Ming Zhang
Journal:  Front Oncol       Date:  2021-09-20       Impact factor: 6.244

Review 6.  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.  Radiomics for the Preoperative Evaluation of Microvascular Invasion in Hepatocellular Carcinoma: A Meta-Analysis.

Authors:  Liujun Li; Chaoqun Wu; Yongquan Huang; Jiaxin Chen; Dalin Ye; Zhongzhen Su
Journal:  Front Oncol       Date:  2022-04-07       Impact factor: 5.738

8.  AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models.

Authors:  A V Krauze; Y Zhuge; R Zhao; E Tasci; K Camphausen
Journal:  J Biotechnol Biomed       Date:  2022-01-10
  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.