病变周围区域与病变内部区域的MRI影像组学特征对临床显著性前列腺癌的诊断价值

doi:10.19739/j.cnki.issn1001-9510.2021.01.012

Abstract
Figure/Table
References
Related Citation (5)

Download: PDF (1011 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Objective To compare value of perilesional volume (PLV) and intralesional volume (ILV) radiomics features for diagnosis of clinically significant prostate cancer. Methods One hundred and forty patients who received prostate magnetic resonance imaging (MRI) examination (training set 112, testing set 28) was respectively analyzed. ILV and PLV were segmented on T2 weighted imaging (T2WI), apparent diffusion coefficient (ADC) map, dynamic contrast enhanced magnetic resonance imaging (DCE-MRI), respectively. Radiomic features extracted from ILV and PLV were selected via univariate analysis and least absolute shrinkage and selection operator (LASSO) combined with 10-fold cross validation. ILV and PLV prediction models were built based on LASSO regression. Area under receiver operating characteristic curve (AUC) and DeLong test were used to evaluate and compare the models. Results AUC of ILV model in training and testing set were 0.91, 0.91, respectively. AUC of PLV model in training and testing set were 0.89, 0.87, respectively. Prediction ability of two models were not significantly different. Conclusion The value of PLV radiomics features was lower than ILV radiomics features for diagnosis of csPCa. There was no significant difference between them.

Key words： radiomics clinically significant prostate cancer perilesional volume magnetic resonance imaging

Received: 09 September 2020

PACS:

R816.7

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Han
	MAO Ning
	XIE Haizhu
	LI Tianping
	LUO Xunrong
	LI Xianglin

Cite this article:

ZHANG Han,MAO Ning,XIE Haizhu, et al. Comparison of value of perilesional and intralesional radiomics features for diagnosis of clinically significant prostate cancer[J]. 滨州医学院学报, 2021, 44(1): 57-60.

URL:

http://manu58.magtech.com.cn/Jwk_bzyxy/EN/10.19739/j.cnki.issn1001-9510.2021.01.012 OR http://manu58.magtech.com.cn/Jwk_bzyxy/EN/Y2021/V44/I1/57

[1] BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA: a cancer journal for clinicians, 2018, 68(6): 394-424.
[2] 邱腾,胡小桃.经尿道前列腺电切术联合内分泌治疗晚期前列腺癌的临床疗效及不良反应分析[J].滨州医学院学报,2019,42(6):421-423.
[3] JL M, ES A, AJ A, et al. Prostate Cancer, Version 2.2019, NCCN Clinical Practice Guidelines in Oncology[J]. Journal of the National Comprehensive Cancer Network : JNCCN, 2019, 17(5): 479-505.
[4] ALGOHARY A, VISWANATH S, SHIRADKAR R, et al. Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: Preliminary findings[J]. J Magn Reson Imaging, 2018, 10.1002/jmri.25983.
[5] CHADDAD A, KUCHARCZYK M, NIAZI T. Multimodal Radiomic Features for the Predicting Gleason Score of Prostate Cancer[J]. Cancers (Basel), 2018, 10(8): 249.
[6] MIN X, LI M, DONG D, et al. Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: Cross-validation of a machine learning method[J]. Eur J Radiol, 2019, 115: 16-21.
[7] CUOCOLO R, STANZIONE A, PONSIGLIONE A, et al. Clinically significant prostate cancer detection on MRI: A radiomic shape features study[J]. Eur J Radiol, 2019, 116: 144-149.
[8] BHOWMICK N, NEILSON E, MOSES H. Stromal fibroblasts in cancer initiation and progression[J]. Nature, 2004, 432(7015): 332-337.
[9] TU Z, SCHMÖLLERL J, CUIFFO B, et al. Microenvironmental Regulation of Long Noncoding RNA LINC01133 Promotes Cancer Stem Cell-Like Phenotypic Traits in Triple-Negative Breast Cancers[J]. Stem cells (Dayton, Ohio), 2019, 37(10): 1281-1292.
[10] A F, R B, J K-C, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network[J]. Magnetic resonance imaging, 2012, 30(9): 1323-1341.
[11] ZHANG Y, CHEN W, YUE X, et al. Development of a Novel, Multi-Parametric, MRI-Based Radiomic Nomogram for Differentiating Between Clinically Significant and Insignificant Prostate Cancer[J]. Frontiers in oncology, 2020, 10: 888.
[12] BERNATZ S, ACKERMANN J, MANDEL P, et al. Comparison of machine learning algorithms to predict clinically significant prostate cancer of the peripheral zone with multiparametric MRI using clinical assessment categories and radiomic features[J]. Eur Radiol, 2020,30(12):6757-6769.
[13] LIU B, CHENG J, GUO D, et al. Prediction of prostate cancer aggressiveness with a combination of radiomics and machine learning-based analysis of dynamic contrast-enhanced MRI[J]. Clinical radiology, 2019, 74(11): 896.
[14] NIE K, SHI L, CHEN Q, et al. Rectal Cancer: Assessment of Neoadjuvant Chemoradiation Outcome based on Radiomics of Multiparametric MRI[J]. Clinical cancer research : an official journal of the American Association for Cancer Research, 2016, 22(21): 5256-5264.
[15] FAN M, WU G, CHENG H, et al. Radiomic analysis of DCE-MRI for prediction of response to neoadjuvant chemotherapy in breast cancer patients[J]. Eur J Radiol, 2017, 94: 140-147.