Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer

Abstract Purpose The Ki67 expression is associated with the advanced clinicopathological features and poor prognosis in bladder cancer (BCa). We aimed to develop and validate magnetic resonance imaging (MRI)-based radiomics signatures to preoperatively predict the Ki67 expression status in BCa. Meth...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zongtai Zheng, Zhuoran Gu, Feijia Xu, Niraj Maskey, Yanyan He, Yang Yan, Tianyuan Xu, Shenghua Liu, Xudong Yao
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Bladder cancer Magnetic resonance imaging Ki67 Radiomics Medical physics. Medical radiology. Nuclear medicine R895-920 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/cd62f2b4b1834d489f240ce31af442ff
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cd62f2b4b1834d489f240ce31af442ff
record_format	dspace
spelling	oai:doaj.org-article:cd62f2b4b1834d489f240ce31af442ff2021-12-05T12:26:06ZMagnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer10.1186/s40644-021-00433-31470-7330https://doaj.org/article/cd62f2b4b1834d489f240ce31af442ff2021-12-01T00:00:00Zhttps://doi.org/10.1186/s40644-021-00433-3https://doaj.org/toc/1470-7330Abstract Purpose The Ki67 expression is associated with the advanced clinicopathological features and poor prognosis in bladder cancer (BCa). We aimed to develop and validate magnetic resonance imaging (MRI)-based radiomics signatures to preoperatively predict the Ki67 expression status in BCa. Methods and materials We retrospectively collected 179 BCa patients with Ki67 expression and preoperative MRI. Radiomics features were extracted from T2-weighted (T2WI) and dynamic contrast-enhancement (DCE) images. The synthetic minority over-sampling technique (SMOTE) was used to balance the minority group (low Ki67 expression group) in the training set. Minimum redundancy maximum relevance was used to identify the best features associated with Ki67 expression. Support vector machine and Least Absolute Shrinkage and Selection Operator algorithms (LASSO) were used to construct radiomics signatures in training and SMOTE-training sets, and diagnostic performance was assessed by the area under the curve (AUC) and accuracy. The decision curve analyses (DCA) and calibration curve and were used to investigate the clinical usefulness and calibration of radiomics signatures, respectively. The Kaplan-Meier test was performed to investigate the prognostic value of radiomics-predicted Ki67 expression status. Results 1218 radiomics features were extracted from T2WI and DCE images, respectively. The SMOTE-LASSO model based on nine features achieved the best predictive performance in the SMOTE-training (AUC, 0.859; accuracy, 80.3%) and validation sets (AUC, 0.819; accuracy, 81.5%) with a good calibration performance and clinical usefulness. Immunohistochemistry-based high Ki67 expression and radiomics-predicted high Ki67 expression based on the SMOTE-LASSO model were significantly associated with poor disease-free survival in training and validation sets (all P < 0.05). Conclusions The SMOTE-LASSO model could predict the Ki67 expression status and was associated with survival outcomes of the BCa patients, thereby may aid in clinical decision-making.Zongtai ZhengZhuoran GuFeijia XuNiraj MaskeyYanyan HeYang YanTianyuan XuShenghua LiuXudong YaoBMCarticleBladder cancerMagnetic resonance imagingKi67RadiomicsMedical physics. Medical radiology. Nuclear medicineR895-920Neoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENCancer Imaging, Vol 21, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Bladder cancer Magnetic resonance imaging Ki67 Radiomics Medical physics. Medical radiology. Nuclear medicine R895-920 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	Bladder cancer Magnetic resonance imaging Ki67 Radiomics Medical physics. Medical radiology. Nuclear medicine R895-920 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Zongtai Zheng Zhuoran Gu Feijia Xu Niraj Maskey Yanyan He Yang Yan Tianyuan Xu Shenghua Liu Xudong Yao Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer
description	Abstract Purpose The Ki67 expression is associated with the advanced clinicopathological features and poor prognosis in bladder cancer (BCa). We aimed to develop and validate magnetic resonance imaging (MRI)-based radiomics signatures to preoperatively predict the Ki67 expression status in BCa. Methods and materials We retrospectively collected 179 BCa patients with Ki67 expression and preoperative MRI. Radiomics features were extracted from T2-weighted (T2WI) and dynamic contrast-enhancement (DCE) images. The synthetic minority over-sampling technique (SMOTE) was used to balance the minority group (low Ki67 expression group) in the training set. Minimum redundancy maximum relevance was used to identify the best features associated with Ki67 expression. Support vector machine and Least Absolute Shrinkage and Selection Operator algorithms (LASSO) were used to construct radiomics signatures in training and SMOTE-training sets, and diagnostic performance was assessed by the area under the curve (AUC) and accuracy. The decision curve analyses (DCA) and calibration curve and were used to investigate the clinical usefulness and calibration of radiomics signatures, respectively. The Kaplan-Meier test was performed to investigate the prognostic value of radiomics-predicted Ki67 expression status. Results 1218 radiomics features were extracted from T2WI and DCE images, respectively. The SMOTE-LASSO model based on nine features achieved the best predictive performance in the SMOTE-training (AUC, 0.859; accuracy, 80.3%) and validation sets (AUC, 0.819; accuracy, 81.5%) with a good calibration performance and clinical usefulness. Immunohistochemistry-based high Ki67 expression and radiomics-predicted high Ki67 expression based on the SMOTE-LASSO model were significantly associated with poor disease-free survival in training and validation sets (all P < 0.05). Conclusions The SMOTE-LASSO model could predict the Ki67 expression status and was associated with survival outcomes of the BCa patients, thereby may aid in clinical decision-making.
format	article
author	Zongtai Zheng Zhuoran Gu Feijia Xu Niraj Maskey Yanyan He Yang Yan Tianyuan Xu Shenghua Liu Xudong Yao
author_facet	Zongtai Zheng Zhuoran Gu Feijia Xu Niraj Maskey Yanyan He Yang Yan Tianyuan Xu Shenghua Liu Xudong Yao
author_sort	Zongtai Zheng
title	Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer
title_short	Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer
title_full	Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer
title_fullStr	Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer
title_full_unstemmed	Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer
title_sort	magnetic resonance imaging-based radiomics signature for preoperative prediction of ki67 expression in bladder cancer
publisher	BMC
publishDate	2021
url	https://doaj.org/article/cd62f2b4b1834d489f240ce31af442ff
work_keys_str_mv	AT zongtaizheng magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT zhuorangu magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT feijiaxu magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT nirajmaskey magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT yanyanhe magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT yangyan magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT tianyuanxu magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT shenghualiu magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer AT xudongyao magneticresonanceimagingbasedradiomicssignatureforpreoperativepredictionofki67expressioninbladdercancer
_version_	1718371926668214272

Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer

Ejemplares similares