Share Email Print

Proceedings Paper

Intratumor heterogeneity of DCE-MRI reveals Ki-67 proliferation status in breast cancer
Author(s): Hu Cheng; Ming Fan; Peng Zhang; Bin Liu; Guoliang Shao; Lihua Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Breast cancer is a highly heterogeneous disease both biologically and clinically, and certain pathologic parameters, i.e., Ki67 expression, are useful in predicting the prognosis of patients. The aim of the study is to identify intratumor heterogeneity of breast cancer for predicting Ki-67 proliferation status in estrogen receptor (ER)-positive breast cancer patients. A dataset of 77 patients was collected who underwent dynamic contrast enhancement magnetic resonance imaging (DCE-MRI) examination. Of these patients, 51 were high-Ki-67 expression and 26 were low-Ki-67 expression. We partitioned the breast tumor into subregions using two methods based on the values of time to peak (TTP) and peak enhancement rate (PER). Within each tumor subregion, image features were extracted including statistical and morphological features from DCE-MRI. The classification models were applied on each region separately to assess whether the classifiers based on features extracted from various subregions features could have different performance for prediction. An area under a receiver operating characteristic curve (AUC) was computed using leave-one-out cross-validation (LOOCV) method. The classifier using features related with moderate time to peak achieved best performance with AUC of 0.826 than that based on the other regions. While using multi-classifier fusion method, the AUC value was significantly (P=0.03) increased to 0.858±0.032 compare to classifier with AUC of 0.778 using features from the entire tumor. The results demonstrated that features reflect heterogeneity in intratumoral subregions can improve the classifier performance to predict the Ki-67 proliferation status than the classifier using features from entire tumor alone.

Paper Details

Date Published: 6 March 2018
PDF: 8 pages
Proc. SPIE 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, 1057906 (6 March 2018); doi: 10.1117/12.2293042
Show Author Affiliations
Hu Cheng, Hangzhou Dianzi Univ. (China)
Ming Fan, Hangzhou Dianzi Univ. (China)
Peng Zhang, Hangzhou Dianzi Univ. (China)
Bin Liu, Hangzhou Dianzi Univ. (China)
Guoliang Shao, Zhejiang Cancer Hospital (China)
Lihua Li, Hangzhou Dianzi Univ. (China)

Published in SPIE Proceedings Vol. 10579:
Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications
Jianguo Zhang; Po-Hao Chen, Editor(s)

© SPIE. Terms of Use
Back to Top