Premium
Prediction of chemotherapeutic response in bladder cancer using K‐means clustering of dynamic contrast‐enhanced (DCE)‐MRI pharmacokinetic parameters
Author(s) -
Nguyen Huyen T.,
Jia Guang,
Shah Zarine K.,
Pohar Kamal,
Mortazavi Amir,
Zynger Debra L.,
Wei Lai,
Yang Xiangyu,
Clark Daniel,
Knopp Michael V.
Publication year - 2015
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.24663
Subject(s) - bladder cancer , receiver operating characteristic , medicine , cluster analysis , area under the curve , cluster (spacecraft) , dynamic contrast enhanced mri , pharmacokinetics , biomarker , cutoff , chemotherapeutic drugs , cancer , bladder tumor , magnetic resonance imaging , nuclear medicine , dynamic contrast , oncology , radiology , computer science , chemistry , artificial intelligence , physics , biochemistry , quantum mechanics , programming language
Purpose To apply k‐means clustering of two pharmacokinetic parameters derived from 3T dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) to predict the chemotherapeutic response in bladder cancer at the mid‐cycle timepoint. Materials and Methods With the predetermined number of three clusters, k‐means clustering was performed on nondimensionalized Amp and k ep estimates of each bladder tumor. Three cluster volume fractions (VFs) were calculated for each tumor at baseline and mid‐cycle. The changes of three cluster VFs from baseline to mid‐cycle were correlated with the tumor's chemotherapeutic response. Receiver‐operating‐characteristics curve analysis was used to evaluate the performance of each cluster VF change as a biomarker of chemotherapeutic response in bladder cancer. Results The k‐means clustering partitioned each bladder tumor into cluster 1 (low k ep and low Amp ), cluster 2 (low k ep and high Amp ), cluster 3 (high k ep and low Amp ). The changes of all three cluster VFs were found to be associated with bladder tumor response to chemotherapy. The VF change of cluster 2 presented with the highest area‐under‐the‐curve value (0.96) and the highest sensitivity/specificity/accuracy (96%/100%/97%) with a selected cutoff value. Conclusion The k‐means clustering of the two DCE‐MRI pharmacokinetic parameters can characterize the complex microcirculatory changes within a bladder tumor to enable early prediction of the tumor's chemotherapeutic response. J. Magn. Reson. Imaging 2015;41:1374–1382. © 2014 Wiley Periodicals, Inc.