PROJECT TITLE :
Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk
Goal: Heterogeneity in cancer can have an effect on response to therapy and patient prognosis. Histologic measures have classically been used to measure heterogeneity, though a reliable noninvasive measurement is required each to determine baseline risk of recurrence and monitor response to treatment. Here, we propose using spatiotemporal wavelet kinetic options from dynamic contrast-enhanced magnetic resonance imaging to quantify intratumor heterogeneity in breast cancer. Ways: Tumor pixels are 1st partitioned into homogeneous subregions using pharmacokinetic measures. Heterogeneity wavelet kinetic (HetWave) features are then extracted from these partitions to obtain spatiotemporal patterns of the wavelet coefficients and therefore the distinction agent uptake. The HetWave options are evaluated in terms of their prognostic value employing a logistic regression classifier with genetic algorithm wrapper-based mostly feature selection to classify breast cancer recurrence risk as determined by a validated gene expression assay. Results: Receiver operating characteristic analysis and area underneath the curve (AUC) are computed to assess classifier performance using leave-one-out cross validation. The HetWave features outperform alternative commonly used options (AUC = 0.88 HetWave versus 0.seventy customary features). The combination of HetWave and customary features any will increase classifier performance (AUCs zero.ninety four). Conclusion: The rate of the spatial frequency pattern over the pharmacokinetic partitions can give valuable prognostic information. Significance: HetWave might be a powerful feature extraction approach for characterizing tumor heterogeneity, providing valuable prognostic data.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here