Reference region extraction by clustering for the pharmacokinetic analysis of dynamic contrast-enhanced MRI in prostate cancer
| Autor: | Tatsuya Higashi, Yoko Ikoma, Goro Kasuya, Takayuki Obata, Hiroshi Tsuji, Tokuhiko Omatsu, Hirokazu Makishima, Riwa Kishimoto, Yasuhiko Tachibana |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Male
Computer science Feature vector Biomedical Engineering Biophysics Contrast Media computer.software_genre 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Voxel medicine Cluster Analysis Humans Radiology Nuclear Medicine and imaging Cluster analysis Aged medicine.diagnostic_test business.industry Prostate Prostatic Neoplasms Reproducibility of Results Magnetic resonance imaging Pattern recognition Middle Aged Image Enhancement Mixture model Magnetic Resonance Imaging Feature (computer vision) Dynamic contrast-enhanced MRI Artificial intelligence Reference Region business computer Algorithms 030217 neurology & neurosurgery |
| Zdroj: | Magnetic Resonance Imaging. 66:185-192 |
| ISSN: | 0730-725X |
| DOI: | 10.1016/j.mri.2019.08.034 |
| Popis: | Purpose Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) measures changes in the concentration of an administered contrast agent to quantitatively evaluate blood circulation in a tumor or normal tissues. This method uses a pharmacokinetic analysis based on the time course of a reference region, such as muscle, rather than arterial input function. However, it is difficult to manually define a homogeneous reference region. In the present study, we developed a method for automatic extraction of the reference region using a clustering algorithm based on a time course pattern for DCE-MRI studies of patients with prostate cancer. Methods Two feature values related to the shape of the time course were extracted from the time course of all voxels in the DCE-MRI images. Each voxel value of T1-weighted images acquired before administration were also added as anatomical data. Using this three-dimensional feature vector, all voxels were segmented into five clusters by the Gaussian mixture model, and one of these clusters that included the gluteus muscle was selected as the reference region. Results Each region of arterial vessel, muscle, and fat was segmented as a different cluster from the tumor and normal tissues in the prostate. In the extracted reference region, other tissue elements including scattered fat and blood vessels were removed from the muscle region. Conclusions Our proposed method can automatically extract the reference region using the clustering algorithm with three types of features based on the time course pattern and anatomical data. This method may be useful for evaluating tumor circulatory function in DCE-MRI studies. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect