TY - JOUR
T1 - Gaussian mixture model-based cluster analysis of apparent diffusion coefficient values
T2 - a novel approach to evaluate uterine endometrioid carcinoma grade
AU - Kageyama, Sakiko
AU - Mori, Naoko
AU - Mugikura, Shunji
AU - Tokunaga, Hideki
AU - Takase, Kei
N1 - Funding Information:
The authors thank Kenichi Higuchi, Naoko Hirose, Kanako Shibui, Kyuhei Takahashi, and You Oguma in Tohoku University for their kind support.
Funding Information:
This study has received funding by JSPS KAKENHI (18K07742 and 18K07662). Acknowledgments
Publisher Copyright:
© 2020, European Society of Radiology.
PY - 2021/1
Y1 - 2021/1
N2 - Objectives: The purpose of our study was to perform Gaussian mixture model (GMM)-based cluster analysis of the apparent diffusion coefficient (ADC) data of patients with endometrioid carcinoma, and to evaluate the relationship between histological grade and the ratios of the different clusters in each patient. Methods: This retrospective study enrolled 122 patients (training: n = 63; and validation: n = 59) imaged between May 2015 and February 2020. In the training cohort, manual segmentation was performed on the ADC maps to obtain the ADC data of each patient, and these ADC data were summated to obtain the “All-patient” ADC data. Cluster analysis (three clusters) was performed on this All-patient ADC data, and the ADC ranges of each cluster were defined as follows: cluster 1, 490–699 × 10−6 mm2/s; cluster 2, 700–932 × 10−6 mm2/s; and cluster 3, over 933 × 10−6 mm2/s. In the training and validation cohorts, the ADC data of each patient was classified into three clusters according to these ADC ranges. The cluster ratios of each patient were calculated and compared with histological grade. Results: In the training cohort, a significant positive correlation was found between the cluster 1 ratio and histological grade (ρ = 0.34, p = 0.0059). The cluster 1 ratios of high-grade lesions (grade 3) were significantly higher than those of low-grade lesions (grades 1 and 2) (p = 0.0084). A similar significant positive correlation was found between the cluster 1 ratio and histological grade in the validation cohort (ρ = 0.44, p = 0.0006). Conclusions: The cluster 1 ratio containing voxels with low ADC was significantly correlated with the histological grade of endometrioid carcinoma. Key Points: • We performed Gaussian mixture model (GMM)-based cluster analysis of the apparent diffusion coefficient (ADC) data of patients with endometrioid carcinoma. • The cluster 1 ratio, which included low ADC values, was significantly positive correlated with histological grade in the training and validation cohorts. • The GMM-based cluster analysis of voxel-based ADC data was effective for grading endometrioid carcinoma.
AB - Objectives: The purpose of our study was to perform Gaussian mixture model (GMM)-based cluster analysis of the apparent diffusion coefficient (ADC) data of patients with endometrioid carcinoma, and to evaluate the relationship between histological grade and the ratios of the different clusters in each patient. Methods: This retrospective study enrolled 122 patients (training: n = 63; and validation: n = 59) imaged between May 2015 and February 2020. In the training cohort, manual segmentation was performed on the ADC maps to obtain the ADC data of each patient, and these ADC data were summated to obtain the “All-patient” ADC data. Cluster analysis (three clusters) was performed on this All-patient ADC data, and the ADC ranges of each cluster were defined as follows: cluster 1, 490–699 × 10−6 mm2/s; cluster 2, 700–932 × 10−6 mm2/s; and cluster 3, over 933 × 10−6 mm2/s. In the training and validation cohorts, the ADC data of each patient was classified into three clusters according to these ADC ranges. The cluster ratios of each patient were calculated and compared with histological grade. Results: In the training cohort, a significant positive correlation was found between the cluster 1 ratio and histological grade (ρ = 0.34, p = 0.0059). The cluster 1 ratios of high-grade lesions (grade 3) were significantly higher than those of low-grade lesions (grades 1 and 2) (p = 0.0084). A similar significant positive correlation was found between the cluster 1 ratio and histological grade in the validation cohort (ρ = 0.44, p = 0.0006). Conclusions: The cluster 1 ratio containing voxels with low ADC was significantly correlated with the histological grade of endometrioid carcinoma. Key Points: • We performed Gaussian mixture model (GMM)-based cluster analysis of the apparent diffusion coefficient (ADC) data of patients with endometrioid carcinoma. • The cluster 1 ratio, which included low ADC values, was significantly positive correlated with histological grade in the training and validation cohorts. • The GMM-based cluster analysis of voxel-based ADC data was effective for grading endometrioid carcinoma.
KW - Cluster analysis
KW - Endometrioid carcinoma
KW - Magnetic resonance imaging
KW - Uterus
UR - http://www.scopus.com/inward/record.url?scp=85088694498&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85088694498&partnerID=8YFLogxK
U2 - 10.1007/s00330-020-07047-6
DO - 10.1007/s00330-020-07047-6
M3 - Article
C2 - 32725334
AN - SCOPUS:85088694498
SN - 0938-7994
VL - 31
SP - 55
EP - 64
JO - European Radiology
JF - European Radiology
IS - 1
ER -