TY - JOUR
T1 - Radiomic features based on Hessian index for prediction of prognosis in head-and-neck cancer patients
AU - Le, Quoc Cuong
AU - Arimura, Hidetaka
AU - Ninomiya, Kenta
AU - Kabata, Yutaro
N1 - Funding Information:
This study was supported by Center for Clinical and Translational Research of Kyushu University Hospital and JSPS KAKENHI Grant Number 20K08084. The authors are grateful to all members in Arimura laboratory (http:// web.shs.kyushu-u.ac.jp/~arimura), whose comments made enormous contribution to this study. We also would like to express our gratitude to the TCIA database for hosting a large archive of medical images of cancer for the research community.
Publisher Copyright:
© 2020, The Author(s).
PY - 2020/12
Y1 - 2020/12
N2 - This study demonstrated the usefulness of radiomic features based on the Hessian index of differential topology for the prediction of prognosis prior to treatment in head-and-neck (HN) cancer patients. The Hessian index, which can indicate tumor heterogeneity with convex, concave, and other points (saddle points), was calculated as the number of negative eigenvalues of the Hessian matrix at each voxel on computed tomography (CT) images. Three types of signatures were constructed in a training cohort (n = 126), one type each from CT conventional features, Hessian index features, and combined features from the conventional and index feature sets. The prognostic value of the signatures were evaluated using statistically significant difference (p value, log-rank test) to compare the survival curves of low- and high-risk groups. In a test cohort (n = 68), the p values of the models built with conventional, index, combined features, and clinical variables were 2.95 × 10–2, 1.85 × 10–2, 3.17 × 10–2, and 1.87 × 10–3, respectively. When the features were integrated with clinical variables, the p values of conventional, index, and combined features were 3.53 × 10–3, 1.28 × 10–3, and 1.45 × 10–3, respectively. This result indicates that index features could provide more prognostic information than conventional features and further increase the prognostic value of clinical variables in HN cancer patients.
AB - This study demonstrated the usefulness of radiomic features based on the Hessian index of differential topology for the prediction of prognosis prior to treatment in head-and-neck (HN) cancer patients. The Hessian index, which can indicate tumor heterogeneity with convex, concave, and other points (saddle points), was calculated as the number of negative eigenvalues of the Hessian matrix at each voxel on computed tomography (CT) images. Three types of signatures were constructed in a training cohort (n = 126), one type each from CT conventional features, Hessian index features, and combined features from the conventional and index feature sets. The prognostic value of the signatures were evaluated using statistically significant difference (p value, log-rank test) to compare the survival curves of low- and high-risk groups. In a test cohort (n = 68), the p values of the models built with conventional, index, combined features, and clinical variables were 2.95 × 10–2, 1.85 × 10–2, 3.17 × 10–2, and 1.87 × 10–3, respectively. When the features were integrated with clinical variables, the p values of conventional, index, and combined features were 3.53 × 10–3, 1.28 × 10–3, and 1.45 × 10–3, respectively. This result indicates that index features could provide more prognostic information than conventional features and further increase the prognostic value of clinical variables in HN cancer patients.
UR - http://www.scopus.com/inward/record.url?scp=85097087114&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097087114&partnerID=8YFLogxK
U2 - 10.1038/s41598-020-78338-7
DO - 10.1038/s41598-020-78338-7
M3 - Article
C2 - 33277570
AN - SCOPUS:85097087114
VL - 10
JO - Scientific Reports
JF - Scientific Reports
SN - 2045-2322
IS - 1
M1 - 21301
ER -
