Study on the stability of lung cancer radiotherapy dosiomic features under respiratory motion

To assess the stability of dosiomic features in response to dose distribution variations caused by respiratory motion.

A total of 24 lung cancer patients who underwent 4DCT scanning and radiotherapy were included. For each patient, a 3D dose matrix and three 4D dose matrices generated using three distinct methods were calculated. Dosiomic features were extracted from dose distributions for four regions of interest: the gross tumor volume (GTV), the planning target volume (PTV), the heart, and the lung. The stability of each dosiomic feature was evaluated using the coefficient of variation (CV), while reproducibility was assessed using the intraclass correlation coefficient (ICC). The differences between 3D and 4D dose features were determined using the normalized difference (ND).

5.0% of dosiomic features had a CV greater than or equal to 20%. The CVs were highest in the GTV region and lowest in the lung region. Additionally, 0.27% of features had an ICC less than 0.5, while 92.74% had an ICC greater than 0.9. 16.48% of features had an absolute value of the ND greater than 0.4.

The stability of certain dosiomic features is strongly influenced by respiratory motion in radiotherapy. To ensure result reproducibility, dosiomic studies should fully consider the impact of respiratory motion during dose calculation or excluding unstable features to enhance model stability.