Dose-volume-based evaluation of convolutional neural network-based auto-segmentation of thoracic organs at risk.

Abstract

The geometrical accuracy of auto-segmentation using convolutional neural networks (CNNs) has been demonstrated. This study aimed to investigate the dose-volume impact of differences between automatic and manual OARs for locally advanced (LA) and peripherally located early-stage (ES) non-small cell lung cancer (NSCLC). A single CNN was created for automatic delineation of the heart, lungs, main left and right bronchus, esophagus, spinal cord and trachea using 55/10/40 patients for training/validation/testing. Dice score coefficient (DSC) and 95th percentile Hausdorff distance (HD95) were used for geometrical analysis. A new treatment plan based on the auto-segmented OARs was created for each test patient using 3D for ES-NSCLC (SBRT, 3-8 fractions) and IMRT for LA-NSCLC (24-35 fractions). The correlation between geometrical metrics and dose-volume differences was investigated. The average (±1 SD) DSC and HD95 were 0.82±0.07 and 16.2±22.4mm, while the average dose-volume differences were 0.5±1.5Gy (ES) and 1.5±2.8Gy (LA). The geometrical metrics did not correlate with the observed dose-volume differences (average Pearson for DSC: -0.27±0.18 (ES) and -0.09±0.12 (LA); HD95: 0.1±0.3mm (ES) and 0.2±0.2mm (LA)). After post-processing, manual adjustments of automatic contours are only needed for clinically relevant OARs situated close to the tumor or within an entry or exit beam e.g., the heart and the esophagus for LA-NSCLC and the bronchi for ES-NSCLC. The lungs do not need to be checked further in detail.