The clinical evaluation of atlas-based auto-segmentation for automatic contouring during cervical cancer radiotherapy

Abstract

PurposeOur purpose was to investigate the influence of atlas library size and CT cross-slice number on the accuracy and efficiency of the atlas-based auto-segmentation (ABAS) method for the automatic contouring of clinical treatment volume (CTV) and organs at risk (OARs) during cervical cancer radiotherapy.MethodsOf 140 cervical cancer patients, contours from 20, 40, 60, 80, 100, and 120 patients were selected incrementally to create six atlas library groups in ABAS. Another 20 tested patients were automatically contoured with the ABAS method and manually contoured by the same professional oncologist. Contours included CTV, bladder, rectum, femoral head-L, femoral head-R, and spinal cord. The CT cross-slice numbers of the 20 tested patients included 61, 65, 72, 75, 81, and 84. The index of dice similarity coefficients (DSCs) and Hausdorff distance (HD) were used to assess the consistency between ABAS automatic contouring and manual contouring. The randomized block analysis of variance and paired t-test were used for statistical analysis.ResultsThe mean DSC values of “CTV, bladder, femoral head, and spinal cord” were all larger than 0.8. The femoral head and spinal cord showed a high degree of agreement between ABAS automatic contouring and manual contouring, with a mean DC >0.80 and HD <1 cm in all atlas library groups. A post-hoc least significant difference comparison indicated that no significant difference had been found between different atlas library sizes with DSC and HD values. For ABAS efficiency, the atlas library size had no effect on the time of ABAS automatic contouring. The time of automatic contouring increased slightly with the increase in CT cross-slice numbers, which were 99.9, 106.8, 114.0, 120.6, 127.9, and 134.8 s with CT cross-slices of 61, 65, 72, 75, 81, and 84, respectively.ConclusionA total of 20 atlas library sizes and a minimum CT cross-slice number including CTV and OARs are enough for ensuring the accuracy and efficiency of ABAS automatic contouring during cervical cancer radiotherapy.

Cervical cancer segmentation based on medical images: a literature review

“…Typically, the accuracy is higher when the images in the atlas library are more similar to the image being segmented. Langerak et al ( 16 ), Kim et al ( 17 ) and Li et al ( 18 ) have used the atlas method in their studies for the segmentation of cervical cancer. The effect of atlas library size on the accuracy and efficiency of the automatic atlas-based segmentation (ABAS) method has also been explored by Kim et al ( 17 ) and Li et al ( 18 ).…”

“…Langerak et al ( 16 ), Kim et al ( 17 ) and Li et al ( 18 ) have used the atlas method in their studies for the segmentation of cervical cancer. The effect of atlas library size on the accuracy and efficiency of the automatic atlas-based segmentation (ABAS) method has also been explored by Kim et al ( 17 ) and Li et al ( 18 ). However, they reached opposite conclusions regarding the optimal atlas library size.…”

“…They found that increasing the number of patients in the atlas improved the segmentation accuracy. On the other hand, Li et al ( 18 ) concluded that no significant differences were found in the segmentation accuracy, measured using the dice similarity coefficient (DSC) and hausdorff distance (HD) metrics, between different atlas library sizes. These differing conclusions highlight the importance of carefully selecting the optimal atlas library size for the specific application at hand.…”