All 3D models outperformed the 2D segmentation model. For CT segmentation, combining classification and registration in the proposed joint model proved beneficial, achieving a Dice score of 0.87 and a mean squared error (MSE) of the surface distance below 1.7 mm. No such synergy was observed for CBCT segmentation, for which the joint and the deformation-only model performed similarly, achieving a Dice score of about 0.80 and an MSE surface distance of 2.5 mm. However, the segmentation-only model performed notably worse in this low contrast regime. Visual inspection revealed that this performance drop translated into geometric inconsistencies between the prior and target segmentation. Such inconsistencies were not observed for the deformation-based models.
Automatic cervix-uterus segmentation of the clinical target volume (CTV) on CT and cone-beam CT (CBCT) scans is challenged by the limited visibility and the non-anatomical definition of certain border regions. We study the potential performance gain of convolutional neural networks by regulating the segmentation predictions as diffeomorphic deformations of a segmentation prior.
We introduce a 3D convolutional neural network that segments the target scan by joint voxel-wise classification and the registration of a given prior. We compare this network to two other 3D baseline models: One treating segmentation as a classification problem (segmentation-only), the other as a registration problem (deformation-only). For reference and to highlight the benefits of a 3D model, these models are also benchmarked against a 2D segmentation model. Network performances are reported for CT and CBCT segmentation of the cervix-uterus CTV. We train the networks on the data of 84 patients. The prior is provided by the CTV segmentation of a planning CT. Repeat CT or CBCT scans constitute the target scans to be segmented.
Constraining the solution space of admissible segmentation predictions to those reachable by a diffeomorphic deformation of the prior proved beneficial as it improved geometric consistency. Especially for CBCT, with its poor soft-tissue contrast, this type of regularization becomes important as shown by quantitative and qualitative evaluation.