Interactive Radiotherapy Target Delineation with 3D-Fused Context Propagation
This work provides a more efficient interactive refinement tool for radiation oncologists to correct CNN-based tumor delineations, addressing a critical bottleneck in clinical radiotherapy planning. It is an incremental improvement to existing CNN workflows.
This paper addresses the need for efficient expert refinement of CNN-based tumor volume delineations in radiotherapy. It proposes 3D-fused context propagation, a method that allows radiation oncologists to correct CNN predictions by editing only a few slices, which then propagates the changes to the entire 3D volume without retraining the model. The method was evaluated on nasopharyngeal and esophageal cancer datasets, showing effective improvement of existing segmentation predictions.
Gross tumor volume (GTV) delineation on tomography medical imaging is crucial for radiotherapy planning and cancer diagnosis. Convolutional neural networks (CNNs) has been predominated on automatic 3D medical segmentation tasks, including contouring the radiotherapy target given 3D CT volume. While CNNs may provide feasible outcome, in clinical scenario, double-check and prediction refinement by experts is still necessary because of CNNs' inconsistent performance on unexpected patient cases. To provide experts an efficient way to modify the CNN predictions without retrain the model, we propose 3D-fused context propagation, which propagates any edited slice to the whole 3D volume. By considering the high-level feature maps, the radiation oncologists would only required to edit few slices to guide the correction and refine the whole prediction volume. Specifically, we leverage the backpropagation for activation technique to convey the user editing information backwardly to the latent space and generate new prediction based on the updated and original feature. During the interaction, our proposed approach reuses the extant extracted features and does not alter the existing 3D CNN model architectures, avoiding the perturbation on other predictions. The proposed method is evaluated on two published radiotherapy target contouring datasets of nasopharyngeal and esophageal cancer. The experimental results demonstrate that our proposed method is able to further effectively improve the existing segmentation prediction from different model architectures given oncologists' interactive inputs.