Convolutions, Transformers, and their Ensembles for the Segmentation of Organs at Risk in Radiation Treatment of Cervical Cancer
This work addresses the choice of neural network architecture for medical image segmentation in cervical cancer treatment, but it is incremental as it focuses on comparing and combining existing methods.
The study compared and combined various deep neural network architectures, including state-of-the-art and hybrid models, for segmenting organs at risk in cervical cancer MRI scans, finding that ensembles of top-performing models from different categories yielded the best results, with most models achieving over 0.8 Dice Coefficient.
Segmentation of regions of interest in images of patients, is a crucial step in many medical procedures. Deep neural networks have proven to be particularly adept at this task. However, a key question is what type of deep neural network to choose, and whether making a certain choice makes a difference. In this work, we will answer this question for the task of segmentation of the Organs At Risk (OARs) in radiation treatment of cervical cancer (i.e., bladder, bowel, rectum, sigmoid) in Magnetic Resonance Imaging (MRI) scans. We compare several state-of-the-art models belonging to different architecture categories, as well as a few new models that combine aspects of several state-of-the-art models, to see if the results one gets are markedly different. We visualize model predictions, create all possible ensembles of models by averaging their output probabilities, and calculate the Dice Coefficient between predictions of models, in order to understand the differences between them and the potential of possible combinations. The results show that small improvements in metrics can be achieved by advancing and merging architectures, but the predictions of the models are quite similar (most models achieve on average more than 0.8 Dice Coefficient when compared to the outputs of other models). However, the results from the ensemble experiments indicate that the best results are obtained when the best performing models from every category of the architectures are combined.