Assessing the Role of Random Forests in Medical Image Segmentation
This provides a GPU-free alternative for medical image segmentation, which is incremental as it validates existing random forest methods against neural networks.
The study compared two random forest approaches with a state-of-the-art deep convolutional neural network for medical image segmentation, finding that while the neural network performed best, one random forest method achieved similar high performance, enabling GPU-free segmentation.
Neural networks represent a field of research that can quickly achieve very good results in the field of medical image segmentation using a GPU. A possible way to achieve good results without GPUs are random forests. For this purpose, two random forest approaches were compared with a state-of-the-art deep convolutional neural network. To make the comparison the PhC-C2DH-U373 and the retinal imaging datasets were used. The evaluation showed that the deep convolutional neutral network achieved the best results. However, one of the random forest approaches also achieved a similar high performance. Our results indicate that random forest approaches are a good alternative to deep convolutional neural networks and, thus, allow the usage of medical image segmentation without a GPU.