COBRA: Cpu-Only aBdominal oRgan segmentAtion
This work addresses the need for efficient, hardware-accessible segmentation tools in clinical settings, enabling widespread deployment without GPUs.
The paper tackles the problem of abdominal organ segmentation by developing a CPU-only method that achieves high accuracy with Dice scores of 97.3% for liver, 94.8% for kidneys, 96.4% for spleen, and 80.9% for pancreas, and processes images in 1.6 seconds.
Abdominal organ segmentation is a difficult and time-consuming task. To reduce the burden on clinical experts, fully-automated methods are highly desirable. Current approaches are dominated by Convolutional Neural Networks (CNNs) however the computational requirements and the need for large data sets limit their application in practice. By implementing a small and efficient custom 3D CNN, compiling the trained model and optimizing the computational graph: our approach produces high accuracy segmentations (Dice Similarity Coefficient (%): Liver: 97.3$\pm$1.3, Kidneys: 94.8$\pm$3.6, Spleen: 96.4$\pm$3.0, Pancreas: 80.9$\pm$10.1) at a rate of 1.6 seconds per image. Crucially, we are able to perform segmentation inference solely on CPU (no GPU required), thereby facilitating easy and widespread deployment of the model without specialist hardware.