2022/07/21 by Edward G. A. Henderson, E HENDERSON, Dónal M. McSweeney +5
Computer Science · Engineering · #Advanced Neural Network Applications #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Dice #FOS: Computer and information sciences #FOS: Electrical engineering #Graph #Image and Video Processing (eess.IV) #Image segmentation #Inference #Machine learning #Pattern recognition (psychology) #Segmentation #Task (project management) #Theoretical computer science #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2207.10446
published in arXiv (Cornell University) (Cornell University) · MCR-RRR submission for the Fast and Low GPU memory Abdominal oRgan sEgmentation Challenge (FLARE) at MICCAI 2021
arxiv created 2022/07/21 · openalex publication_date 2022/07/21 · arxiv updated 2022/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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±1.3, Kidneys: 94.8±3.6, Spleen: 96.4±3.0, Pancreas: 80.9±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.