2020/03/31 by Tianyu Ma, Ajay Gupta, Mert R. Sabuncu
Computer Science · Engineering · Medicine · #Artificial intelligence #Artificial neural network #Cartography #Computer science #Computer vision #Deep learning #Deep neural networks #Geography #Landmark #Medical Image Segmentation Techniques #Medical Imaging and Analysis #Pattern recognition (psychology) #Resampling #Retinal Imaging and Analysis #Robustness (evolution) #Scale (ratio) #cs.CV #cs.LG #eess.IV
paper · pdf · doi:10.1109/isbi45749.2020.9098620
5 pages, 5 figures
openalex publication_date 2020/04/01 · arxiv created 2020/10/16 · arxiv updated 2021/12/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Deep neural networks yield promising results in a wide range of computer vision applications, including landmark detection. A major challenge for accurate anatomical landmark detection in volumetric images such as clinical CT scans is that large-scale data often constrain the capacity of the employed neural network architecture due to GPU memory limitations, which in turn can limit the precision of the output. We propose a multi-scale, end-to-end deep learning method that achieves fast and memory-efficient landmark detection in 3D images. Our architecture consists of blocks of shift-equivariant networks, each of which performs landmark detection at a different spatial scale. These blocks are connected from coarse to fine-scale, with differentiable resampling layers, so that all levels can be trained together. We also present a noise injection strategy that increases the robustness of the model and allows us to quantify uncertainty at test time. We evaluate our method for carotid artery bifurcations detection on 263 CT volumes and achieve a better than state-of-the-art accuracy with mean Euclidean distance error of 2.81mm.