2017/12/05 by Rens Janssens, Janssens, Rens, Guodong Zeng +3 · 2 citations
Computer Science · Engineering · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Medical Imaging and Analysis #Spinal Fractures and Fixation Techniques #Spine and Intervertebral Disc Pathology #cs.CV
paper · pdf · doi:10.48550/arxiv.1712.01509
5 pages and 5 figures
arxiv created 2017/12/05 · openalex publication_date 2017/12/05 · arxiv updated 2017/12/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present a method to address the challenging problem of segmentation of lumbar vertebrae from CT images acquired with varying fields of view. Our method is based on cascaded 3D Fully Convolutional Networks (FCNs) consisting of a localization FCN and a segmentation FCN. More specifically, in the first step we train a regression 3D FCN (we call it "LocalizationNet") to find the bounding box of the lumbar region. After that, a 3D U-net like FCN (we call it "SegmentationNet") is then developed, which after training, can perform a pixel-wise multi-class segmentation to map a cropped lumber region volumetric data to its volume-wise labels. Evaluated on publicly available datasets, our method achieved an average Dice coefficient of 95.77 ± 0.81% and an average symmetric surface distance of 0.37 ± 0.06 mm.