Hyun-Jin Bae1, Heejung Hyun2, Younghwa Byeon2, Keewon Shin2, Yongwon Cho2, Young Ji Song2, Seong Yi3, Sung-Uk Kuh4, Jin S Yeom5, Namkug Kim6. 1. Department of Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Republic of Korea; Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Republic of Korea. 2. Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Republic of Korea. 3. Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul 03722, Republic of Korea. 4. Department of Neurosurgery, Spine and Spinal Cord Institute, Gangnam Severance Spine Hospital, Yonsei University College of Medicine, Seoul 06273, Republic of Korea. 5. Spine Center and Department of Orthopaedic Surgery, Seoul National University College of Medicine and Seoul National University Bundang Hospital, Sungnam 13620, Republic of Korea. 6. Department of Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Republic of Korea; Department of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Republic of Korea. Electronic address: namkugkim@gmail.com.
Abstract
BACKGROUND AND OBJECTIVE: We investigated a novel method using a 2D convolutional neural network (CNN) to identify superior and inferior vertebrae in a single slice of CT images, and a post-processing for 3D segmentation and separation of cervical vertebrae. METHODS: The cervical spines of patients (N == 17, 1684 slices) from Severance and Gangnam Severance Hospitals (S/GSH) and healthy controls (N == 24, 3490 slices) from Seoul National University Bundang Hospital (SNUBH) were scanned by using various volumetric CT protocols. To prepare gold standard masks of cervical spine in CT images, each spine was segmented by using conventional image-processing methods and manually corrected by an expert. The gold standard masks were preprocessed and labeled into superior and inferior cervical vertebrae separately in the axial slices. The 2D U-Net model was trained by using the disease dataset (S/GSH) and additional validation was performed by using the healthy control dataset (SNUBH), and then the training and validation were repeated by switching the two datasets. RESULTS: In case of the model was trained with the disease dataset (S/GSH) and validated with the healthy control (SNUBH), the mean and standard deviation (SD) of the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were 94.37%% ± 1.45%, 89.47%% ± 2.55%, 0.33 ± 0.12 mm and 20.89 ± 3.98 mm, and 88.67%% ± 5.82%, 80.83%% ± 8.09%, 1.05 ± 0.63 mm and 29.17 ± 19.74 mm, respectively. In case of the model was trained with the healthy control (SNUBH) and validated with the disease dataset (S/GSH), the mean and SD of DSC, JSC, MSD, and HSD were 96.23%% ± 1.55%, 92.95%% ± 2.58%, 0.39 ± 0.20 mm and 16.23 ± 6.72 mm, and 93.15%% ± 3.09%, 87.54%% ± 5.11%, 0.38 ± 0.17 mm and 20.85 ± 7.11 mm, respectively. CONCLUSIONS: The results demonstrated that our fully automated method achieved comparable accuracies with inter- and intra-observer variabilities of manual segmentation by human experts, which is time consuming.
BACKGROUND AND OBJECTIVE: We investigated a novel method using a 2D convolutional neural network (CNN) to identify superior and inferior vertebrae in a single slice of CT images, and a post-processing for 3D segmentation and separation of cervical vertebrae. METHODS: The cervical spines of patients (N == 17, 1684 slices) from Severance and Gangnam Severance Hospitals (S/GSH) and healthy controls (N == 24, 3490 slices) from Seoul National University Bundang Hospital (SNUBH) were scanned by using various volumetric CT protocols. To prepare gold standard masks of cervical spine in CT images, each spine was segmented by using conventional image-processing methods and manually corrected by an expert. The gold standard masks were preprocessed and labeled into superior and inferior cervical vertebrae separately in the axial slices. The 2D U-Net model was trained by using the disease dataset (S/GSH) and additional validation was performed by using the healthy control dataset (SNUBH), and then the training and validation were repeated by switching the two datasets. RESULTS: In case of the model was trained with the disease dataset (S/GSH) and validated with the healthy control (SNUBH), the mean and standard deviation (SD) of the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were 94.37%% ± 1.45%, 89.47%% ± 2.55%, 0.33 ± 0.12 mm and 20.89 ± 3.98 mm, and 88.67%% ± 5.82%, 80.83%% ± 8.09%, 1.05 ± 0.63 mm and 29.17 ± 19.74 mm, respectively. In case of the model was trained with the healthy control (SNUBH) and validated with the disease dataset (S/GSH), the mean and SD of DSC, JSC, MSD, and HSD were 96.23%% ± 1.55%, 92.95%% ± 2.58%, 0.39 ± 0.20 mm and 16.23 ± 6.72 mm, and 93.15%% ± 3.09%, 87.54%% ± 5.11%, 0.38 ± 0.17 mm and 20.85 ± 7.11 mm, respectively. CONCLUSIONS: The results demonstrated that our fully automated method achieved comparable accuracies with inter- and intra-observer variabilities of manual segmentation by human experts, which is time consuming.
Authors: Fabio A Casari; Nassir Navab; Laura A Hruby; Philipp Kriechling; Ricardo Nakamura; Romero Tori; Fátima de Lourdes Dos Santos Nunes; Marcelo C Queiroz; Philipp Fürnstahl; Mazda Farshad Journal: Curr Rev Musculoskelet Med Date: 2021-02-05