1
|
Zhou J, Ye J, Liang Y, Zhao J, Wu Y, Luo S, Lai X, Wang J. scSE-NL V-Net: A Brain Tumor Automatic Segmentation Method Based on Spatial and Channel "Squeeze-and-Excitation" Network With Non-local Block. Front Neurosci 2022; 16:916818. [PMID: 35712454 PMCID: PMC9197379 DOI: 10.3389/fnins.2022.916818] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2022] [Accepted: 04/27/2022] [Indexed: 11/23/2022] Open
Abstract
Intracranial tumors are commonly known as brain tumors, which can be life-threatening in severe cases. Magnetic resonance imaging (MRI) is widely used in diagnosing brain tumors because of its harmless to the human body and high image resolution. Due to the heterogeneity of brain tumor height, MRI imaging is exceptionally irregular. How to accurately and quickly segment brain tumor MRI images is still one of the hottest topics in the medical image analysis community. However, according to the brain tumor segmentation algorithms, we could find now, most segmentation algorithms still stay in two-dimensional (2D) image segmentation, which could not obtain the spatial dependence between features effectively. In this study, we propose a brain tumor automatic segmentation method called scSE-NL V-Net. We try to use three-dimensional (3D) data as the model input and process the data by 3D convolution to get some relevance between dimensions. Meanwhile, we adopt non-local block as the self-attention block, which can reduce inherent image noise interference and make up for the lack of spatial dependence due to convolution. To improve the accuracy of convolutional neural network (CNN) image recognition, we add the "Spatial and Channel Squeeze-and-Excitation" Network (scSE-Net) to V-Net. The dataset used in this paper is from the brain tumor segmentation challenge 2020 database. In the test of the official BraTS2020 verification set, the Dice similarity coefficient is 0.65, 0.82, and 0.76 for the enhanced tumor (ET), whole tumor (WT), and tumor core (TC), respectively. Thereby, our model can make an auxiliary effect on the diagnosis of brain tumors established.
Collapse
Affiliation(s)
- Juhua Zhou
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| | - Jianming Ye
- The First Affiliated Hospital, Gannan Medical University, Ganzhou, China
| | - Yu Liang
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| | - Jialu Zhao
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| | - Yan Wu
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| | - Siyuan Luo
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| | - Xiaobo Lai
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| | - Jianqing Wang
- School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, China
| |
Collapse
|
2
|
Han T, Ai D, An R, Fan J, Song H, Wang Y, Yang J. Ordered multi-path propagation for vessel centerline extraction. Phys Med Biol 2021; 66. [PMID: 34157702 DOI: 10.1088/1361-6560/ac0d8e] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Accepted: 06/22/2021] [Indexed: 11/12/2022]
Abstract
Vessel centerline extraction from x-ray angiography images is essential for vessel structure analysis in the diagnosis of coronary artery disease. However, complete and continuous centerline extraction remains a challenging task due to image noise, poor contrast, and complexity of vessel structure. Thus, an iterative multi-path search framework for automatic vessel centerline extraction is proposed. First, the seed points of the vessel structure are detected and sorted by confidence. With the ordered seed points, multi-bifurcation centerline is searched through multi-path propagation of wavefront and accumulated voting. Finally, the centerline is further extended piecewise by wavefront propagation on the basis of keypoint detection. The latter two steps are performed alternately to obtain the final centerline result. The proposed method is qualitatively and quantitatively evaluated on 1260 synthetic images and 50 clinical angiography images. The results demonstrate that our method has a highF1score of 87.8% ± 2.7% for the angiography images and achieves accurate and continuous results of vessel centerline extraction.
Collapse
Affiliation(s)
- Tao Han
- Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China
| | - Danni Ai
- Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China
| | - Ruirui An
- Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China
| | - Jingfan Fan
- Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China
| | - Hong Song
- School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, People's Republic of China
| | - Yining Wang
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, People's Republic of China
| | - Jian Yang
- Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China
| |
Collapse
|
3
|
Yoon S, Yoon CH, Lee D. Topological recovery for non-rigid 2D/3D registration of coronary artery models. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 200:105922. [PMID: 33440300 DOI: 10.1016/j.cmpb.2020.105922] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/10/2019] [Accepted: 12/23/2020] [Indexed: 06/12/2023]
Abstract
BACKGROUND AND OBJECTIVE Intra-operative X-ray angiography, the current standard method for visualizing and diagnosing cardiovascular disease, is limited in its ability to provide essential 3D information. These limitations are disadvantages in treating patients. For example, it is a cause of lowering the success rate of interventional procedures. Here, we propose a novel 2D-3D non-rigid registration method to understand vascular geometry during percutaneous coronary intervention. METHODS The proposed method uses the local bijection pair distance as a cost function to minimize the effect of inconsistencies from center-line extraction. Moreover, novel cage-based 3D deformation and multi-threaded particle swarm optimization are utilized to implement real-time registration. We evaluated the proposed method for 154 examinations from 10 anonymous patients by coverage percentage, comparing the average distance of the 2D extracted center-line with that of the registered 3D center-line. RESULTS The proposed 2D-3D non-rigid registration method achieved an average distance of 1.98 mm with a 0.54 s computation time. Additionally, in aiming to reduce the uncertainty of XA images, we used the proposed method to retrospectively visualize the connections between 2D vascular segments and the distal part of occlusions. CONCLUSIONS Ultimately, the proposed 2D/3D non-rigid registration method can successfully register the 3D center-line of coronary arteries with corresponding 2D XA images, and is computationally sufficient for online usage. Therefore, this method can improve the success rate of such procedures as a percutaneous coronary intervention and provide the information necessary to diagnose cardiovascular diseases better.
Collapse
Affiliation(s)
- Siyeop Yoon
- 5, Hwarang-ro 14-gil, Seongbuk-gu, Seoul,Center for Healthcare Robotics, Korea Institute of Science and Technology, South Korea; 5, Hwarang-ro 14-gil, Seongbuk-gu, Seoul, KIST School, Korea University of Science and Technology, South Korea.
| | - Chang Hwan Yoon
- Gumi-ro, 82-gil 173, Bundang-gu, Seongnam, Seoul national university Bundang Hospital, South Korea.
| | - Deukhee Lee
- 5, Hwarang-ro 14-gil, Seongbuk-gu, Seoul,Center for Healthcare Robotics, Korea Institute of Science and Technology, South Korea; 5, Hwarang-ro 14-gil, Seongbuk-gu, Seoul, KIST School, Korea University of Science and Technology, South Korea.
| |
Collapse
|
4
|
Xia S, Zhu H, Liu X, Gong M, Huang X, Xu L, Zhang H, Guo J. Vessel Segmentation of X-Ray Coronary Angiographic Image Sequence. IEEE Trans Biomed Eng 2019; 67:1338-1348. [PMID: 31494537 DOI: 10.1109/tbme.2019.2936460] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
OBJECTIVE To facilitate the analysis and diagnosis of X-ray coronary angiography in interventional surgery, it is necessary to extract vessel from X-ray coronary angiography. However, vessel images of angiography suffer from low quality with large artefacts, which challenges the existing vascular technology. METHODS In this paper, we propose a ávessel framework to detect vessels and segment vessels in angiographic vessel data. In this framework, we develop a new matrix decomposition model with gradient sparse in the tensor representation. Then, the energy function with the input of the hierarchical vessel is used in vessel detection and vessel segmentation. RESULTS Through experiments conducted on angiographic data, we have demonstrated the good performance of the proposed method in removing background structure. CONCLUSION We evaluated our method for vessel detection and segmentation in different clinical settings, including LAO/RAO with cranial and caudal angulation, and showed its competitive results compared with eight state-of-the-art methods in terms of extensive qualitative and quantitative evaluation. SIGNIFICANCE Our method can remove a large number of background artefacts and obtain a better vascular structure, which has contributed to the clinical diagnosis of coronary artery diseases.
Collapse
|
5
|
Qin B, Jin M, Hao D, Lv Y, Liu Q, Zhu Y, Ding S, Zhao J, Fei B. Accurate vessel extraction via tensor completion of background layer in X-ray coronary angiograms. PATTERN RECOGNITION 2019; 87:38-54. [PMID: 31447490 PMCID: PMC6708416 DOI: 10.1016/j.patcog.2018.09.015] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
This paper proposes an effective method for accurately recovering vessel structures and intensity information from the X-ray coronary angiography (XCA) images of moving organs or tissues. Specifically, a global logarithm transformation of XCA images is implemented to fit the X-ray attenuation sum model of vessel/background layers into a low-rank, sparse decomposition model for vessel/background separation. The contrast-filled vessel structures are extracted by distinguishing the vessels from the low-rank backgrounds by using a robust principal component analysis and by constructing a vessel mask via Radon-like feature filtering plus spatially adaptive thresholding. Subsequently, the low-rankness and inter-frame spatio-temporal connectivity in the complex and noisy backgrounds are used to recover the vessel-masked background regions using tensor completion of all other background regions, while the twist tensor nuclear norm is minimized to complete the background layers. Finally, the method is able to accurately extract vessels' intensities from the noisy XCA data by subtracting the completed background layers from the overall XCA images. We evaluated the vessel visibility of resulting images on real X-ray angiography data and evaluated the accuracy of vessel intensity recovery on synthetic data. Experiment results show the superiority of the proposed method over the state-of-the-art methods.
Collapse
Affiliation(s)
- Binjie Qin
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Mingxin Jin
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Dongdong Hao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Yisong Lv
- School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Qiegen Liu
- Department of Electronic Information Engineering, Nanchang University, Nanchang 330031, China
| | - Yueqi Zhu
- Department of Radiology, Shanghai Jiao Tong University Affiliated Sixth People’s Hospital, Shanghai Jiao Tong University, 600 Yi Shan Road, Shanghai 200233, China
| | - Song Ding
- Department of Cardiology, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, China
| | - Jun Zhao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Baowei Fei
- Department of Bioengineering, Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX 75080, USA
| |
Collapse
|
6
|
Abstract
An automatic coronary artery tree labeling algorithm is described to identify the anatomical segments of the extracted centerlines from coronary computed tomography angiography (CCTA) images. This method will facilitate the automatic lesion reporting and risk stratification of cardiovascular disease. Three-dimensional (3D) models for both right dominant (RD) and left dominant (LD) coronary circulations were built. All labels in the model were matched with their possible candidates in the extracted tree to find the optimal labeling result. In total, 83 CCTA datasets with 1149 segments were included in the testing of the algorithm. The results of the automatic labeling were compared with those by two experts. In all cases, the proximal parts of main branches including LM were labeled correctly. The automatic labeling algorithm was able to identify and assign labels to 89.2% RD and 83.6% LD coronary tree segments in comparison with the agreements of the two experts (97.6% RD, 87.6% LD). The average precision of start and end points of segments was 92.0% for RD and 90.7% for LD in comparison with the manual identification by two experts while average differences in experts is 1.0% in RD and 2.2% in LD cases. All cases got similar clinical risk scores as the two experts. The presented fully automatic labeling algorithm can identify and assign labels to the extracted coronary centerlines for both RD and LD circulations.
Collapse
|
7
|
Wu CH, Tsai WH, Chen YH, Liu JK, Sun YN. Model-Based Orthodontic Assessments for Dental Panoramic Radiographs. IEEE J Biomed Health Inform 2017; 22:545-551. [PMID: 28141539 DOI: 10.1109/jbhi.2017.2660527] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
For better treatment outcomes, dentists usually use a set of parameters for orthodontic evaluation. In this study, a new method is proposed to assist dentists in obtaining reliable assessment of these parameters. The proposed method is based on dental panoramic radiographs and can be divided into four stages: image preprocessing, model training, tooth segmentation, and assessment of orthodontic parameters. The image is first normalized and enhanced. Then, the model training stage consists of shape and image model training, energy function training, and weight training. Next, we automatically segment the tooth contours in an energy-minimized manner. Finally, the automatic assessment of orthodontic parameters is carried out. The experimental results show that the average of absolute distance, the Dice similarity coefficient, and the average qualitative score ranged between 4.17 and 6.03, 0.87 and 0.90, as well as 2.58 and 3.12, respectively. The orthodontic assessment also is close to the evaluation of orthodontists. It has been shown that the proposed method can obtain accurate and consistent measurement in helping dentists to obtain an objective treatment evaluation.
Collapse
|