1
|
Wang B, Yang J, Zhou Y, Yang Y, Tian X, Zhang G, Zhang X. LEACS: a learnable and efficient active contour model with space-frequency pooling for medical image segmentation. Phys Med Biol 2024; 69:015026. [PMID: 38048633 DOI: 10.1088/1361-6560/ad1212] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2023] [Accepted: 12/04/2023] [Indexed: 12/06/2023]
Abstract
Diseases can be diagnosed and monitored by extracting regions of interest (ROIs) from medical images. However, accurate and efficient delineation and segmentation of ROIs in medical images remain challenging due to unrefined boundaries, inhomogeneous intensity and limited image acquisition. To overcome these problems, we propose an end-to-end learnable and efficient active contour segmentation model, which integrates a global convex segmentation (GCS) module into a light-weighted encoder-decoder convolutional segmentation network with a multiscale attention module (ED-MSA). The GCS automatically obtains the initialization and corresponding parameters of the curve deformation according to the prediction map generated by the ED-MSA, while provides the refined object boundary prediction for ED-MSA optimization. To provide precise and reliable initial contour for the GCS, we design the space-frequency pooling operation layers in the encoder stage of ED-MSA, which can effectively reduce the number of iterations of the GCS. Beside, we construct ED-MSA using the depth-wise separable convolutional residual module to mitigate the overfitting of the model. The effectiveness of our method is validated on four challenging medical image datasets. Code is here:https://github.com/Yang-fashion/ED-MSA_GCS.
Collapse
Affiliation(s)
- Bing Wang
- College of Mathematics and Information Science, Hebei University, Baoding, 071000, Hebei, People's Republic of China
- Hebei Key Laboratory of machine Learning and Computational Intelligence, Hebei University, Baoding, 071000, Hebei, People's Republic of China
| | - Jie Yang
- College of Mathematics and Information Science, Hebei University, Baoding, 071000, Hebei, People's Republic of China
| | - Yunlai Zhou
- College of Mathematics and Information Science, Hebei University, Baoding, 071000, Hebei, People's Republic of China
| | - Ying Yang
- Hebei University Affiliated Hospital, Baoding, 071000, Hebei, People's Republic of China
| | - Xuedong Tian
- College of Cyber Security and Computer, Hebei University, Baoding, 071000, Hebei, People's Republic of China
| | - Guochun Zhang
- Hebei Key Laboratory of machine Learning and Computational Intelligence, Hebei University, Baoding, 071000, Hebei, People's Republic of China
| | - Xin Zhang
- College of Electronic Information Engineering, Hebei University, Baoding, 071000, Hebei, People's Republic of China
| |
Collapse
|
2
|
Adaptive segmentation model for liver CT images based on neural network and level set method. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2021.01.081] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
3
|
Shoreline Extraction in SAR Image Based on Advanced Geometric Active Contour Model. REMOTE SENSING 2021. [DOI: 10.3390/rs13040642] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Rapid and accurate extraction of shoreline is of great significance for the use and management of sea area. Remote sensing has a strong ability to obtain data and has obvious advantages in shoreline survey. Compared with visible-light remote sensing, synthetic aperture radar (SAR) has the characteristics of all-weather and all-day working. It has been well-applied in shoreline extraction. However, due to the influence of natural conditions there is a problem of weak boundary in extracting shoreline from SAR images. In addition, the complex micro topography near the shoreline makes it difficult for traditional visual interpretation and image edge detection methods based on edge information to obtain a continuous and complete shoreline in SAR images. In order to solve these problems, this paper proposes a method to detect the land–sea boundary based on a geometric active contour model. In this method, a new symbolic pressure function is used to improve the geometric active-contour model, and the global regional smooth information is used as the convergence condition of curve evolution. Then, the influence of different initial contours on the number and time of iterations is studied. The experimental results show that this method has the advantages of fewer iteration times, good stability and high accuracy.
Collapse
|
4
|
Yang Y, Xie R, Jia W, Chen Z, Yang Y, Xie L, Jiang B. Accurate and automatic tooth image segmentation model with deep convolutional neural networks and level set method. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2020.07.110] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
5
|
Jayaraman T, Reddy M S, Mahadevappa M, Sadhu A, Dutta PK. Modified distance regularized level set evolution for brain ventricles segmentation. Vis Comput Ind Biomed Art 2020; 3:29. [PMID: 33283254 PMCID: PMC7719594 DOI: 10.1186/s42492-020-00064-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2020] [Accepted: 11/13/2020] [Indexed: 12/02/2022] Open
Abstract
Neurodegenerative disorders are commonly characterized by atrophy of the brain which is caused by neuronal loss. Ventricles are one of the prominent structures in the brain; their shape changes, due to their content, the cerebrospinal fluid. Analyzing the morphological changes of ventricles, aids in the diagnosis of atrophy, for which the region of interest needs to be separated from the background. This study presents a modified distance regularized level set evolution segmentation method, incorporating regional intensity information. The proposed method is implemented for segmenting ventricles from brain images for normal and atrophy subjects of magnetic resonance imaging and computed tomography images. Results of the proposed method were compared with ground truth images and produced sensitivity in the range of 65%–90%, specificity in the range of 98%–99%, and accuracy in the range of 95%–98%. Peak signal to noise ratio and structural similarity index were also used as performance measures for determining segmentation accuracy: 95% and 0.95, respectively. The parameters of level set formulation vary for different datasets. An optimization procedure was followed to fine tune parameters. The proposed method was found to be efficient and robust against noisy images. The proposed method is adaptive and multimodal.
Collapse
Affiliation(s)
- Thirumagal Jayaraman
- School of Medical Science and Technology, IIT Kharagpur, Kharagpur, 721302, India
| | - Sravan Reddy M
- Department of Electronics and Communications, JNTUA-College of Engineering, Pulivendula, 516390, India
| | | | - Anup Sadhu
- EKO CT & MRI Scan Centre, Medical College, Calcutta, 700073, India
| | - Pranab Kumar Dutta
- Department of Electrical Engineering, IIT Kharagpur, Kharagpur, 721302, India
| |
Collapse
|
6
|
Robust active contours driven by order-statistic filtering energy for fast image segmentation. Knowl Based Syst 2020. [DOI: 10.1016/j.knosys.2020.105882] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
7
|
Yang Y, Tian D, Jia W, Shu X, Wu B. Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images. Magn Reson Imaging 2019; 57:50-67. [DOI: 10.1016/j.mri.2018.10.005] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2018] [Revised: 09/28/2018] [Accepted: 10/06/2018] [Indexed: 10/28/2022]
|
8
|
Fedele M, Faggiano E, Dedè L, Quarteroni A. A patient-specific aortic valve model based on moving resistive immersed implicit surfaces. Biomech Model Mechanobiol 2017; 16:1779-1803. [PMID: 28593469 DOI: 10.1007/s10237-017-0919-1] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2016] [Accepted: 05/12/2017] [Indexed: 11/26/2022]
Abstract
In this paper, we propose a full computational framework to simulate the hemodynamics in the aorta including the valve. Closed and open valve surfaces, as well as the lumen aorta, are reconstructed directly from medical images using new ad hoc algorithms, allowing a patient-specific simulation. The fluid dynamics problem that accounts from the movement of the valve is solved by a new 3D-0D fluid-structure interaction model in which the valve surface is implicitly represented through level set functions, yielding, in the Navier-Stokes equations, a resistive penalization term enforcing the blood to adhere to the valve leaflets. The dynamics of the valve between its closed and open position is modeled using a reduced geometric 0D model. At the discrete level, a finite element formulation is used and the SUPG stabilization is extended to include the resistive term in the Navier-Stokes equations. Then, after time discretization, the 3D fluid and 0D valve models are coupled through a staggered approach. This computational framework, applied to a patient-specific geometry and data, allows to simulate the movement of the valve, the sharp pressure jump occurring across the leaflets, and the blood flow pattern inside the aorta.
Collapse
Affiliation(s)
- Marco Fedele
- CMCS - MATHICSE - SB, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
- CompMech Group, Department of Civil Engineering and Architecture, University of Pavia, Pavia, Italy
| | - Elena Faggiano
- CMCS - MATHICSE - SB, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
- CompMech Group, Department of Civil Engineering and Architecture, University of Pavia, Pavia, Italy.
| | - Luca Dedè
- CMCS - MATHICSE - SB, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
- MOX, Dipartimento di Matematica, Politecnico di Milano, Milan, Italy
| | - Alfio Quarteroni
- CMCS - MATHICSE - SB, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
- MOX, Dipartimento di Matematica, Politecnico di Milano, Milan, Italy
| |
Collapse
|
9
|
Modified localized multiplicative graph cuts based active contour model for object segmentation based on dynamic narrow band scheme. Biomed Signal Process Control 2017. [DOI: 10.1016/j.bspc.2016.11.019] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
10
|
Zeng Z, Wang J, Tiddeman B, Zwiggelaar R. Unsupervised tumour segmentation in PET using local and global intensity-fitting active surface and alpha matting. Comput Biol Med 2013; 43:1530-44. [PMID: 24034745 DOI: 10.1016/j.compbiomed.2013.07.027] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2013] [Revised: 07/20/2013] [Accepted: 07/24/2013] [Indexed: 11/26/2022]
Abstract
This paper proposes an unsupervised tumour segmentation approach for PET data. The method computes the volumes of interest (VOIs) with sub-voxel precision by considering the limited image resolution and partial volume effects. First, an improved anisotropic diffusion filter is used to remove image noise. A hierarchical local and global intensity active surface modelling scheme is then applied to segment VOIs, followed by an alpha matting step to further refine the segmentation boundary. The proposed method is validated on real PET images of head-and-neck cancer patients with ground truth provided by human experts, as well as custom-designed phantom PET images with objective ground truth. Experimental results show that our method outperforms previous automatic approaches in terms of segmentation accuracy.
Collapse
Affiliation(s)
- Ziming Zeng
- Department of Computer Science, Aberystwyth University, Aberystwyth, UK; Faculty of Information and Control Engineering, Shenyang Jianzhu University, Shenyang, China.
| | | | | | | |
Collapse
|
11
|
Shepherd T, Teras M, Beichel RR, Boellaard R, Bruynooghe M, Dicken V, Gooding MJ, Julyan PJ, Lee JA, Lefèvre S, Mix M, Naranjo V, Wu X, Zaidi H, Zeng Z, Minn H. Comparative study with new accuracy metrics for target volume contouring in PET image guided radiation therapy. IEEE TRANSACTIONS ON MEDICAL IMAGING 2012; 31:2006-24. [PMID: 22692898 PMCID: PMC5570440 DOI: 10.1109/tmi.2012.2202322] [Citation(s) in RCA: 54] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
The impact of PET on radiation therapy is held back by poor methods of defining functional volumes of interest. Many new software tools are being proposed for contouring target volumes but the different approaches are not adequately compared and their accuracy is poorly evaluated due to the illdefinition of ground truth. This paper compares the largest cohort to date of established, emerging and proposed PET contouring methods, in terms of accuracy and variability. We emphasise spatial accuracy and present a new metric that addresses the lack of unique ground truth. 30 methods are used at 13 different institutions to contour functional VOIs in clinical PET/CT and a custom-built PET phantom representing typical problems in image guided radiotherapy. Contouring methods are grouped according to algorithmic type, level of interactivity and how they exploit structural information in hybrid images. Experiments reveal benefits of high levels of user interaction, as well as simultaneous visualisation of CT images and PET gradients to guide interactive procedures. Method-wise evaluation identifies the danger of over-automation and the value of prior knowledge built into an algorithm.
Collapse
|
12
|
Zeng Z, Shepherd T, Zwiggelaar R. Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2012; 2012:2339-2342. [PMID: 23366393 DOI: 10.1109/embc.2012.6346432] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/01/2023]
Abstract
This paper proposes an unsupervised tumour segmentation scheme for PET data. The method computes the volume of interests (VOIs) with subpixel precision by considering the limited resolution and partial volume effect. Firstly, it uses local and global intensity active surface modelling to segment VOIs, then an alpha matting method is used to eliminate false negative classification and refine the segmentation results. We have validated our method on real PET images of head-and-neck cancer patients as well as images of a custom designed PET phantom. Experiments show that our method can generate more accurate segmentation results compared with alternative approaches.
Collapse
Affiliation(s)
- Ziming Zeng
- Faculty of Information and Control Engineering, Shenyang Jianzhu University, Shenyang, China.
| | | | | |
Collapse
|