1
|
Lin W, Gao Z, Liu H, Zhang H. A Deformable Constraint Transport Network for Optimal Aortic Segmentation From CT Images. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:1462-1475. [PMID: 38048241 DOI: 10.1109/tmi.2023.3339142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/06/2023]
Abstract
Aortic segmentation from computed tomography (CT) is crucial for facilitating aortic intervention, as it enables clinicians to visualize aortic anatomy for diagnosis and measurement. However, aortic segmentation faces the challenge of variable geometry in space, as the geometric diversity of different diseases and the geometric transformations that occur between raw and measured images. Existing constraint-based methods can potentially solve the challenge, but they are hindered by two key issues: inaccurate definition of properties and inappropriate topology of transformation in space. In this paper, we propose a deformable constraint transport network (DCTN). The DCTN adaptively extracts aortic features to define intra-image constrained properties and guides topological implementation in space to constrain inter-image geometric transformation between raw and curved planar reformation (CPR) images. The DCTN contains a deformable attention extractor, a geometry-aware decoder and an optimal transport guider. The extractor generates variable patches that preserve semantic integrity and long-range dependency in long-sequence images. The decoder enhances the perception of geometric texture and semantic features, particularly for low-intensity aortic coarctation and false lumen, which removes background interference. The guider explores the geometric discrepancies between raw and CPR images, constructs probability distributions of discrepancies, and matches them with inter-image transformation to guide geometric topology in space. Experimental studies on 267 aortic subjects and four public datasets show the superiority of our DCTN over 23 methods. The results demonstrate DCTN's advantages in aortic segmentation for different types of aortic disease, for different aortic segments, and in the measurement of clinical indexes.
Collapse
|
2
|
Wiputra H, Matsumoto S, Wagenseil JE, Braverman AC, Voeller RK, Barocas VH. Statistical shape representation of the thoracic aorta: accounting for major branches of the aortic arch. Comput Methods Biomech Biomed Engin 2023; 26:1557-1571. [PMID: 36165506 PMCID: PMC10040462 DOI: 10.1080/10255842.2022.2128672] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2022] [Revised: 08/24/2022] [Accepted: 09/11/2022] [Indexed: 11/03/2022]
Abstract
Statistical shape modeling (SSM) is an emerging tool for risk assessment of thoracic aortic aneurysm. However, the head branches of the aortic arch are often excluded in SSM. We introduced an SSM strategy based on principal component analysis that accounts for aortic branches and applied it to a set of patient scans. Computational fluid dynamics were performed on the reconstructed geometries to identify the extent to which branch model accuracy affects the calculated wall shear stress (WSS) and pressure. Surface-averaged and location-specific values of pressure did not change significantly, but local WSS error was high near branches when inaccurately modeled.
Collapse
Affiliation(s)
- Hadi Wiputra
- Department of Biomedical Engineering, University of Minnesota
| | - Shion Matsumoto
- Department of Biomedical Engineering, University of Michigan
| | | | - Alan C. Braverman
- Department of Medicine, Cardiovascular Division, Washington University School of Medicine
| | | | | |
Collapse
|
3
|
Benčević M, Qiu Y, Galić I, Pižurica A. Segment-then-Segment: Context-Preserving Crop-Based Segmentation for Large Biomedical Images. SENSORS (BASEL, SWITZERLAND) 2023; 23:633. [PMID: 36679429 PMCID: PMC9866819 DOI: 10.3390/s23020633] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Revised: 12/23/2022] [Accepted: 01/04/2023] [Indexed: 06/17/2023]
Abstract
Medical images are often of huge size, which presents a challenge in terms of memory requirements when training machine learning models. Commonly, the images are downsampled to overcome this challenge, but this leads to a loss of information. We present a general approach for training semantic segmentation neural networks on much smaller input sizes called Segment-then-Segment. To reduce the input size, we use image crops instead of downscaling. One neural network performs the initial segmentation on a downscaled image. This segmentation is then used to take the most salient crops of the full-resolution image with the surrounding context. Each crop is segmented using a second specially trained neural network. The segmentation masks of each crop are joined to form the final output image. We evaluate our approach on multiple medical image modalities (microscopy, colonoscopy, and CT) and show that this approach greatly improves segmentation performance with small network input sizes when compared to baseline models trained on downscaled images, especially in terms of pixel-wise recall.
Collapse
Affiliation(s)
- Marin Benčević
- Faculty of Electrical Engineering, Computer Science and Information Technology, J. J. Strossmayer University, 31000 Osijek, Croatia
- TELIN-GAIM, Faculty of Engineering and Architecture, Ghent University, 9000 Ghent, Belgium
| | - Yuming Qiu
- TELIN-GAIM, Faculty of Engineering and Architecture, Ghent University, 9000 Ghent, Belgium
- Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, China
| | - Irena Galić
- Faculty of Electrical Engineering, Computer Science and Information Technology, J. J. Strossmayer University, 31000 Osijek, Croatia
| | - Aleksandra Pižurica
- TELIN-GAIM, Faculty of Engineering and Architecture, Ghent University, 9000 Ghent, Belgium
| |
Collapse
|
4
|
Geronzi L, Haigron P, Martinez A, Yan K, Rochette M, Bel-Brunon A, Porterie J, Lin S, Marin-Castrillon DM, Lalande A, Bouchot O, Daniel M, Escrig P, Tomasi J, Valentini PP, Biancolini ME. Assessment of shape-based features ability to predict the ascending aortic aneurysm growth. Front Physiol 2023; 14:1125931. [PMID: 36950300 PMCID: PMC10025384 DOI: 10.3389/fphys.2023.1125931] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Accepted: 02/24/2023] [Indexed: 03/08/2023] Open
Abstract
The current guidelines for the ascending aortic aneurysm (AsAA) treatment recommend surgery mainly according to the maximum diameter assessment. This criterion has already proven to be often inefficient in identifying patients at high risk of aneurysm growth and rupture. In this study, we propose a method to compute a set of local shape features that, in addition to the maximum diameter D, are intended to improve the classification performances for the ascending aortic aneurysm growth risk assessment. Apart from D, these are the ratio DCR between D and the length of the ascending aorta centerline, the ratio EILR between the length of the external and the internal lines and the tortuosity T. 50 patients with two 3D acquisitions at least 6 months apart were segmented and the growth rate (GR) with the shape features related to the first exam computed. The correlation between them has been investigated. After, the dataset was divided into two classes according to the growth rate value. We used six different classifiers with input data exclusively from the first exam to predict the class to which each patient belonged. A first classification was performed using only D and a second with all the shape features together. The performances have been evaluated by computing accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC) and positive (negative) likelihood ratio LHR+ (LHR-). A positive correlation was observed between growth rate and DCR (r = 0.511, p = 1.3e-4) and between GR and EILR (r = 0.472, p = 2.7e-4). Overall, the classifiers based on the four metrics outperformed the same ones based only on D. Among the diameter-based classifiers, k-nearest neighbours (KNN) reported the best accuracy (86%), sensitivity (55.6%), AUROC (0.74), LHR+ (7.62) and LHR- (0.48). Concerning the classifiers based on the four shape features, we obtained the best accuracy (94%), sensitivity (66.7%), specificity (100%), AUROC (0.94), LHR+ (+∞) and LHR- (0.33) with support vector machine (SVM). This demonstrates how automatic shape features detection combined with risk classification criteria could be crucial in planning the follow-up of patients with ascending aortic aneurysm and in predicting the possible dangerous progression of the disease.
Collapse
Affiliation(s)
- Leonardo Geronzi
- Department of Enterprise Engineering “Mario Lucertini”, University of Rome Tor Vergata, Rome, Italy
- Ansys France, Villeurbanne, France
- *Correspondence: Leonardo Geronzi,
| | - Pascal Haigron
- LTSI–UMR 1099, CHU Rennes, Inserm, University of Rennes, Rennes, France
| | - Antonio Martinez
- Department of Enterprise Engineering “Mario Lucertini”, University of Rome Tor Vergata, Rome, Italy
- Ansys France, Villeurbanne, France
| | - Kexin Yan
- Ansys France, Villeurbanne, France
- LaMCoS, Laboratoire de Mécanique des Contacts et des Structures, CNRS UMR5259, INSA Lyon, University of Lyon, Villeurbanne, France
| | | | - Aline Bel-Brunon
- LaMCoS, Laboratoire de Mécanique des Contacts et des Structures, CNRS UMR5259, INSA Lyon, University of Lyon, Villeurbanne, France
| | - Jean Porterie
- Cardiac Surgery Department, Rangueil University Hospital, Toulouse, France
| | - Siyu Lin
- IMVIA Laboratory, University of Burgundy, Dijon, France
- Medical Imaging Department, University Hospital of Dijon, Dijon, France
| | - Diana Marcela Marin-Castrillon
- IMVIA Laboratory, University of Burgundy, Dijon, France
- Medical Imaging Department, University Hospital of Dijon, Dijon, France
| | - Alain Lalande
- IMVIA Laboratory, University of Burgundy, Dijon, France
- Medical Imaging Department, University Hospital of Dijon, Dijon, France
| | - Olivier Bouchot
- Department of Cardio-Vascular and Thoracic Surgery, University Hospital of Dijon, Dijon, France
| | - Morgan Daniel
- LTSI–UMR 1099, CHU Rennes, Inserm, University of Rennes, Rennes, France
| | - Pierre Escrig
- LTSI–UMR 1099, CHU Rennes, Inserm, University of Rennes, Rennes, France
| | - Jacques Tomasi
- LTSI–UMR 1099, CHU Rennes, Inserm, University of Rennes, Rennes, France
| | - Pier Paolo Valentini
- Department of Enterprise Engineering “Mario Lucertini”, University of Rome Tor Vergata, Rome, Italy
| | | |
Collapse
|