1
|
Kreitner L, Paetzold JC, Rauch N, Chen C, Hagag AM, Fayed AE, Sivaprasad S, Rausch S, Weichsel J, Menze BH, Harders M, Knier B, Rueckert D, Menten MJ. Synthetic Optical Coherence Tomography Angiographs for Detailed Retinal Vessel Segmentation Without Human Annotations. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:2061-2073. [PMID: 38224512 DOI: 10.1109/tmi.2024.3354408] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/17/2024]
Abstract
Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality that can acquire high-resolution volumes of the retinal vasculature and aid the diagnosis of ocular, neurological and cardiac diseases. Segmenting the visible blood vessels is a common first step when extracting quantitative biomarkers from these images. Classical segmentation algorithms based on thresholding are strongly affected by image artifacts and limited signal-to-noise ratio. The use of modern, deep learning-based segmentation methods has been inhibited by a lack of large datasets with detailed annotations of the blood vessels. To address this issue, recent work has employed transfer learning, where a segmentation network is trained on synthetic OCTA images and is then applied to real data. However, the previously proposed simulations fail to faithfully model the retinal vasculature and do not provide effective domain adaptation. Because of this, current methods are unable to fully segment the retinal vasculature, in particular the smallest capillaries. In this work, we present a lightweight simulation of the retinal vascular network based on space colonization for faster and more realistic OCTA synthesis. We then introduce three contrast adaptation pipelines to decrease the domain gap between real and artificial images. We demonstrate the superior segmentation performance of our approach in extensive quantitative and qualitative experiments on three public datasets that compare our method to traditional computer vision algorithms and supervised training using human annotations. Finally, we make our entire pipeline publicly available, including the source code, pretrained models, and a large dataset of synthetic OCTA images.
Collapse
|
2
|
He H, Paetzold JC, Borner N, Riedel E, Gerl S, Schneider S, Fisher C, Ezhov I, Shit S, Li H, Ruckert D, Aguirre J, Biedermann T, Darsow U, Menze B, Ntziachristos V. Machine Learning Analysis of Human Skin by Optoacoustic Mesoscopy for Automated Extraction of Psoriasis and Aging Biomarkers. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:2074-2085. [PMID: 38241120 DOI: 10.1109/tmi.2024.3356180] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/21/2024]
Abstract
Ultra-wideband raster-scan optoacoustic mesoscopy (RSOM) is a novel modality that has demonstrated unprecedented ability to visualize epidermal and dermal structures in-vivo. However, an automatic and quantitative analysis of three-dimensional RSOM datasets remains unexplored. In this work we present our framework: Deep Learning RSOM Analysis Pipeline (DeepRAP), to analyze and quantify morphological skin features recorded by RSOM and extract imaging biomarkers for disease characterization. DeepRAP uses a multi-network segmentation strategy based on convolutional neural networks with transfer learning. This strategy enabled the automatic recognition of skin layers and subsequent segmentation of dermal microvasculature with an accuracy equivalent to human assessment. DeepRAP was validated against manual segmentation on 25 psoriasis patients under treatment and our biomarker extraction was shown to characterize disease severity and progression well with a strong correlation to physician evaluation and histology. In a unique validation experiment, we applied DeepRAP in a time series sequence of occlusion-induced hyperemia from 10 healthy volunteers. We observe how the biomarkers decrease and recover during the occlusion and release process, demonstrating accurate performance and reproducibility of DeepRAP. Furthermore, we analyzed a cohort of 75 volunteers and defined a relationship between aging and microvascular features in-vivo. More precisely, this study revealed that fine microvascular features in the dermal layer have the strongest correlation to age. The ability of our newly developed framework to enable the rapid study of human skin morphology and microvasculature in-vivo promises to replace biopsy studies, increasing the translational potential of RSOM.
Collapse
|
3
|
Linninger AA, Ventimiglia T, Jamshidi M, Pascal Suisse M, Alaraj A, Lesage F, Li X, Schwartz DL, Rooney WD. Vascular synthesis based on hemodynamic efficiency principle recapitulates measured cerebral circulation properties in the human brain. J Cereb Blood Flow Metab 2024; 44:801-816. [PMID: 37988131 PMCID: PMC11197140 DOI: 10.1177/0271678x231214840] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 09/20/2023] [Accepted: 10/21/2023] [Indexed: 11/22/2023]
Abstract
Quantifying anatomical and hemodynamical properties of the brain vasculature in vivo is difficult due to limited spatiotemporal resolution neuroimaging, variability between subjects, and bias between acquisition techniques. This work introduces a metabolically inspired vascular synthesis algorithm for creating a digital representation of the cortical blood supply in humans. Spatial organization and segment resistances of a cortical vascular network were generated. Cortical folding and macroscale arterial and venous vessels were reconstructed from anatomical MRI and MR angiography. The remaining network, including ensembles representing the parenchymal capillary bed, were synthesized following a mechanistic principle based on hydrodynamic efficiency of the cortical blood supply. We evaluated the digital model by comparing its simulated values with in vivo healthy human brain measurements of macrovessel blood velocity from phase contrast MRI and capillary bed transit times and bolus arrival times from dynamic susceptibility contrast. We find that measured and simulated values reasonably agree and that relevant neuroimaging observables can be recapitulated in silico. This work provides a basis for describing and testing quantitative aspects of the cerebrovascular circulation that are not directly observable. Future applications of such digital brains include the investigation of the organ-wide effects of simulated vascular and metabolic pathologies.
Collapse
Affiliation(s)
- Andreas A Linninger
- Department of Biomedical Engineering, University of Illinois at Chicago, Chicago, IL, USA
- Department of Neurosurgery, University of Illinois at Chicago, Chicago, IL, USA
| | - Thomas Ventimiglia
- Department of Biomedical Engineering, University of Illinois at Chicago, Chicago, IL, USA
| | - Mohammad Jamshidi
- Department of Biomedical Engineering, University of Illinois at Chicago, Chicago, IL, USA
| | - Mathieu Pascal Suisse
- Department of Biomedical Engineering, University of Illinois at Chicago, Chicago, IL, USA
| | - Ali Alaraj
- Department of Neurosurgery, University of Illinois at Chicago, Chicago, IL, USA
| | - Frédéric Lesage
- Department of Electrical Engineering, Polytechnique Montréal, Montréal, QC, Canada
| | - Xin Li
- Advanced Imaging Research Center, Oregon Health & Science University, Portland, OR, USA
| | - Daniel L Schwartz
- Advanced Imaging Research Center, Oregon Health & Science University, Portland, OR, USA
- Department of Neurology, Oregon Health & Science University, Portland, OR, USA
| | - William D Rooney
- Advanced Imaging Research Center, Oregon Health & Science University, Portland, OR, USA
- Department of Neurology, Oregon Health & Science University, Portland, OR, USA
| |
Collapse
|
4
|
Waszkiewicz R, Shaw JB, Lisicki M, Szymczak P. Goldilocks Fluctuations: Dynamic Constraints on Loop Formation in Scale-Free Transport Networks. PHYSICAL REVIEW LETTERS 2024; 132:137401. [PMID: 38613264 DOI: 10.1103/physrevlett.132.137401] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Accepted: 02/26/2024] [Indexed: 04/14/2024]
Abstract
Adaptive transport networks are known to contain loops when subject to hydrodynamic fluctuations. However, fluctuations are no guarantee that a loop will form, as shown by loop-free networks driven by oscillating flows. We provide a complete stability analysis of the dynamical behavior of any loop formed by fluctuating flows. We find a threshold for loop stability that involves an interplay of geometric constraints and hydrodynamic forcing mapped to constant and fluctuating components. Loops require fluctuation in the relative size of the flux between nodes, not just a temporal variation in the flux at a given node. Hence, there is both a minimum and a maximum amount of fluctuation relative to the constant-flux component where loops are supported.
Collapse
Affiliation(s)
- Radost Waszkiewicz
- Institute of Theoretical Physics, Faculty of Physics, University of Warsaw, Pasteura 5, 02-093 Warsaw, Poland
| | - John Burnham Shaw
- Department of Geosciences, University of Arkansas, Fayetteville, Arkansas, USA
| | - Maciej Lisicki
- Institute of Theoretical Physics, Faculty of Physics, University of Warsaw, Pasteura 5, 02-093 Warsaw, Poland
| | - Piotr Szymczak
- Institute of Theoretical Physics, Faculty of Physics, University of Warsaw, Pasteura 5, 02-093 Warsaw, Poland
| |
Collapse
|
5
|
Kato S, Hotta K. Expanded tube attention for tubular structure segmentation. Int J Comput Assist Radiol Surg 2023:10.1007/s11548-023-03038-2. [PMID: 38112883 DOI: 10.1007/s11548-023-03038-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Accepted: 11/13/2023] [Indexed: 12/21/2023]
Abstract
PURPOSE Semantic segmentation of tubular structures, such as blood vessels and cell membranes, is a very difficult task, and it tends to break many predicted regions in the middle. This problem is due to the fact that tubular ground truth is very thin, and the number of pixels is extremely unbalanced compared to the background. METHODS We present a novel training method using pseudo-labels generated by morphological transformation. Furthermore, we present an attention module using thickened pseudo-labels, called the expanded tube attention (ETA) module. By using the ETA module, the network learns thickened regions based on pseudo-labels at first and then gradually learns thinned original regions while transferring information in the thickened regions as an attention map. RESULTS Through experiments conducted on retina vessel image datasets using various evaluation measures, we confirmed that the proposed method using ETA modules improved the clDice metric accuracy in comparison with the conventional methods. CONCLUSIONS We demonstrated that the proposed novel expanded tube attention module using thickened pseudo-labels can achieve easy-to-hard learning.
Collapse
Affiliation(s)
- Sota Kato
- Department of Electrical, Information, Materials and Materials Engineering, Meijo University, Tempaku-ku, Nagoya, Aichi, 468-8502, Japan.
| | - Kazuhiro Hotta
- Department of Electrical and Electronic Engineering, Meijo University, Tempaku-ku, Nagoya, Aichi, Japan
| |
Collapse
|
6
|
Wijethilake N, Anandakumar M, Zheng C, So PTC, Yildirim M, Wadduwage DN. DEEP-squared: deep learning powered De-scattering with Excitation Patterning. LIGHT, SCIENCE & APPLICATIONS 2023; 12:228. [PMID: 37704619 PMCID: PMC10499829 DOI: 10.1038/s41377-023-01248-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Revised: 07/21/2023] [Accepted: 07/29/2023] [Indexed: 09/15/2023]
Abstract
Limited throughput is a key challenge in in vivo deep tissue imaging using nonlinear optical microscopy. Point scanning multiphoton microscopy, the current gold standard, is slow especially compared to the widefield imaging modalities used for optically cleared or thin specimens. We recently introduced "De-scattering with Excitation Patterning" or "DEEP" as a widefield alternative to point-scanning geometries. Using patterned multiphoton excitation, DEEP encodes spatial information inside tissue before scattering. However, to de-scatter at typical depths, hundreds of such patterned excitations were needed. In this work, we present DEEP2, a deep learning-based model that can de-scatter images from just tens of patterned excitations instead of hundreds. Consequently, we improve DEEP's throughput by almost an order of magnitude. We demonstrate our method in multiple numerical and experimental imaging studies, including in vivo cortical vasculature imaging up to 4 scattering lengths deep in live mice.
Collapse
Affiliation(s)
- Navodini Wijethilake
- Center for Advanced Imaging, Faculty of Arts and Sciences, Harvard University, Cambridge, MA, USA
- Department of Electronic and Telecommunication Engineering, University of Moratuwa, Moratuwa, Sri Lanka
| | - Mithunjha Anandakumar
- Center for Advanced Imaging, Faculty of Arts and Sciences, Harvard University, Cambridge, MA, USA
| | - Cheng Zheng
- Department of Mechanical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
- Laser Biomedical Research Center, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
| | - Peter T C So
- Department of Mechanical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
- Laser Biomedical Research Center, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
- Department of Biological Engineering, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
| | - Murat Yildirim
- Laser Biomedical Research Center, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
- Picower Institute for Learning and Memory, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, 02139, USA
- Department of Neuroscience, Cleveland Clinic Lerner Research Institute, Cleveland, OH, 44195, USA
| | - Dushan N Wadduwage
- Center for Advanced Imaging, Faculty of Arts and Sciences, Harvard University, Cambridge, MA, USA.
| |
Collapse
|
7
|
Chen C, Zhou K, Wang Z, Zhang Q, Xiao R. All answers are in the images: A review of deep learning for cerebrovascular segmentation. Comput Med Imaging Graph 2023; 107:102229. [PMID: 37043879 DOI: 10.1016/j.compmedimag.2023.102229] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Revised: 03/03/2023] [Accepted: 04/03/2023] [Indexed: 04/14/2023]
Abstract
Cerebrovascular imaging is a common examination. Its accurate cerebrovascular segmentation become an important auxiliary method for the diagnosis and treatment of cerebrovascular diseases, which has received extensive attention from researchers. Deep learning is a heuristic method that encourages researchers to derive answers from the images by driving datasets. With the continuous development of datasets and deep learning theory, it has achieved important success for cerebrovascular segmentation. Detailed survey is an important reference for researchers. To comprehensively analyze the newest cerebrovascular segmentation, we have organized and discussed researches centered on deep learning. This survey comprehensively reviews deep learning for cerebrovascular segmentation since 2015, it mainly includes sliding window based models, U-Net based models, other CNNs based models, small-sample based models, semi-supervised or unsupervised models, fusion based models, Transformer based models, and graphics based models. We organize the structures, improvement, and important parameters of these models, as well as analyze development trends and quantitative assessment. Finally, we have discussed the challenges and opportunities of possible research directions, hoping that our survey can provide researchers with convenient reference.
Collapse
Affiliation(s)
- Cheng Chen
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
| | - Kangneng Zhou
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
| | - Zhiliang Wang
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
| | - Qian Zhang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China; China National Clinical Research Center for Neurological Diseases, Beijing 100070, China
| | - Ruoxiu Xiao
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China; Shunde Innovation School, University of Science and Technology Beijing, Foshan 100024, China.
| |
Collapse
|
8
|
A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation. Med Image Anal 2023; 85:102745. [PMID: 36630869 DOI: 10.1016/j.media.2023.102745] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2022] [Revised: 12/13/2022] [Accepted: 01/05/2023] [Indexed: 01/11/2023]
Abstract
Automatic segmentation of coronary arteries provides vital assistance to enable accurate and efficient diagnosis and evaluation of coronary artery disease (CAD). However, the task of coronary artery segmentation (CAS) remains highly challenging due to the large-scale variations exhibited by coronary arteries, their complicated anatomical structures and morphologies, as well as the low contrast between vessels and their background. To comprehensively tackle these challenges, we propose a novel multi-attention, multi-scale 3D deep network for CAS, which we call CAS-Net. Specifically, we first propose an attention-guided feature fusion (AGFF) module to efficiently fuse adjacent hierarchical features in the encoding and decoding stages to capture more effectively latent semantic information. Then, we propose a scale-aware feature enhancement (SAFE) module, aiming to dynamically adjust the receptive fields to extract more expressive features effectively, thereby enhancing the feature representation capability of the network. Furthermore, we employ the multi-scale feature aggregation (MSFA) module to learn a more distinctive semantic representation for refining the vessel maps. In addition, considering that the limited training data annotated with a quality golden standard are also a significant factor restricting the development of CAS, we construct a new dataset containing 119 cases consisting of coronary computed tomographic angiography (CCTA) volumes and annotated coronary arteries. Extensive experiments on our self-collected dataset and three publicly available datasets demonstrate that the proposed method has good segmentation performance and generalization ability, outperforming multiple state-of-the-art algorithms on various metrics. Compared with U-Net3D, the proposed method significantly improves the Dice similarity coefficient (DSC) by at least 4% on each dataset, due to the synergistic effect among the three core modules, AGFF, SAFE, and MSFA. Our implementation is released at https://github.com/Cassie-CV/CAS-Net.
Collapse
|
9
|
Through history to growth dynamics: deciphering the evolution of spatial networks. Sci Rep 2022; 12:20407. [PMID: 36437299 PMCID: PMC9701698 DOI: 10.1038/s41598-022-24656-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Accepted: 11/18/2022] [Indexed: 11/29/2022] Open
Abstract
Many ramified, network-like patterns in nature, such as river networks or blood vessels, form as a result of unstable growth of moving boundaries in an external diffusive field. Here, we pose the inverse problem for the network growth-can the growth dynamics be inferred from the analysis of the final pattern? We show that by evolving the network backward in time one can not only reconstruct the growth rules but also get an insight into the conditions under which branch splitting occurs. Determining the growth rules from a single snapshot in time is particularly important for growth processes so slow that they cannot be directly observed, such as growth of river networks and deltas or cave passages. We apply this approach to analyze the growth of a real river network in Vermont, USA. We determine its growth rule and argue that branch splitting events are triggered by an increase in the tip growth velocity.
Collapse
|
10
|
Fritz M, Köppl T, Oden JT, Wagner A, Wohlmuth B, Wu C. A 1D-0D-3D coupled model for simulating blood flow and transport processes in breast tissue. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2022; 38:e3612. [PMID: 35522186 DOI: 10.1002/cnm.3612] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Revised: 03/30/2022] [Accepted: 04/27/2022] [Indexed: 06/14/2023]
Abstract
In this work, we present mixed dimensional models for simulating blood flow and transport processes in breast tissue and the vascular tree supplying it. These processes are considered, to start from the aortic inlet to the capillaries and tissue of the breast. Large variations in biophysical properties and flow conditions exist in this system necessitating the use of different flow models for different geometries and flow regimes. In total, we consider four different model types. First, a system of 1D nonlinear hyperbolic partial differential equations (PDEs) is considered to simulate blood flow in larger arteries with highly elastic vessel walls. Second, we assign 1D linearized hyperbolic PDEs to model the smaller arteries with stiffer vessel walls. The third model type consists of ODE systems (0D models). It is used to model the arterioles and peripheral circulation. Finally, homogenized 3D porous media models are considered to simulate flow and transport in capillaries and tissue within the breast volume. Sink terms are used to account for the influence of the venous and lymphatic systems. Combining the four model types, we obtain two different 1D-0D-3D coupled models for simulating blood flow and transport processes: The first model results in a fully coupled 1D-0D-3D model covering the complete path from the aorta to the breast combining a generic arterial network with a patient specific breast network and geometry. The second model is a reduced one based on the separation of the generic and patient specific parts. The information from a calibrated fully coupled model is used as inflow condition for the patient specific sub-model allowing a significant computational cost reduction. Several numerical experiments are conducted to calibrate the generic model parameters and to demonstrate realistic flow simulations compared to existing data on blood flow in the human breast and vascular system. Moreover, we use two different breast vasculature and tissue data sets to illustrate the robustness of our reduced sub-model approach.
Collapse
Affiliation(s)
- Marvin Fritz
- Department of Mathematics, Technical University of Munich, Garching, Germany
| | - Tobias Köppl
- Department of Mathematics, Technical University of Munich, Garching, Germany
| | - John Tinsley Oden
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas, USA
| | - Andreas Wagner
- Department of Mathematics, Technical University of Munich, Garching, Germany
| | - Barbara Wohlmuth
- Department of Mathematics, Technical University of Munich, Garching, Germany
| | - Chengyue Wu
- Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas, USA
| |
Collapse
|
11
|
Li Y, Ren T, Li J, Wang H, Li X, Li A. VBNet: An end-to-end 3D neural network for vessel bifurcation point detection in mesoscopic brain images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 214:106567. [PMID: 34906786 DOI: 10.1016/j.cmpb.2021.106567] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/20/2021] [Revised: 11/29/2021] [Accepted: 11/29/2021] [Indexed: 06/14/2023]
Abstract
BACKGROUND AND OBJECTIVE Accurate detection of vessel bifurcation points from mesoscopic whole-brain images plays an important role in reconstructing cerebrovascular networks and understanding the pathogenesis of brain diseases. Existing detection methods are either less accurate or inefficient. In this paper, we propose VBNet, an end-to-end, one-stage neural network to detect vessel bifurcation points in 3D images. METHODS Firstly, we designed a 3D convolutional neural network (CNN), which input a 3D image and output the coordinates of bifurcation points in this image. The network contains a two-scale architecture to detect large bifurcation points and small bifurcation points, respectively, which takes into account the accuracy and efficiency of detection. Then, to solve the problem of low accuracy caused by the imbalance between the numbers of large bifurcations and small bifurcations, we designed a weighted loss function based on the radius distribution of blood vessels. Finally, we extended the method to detect bifurcation points in large-scale volumes. RESULTS The proposed method was tested on two mouse cerebral vascular datasets and a synthetic dataset. In the synthetic dataset, the F1-score of the proposed method reached 96.37%. In two real datasets, the F1-score was 92.35% and 86.18%, respectively. The detection effect of the proposed method reached the state-of-the-art level. CONCLUSIONS We proposed a novel method for detecting vessel bifurcation points in 3D images. It can be used to precisely locate vessel bifurcations from various cerebrovascular images. This method can be further used to reconstruct and analyze vascular networks, and also for researchers to design detection methods for other targets in 3D biomedical images.
Collapse
Affiliation(s)
- Yuxin Li
- Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710048, China.
| | - Tong Ren
- Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710048, China
| | - Junhuai Li
- Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710048, China
| | - Huaijun Wang
- Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710048, China
| | - Xiangning Li
- Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, MoE Key Laboratory for Biomedical Photonics, School of Engineering Sciences, Huazhong University of Science and Technology, Wuhan 430074, China; HUST-Suzhou Institute for Brainsmatics, Suzhou 215123, China
| | - Anan Li
- Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, MoE Key Laboratory for Biomedical Photonics, School of Engineering Sciences, Huazhong University of Science and Technology, Wuhan 430074, China; HUST-Suzhou Institute for Brainsmatics, Suzhou 215123, China.
| |
Collapse
|
12
|
Dang VN, Galati F, Cortese R, Di Giacomo G, Marconetto V, Mathur P, Lekadir K, Lorenzi M, Prados F, Zuluaga MA. Vessel-CAPTCHA: An efficient learning framework for vessel annotation and segmentation. Med Image Anal 2021; 75:102263. [PMID: 34731770 DOI: 10.1016/j.media.2021.102263] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2021] [Revised: 10/04/2021] [Accepted: 10/06/2021] [Indexed: 12/22/2022]
Abstract
Deep learning techniques for 3D brain vessel image segmentation have not been as successful as in the segmentation of other organs and tissues. This can be explained by two factors. First, deep learning techniques tend to show poor performances at the segmentation of relatively small objects compared to the size of the full image. Second, due to the complexity of vascular trees and the small size of vessels, it is challenging to obtain the amount of annotated training data typically needed by deep learning methods. To address these problems, we propose a novel annotation-efficient deep learning vessel segmentation framework. The framework avoids pixel-wise annotations, only requiring weak patch-level labels to discriminate between vessel and non-vessel 2D patches in the training set, in a setup similar to the CAPTCHAs used to differentiate humans from bots in web applications. The user-provided weak annotations are used for two tasks: (1) to synthesize pixel-wise pseudo-labels for vessels and background in each patch, which are used to train a segmentation network, and (2) to train a classifier network. The classifier network allows to generate additional weak patch labels, further reducing the annotation burden, and it acts as a second opinion for poor quality images. We use this framework for the segmentation of the cerebrovascular tree in Time-of-Flight angiography (TOF) and Susceptibility-Weighted Images (SWI). The results show that the framework achieves state-of-the-art accuracy, while reducing the annotation time by ∼77% w.r.t. learning-based segmentation methods using pixel-wise labels for training.
Collapse
Affiliation(s)
- Vien Ngoc Dang
- Data Science Department, EURECOM, Sophia Antipolis, France; Artificial Intelligence in Medicine Lab, Facultat de Matemátiques I Informática, Universitat de Barcelona, Spain
| | | | - Rosa Cortese
- Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, University College London, UK; Department of Medicine, Surgery and Neuroscience, University of Siena, Italy
| | - Giuseppe Di Giacomo
- Data Science Department, EURECOM, Sophia Antipolis, France; Politecnico di Torino, Turin, Italy
| | - Viola Marconetto
- Data Science Department, EURECOM, Sophia Antipolis, France; Politecnico di Torino, Turin, Italy
| | - Prateek Mathur
- Data Science Department, EURECOM, Sophia Antipolis, France
| | - Karim Lekadir
- Artificial Intelligence in Medicine Lab, Facultat de Matemátiques I Informática, Universitat de Barcelona, Spain
| | - Marco Lorenzi
- Université Côte d'Azur, Inria Sophia Antipolis, Epione Research Group, Valbonne, France
| | - Ferran Prados
- Centre for Medical Image Computing, Department of Medical Physics and Bioengineering, University College London, UK; Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, University College London, UK; National Institute for Health Research, University College London Hospitals, Biomedical Research Centre, London, UK; e-health Center, Universitat Oberta de Catalunya, Barcelona, Spain
| | | |
Collapse
|
13
|
Lu Y, Hu D, Ying W. A fast numerical method for oxygen supply in tissue with complex blood vessel network. PLoS One 2021; 16:e0247641. [PMID: 33635924 PMCID: PMC7909958 DOI: 10.1371/journal.pone.0247641] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2020] [Accepted: 02/10/2021] [Indexed: 11/20/2022] Open
Abstract
Angiogenesis plays an essential role in many pathological processes such as tumor growth, wound healing, and keloid development. Low oxygen level is the main driving stimulus for angiogenesis. In an animal tissue, the oxygen level is mainly determined by three effects—the oxygen delivery through blood flow in a refined vessel network, the oxygen diffusion from blood to tissue, and the oxygen consumption in cells. Evaluation of the oxygen field is usually the bottleneck in large scale modeling and simulation of angiogenesis and related physiological processes. In this work, a fast numerical method is developed for the simulation of oxygen supply in tissue with a large-scale complex vessel network. This method employs an implicit finite-difference scheme to compute the oxygen field. By virtue of an oxygen source distribution technique from vessel center lines to mesh points and a corresponding post-processing technique that eliminate the local numerical error induced by source distribution, square mesh with relatively large mesh sizes can be applied while sufficient numerical accuracy is maintained. The new method has computational complexity which is slightly higher than linear with respect to the number of mesh points and has a convergence order which is slightly lower than second order with respect to the mesh size. With this new method, accurate evaluation of the oxygen field in a fully vascularized tissue on the scale of centimeter becomes possible.
Collapse
Affiliation(s)
- Yuankai Lu
- School of Mathematical Sciences, Institute of Natural Sciences, and MOE-LSC, Shanghai Jiao Tong University, Shanghai, China
| | - Dan Hu
- School of Mathematical Sciences, Institute of Natural Sciences, and MOE-LSC, Shanghai Jiao Tong University, Shanghai, China
- * E-mail:
| | - Wenjun Ying
- School of Mathematical Sciences, Institute of Natural Sciences, and MOE-LSC, Shanghai Jiao Tong University, Shanghai, China
| |
Collapse
|
14
|
Tetteh G, Efremov V, Forkert ND, Schneider M, Kirschke J, Weber B, Zimmer C, Piraud M, Menze BH. DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes. Front Neurosci 2020; 14:592352. [PMID: 33363452 PMCID: PMC7753013 DOI: 10.3389/fnins.2020.592352] [Citation(s) in RCA: 57] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2020] [Accepted: 11/16/2020] [Indexed: 11/13/2022] Open
Abstract
We present DeepVesselNet, an architecture tailored to the challenges faced when extracting vessel trees and networks and corresponding features in 3-D angiographic volumes using deep learning. We discuss the problems of low execution speed and high memory requirements associated with full 3-D networks, high-class imbalance arising from the low percentage (<3%) of vessel voxels, and unavailability of accurately annotated 3-D training data-and offer solutions as the building blocks of DeepVesselNet. First, we formulate 2-D orthogonal cross-hair filters which make use of 3-D context information at a reduced computational burden. Second, we introduce a class balancing cross-entropy loss function with false-positive rate correction to handle the high-class imbalance and high false positive rate problems associated with existing loss functions. Finally, we generate a synthetic dataset using a computational angiogenesis model capable of simulating vascular tree growth under physiological constraints on local network structure and topology and use these data for transfer learning. We demonstrate the performance on a range of angiographic volumes at different spatial scales including clinical MRA data of the human brain, as well as CTA microscopy scans of the rat brain. Our results show that cross-hair filters achieve over 23% improvement in speed, lower memory footprint, lower network complexity which prevents overfitting and comparable accuracy that does not differ from full 3-D filters. Our class balancing metric is crucial for training the network, and transfer learning with synthetic data is an efficient, robust, and very generalizable approach leading to a network that excels in a variety of angiography segmentation tasks. We observe that sub-sampling and max pooling layers may lead to a drop in performance in tasks that involve voxel-sized structures. To this end, the DeepVesselNet architecture does not use any form of sub-sampling layer and works well for vessel segmentation, centerline prediction, and bifurcation detection. We make our synthetic training data publicly available, fostering future research, and serving as one of the first public datasets for brain vessel tree segmentation and analysis.
Collapse
Affiliation(s)
- Giles Tetteh
- Department of Computer Science, TU München, München, Germany
| | - Velizar Efremov
- Department of Computer Science, TU München, München, Germany
- Institute of Pharmacology and Toxicology, University of Zurich, Zurich, Switzerland
| | - Nils D. Forkert
- Department of Radiology, University of Calgary, Calgary, AB, Canada
| | - Matthias Schneider
- Institute of Pharmacology and Toxicology, University of Zurich, Zurich, Switzerland
| | - Jan Kirschke
- Neuroradiology, Klinikum Rechts der Isar, TU München, München, Germany
| | - Bruno Weber
- Institute of Pharmacology and Toxicology, University of Zurich, Zurich, Switzerland
| | - Claus Zimmer
- Neuroradiology, Klinikum Rechts der Isar, TU München, München, Germany
| | - Marie Piraud
- Department of Computer Science, TU München, München, Germany
| | - Björn H. Menze
- Department of Computer Science, TU München, München, Germany
- Department for Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| |
Collapse
|
15
|
Mou L, Zhao Y, Fu H, Liu Y, Cheng J, Zheng Y, Su P, Yang J, Chen L, Frangi AF, Akiba M, Liu J. CS 2-Net: Deep learning segmentation of curvilinear structures in medical imaging. Med Image Anal 2020; 67:101874. [PMID: 33166771 DOI: 10.1016/j.media.2020.101874] [Citation(s) in RCA: 94] [Impact Index Per Article: 23.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2020] [Revised: 08/26/2020] [Accepted: 10/05/2020] [Indexed: 12/20/2022]
Abstract
Automated detection of curvilinear structures, e.g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases. Precise measurement of the morphological changes of these curvilinear organ structures informs clinicians for understanding the mechanism, diagnosis, and treatment of e.g. cardiovascular, kidney, eye, lung, and neurological conditions. In this work, we propose a generic and unified convolution neural network for the segmentation of curvilinear structures and illustrate in several 2D/3D medical imaging modalities. We introduce a new curvilinear structure segmentation network (CS2-Net), which includes a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures. Two types of attention modules - spatial attention and channel attention - are utilized to enhance the inter-class discrimination and intra-class responsiveness, to further integrate local features with their global dependencies and normalization, adaptively. Furthermore, to facilitate the segmentation of curvilinear structures in medical images, we employ a 1×3 and a 3×1 convolutional kernel to capture boundary features. Besides, we extend the 2D attention mechanism to 3D to enhance the network's ability to aggregate depth information across different layers/slices. The proposed curvilinear structure segmentation network is thoroughly validated using both 2D and 3D images across six different imaging modalities. Experimental results across nine datasets show the proposed method generally outperforms other state-of-the-art algorithms in various metrics.
Collapse
Affiliation(s)
- Lei Mou
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
| | - Yitian Zhao
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China.
| | - Huazhu Fu
- Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
| | - Yonghuai Liu
- Department of Computer Science, Edge Hill University, Ormskirk, UK
| | - Jun Cheng
- UBTech Research, UBTech Robotics Corp Ltd, Shenzhen, China
| | - Yalin Zheng
- Department of Eye and Vision Science, University of Liverpool, Liverpool, UK; Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
| | - Pan Su
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
| | - Jianlong Yang
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China
| | - Li Chen
- School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China
| | - Alejandro F Frangi
- Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China; Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), School of Computing and School of Medicine, University of Leeds, Leeds, UK; Leeds Institute of Cardiovascular and Metabolic Medicine, School of Medicine, University of Leeds, Leeds, UK; Medical Imaging Research Centre (MIRC), University Hospital Gasthuisberg, Cardiovascular Sciences and Electrical Engineering Departments, KU Leuven, Leuven, Belgium
| | | | - Jiang Liu
- Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China; Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China; Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.
| |
Collapse
|
16
|
Köppl T, Vidotto E, Wohlmuth B. A 3D-1D coupled blood flow and oxygen transport model to generate microvascular networks. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2020; 36:e3386. [PMID: 32659047 DOI: 10.1002/cnm.3386] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/20/2020] [Revised: 05/18/2020] [Accepted: 07/05/2020] [Indexed: 06/11/2023]
Abstract
In this work, we introduce an algorithmic approach to generate microvascular networks starting from larger vessels that can be reconstructed without noticeable segmentation errors. Contrary to larger vessels, the reconstruction of fine-scale components of microvascular networks shows significant segmentation errors, and an accurate mapping is time and cost intense. Thus there is a need for fast and reliable reconstruction algorithms yielding surrogate networks having similar stochastic properties as the original ones. The microvascular networks are constructed in a marching way by adding vessels to the outlets of the vascular tree from the previous step. To optimise the structure of the vascular trees, we use Murray's law to determine the radii of the vessels and bifurcation angles. In each step, we compute the local gradient of the partial pressure of oxygen and adapt the orientation of the new vessels to this gradient. At the same time, we use the partial pressure of oxygen to check whether the considered tissue block is supplied sufficiently with oxygen. Computing the partial pressure of oxygen, we use a 3D-1D coupled model for blood flow and oxygen transport. To decrease the complexity of a fully coupled 3D model, we reduce the blood vessel network to a 1D graph structure and use a bi-directional coupling with the tissue which is described by a 3D homogeneous porous medium. The resulting surrogate networks are analysed with respect to morphological and physiological aspects.
Collapse
Affiliation(s)
- Tobias Köppl
- Chair for Numerics, University of Technology Munich, Garching, Germany
| | - Ettore Vidotto
- Chair for Numerics, University of Technology Munich, Garching, Germany
| | - Barbara Wohlmuth
- Chair for Numerics, University of Technology Munich, Garching, Germany
- Department of Mathematics, University of Bergen, Allegaten 41, 5020 Bergen, Norway, Germany
| |
Collapse
|
17
|
Todorov MI, Paetzold JC, Schoppe O, Tetteh G, Shit S, Efremov V, Todorov-Völgyi K, Düring M, Dichgans M, Piraud M, Menze B, Ertürk A. Machine learning analysis of whole mouse brain vasculature. Nat Methods 2020; 17:442-449. [PMID: 32161395 PMCID: PMC7591801 DOI: 10.1038/s41592-020-0792-1] [Citation(s) in RCA: 138] [Impact Index Per Article: 34.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2019] [Accepted: 02/14/2020] [Indexed: 11/09/2022]
Abstract
Tissue clearing methods enable the imaging of biological specimens without sectioning. However, reliable and scalable analysis of large imaging datasets in three dimensions remains a challenge. Here we developed a deep learning-based framework to quantify and analyze brain vasculature, named Vessel Segmentation & Analysis Pipeline (VesSAP). Our pipeline uses a convolutional neural network (CNN) with a transfer learning approach for segmentation and achieves human-level accuracy. By using VesSAP, we analyzed the vascular features of whole C57BL/6J, CD1 and BALB/c mouse brains at the micrometer scale after registering them to the Allen mouse brain atlas. We report evidence of secondary intracranial collateral vascularization in CD1 mice and find reduced vascularization of the brainstem in comparison to the cerebrum. Thus, VesSAP enables unbiased and scalable quantifications of the angioarchitecture of cleared mouse brains and yields biological insights into the vascular function of the brain.
Collapse
Affiliation(s)
- Mihail Ivilinov Todorov
- Institute for Tissue Engineering and Regenerative Medicine (iTERM), Helmholtz Zentrum München, Neuherberg, Germany
- Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität (LMU), Munich, Germany
- Graduate School of Neuroscience (GSN), Munich, Germany
| | - Johannes Christian Paetzold
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany
- Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany
- Munich School of Bioengineering, Technical University of Munich (TUM), Munich, Germany
| | - Oliver Schoppe
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany
- Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany
| | - Giles Tetteh
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany
| | - Suprosanna Shit
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany
- Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany
- Munich School of Bioengineering, Technical University of Munich (TUM), Munich, Germany
| | - Velizar Efremov
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany
- Institute of Pharmacology and Toxicology, University of Zurich (UZH), Zurich, Switzerland
| | - Katalin Todorov-Völgyi
- Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität (LMU), Munich, Germany
| | - Marco Düring
- Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität (LMU), Munich, Germany
- Munich Cluster for Systems Neurology (SyNergy), Munich, Germany
| | - Martin Dichgans
- Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität (LMU), Munich, Germany
- Munich Cluster for Systems Neurology (SyNergy), Munich, Germany
- German Center for Neurodegenerative Diseases (DZNE), Munich, Germany
| | - Marie Piraud
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany
| | - Bjoern Menze
- Department of Computer Science, Technical University of Munich (TUM), Munich, Germany.
- Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany.
- Munich School of Bioengineering, Technical University of Munich (TUM), Munich, Germany.
| | - Ali Ertürk
- Institute for Tissue Engineering and Regenerative Medicine (iTERM), Helmholtz Zentrum München, Neuherberg, Germany.
- Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität (LMU), Munich, Germany.
- Munich Cluster for Systems Neurology (SyNergy), Munich, Germany.
| |
Collapse
|
18
|
Meigel FJ, Cha P, Brenner MP, Alim K. Robust Increase in Supply by Vessel Dilation in Globally Coupled Microvasculature. PHYSICAL REVIEW LETTERS 2019; 123:228103. [PMID: 31868401 DOI: 10.1103/physrevlett.123.228103] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/02/2019] [Indexed: 06/10/2023]
Abstract
Neuronal activity induces changes in blood flow by locally dilating vessels in the brain microvasculature. How can the local dilation of a single vessel increase flow-based metabolite supply, given that flows are globally coupled within microvasculature? Solving the supply dynamics for rat brain microvasculature, we find one parameter regime to dominate physiologically. This regime allows for robust increase in supply independent of the position in the network, which we explain analytically. We show that local coupling of vessels promotes spatially correlated increased supply by dilation.
Collapse
Affiliation(s)
- Felix J Meigel
- Max Planck Institute for Dynamics and Self-Organization, 37077 Göttingen, Germany
| | - Peter Cha
- John A. Paulson School of Engineering and Applied Sciences and Kavli Institute for Bionano Science and Technology, Harvard University, Cambridge, Massachusetts 02138, USA
| | - Michael P Brenner
- John A. Paulson School of Engineering and Applied Sciences and Kavli Institute for Bionano Science and Technology, Harvard University, Cambridge, Massachusetts 02138, USA
| | - Karen Alim
- Max Planck Institute for Dynamics and Self-Organization, 37077 Göttingen, Germany
- Physik-Department, Technische Universität München, 85748 Garching, Germany
| |
Collapse
|
19
|
Helthuis JHG, van Doormaal TPC, Hillen B, Bleys RLAW, Harteveld AA, Hendrikse J, van der Toorn A, Brozici M, Zwanenburg JJM, van der Zwan A. Branching Pattern of the Cerebral Arterial Tree. Anat Rec (Hoboken) 2018; 302:1434-1446. [PMID: 30332725 PMCID: PMC6767475 DOI: 10.1002/ar.23994] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2018] [Revised: 08/19/2018] [Accepted: 09/06/2018] [Indexed: 12/19/2022]
Abstract
Quantitative data on branching patterns of the human cerebral arterial tree are lacking in the 1.0–0.1 mm radius range. We aimed to collect quantitative data in this range, and to study if the cerebral artery tree complies with the principle of minimal work (Law of Murray). To enable easy quantification of branching patterns a semi‐automatic method was employed to measure 1,294 bifurcations and 2,031 segments on 7 T‐MRI scans of two corrosion casts embedded in a gel. Additionally, to measure segments with a radius smaller than 0.1 mm, 9.4 T‐MRI was used on a small cast section to characterize 1,147 bifurcations and 1,150 segments. Besides MRI, traditional methods were employed. Seven hundred thirty‐three bifurcations were manually measured on a corrosion cast and 1,808 bifurcations and 1,799 segment lengths were manually measured on a fresh dissected cerebral arterial tree. Data showed a large variation in branching pattern parameters (asymmetry‐ratio, area‐ratio, length‐radius‐ratio, tapering). Part of the variation may be explained by the variation in measurement techniques, number of measurements and location of measurement in the vascular tree. This study confirms that the cerebral arterial tree complies with the principle of minimum work. These data are essential in the future development of more accurate mathematical blood flow models. Anat Rec, 302:1434–1446, 2019. © 2018 The Authors. The Anatomical Record published by Wiley Periodicals, Inc. on behalf of American Association of Anatomists.
Collapse
Affiliation(s)
- Jasper H G Helthuis
- Department of Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands.,Brain Technology Institute, Utrecht, The Netherlands
| | - Tristan P C van Doormaal
- Department of Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands.,Brain Technology Institute, Utrecht, The Netherlands
| | - Berend Hillen
- Departent of Anatomy, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Ronald L A W Bleys
- Department of Anatomy, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Anita A Harteveld
- Department of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Jeroen Hendrikse
- Department of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Annette van der Toorn
- Department of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Mariana Brozici
- Department of Anatomy, University Medical Center Utrecht, Utrecht, The Netherlands.,Department of Pulmonology, Heilig Hart Ziekenhuis, Mol, Belgium
| | - Jaco J M Zwanenburg
- Department of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Albert van der Zwan
- Department of Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands.,Brain Technology Institute, Utrecht, The Netherlands
| |
Collapse
|
20
|
Meigel FJ, Alim K. Flow rate of transport network controls uniform metabolite supply to tissue. J R Soc Interface 2018; 15:20180075. [PMID: 29720455 PMCID: PMC6000175 DOI: 10.1098/rsif.2018.0075] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2018] [Accepted: 04/10/2018] [Indexed: 02/03/2023] Open
Abstract
Life and functioning of higher organisms depends on the continuous supply of metabolites to tissues and organs. What are the requirements on the transport network pervading a tissue to provide a uniform supply of nutrients, minerals or hormones? To theoretically answer this question, we present an analytical scaling argument and numerical simulations on how flow dynamics and network architecture control active spread and uniform supply of metabolites by studying the example of xylem vessels in plants. We identify the fluid inflow rate as the key factor for uniform supply. While at low inflow rates metabolites are already exhausted close to flow inlets, too high inflow flushes metabolites through the network and deprives tissue close to inlets of supply. In between these two regimes, there exists an optimal inflow rate that yields a uniform supply of metabolites. We determine this optimal inflow analytically in quantitative agreement with numerical results. Optimizing network architecture by reducing the supply variance over all network tubes, we identify patterns of tube dilation or contraction that compensate sub-optimal supply for the case of too low or too high inflow rate.
Collapse
Affiliation(s)
- Felix J Meigel
- Max Planck Institute for Dynamics and Self-Organization, 37077 Göttingen, Germany
| | - Karen Alim
- Max Planck Institute for Dynamics and Self-Organization, 37077 Göttingen, Germany
| |
Collapse
|
21
|
Rohan E, Lukeš V, Jonášová A. Modeling of the contrast-enhanced perfusion test in liver based on the multi-compartment flow in porous media. J Math Biol 2018; 77:421-454. [PMID: 29368273 DOI: 10.1007/s00285-018-1209-y] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2016] [Revised: 01/15/2018] [Indexed: 12/20/2022]
Abstract
The paper deals with modeling the liver perfusion intended to improve quantitative analysis of the tissue scans provided by the contrast-enhanced computed tomography (CT). For this purpose, we developed a model of dynamic transport of the contrast fluid through the hierarchies of the perfusion trees. Conceptually, computed time-space distributions of the so-called tissue density can be compared with the measured data obtained from CT; such a modeling feedback can be used for model parameter identification. The blood flow is characterized at several scales for which different models are used. Flows in upper hierarchies represented by larger branching vessels are described using simple 1D models based on the Bernoulli equation extended by correction terms to respect the local pressure losses. To describe flows in smaller vessels and in the tissue parenchyma, we propose a 3D continuum model of porous medium defined in terms of hierarchically matched compartments characterized by hydraulic permeabilities. The 1D models corresponding to the portal and hepatic veins are coupled with the 3D model through point sources, or sinks. The contrast fluid saturation is governed by transport equations adapted for the 1D and 3D flow models. The complex perfusion model has been implemented using the finite element and finite volume methods. We report numerical examples computed for anatomically relevant geometries of the liver organ and of the principal vascular trees. The simulated tissue density corresponding to the CT examination output reflects a pathology modeled as a localized permeability deficiency.
Collapse
Affiliation(s)
- Eduard Rohan
- NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Univerzitní 8, 30614, Pilsen, Czech Republic.
| | - Vladimír Lukeš
- NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Univerzitní 8, 30614, Pilsen, Czech Republic
| | - Alena Jonášová
- NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Univerzitní 8, 30614, Pilsen, Czech Republic
| |
Collapse
|
22
|
Segmentation of the hippocampus by transferring algorithmic knowledge for large cohort processing. Med Image Anal 2018; 43:214-228. [DOI: 10.1016/j.media.2017.11.004] [Citation(s) in RCA: 43] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2017] [Revised: 09/14/2017] [Accepted: 11/06/2017] [Indexed: 01/27/2023]
|
23
|
Humeau-Heurtier A, Mahé G, Abraham P. Multi-dimensional complete ensemble empirical mode decomposition with adaptive noise applied to laser speckle contrast images. IEEE TRANSACTIONS ON MEDICAL IMAGING 2015; 34:2103-2117. [PMID: 25850087 DOI: 10.1109/tmi.2015.2419711] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
Laser speckle contrast imaging (LSCI) is a noninvasive full-field optical technique which allows analyzing the dynamics of microvascular blood flow. LSCI has attracted attention because it is able to image blood flow in different kinds of tissue with high spatial and temporal resolutions. Additionally, it is simple and necessitates low-cost devices. However, the physiological information that can be extracted directly from the images is not completely determined yet. In this work, a novel multi-dimensional complete ensemble empirical mode decomposition with adaptive noise (MCEEMDAN) is introduced and applied in LSCI data recorded in three physiological conditions (rest, vascular occlusion and post-occlusive reactive hyperaemia). MCEEMDAN relies on the improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and our algorithm is specifically designed to analyze multi-dimensional data (such as images). Over the recent multi-dimensional ensemble empirical mode decomposition (MEEMD), MCEEMDAN has the advantage of leading to an exact reconstruction of the original data. The results show that MCEEMDAN leads to intrinsic mode functions and residue that reveal hidden patterns in LSCI data. Moreover, these patterns differ with physiological states. MCEEMDAN appears as a promising way to extract features in LSCI data for an improvement of the image understanding.
Collapse
|
24
|
Gagnon L, Sakadžić S, Lesage F, Mandeville ET, Fang Q, Yaseen MA, Boas DA. Multimodal reconstruction of microvascular-flow distributions using combined two-photon microscopy and Doppler optical coherence tomography. NEUROPHOTONICS 2015; 2:015008. [PMID: 26157987 PMCID: PMC4478873 DOI: 10.1117/1.nph.2.1.015008] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/07/2014] [Accepted: 02/20/2015] [Indexed: 05/04/2023]
Abstract
Computing microvascular cerebral blood flow ([Formula: see text]) in real cortical angiograms is challenging. Here, we investigated whether the use of Doppler optical coherence tomography (DOCT) flow measurements in individual vessel segments can help in reconstructing [Formula: see text] across the entire vasculature of a truncated cortical angiogram. A [Formula: see text] computational framework integrating DOCT measurements is presented. Simulations performed on a synthetic angiogram showed that the addition of DOCT measurements, especially close to large inflowing or outflowing vessels, reduces the impact of pressure boundary conditions and estimated vessel resistances resulting in a more accurate reconstruction of [Formula: see text]. Our technique was then applied to reconstruct microvascular flow distributions in the mouse cortex down to [Formula: see text] by combining two-photon laser scanning microscopy angiography with DOCT.
Collapse
Affiliation(s)
- Louis Gagnon
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Building 149 13th Street, Charlestown, Massachusetts 02129, United States
- Harvard-MIT Division of Health Sciences and Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States
- Ecole Polytechnique de Montreal, Department of Electrical Engineering, 2900 Boulevard Edouard-Montpetit, Montreal, Quebec H3T 1J4, Canada
- Address all correspondence to: Louis Gagnon, E-mail:
| | - Sava Sakadžić
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Building 149 13th Street, Charlestown, Massachusetts 02129, United States
| | - Fréderic Lesage
- Ecole Polytechnique de Montreal, Department of Electrical Engineering, 2900 Boulevard Edouard-Montpetit, Montreal, Quebec H3T 1J4, Canada
| | - Emiri T. Mandeville
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Building 149 13th Street, Charlestown, Massachusetts 02129, United States
| | - Qianqian Fang
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Building 149 13th Street, Charlestown, Massachusetts 02129, United States
| | - Mohammad A. Yaseen
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Building 149 13th Street, Charlestown, Massachusetts 02129, United States
| | - David A. Boas
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Building 149 13th Street, Charlestown, Massachusetts 02129, United States
- Harvard-MIT Division of Health Sciences and Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
25
|
Schneider M, Hirsch S, Weber B, Székely G, Menze BH. Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters. Med Image Anal 2015; 19:220-49. [DOI: 10.1016/j.media.2014.09.007] [Citation(s) in RCA: 63] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2014] [Revised: 09/12/2014] [Accepted: 09/25/2014] [Indexed: 11/26/2022]
|
26
|
Jurczuk K, Kretowski M, Eliat PA, Saint-Jalmes H, Bezy-Wendling J. In silico modeling of magnetic resonance flow imaging in complex vascular networks. IEEE TRANSACTIONS ON MEDICAL IMAGING 2014; 33:2191-2209. [PMID: 25020068 DOI: 10.1109/tmi.2014.2336756] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
The paper presents a computational model of magnetic resonance (MR) flow imaging. The model consists of three components. The first component is used to generate complex vascular structures, while the second one provides blood flow characteristics in the generated vascular structures by the lattice Boltzmann method. The third component makes use of the generated vascular structures and flow characteristics to simulate MR flow imaging. To meet computational demands, parallel algorithms are applied in all the components. The proposed approach is verified in three stages. In the first stage, experimental validation is performed by an in vitro phantom. Then, the simulation possibilities of the model are shown. Flow and MR flow imaging in complex vascular structures are presented and evaluated. Finally, the computational performance is tested. Results show that the model is able to reproduce flow behavior in large vascular networks in a relatively short time. Moreover, simulated MR flow images are in accordance with the theoretical considerations and experimental images. The proposed approach is the first such an integrative solution in literature. Moreover, compared to previous works on flow and MR flow imaging, this approach distinguishes itself by its computational efficiency. Such a connection of anatomy, physiology and image formation in a single computer tool could provide an in silico solution to improving our understanding of the processes involved, either considered together or separately.
Collapse
|
27
|
Schneider M, Hirsch S, Weber B, Székely G, Menze BH. TGIF: Topological Gap In-Fill for Vascular Networks. ACTA ACUST UNITED AC 2014; 17:89-96. [DOI: 10.1007/978-3-319-10470-6_12] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/21/2023]
|
28
|
Linninger AA, Gould IG, Marrinan T, Hsu CY, Chojecki M, Alaraj A. Cerebral microcirculation and oxygen tension in the human secondary cortex. Ann Biomed Eng 2013; 41:2264-84. [PMID: 23842693 DOI: 10.1007/s10439-013-0828-0] [Citation(s) in RCA: 87] [Impact Index Per Article: 7.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2013] [Accepted: 05/10/2013] [Indexed: 02/04/2023]
Abstract
The three-dimensional spatial arrangement of the cortical microcirculatory system is critical for understanding oxygen exchange between blood vessels and brain cells. A three-dimensional computer model of a 3 × 3 × 3 mm(3) subsection of the human secondary cortex was constructed to quantify oxygen advection in the microcirculation, tissue oxygen perfusion, and consumption in the human cortex. This computer model accounts for all arterial, capillary and venous blood vessels of the cerebral microvascular bed as well as brain tissue occupying the extravascular space. Microvessels were assembled with optimization algorithms emulating angiogenic growth; a realistic capillary bed was built with space filling procedures. The extravascular tissue was modeled as a porous medium supplied with oxygen by advection-diffusion to match normal metabolic oxygen demand. The resulting synthetic computer generated network matches prior measured morphometrics and fractal patterns of the cortical microvasculature. This morphologically accurate, physiologically consistent, multi-scale computer network of the cerebral microcirculation predicts the oxygen exchange of cortical blood vessels with the surrounding gray matter. Oxygen tension subject to blood pressure and flow conditions were computed and validated for the blood as well as brain tissue. Oxygen gradients along arterioles, capillaries and veins agreed with in vivo trends observed recently in imaging studies within experimental tolerances and uncertainty.
Collapse
Affiliation(s)
- A A Linninger
- Department of Bioengineering, University of Illinois at Chicago, 851 S. Morgan St, 218 SEO, M/C 063, Chicago, IL, 60607-7000, USA,
| | | | | | | | | | | |
Collapse
|
29
|
Frangi AF, Hose DR, Hunter PJ, Ayache N, Brooks D. Special issue on medical imaging and image computing in computational physiology. IEEE TRANSACTIONS ON MEDICAL IMAGING 2013; 32:1-7. [PMID: 23409282 DOI: 10.1109/tmi.2012.2234320] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/01/2023]
|