• Je něco špatně v tomto záznamu ?

3D Visualization, Skeletonization and Branching Analysis of Blood Vessels in Angiogenesis

V. Ramakrishnan, R. Schönmehl, A. Artinger, L. Winter, H. Böck, S. Schreml, F. Gürtler, J. Daza, VH. Schmitt, A. Mamilos, P. Arbelaez, A. Teufel, T. Niedermair, O. Topolcan, M. Karlíková, S. Sossalla, CB. Wiedenroth, M. Rupp, C. Brochhausen

. 2023 ; 24 (9) : . [pub] 20230423

Jazyk angličtina Země Švýcarsko

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc23011725

Grantová podpora
Ziel ETZ-352 2014 -2020 European Union

Angiogenesis is the process of new blood vessels growing from existing vasculature. Visualizing them as a three-dimensional (3D) model is a challenging, yet relevant, task as it would be of great help to researchers, pathologists, and medical doctors. A branching analysis on the 3D model would further facilitate research and diagnostic purposes. In this paper, a pipeline of vision algorithms is elaborated to visualize and analyze blood vessels in 3D from formalin-fixed paraffin-embedded (FFPE) granulation tissue sections with two different staining methods. First, a U-net neural network is used to segment blood vessels from the tissues. Second, image registration is used to align the consecutive images. Coarse registration using an image-intensity optimization technique, followed by finetuning using a neural network based on Spatial Transformers, results in an excellent alignment of images. Lastly, the corresponding segmented masks depicting the blood vessels are aligned and interpolated using the results of the image registration, resulting in a visualized 3D model. Additionally, a skeletonization algorithm is used to analyze the branching characteristics of the 3D vascular model. In summary, computer vision and deep learning is used to reconstruct, visualize and analyze a 3D vascular model from a set of parallel tissue samples. Our technique opens innovative perspectives in the pathophysiological understanding of vascular morphogenesis under different pathophysiological conditions and its potential diagnostic role.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc23011725
003      
CZ-PrNML
005      
20230801133259.0
007      
ta
008      
230718s2023 sz f 000 0|eng||
009      
AR
024    7_
$a 10.3390/ijms24097714 $2 doi
035    __
$a (PubMed)37175421
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a sz
100    1_
$a Ramakrishnan, Vignesh $u Institute of Pathology, University of Regensburg, 93053 Regensburg, Germany $u Central Biobank Regensburg, University and University Hospital Regensburg, 93053 Regensburg, Germany $1 https://orcid.org/0000000330551017
245    10
$a 3D Visualization, Skeletonization and Branching Analysis of Blood Vessels in Angiogenesis / $c V. Ramakrishnan, R. Schönmehl, A. Artinger, L. Winter, H. Böck, S. Schreml, F. Gürtler, J. Daza, VH. Schmitt, A. Mamilos, P. Arbelaez, A. Teufel, T. Niedermair, O. Topolcan, M. Karlíková, S. Sossalla, CB. Wiedenroth, M. Rupp, C. Brochhausen
520    9_
$a Angiogenesis is the process of new blood vessels growing from existing vasculature. Visualizing them as a three-dimensional (3D) model is a challenging, yet relevant, task as it would be of great help to researchers, pathologists, and medical doctors. A branching analysis on the 3D model would further facilitate research and diagnostic purposes. In this paper, a pipeline of vision algorithms is elaborated to visualize and analyze blood vessels in 3D from formalin-fixed paraffin-embedded (FFPE) granulation tissue sections with two different staining methods. First, a U-net neural network is used to segment blood vessels from the tissues. Second, image registration is used to align the consecutive images. Coarse registration using an image-intensity optimization technique, followed by finetuning using a neural network based on Spatial Transformers, results in an excellent alignment of images. Lastly, the corresponding segmented masks depicting the blood vessels are aligned and interpolated using the results of the image registration, resulting in a visualized 3D model. Additionally, a skeletonization algorithm is used to analyze the branching characteristics of the 3D vascular model. In summary, computer vision and deep learning is used to reconstruct, visualize and analyze a 3D vascular model from a set of parallel tissue samples. Our technique opens innovative perspectives in the pathophysiological understanding of vascular morphogenesis under different pathophysiological conditions and its potential diagnostic role.
650    12
$a zobrazování trojrozměrné $x metody $7 D021621
650    12
$a neuronové sítě $7 D016571
650    _2
$a algoritmy $7 D000465
650    _2
$a kardiovaskulární fyziologické jevy $7 D002320
650    _2
$a morfogeneze $7 D009024
650    _2
$a počítačové zpracování obrazu $7 D007091
655    _2
$a časopisecké články $7 D016428
700    1_
$a Schönmehl, Rebecca $u Institute of Pathology, University Medical Centre Mannheim, Heidelberg University, 68167 Mannheim, Germany
700    1_
$a Artinger, Annalena $u Institute of Pathology, University Medical Centre Mannheim, Heidelberg University, 68167 Mannheim, Germany $1 https://orcid.org/0000000202361147
700    1_
$a Winter, Lina $u Institute of Pathology, University Medical Centre Mannheim, Heidelberg University, 68167 Mannheim, Germany $1 https://orcid.org/0009000579310662
700    1_
$a Böck, Hendrik $u Institute of Pathology, University Medical Centre Mannheim, Heidelberg University, 68167 Mannheim, Germany
700    1_
$a Schreml, Stephan $u Department of Dermatology, University Medical Centre Regensburg, 93053 Regensburg, Germany $1 https://orcid.org/0000000228201942
700    1_
$a Gürtler, Florian $u Institute of Pathology, University of Regensburg, 93053 Regensburg, Germany $u Central Biobank Regensburg, University and University Hospital Regensburg, 93053 Regensburg, Germany $1 https://orcid.org/0000000323045239
700    1_
$a Daza, Jimmy $u Department of Internal Medicine II, Division of Hepatology, Medical Faculty Mannheim, Heidelberg University, 68167 Mannheim, Germany $1 https://orcid.org/0000000199025440
700    1_
$a Schmitt, Volker H $u Department of Cardiology, University Medical Centre, Johannes Gutenberg University of Mainz, 55131 Mainz, Germany $1 https://orcid.org/0000000150707280
700    1_
$a Mamilos, Andreas $u Institute of Pathology, University of Regensburg, 93053 Regensburg, Germany $u Central Biobank Regensburg, University and University Hospital Regensburg, 93053 Regensburg, Germany $1 https://orcid.org/0000000208955675
700    1_
$a Arbelaez, Pablo $u Center for Research and Formation in Artificial Intelligence (CinfonIA), Universidad de Los Andes, 111711 Bogota, Colombia
700    1_
$a Teufel, Andreas $u Department of Internal Medicine II, Division of Hepatology, Medical Faculty Mannheim, Heidelberg University, 68167 Mannheim, Germany $1 https://orcid.org/0000000179538927
700    1_
$a Niedermair, Tanja $u Institute of Pathology, University of Regensburg, 93053 Regensburg, Germany $u Central Biobank Regensburg, University and University Hospital Regensburg, 93053 Regensburg, Germany
700    1_
$a Topolcan, Ondrej $u Biomedical Center, Faculty of Medicine in Pilsen, Charles University, 32300 Pilsen, Czech Republic
700    1_
$a Karlíková, Marie $u Biomedical Center, Faculty of Medicine in Pilsen, Charles University, 32300 Pilsen, Czech Republic
700    1_
$a Sossalla, Samuel $u Department of Internal Medicine II, University Hospital Regensburg, 93053 Regensburg, Germany $1 https://orcid.org/0000000180342673
700    1_
$a Wiedenroth, Christoph B $u Department of Thoracic Surgery, Kerckhoff Clinic, 61231 Bad Nauheim, Germany
700    1_
$a Rupp, Markus $u Department of Trauma Surgery, University Medical Centre Regensburg, 93053 Regensburg, Germany $1 https://orcid.org/0000000172213783
700    1_
$a Brochhausen, Christoph $u Institute of Pathology, University of Regensburg, 93053 Regensburg, Germany $u Institute of Pathology, University Medical Centre Mannheim, Heidelberg University, 68167 Mannheim, Germany
773    0_
$w MED00176142 $t International journal of molecular sciences $x 1422-0067 $g Roč. 24, č. 9 (2023)
856    41
$u https://pubmed.ncbi.nlm.nih.gov/37175421 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20230718 $b ABA008
991    __
$a 20230801133256 $b ABA008
999    __
$a ok $b bmc $g 1963893 $s 1197990
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2023 $b 24 $c 9 $e 20230423 $i 1422-0067 $m International journal of molecular sciences $n Int J Mol Sci $x MED00176142
GRA    __
$a Ziel ETZ-352 2014 -2020 $p European Union
LZP    __
$a Pubmed-20230718

Najít záznam

Citační ukazatele

Možnosti archivace