Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework
<i>Background:</i> Atherosclerotic plaque detection is a clinical and technological problem that has been approached by different studies. Nowadays, intravascular ultrasound (IVUS) is the standard used to capture images of the coronary walls and to detect plaques. However, IVUS images ar...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/21/4020 |
| _version_ | 1827646228736770048 |
|---|---|
| author | Álvaro T. Latorre Miguel A. Martínez Myriam Cilla Jacques Ohayon Estefanía Peña |
| author_facet | Álvaro T. Latorre Miguel A. Martínez Myriam Cilla Jacques Ohayon Estefanía Peña |
| author_sort | Álvaro T. Latorre |
| collection | DOAJ |
| description | <i>Background:</i> Atherosclerotic plaque detection is a clinical and technological problem that has been approached by different studies. Nowadays, intravascular ultrasound (IVUS) is the standard used to capture images of the coronary walls and to detect plaques. However, IVUS images are difficult to segment, which complicates obtaining geometric measurements of the plaque. <i>Objective:</i> IVUS, in combination with new techniques, allows estimation of strains in the coronary section. In this study, we have proposed the use of estimated strains to develop a methodology for plaque segmentation. <i>Methods:</i> The process is based on the representation of strain gradients and the combination of the Watershed and Gradient Vector Flow algorithms. Since it is a theoretical framework, the methodology was tested with idealized and real IVUS geometries. <i>Results:</i> We achieved measurements of the lipid area and fibrous cap thickness, which are essential clinical information, with promising results. The success of the segmentation depends on the plaque geometry and the strain gradient variable (SGV) that was selected. However, there are some SGV combinations that yield good results regardless of plaque geometry such as <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>v</mi><mi>M</mi><mi>i</mi><mi>s</mi><mi>e</mi><mi>s</mi></mrow></msub></mfenced><mo>+</mo><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>r</mi><mi>θ</mi></mrow></msub></mfenced></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>y</mi><mi>y</mi></mrow></msub></mfenced><mo>+</mo><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>r</mi><mi>r</mi></mrow></msub></mfenced></mrow></semantics></math></inline-formula> or <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub></mfenced><mo>+</mo><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>T</mi><mi>r</mi><mi>e</mi><mi>s</mi><mi>c</mi><mi>a</mi></mrow></msub></mfenced></mrow></semantics></math></inline-formula>. These combinations of SGVs achieve good segmentations, with an accuracy between 97.10% and 94.39% in the best pairs. <i>Conclusions:</i> The new methodology provides fast segmentation from different strain variables, without an optimization step. |
| first_indexed | 2024-03-09T18:52:03Z |
| format | Article |
| id | doaj.art-934cac5a2e0645218637db0e66a05f47 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T18:52:03Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-934cac5a2e0645218637db0e66a05f472023-11-24T05:43:39ZengMDPI AGMathematics2227-73902022-10-011021402010.3390/math10214020Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical FrameworkÁlvaro T. Latorre0Miguel A. Martínez1Myriam Cilla2Jacques Ohayon3Estefanía Peña4Aragón Institute for Engineering Research (I3A), University of Zaragoza, 50018 Zaragoza, SpainAragón Institute for Engineering Research (I3A), University of Zaragoza, 50018 Zaragoza, SpainAragón Institute for Engineering Research (I3A), University of Zaragoza, 50018 Zaragoza, SpainLaboratory TIMC-IMAG, CNRS UMR 5525, Grenoble-Alpes University, 38400 Grenoble, FranceAragón Institute for Engineering Research (I3A), University of Zaragoza, 50018 Zaragoza, Spain<i>Background:</i> Atherosclerotic plaque detection is a clinical and technological problem that has been approached by different studies. Nowadays, intravascular ultrasound (IVUS) is the standard used to capture images of the coronary walls and to detect plaques. However, IVUS images are difficult to segment, which complicates obtaining geometric measurements of the plaque. <i>Objective:</i> IVUS, in combination with new techniques, allows estimation of strains in the coronary section. In this study, we have proposed the use of estimated strains to develop a methodology for plaque segmentation. <i>Methods:</i> The process is based on the representation of strain gradients and the combination of the Watershed and Gradient Vector Flow algorithms. Since it is a theoretical framework, the methodology was tested with idealized and real IVUS geometries. <i>Results:</i> We achieved measurements of the lipid area and fibrous cap thickness, which are essential clinical information, with promising results. The success of the segmentation depends on the plaque geometry and the strain gradient variable (SGV) that was selected. However, there are some SGV combinations that yield good results regardless of plaque geometry such as <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>v</mi><mi>M</mi><mi>i</mi><mi>s</mi><mi>e</mi><mi>s</mi></mrow></msub></mfenced><mo>+</mo><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>r</mi><mi>θ</mi></mrow></msub></mfenced></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>y</mi><mi>y</mi></mrow></msub></mfenced><mo>+</mo><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>r</mi><mi>r</mi></mrow></msub></mfenced></mrow></semantics></math></inline-formula> or <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub></mfenced><mo>+</mo><mfenced separators="" open="|" close="|"><mo>▽</mo><msub><mi>ε</mi><mrow><mi>T</mi><mi>r</mi><mi>e</mi><mi>s</mi><mi>c</mi><mi>a</mi></mrow></msub></mfenced></mrow></semantics></math></inline-formula>. These combinations of SGVs achieve good segmentations, with an accuracy between 97.10% and 94.39% in the best pairs. <i>Conclusions:</i> The new methodology provides fast segmentation from different strain variables, without an optimization step.https://www.mdpi.com/2227-7390/10/21/4020atherosclerosisfibrous cap thicknessfinite element modelintravascular ultrasoundsegmentation methodstrain gradient |
| spellingShingle | Álvaro T. Latorre Miguel A. Martínez Myriam Cilla Jacques Ohayon Estefanía Peña Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework Mathematics atherosclerosis fibrous cap thickness finite element model intravascular ultrasound segmentation method strain gradient |
| title | Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework |
| title_full | Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework |
| title_fullStr | Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework |
| title_full_unstemmed | Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework |
| title_short | Atherosclerotic Plaque Segmentation Based on Strain Gradients: A Theoretical Framework |
| title_sort | atherosclerotic plaque segmentation based on strain gradients a theoretical framework |
| topic | atherosclerosis fibrous cap thickness finite element model intravascular ultrasound segmentation method strain gradient |
| url | https://www.mdpi.com/2227-7390/10/21/4020 |
| work_keys_str_mv | AT alvarotlatorre atheroscleroticplaquesegmentationbasedonstraingradientsatheoreticalframework AT miguelamartinez atheroscleroticplaquesegmentationbasedonstraingradientsatheoreticalframework AT myriamcilla atheroscleroticplaquesegmentationbasedonstraingradientsatheoreticalframework AT jacquesohayon atheroscleroticplaquesegmentationbasedonstraingradientsatheoreticalframework AT estefaniapena atheroscleroticplaquesegmentationbasedonstraingradientsatheoreticalframework |