Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset
ObjectivesTo assess the feasibility of extracting radiomics signal intensity based features from the myocardium using cardiovascular magnetic resonance (CMR) imaging stress perfusion sequences. Furthermore, to compare the diagnostic performance of radiomics models against standard-of-care qualitativ...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1141026/full |
| _version_ | 1797682421395619840 |
|---|---|
| author | Zahra Raisi-Estabragh Zahra Raisi-Estabragh Carlos Martin-Isla Louise Nissen Liliana Szabo Liliana Szabo Liliana Szabo Victor M. Campello Sergio Escalera Sergio Escalera Simon Winther Morten Bøttcher Karim Lekadir Steffen E. Petersen Steffen E. Petersen Steffen E. Petersen Steffen E. Petersen |
| author_facet | Zahra Raisi-Estabragh Zahra Raisi-Estabragh Carlos Martin-Isla Louise Nissen Liliana Szabo Liliana Szabo Liliana Szabo Victor M. Campello Sergio Escalera Sergio Escalera Simon Winther Morten Bøttcher Karim Lekadir Steffen E. Petersen Steffen E. Petersen Steffen E. Petersen Steffen E. Petersen |
| author_sort | Zahra Raisi-Estabragh |
| collection | DOAJ |
| description | ObjectivesTo assess the feasibility of extracting radiomics signal intensity based features from the myocardium using cardiovascular magnetic resonance (CMR) imaging stress perfusion sequences. Furthermore, to compare the diagnostic performance of radiomics models against standard-of-care qualitative visual assessment of stress perfusion images, with the ground truth stenosis label being defined by invasive Fractional Flow Reserve (FFR) and quantitative coronary angiography.MethodsWe used the Dan-NICAD 1 dataset, a multi-centre study with coronary computed tomography angiography, 1,5 T CMR stress perfusion, and invasive FFR available for a subset of 148 patients with suspected coronary artery disease. Image segmentation was performed by two independent readers. We used the Pyradiomics platform to extract radiomics first-order (n = 14) and texture (n = 75) features from the LV myocardium (basal, mid, apical) in rest and stress perfusion images.ResultsOverall, 92 patients (mean age 62 years, 56 men) were included in the study, 39 with positive FFR. We double-cross validated the model and, in each inner fold, we trained and validated a per territory model. The conventional analysis results reported sensitivity of 41% and specificity of 84%. Our final radiomics model demonstrated an improvement on these results with an average sensitivity of 53% and specificity of 86%.ConclusionIn this proof-of-concept study from the Dan-NICAD dataset, we demonstrate the feasibility of radiomics analysis applied to CMR perfusion images with a suggestion of superior diagnostic performance of radiomics models over conventional visual analysis of perfusion images in picking up perfusion defects defined by invasive coronary angiography. |
| first_indexed | 2024-03-11T23:59:29Z |
| format | Article |
| id | doaj.art-c361f87706484a03bff1ae17d36b2e44 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-03-11T23:59:29Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-c361f87706484a03bff1ae17d36b2e442023-09-18T05:49:12ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2023-09-011010.3389/fcvm.2023.11410261141026Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD datasetZahra Raisi-Estabragh0Zahra Raisi-Estabragh1Carlos Martin-Isla2Louise Nissen3Liliana Szabo4Liliana Szabo5Liliana Szabo6Victor M. Campello7Sergio Escalera8Sergio Escalera9Simon Winther10Morten Bøttcher11Karim Lekadir12Steffen E. Petersen13Steffen E. Petersen14Steffen E. Petersen15Steffen E. Petersen16William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, London, United KingdomBarts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, London, United KingdomDept. de Matematiques I Informatica, University of Barcelona, Barcelona, SpainDepartment of Cardiology, Regionshospital Gødstrup, Herning, DenmarkWilliam Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, London, United KingdomBarts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, London, United KingdomHeart and Vascular Center, Semmelweis University, Budapest, HungaryDept. de Matematiques I Informatica, University of Barcelona, Barcelona, SpainDepartament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, SpainComputer Vision Center, Univeritat Autònoma de Barcelona, Barcelona, SpainDepartment of Cardiology, Regionshospital Gødstrup, Herning, DenmarkDepartment of Cardiology, Regionshospital Gødstrup, Herning, DenmarkDept. de Matematiques I Informatica, University of Barcelona, Barcelona, SpainWilliam Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, London, United KingdomBarts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, London, United KingdomHealth Data Research UK, London, United KingdomAlan Turing Institute, London, United KingdomObjectivesTo assess the feasibility of extracting radiomics signal intensity based features from the myocardium using cardiovascular magnetic resonance (CMR) imaging stress perfusion sequences. Furthermore, to compare the diagnostic performance of radiomics models against standard-of-care qualitative visual assessment of stress perfusion images, with the ground truth stenosis label being defined by invasive Fractional Flow Reserve (FFR) and quantitative coronary angiography.MethodsWe used the Dan-NICAD 1 dataset, a multi-centre study with coronary computed tomography angiography, 1,5 T CMR stress perfusion, and invasive FFR available for a subset of 148 patients with suspected coronary artery disease. Image segmentation was performed by two independent readers. We used the Pyradiomics platform to extract radiomics first-order (n = 14) and texture (n = 75) features from the LV myocardium (basal, mid, apical) in rest and stress perfusion images.ResultsOverall, 92 patients (mean age 62 years, 56 men) were included in the study, 39 with positive FFR. We double-cross validated the model and, in each inner fold, we trained and validated a per territory model. The conventional analysis results reported sensitivity of 41% and specificity of 84%. Our final radiomics model demonstrated an improvement on these results with an average sensitivity of 53% and specificity of 86%.ConclusionIn this proof-of-concept study from the Dan-NICAD dataset, we demonstrate the feasibility of radiomics analysis applied to CMR perfusion images with a suggestion of superior diagnostic performance of radiomics models over conventional visual analysis of perfusion images in picking up perfusion defects defined by invasive coronary angiography.https://www.frontiersin.org/articles/10.3389/fcvm.2023.1141026/fullradiomicsDan-NICADCMR (cardiovascular magnetic resonance)stress perfusion cardiac MRImachine learning (ML) |
| spellingShingle | Zahra Raisi-Estabragh Zahra Raisi-Estabragh Carlos Martin-Isla Louise Nissen Liliana Szabo Liliana Szabo Liliana Szabo Victor M. Campello Sergio Escalera Sergio Escalera Simon Winther Morten Bøttcher Karim Lekadir Steffen E. Petersen Steffen E. Petersen Steffen E. Petersen Steffen E. Petersen Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset Frontiers in Cardiovascular Medicine radiomics Dan-NICAD CMR (cardiovascular magnetic resonance) stress perfusion cardiac MRI machine learning (ML) |
| title | Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset |
| title_full | Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset |
| title_fullStr | Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset |
| title_full_unstemmed | Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset |
| title_short | Radiomics analysis enhances the diagnostic performance of CMR stress perfusion: a proof-of-concept study using the Dan-NICAD dataset |
| title_sort | radiomics analysis enhances the diagnostic performance of cmr stress perfusion a proof of concept study using the dan nicad dataset |
| topic | radiomics Dan-NICAD CMR (cardiovascular magnetic resonance) stress perfusion cardiac MRI machine learning (ML) |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1141026/full |
| work_keys_str_mv | AT zahraraisiestabragh radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT zahraraisiestabragh radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT carlosmartinisla radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT louisenissen radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT lilianaszabo radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT lilianaszabo radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT lilianaszabo radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT victormcampello radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT sergioescalera radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT sergioescalera radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT simonwinther radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT mortenbøttcher radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT karimlekadir radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT steffenepetersen radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT steffenepetersen radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT steffenepetersen radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset AT steffenepetersen radiomicsanalysisenhancesthediagnosticperformanceofcmrstressperfusionaproofofconceptstudyusingthedannicaddataset |