Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
<h4>Background</h4> <p>Cardiovascular magnetic resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocard...
| Κύριοι συγγραφείς: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Μορφή: | Journal article |
| Γλώσσα: | English |
| Έκδοση: |
BioMed Central
2018
|
| _version_ | 1826271872998703104 |
|---|---|
| author | Bai, W Sinclair, M Tarroni, G Oktay, O Rajchl, M Vaillant, G Lee, AM Aung, N Lukaschuk, E Sanghvi, MM Zemrak, F Fung, K Paiva, JM Carapella, V Kim, YJ Suzuki, H Kainz, B Matthews, PM Petersen, SE Piechnik, SK Neubauer, S Glocker, B Rueckert, D |
| author_facet | Bai, W Sinclair, M Tarroni, G Oktay, O Rajchl, M Vaillant, G Lee, AM Aung, N Lukaschuk, E Sanghvi, MM Zemrak, F Fung, K Paiva, JM Carapella, V Kim, YJ Suzuki, H Kainz, B Matthews, PM Petersen, SE Piechnik, SK Neubauer, S Glocker, B Rueckert, D |
| author_sort | Bai, W |
| collection | OXFORD |
| description | <h4>Background</h4> <p>Cardiovascular magnetic resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images.</p> <h4>Methods</h4> <p>Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV).</p> <h4>Results</h4> <p>By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images. On a short-axis image test set of 600 subjects, it achieves an average Dice metric of 0.94 for the LV cavity, 0.88 for the LV myocardium and 0.90 for the RV cavity. The mean absolute difference between automated measurement and manual measurement is 6.1 mL for LVEDV, 5.3 mL for LVESV, 6.9 gram for LVM, 8.5 mL for RVEDV and 7.2 mL for RVESV. On long-axis image test sets, the average Dice metric is 0.93 for the LA cavity (2-chamber view), 0.95 for the LA cavity (4-chamber view) and 0.96 for the RA cavity (4-chamber view). The performance is comparable to human inter-observer variability.</p> <h4>Conclusions</h4> <p>We show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.</p> |
| first_indexed | 2024-03-06T22:03:36Z |
| format | Journal article |
| id | oxford-uuid:4f697172-f065-401b-8e86-8f4fb4610c0e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:03:36Z |
| publishDate | 2018 |
| publisher | BioMed Central |
| record_format | dspace |
| spelling | oxford-uuid:4f697172-f065-401b-8e86-8f4fb4610c0e2022-03-26T16:07:04ZAutomated cardiovascular magnetic resonance image analysis with fully convolutional networksJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:4f697172-f065-401b-8e86-8f4fb4610c0eEnglishSymplectic Elements at OxfordBioMed Central2018Bai, WSinclair, MTarroni, GOktay, ORajchl, MVaillant, GLee, AMAung, NLukaschuk, ESanghvi, MMZemrak, FFung, KPaiva, JMCarapella, VKim, YJSuzuki, HKainz, BMatthews, PMPetersen, SEPiechnik, SKNeubauer, SGlocker, BRueckert, D <h4>Background</h4> <p>Cardiovascular magnetic resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images.</p> <h4>Methods</h4> <p>Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV).</p> <h4>Results</h4> <p>By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images. On a short-axis image test set of 600 subjects, it achieves an average Dice metric of 0.94 for the LV cavity, 0.88 for the LV myocardium and 0.90 for the RV cavity. The mean absolute difference between automated measurement and manual measurement is 6.1 mL for LVEDV, 5.3 mL for LVESV, 6.9 gram for LVM, 8.5 mL for RVEDV and 7.2 mL for RVESV. On long-axis image test sets, the average Dice metric is 0.93 for the LA cavity (2-chamber view), 0.95 for the LA cavity (4-chamber view) and 0.96 for the RA cavity (4-chamber view). The performance is comparable to human inter-observer variability.</p> <h4>Conclusions</h4> <p>We show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.</p> |
| spellingShingle | Bai, W Sinclair, M Tarroni, G Oktay, O Rajchl, M Vaillant, G Lee, AM Aung, N Lukaschuk, E Sanghvi, MM Zemrak, F Fung, K Paiva, JM Carapella, V Kim, YJ Suzuki, H Kainz, B Matthews, PM Petersen, SE Piechnik, SK Neubauer, S Glocker, B Rueckert, D Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| title | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| title_full | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| title_fullStr | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| title_full_unstemmed | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| title_short | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| title_sort | automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| work_keys_str_mv | AT baiw automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT sinclairm automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT tarronig automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT oktayo automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT rajchlm automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT vaillantg automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT leeam automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT aungn automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT lukaschuke automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT sanghvimm automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT zemrakf automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT fungk automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT paivajm automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT carapellav automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT kimyj automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT suzukih automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT kainzb automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT matthewspm automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT petersense automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT piechniksk automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT neubauers automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT glockerb automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks AT rueckertd automatedcardiovascularmagneticresonanceimageanalysiswithfullyconvolutionalnetworks |