Going deeper into cardiac motion analysis to model fine spatio-temporal features
This paper shows that deep modelling of subtle changes of cardiac motion can help in automated diagnosis of early onset of cardiac disease. In this paper, we model left ventricular (LV) cardiac motion in MRI sequences, based on a hybrid spatio-temporal network. Temporal data over long time periods i...
| Glavni autori: | , , , , , |
|---|---|
| Daljnji autori: | |
| Format: | Conference item |
| Jezik: | English |
| Izdano: |
Springer
2020
|
| _version_ | 1826289227206230016 |
|---|---|
| author | Lu, P Qiu, H Qin, C Bai, W Rueckert, D Noble, JA |
| author2 | Papiez, BW |
| author_facet | Papiez, BW Lu, P Qiu, H Qin, C Bai, W Rueckert, D Noble, JA |
| author_sort | Lu, P |
| collection | OXFORD |
| description | This paper shows that deep modelling of subtle changes of cardiac motion can help in automated diagnosis of early onset of cardiac disease. In this paper, we model left ventricular (LV) cardiac motion in MRI sequences, based on a hybrid spatio-temporal network. Temporal data over long time periods is used as inputs to the model and delivers a dense displacement field (DDF) for regional analysis of LV function. A segmentation mask of the end-diastole (ED) frame is deformed by the predicted DDF from which regional analysis of LV function endocardial radius, thickness, circumferential strain (Ecc) and radial strain (Err) are estimated. Cardiac motion is estimated over MR cine loops. We compare the proposed technique to two other deep learning-based approaches and show that the proposed approach achieves promising predicted DDFs. Predicted DDFs are estimated on imaging data from healthy volunteers and patients with primary pulmonary hypertension from the UK Biobank. Experiments demonstrate that the proposed methods perform well in obtaining estimates of endocardial radii as cardiac motion-characteristic features for regional LV analysis. |
| first_indexed | 2024-03-07T02:25:40Z |
| format | Conference item |
| id | oxford-uuid:a57d651e-d164-403d-9def-9f11822c7f47 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:25:40Z |
| publishDate | 2020 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:a57d651e-d164-403d-9def-9f11822c7f472022-03-27T02:41:00ZGoing deeper into cardiac motion analysis to model fine spatio-temporal featuresConference itemhttp://purl.org/coar/resource_type/c_5794uuid:a57d651e-d164-403d-9def-9f11822c7f47EnglishSymplectic ElementsSpringer2020Lu, PQiu, HQin, CBai, WRueckert, DNoble, JAPapiez, BWNamburete, AILYaqub, MNoble, JAThis paper shows that deep modelling of subtle changes of cardiac motion can help in automated diagnosis of early onset of cardiac disease. In this paper, we model left ventricular (LV) cardiac motion in MRI sequences, based on a hybrid spatio-temporal network. Temporal data over long time periods is used as inputs to the model and delivers a dense displacement field (DDF) for regional analysis of LV function. A segmentation mask of the end-diastole (ED) frame is deformed by the predicted DDF from which regional analysis of LV function endocardial radius, thickness, circumferential strain (Ecc) and radial strain (Err) are estimated. Cardiac motion is estimated over MR cine loops. We compare the proposed technique to two other deep learning-based approaches and show that the proposed approach achieves promising predicted DDFs. Predicted DDFs are estimated on imaging data from healthy volunteers and patients with primary pulmonary hypertension from the UK Biobank. Experiments demonstrate that the proposed methods perform well in obtaining estimates of endocardial radii as cardiac motion-characteristic features for regional LV analysis. |
| spellingShingle | Lu, P Qiu, H Qin, C Bai, W Rueckert, D Noble, JA Going deeper into cardiac motion analysis to model fine spatio-temporal features |
| title | Going deeper into cardiac motion analysis to model fine spatio-temporal features |
| title_full | Going deeper into cardiac motion analysis to model fine spatio-temporal features |
| title_fullStr | Going deeper into cardiac motion analysis to model fine spatio-temporal features |
| title_full_unstemmed | Going deeper into cardiac motion analysis to model fine spatio-temporal features |
| title_short | Going deeper into cardiac motion analysis to model fine spatio-temporal features |
| title_sort | going deeper into cardiac motion analysis to model fine spatio temporal features |
| work_keys_str_mv | AT lup goingdeeperintocardiacmotionanalysistomodelfinespatiotemporalfeatures AT qiuh goingdeeperintocardiacmotionanalysistomodelfinespatiotemporalfeatures AT qinc goingdeeperintocardiacmotionanalysistomodelfinespatiotemporalfeatures AT baiw goingdeeperintocardiacmotionanalysistomodelfinespatiotemporalfeatures AT rueckertd goingdeeperintocardiacmotionanalysistomodelfinespatiotemporalfeatures AT nobleja goingdeeperintocardiacmotionanalysistomodelfinespatiotemporalfeatures |