Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network
Protein trafficking plays a vital role in understanding many biological processes and disease. Automated tracking of protein vesicles is challenging due to their erratic behaviour, changing appearance, and visual clutter. In this paper we present a novel tracking approach which utilizes a two-step l...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2019
|
| _version_ | 1826270111348031488 |
|---|---|
| author | Dmitrieva, M Zenner, HL Richens, J Johnston, DS Rittscher, J |
| author_facet | Dmitrieva, M Zenner, HL Richens, J Johnston, DS Rittscher, J |
| author_sort | Dmitrieva, M |
| collection | OXFORD |
| description | Protein trafficking plays a vital role in understanding many biological processes and disease. Automated tracking of protein vesicles is challenging due to their erratic behaviour, changing appearance, and visual clutter. In this paper we present a novel tracking approach which utilizes a two-step linking process exploiting a probabilistic graphical model to predict tracklet linkage. The vesicles are initially detected with help of a candidate selection process, where the candidates are identified by a multi-scale spot enhancing filter. Subsequently, these candidates are pruned and selected by a light weight convolutional neural network. At the linking stage, the tracklets are formed based on the distance and the detection assignment which is implemented via combinatorial optimization algorithm. A probabilistic model, realised through a Bayesian network, is used to infer which tracklets should be linked. Tracking results are presented for confocal fluorescence microscopy data of protein trafficking in epithelial cells. The proposed method achieves a root mean square error (RMSE) of 1.39 for the vesicle localisation and α of 0.7 representing the degree of track matching with ground truth. The presented method is also evaluated against the state-of-the-art “Trackmate“ framework. |
| first_indexed | 2024-03-06T21:35:44Z |
| format | Conference item |
| id | oxford-uuid:46325b78-264c-4d4b-b94d-c3b2e5e34379 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T21:35:44Z |
| publishDate | 2019 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:46325b78-264c-4d4b-b94d-c3b2e5e343792022-03-26T15:12:17ZProtein tracking by CNN-based candidate pruning and two-step linking with Bayesian networkConference itemhttp://purl.org/coar/resource_type/c_5794uuid:46325b78-264c-4d4b-b94d-c3b2e5e34379EnglishSymplectic ElementsIEEE2019Dmitrieva, MZenner, HLRichens, JJohnston, DSRittscher, JProtein trafficking plays a vital role in understanding many biological processes and disease. Automated tracking of protein vesicles is challenging due to their erratic behaviour, changing appearance, and visual clutter. In this paper we present a novel tracking approach which utilizes a two-step linking process exploiting a probabilistic graphical model to predict tracklet linkage. The vesicles are initially detected with help of a candidate selection process, where the candidates are identified by a multi-scale spot enhancing filter. Subsequently, these candidates are pruned and selected by a light weight convolutional neural network. At the linking stage, the tracklets are formed based on the distance and the detection assignment which is implemented via combinatorial optimization algorithm. A probabilistic model, realised through a Bayesian network, is used to infer which tracklets should be linked. Tracking results are presented for confocal fluorescence microscopy data of protein trafficking in epithelial cells. The proposed method achieves a root mean square error (RMSE) of 1.39 for the vesicle localisation and α of 0.7 representing the degree of track matching with ground truth. The presented method is also evaluated against the state-of-the-art “Trackmate“ framework. |
| spellingShingle | Dmitrieva, M Zenner, HL Richens, J Johnston, DS Rittscher, J Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network |
| title | Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network |
| title_full | Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network |
| title_fullStr | Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network |
| title_full_unstemmed | Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network |
| title_short | Protein tracking by CNN-based candidate pruning and two-step linking with Bayesian network |
| title_sort | protein tracking by cnn based candidate pruning and two step linking with bayesian network |
| work_keys_str_mv | AT dmitrievam proteintrackingbycnnbasedcandidatepruningandtwosteplinkingwithbayesiannetwork AT zennerhl proteintrackingbycnnbasedcandidatepruningandtwosteplinkingwithbayesiannetwork AT richensj proteintrackingbycnnbasedcandidatepruningandtwosteplinkingwithbayesiannetwork AT johnstonds proteintrackingbycnnbasedcandidatepruningandtwosteplinkingwithbayesiannetwork AT rittscherj proteintrackingbycnnbasedcandidatepruningandtwosteplinkingwithbayesiannetwork |