Immediate ROI search for 3-D medical images
The objective of this work is a scalable, real-time, visual search engine for 3-D medical images, where a user is able to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images. <br> We make three contributions: (i) we show that wi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2013
|
| _version_ | 1811140209677434880 |
|---|---|
| author | Simonyan, K Modat, M Ourselin, S Cash, D Criminisi, A Zisserman, A |
| author_facet | Simonyan, K Modat, M Ourselin, S Cash, D Criminisi, A Zisserman, A |
| author_sort | Simonyan, K |
| collection | OXFORD |
| description | The objective of this work is a scalable, real-time, visual search engine for 3-D medical images, where a user is able to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images.
<br>
We make three contributions: (i) we show that with appropriate off-line processing, images can be retrieved and ROIs registered in real time; (ii) we propose and evaluate a number of scalable exemplar-based image registration schemes; (iii) we propose a discriminative method for learning to rank the returned images based on the content of the ROI. The retrieval system is demonstrated on MRI data from the ADNI dataset, and it is shown that the learnt ranking function outperforms the baseline. |
| first_indexed | 2024-09-25T04:18:21Z |
| format | Conference item |
| id | oxford-uuid:17acccf6-d5c2-4bfe-a72a-f5482a00f99e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:18:21Z |
| publishDate | 2013 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:17acccf6-d5c2-4bfe-a72a-f5482a00f99e2024-07-25T15:53:08ZImmediate ROI search for 3-D medical imagesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:17acccf6-d5c2-4bfe-a72a-f5482a00f99eEnglishSymplectic ElementsSpringer2013Simonyan, KModat, MOurselin, SCash, DCriminisi, AZisserman, AThe objective of this work is a scalable, real-time, visual search engine for 3-D medical images, where a user is able to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images. <br> We make three contributions: (i) we show that with appropriate off-line processing, images can be retrieved and ROIs registered in real time; (ii) we propose and evaluate a number of scalable exemplar-based image registration schemes; (iii) we propose a discriminative method for learning to rank the returned images based on the content of the ROI. The retrieval system is demonstrated on MRI data from the ADNI dataset, and it is shown that the learnt ranking function outperforms the baseline. |
| spellingShingle | Simonyan, K Modat, M Ourselin, S Cash, D Criminisi, A Zisserman, A Immediate ROI search for 3-D medical images |
| title | Immediate ROI search for 3-D medical images |
| title_full | Immediate ROI search for 3-D medical images |
| title_fullStr | Immediate ROI search for 3-D medical images |
| title_full_unstemmed | Immediate ROI search for 3-D medical images |
| title_short | Immediate ROI search for 3-D medical images |
| title_sort | immediate roi search for 3 d medical images |
| work_keys_str_mv | AT simonyank immediateroisearchfor3dmedicalimages AT modatm immediateroisearchfor3dmedicalimages AT ourselins immediateroisearchfor3dmedicalimages AT cashd immediateroisearchfor3dmedicalimages AT criminisia immediateroisearchfor3dmedicalimages AT zissermana immediateroisearchfor3dmedicalimages |