Immediate structured visual search for medical images
The objective of this work is a scalable, real-time visual search engine for medical images. In contrast to existing systems that retrieve images that are globally similar to a query image, we enable the user to select a query Region Of Interest (ROI) and automatically detect the corresponding regio...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2011
|
| _version_ | 1824458922621140992 |
|---|---|
| author | Simonyan, K Zisserman, A Criminisi, A |
| author_facet | Simonyan, K Zisserman, A Criminisi, A |
| author_sort | Simonyan, K |
| collection | OXFORD |
| description | The objective of this work is a scalable, real-time visual search engine for medical images. In contrast to existing systems that retrieve images that are globally similar to a query image, we enable the user to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images. This allows the returned images to be ranked on the content of the ROI, rather than the entire image. Our contribution is two-fold: (i) immediate retrieval - the data is appropriately pre-processed so that the search engine returns results in real-time for any query image and ROI; (ii) structured output - returning ROIs with a choice of ranking functions. The retrieval performance is assessed on a number of annotated queries for images from the IRMA X-ray dataset and compared to a baseline. |
| first_indexed | 2025-02-19T04:33:35Z |
| format | Conference item |
| id | oxford-uuid:b3548577-114b-4e09-ac23-5833b1d9ac33 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:33:35Z |
| publishDate | 2011 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:b3548577-114b-4e09-ac23-5833b1d9ac332025-01-14T11:17:08ZImmediate structured visual search for medical imagesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:b3548577-114b-4e09-ac23-5833b1d9ac33EnglishSymplectic ElementsSpringer2011Simonyan, KZisserman, ACriminisi, AThe objective of this work is a scalable, real-time visual search engine for medical images. In contrast to existing systems that retrieve images that are globally similar to a query image, we enable the user to select a query Region Of Interest (ROI) and automatically detect the corresponding regions within all returned images. This allows the returned images to be ranked on the content of the ROI, rather than the entire image. Our contribution is two-fold: (i) immediate retrieval - the data is appropriately pre-processed so that the search engine returns results in real-time for any query image and ROI; (ii) structured output - returning ROIs with a choice of ranking functions. The retrieval performance is assessed on a number of annotated queries for images from the IRMA X-ray dataset and compared to a baseline. |
| spellingShingle | Simonyan, K Zisserman, A Criminisi, A Immediate structured visual search for medical images |
| title | Immediate structured visual search for medical images |
| title_full | Immediate structured visual search for medical images |
| title_fullStr | Immediate structured visual search for medical images |
| title_full_unstemmed | Immediate structured visual search for medical images |
| title_short | Immediate structured visual search for medical images |
| title_sort | immediate structured visual search for medical images |
| work_keys_str_mv | AT simonyank immediatestructuredvisualsearchformedicalimages AT zissermana immediatestructuredvisualsearchformedicalimages AT criminisia immediatestructuredvisualsearchformedicalimages |