Grant: Engage Grants Program
Simon Fraser University
$24,200.00
Similar medical image retrieval by feature extraction
EF 2013-14
Résumé
McKesson Medical Imaging provides diagnostic imaging software tools to radiologists and cardiologists, andturnkey medical imaging management systems for hospitals and imaging centres. Radiologists use the softwareto display imaging 'studies', taken during a patient imaging exam, review and interpret the images forpathologies, and create a report of findings for the referring doctor and the patient. To obtain additional insightinto the current study being interpreted, a radiologist often wants to refer to other known cases through ateaching case system where real studies have been anonymized, vetted and prepared for training, or throughperforming a search of the database of images in their imaging system. This search is currently limited to textsearch, with the best systems going beyond simple keyword matching to use synonyms, phrase matching, andsimple Natural Language Processing (NLP) techniques.A significant advancement would be to provide tools to the radiologist enabling them to define an image orregion of interest within the image, and have the system find a set of 'closest matches' to this image in thedatabase. The search can use structured meta-data from the study, such as same modality, acquisitionparameters, exam types etc., that are usually provided with the images (DICOM header) to limit the searchspace. Due to large content of image data instead of actual pixel values, other higher-level image abstraction,based on pixel distribution, edge structures, shapes and other feature sets need to be used. An image-matchingsearch can then search this abstracted feature space to return a ranked list based on similarity.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
460825-2013
Name nom
Beg, MirzaFaisal
Department département
Engineering Science, School of
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
Award amount
24200
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
Area of application code
1102
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Biomedical engineering
Area of application fr
Génie biomédical
Research subject code
1900
Research subject group en
Biomedical engineering
Research subject group fr
Génie biomédical
Research subject en
Biomedical engineering
Research subject fr
Génie biomédical
Partie
1
Nb partie
1
Application title
Similar medical image retrieval by feature extraction
Keyword
NSERC
Application summary
McKesson Medical Imaging provides diagnostic imaging software tools to radiologists and cardiologists, andturnkey medical imaging management systems for hospitals and imaging centres. Radiologists use the softwareto display imaging 'studies', taken during a patient imaging exam, review and interpret the images forpathologies, and create a report of findings for the referring doctor and the patient. To obtain additional insightinto the current study being interpreted, a radiologist often wants to refer to other known cases through ateaching case system where real studies have been anonymized, vetted and prepared for training, or throughperforming a search of the database of images in their imaging system. This search is currently limited to textsearch, with the best systems going beyond simple keyword matching to use synonyms, phrase matching, andsimple Natural Language Processing (NLP) techniques.A significant advancement would be to provide tools to the radiologist enabling them to define an image orregion of interest within the image, and have the system find a set of 'closest matches' to this image in thedatabase. The search can use structured meta-data from the study, such as same modality, acquisitionparameters, exam types etc., that are usually provided with the images (DICOM header) to limit the searchspace. Due to large content of image data instead of actual pixel values, other higher-level image abstraction,based on pixel distribution, edge structures, shapes and other feature sets need to be used. An image-matchingsearch can then search this abstracted feature space to return a ranked list based on similarity.