Stephen Batty

Prototype System for Semantic Retrieval of Neurological PET Images

Positron Emission Tomography (PET) is used within neurology to study the underlying biochemical basis of cognitive functioning. Due to the inherent lack of anatomical information its study in conjunction with image retrieval is limited. Content based image retrieval (CBIR) relies on visual features to quantify and classify images with a degree of domain specific saliency. Numerous CBIR systems have been developed semantic retrieval, has however not been performed. This paper gives a detailed account of the framework of visual features and semantic information utilized within a prototype image retrieval system, for PET neurological data. Images from patients diagnosed with different and known forms of Dementia are studied and compared to controls. Image characteristics with medical saliency are isolated in a top down manner, from the needs of the clinician - to the explicit visual content. These features are represented via Gabor wavelets and mean activity levels of specific anatomical regions. Preliminary results demonstrate that these representations are effective in reflecting image characteristics and subject diagnosis; consequently they are efficient indices within a semantic retrieval system.

Content based retrieval of lesioned brain images

HI-PACS enable more efficient data-management leading to increased operating efficiency and therefore better patient care, a content based pet image retrieval system would contribute to the development of a HI-PACS. A database of PET neuro-images has been created with a facility for retrieving via visual content. The adaptation of algorithms developed for alternate imaging modalities (eg-MRI) formed the basis of feature detection and measurement algorithms. The application of these algorithms to greyscale PET images results in data that is employed as database indices and similarity metrics. The feature detection and measurement algorithms can be split into two different methods. The first uses the extracted ideal mid sagittal symmetry line to detect differences between the two hemisphere of the brain, while the second utilizes Gabor filters to measure the texture of the whole brain.