| EPSRC Reference: |
GR/M72289/01 |
| Title: |
COMBINING OPTICAL AND ULTRASOUND IMAGING FOR SKIN LESION DIAGNOSIS FOR EVENTUAL USE AT PRIMARY CARE LEVEL |
| Principal Investigator: |
Fish, Professor P |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Electronics |
| Organisation: |
Bangor University |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 January 2000 |
Ends: |
30 April 2003 |
Value (£): |
175,347
|
| EPSRC Research Topic Classifications: |
| Image & Vision Computing |
Instrumentation Eng. & Dev. |
|
| EPSRC Industrial Sector Classifications: |
| Healthcare |
No relevance to Underpinning Sectors |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
It is proposed to investigate a combination of high frequency ultrasound and optical imaging with a view to determining whether such a system could form the basis of a primary-care diagnostic aid. New kinds of microscopic ultrasonic images will be produced of surface reflection, attenuation and skin topography, which may be viewed and analysed in registration with the optical skin surface micrograph. Improved methods of hair-image and specular reflection artefact removal will be explored together with correction for non-uniform illumination and limited depth of focus in optical images. Optical image segmentation (boundary detection) based on edge-focusing will be compared with snakes and a new colour region-based agglomerative clustering (mRAC) method. Segmentation will be used to guide automatic feature extraction from both optical and ultrasound images. Skin pattern disruption (greater by malignant lesions) measured from the optical image and ultrasound profilometry will be quantified and compared. A set of lesion features (size, bulkiness, asymmetry, edge acutance, boundary fractal dimension, degree and area of inflammation and degree of skin pattern disruption, intensity, texture, lesion:background contrast) from the optical and ultrasound images will be used in a multivariate analysis to predict lesion type from a set of lesions of known histological type.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.bangor.ac.uk |