We present an initial study analysing the surface morphology of colorectal polyps from optical projection tomography. The differential geometry of polyp surfaces, segmented using a level sets method, is explored in terms of local, multi-scale shape index and curvedness descriptors. A surface region of interest can be represented using histograms of these descriptors. An experiment is described investigating the ability to predict pit pattern categories from these histograms using support vector machines.
|Title of host publication||Medical Image Understanding and Analysis|
|Subtitle of host publication||MIUA|
|Editors||Constantino Reyes-Aldasoro, Greg Slabaugh|
|Place of Publication||United Kingdom|
|Publisher||British Machine Vision Association and Society for Pattern Recognition|
|Number of pages||6|
|Publication status||Published - Jul 2014|
|Event||18th Annual Conference in Medical Image Understanding and Analysis - Moore Complex, Royal Holloway, London, United Kingdom|
Duration: 9 Jul 2014 → 11 Jul 2014
|Conference||18th Annual Conference in Medical Image Understanding and Analysis|
|Abbreviated title||MIUA 2014|
|Period||9/07/14 → 11/07/14|
Zhang, J., McKenna, S. J., Zhang, J., Coats, M., & Carey, F. A. (2014). Analysing the Surface Morphology of Colorectal Polyps: Differential Geometry and Pit Pattern Prediction. In C. Reyes-Aldasoro, & G. Slabaugh (Eds.), Medical Image Understanding and Analysis: MIUA (pp. 67-72). British Machine Vision Association and Society for Pattern Recognition.