Spatial Intensity Correction of Fluorescent Confocal Laser Scanning Microscope Images.

Sang-Chul Lee and Peter Bajcsy

European Conference on Computer Vision, Workshop on Computer Vision Approaches to Medical Image Analysis (ECCV/CVAMIA 06), Graz, Austria, 2006, Lecture Notes in Computer Science 4241 p143-54 (2006).

This paper addresses the problem of intensity correction of fluorescent confocal laser scanning microscope (CLSM) images. CLSM images are frequently used in medical domain for obtaining 3D information about specimen structures by imaging a set of 2D cross sections and performing 3D volume reconstruction afterwards. However, the images of optical sections acquired from fluorescent CLSM demonstrate significant lateral intensity heterogeneity, which is well understood as one of the major barriers to accurate image analysis, e.g., quantitative analysis, segmentation, or visualization.

The main contribution of the proposed work is in development of an intensity heterogeneity correction technique that (a) adjusts intensity heterogeneity in lateral plane of the sub-volume, (b) preserves fine structural details, and (c) enhances image contrast, by performing spatially adaptive mean-weight filtering. Furthermore, we provide data-driven parameter optimization method and evaluation metrics.

The proposed filtering method is experimentally compared with several existing techniques by using four quality metrics, such as contrast, intensity heterogeneity (entropy) in low frequency domain, intensity distortion in high frequency domain, and saturation, with two realistic synthetic images and one CLSM image of a human histological section of uveal melanoma tissue.