2. IMAGE ACQUISITION 2D images
All images were acquired using a standard microscope. All 2D images were acquired by sample translation and collected either manually or automatically using the motorised stage. Three types of 2D images were acquired. These include the images of histology, fluorescent cells as part of a comet array (comet cells) and in vivo blood vessels. The setup specification for these images is summarised in Table 1. CCD cameras were used to acquire the images with either a IEEE 1394 interface or using a PCI frame grabber (type: by National Instruments, UK). The imaging area is of the order of 1x1 mm2 when using objective x10. CCD cameras introduce two noise effects. One is a dark current and another is a non-uniform pixel response. In order to cancel out the dark current effect, images acquired with no light were subtracted from images of the sample. For cancellation of the non-uniform pixel response, the image of the sample is divided by a blank image acquired with standard illumination of a clean slide. Lens aberrations are also present. All imaging systems, due to such aberrations, suffer to a greater or lesser extent from barrel or pincushion distortion, or their combination. The most difficult conditions for image stitching are those with wide range of ambient lighting i.e. Proceedings of SPIE -- Volume 5701
Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XII,Jose-Angel Conchello, Carol J. Cogswell, Tony Wilson, Editors, March 2005 192 with a large intensity span - spatially varying illumination. It is assumed that rotation and scaling stay the same throughout both the experiments and processing the images. Only translation errors need to be corrected during the stitching process. Table 1 Summary of the setup specification used for the image acquisition 3D images
For the acquisition of 3D images the following setup was used. A Nikon TE
200 fluorescence microscope was used with a modified stage to accommodate rodents. Our in vivo blood vessel images were acquired through a window chamber arrangement. It consists of double sided aluminium frame holding two parallel glass windows. It is located centrally above the objectives [14]. Tumour angiogenesis and vascular response to treatment in both the morphology of blood vessel networks and the function of individual vessels have been investigated using the window chamber. Multi-photon microscopy techniques have been applied to obtain 3D images of tumour vasculature [15], as these techniques are shown to be highly effective in obtaining three-dimensional biological images. The multi-photon microscope system is based on Bio-Rad MRC 1024MP workstation and consists of a solid-statepumped (10W Millennia X, Nd:YVO4, Spectra-Physics), self-mode-locked Ti:Sapphire (Tsunami, Spectra-Physics) laser system, a focal scan-head, confocal detectors and an inverted microscope (Nikon TE200) [15]. Multi-photon microscopy can accurately locate fluorescence within a 3D volume and can be successfully applied to the analysis of vascular morphology. Usually a small tumour (few millimetres in diameter) was implanted into the skin in the window chamber. The whole tumour vasculature was imaged for most experiments. Images were taken with 10X objective for all but the smallest tumours and image covered approximately 1.3x1.3 mm tissue. Stacks of images are taken with a typical stack of 50 slices. It takes typically 13 minutes to acquire images for an entire stack. 3. IMAGE PROCESSING - METHODOLOGY
There are two main stages in processing these images: 1) Image stitching
Stitching is performed by sliding the new image over the composite image and finding the best cross-correlation point. 2) Image blending
Blending was done by separating colour planes, where necessary, applying blending algorithm for each colour band and
recomposing planes together to get full colour image at the output. The blended images should maintain the quality of the input images [16]. These processes are explained in detail below and refer to 2D images unless specified that they refer to 3D images. Algorithms were developed in C programming language under LabWindows/CVI 7.0 (National Instruments) development environment, using IMAQ Image Processing Library and Windows XP Professional operating system. The algorithms are completely automated and they have been tested on a PC with processor speed 1.53GHz and 448MB of RAM.
3.1 Stitching method
In the presented algorithm the stitching is performed by image translation only. The applied procedure can be referred to as mosaicing, tiling, montaging or stitching. The first step is the generation of relative positions of acquired images and the creation of an empty image array in computer memory where these images will be placed. The next step is a search for the point of best correlation which is performed by sliding adjacent image edges in both directions until the best match of edge features is found. This search process requires the choice of an optimum search space shown in Figure 1, in which a search is performed for the best correlation. The use of too many pixels inside this box makes the correlation process time consuming whilst too few pixels reduce the quality of match. The choice of number of pixels used is strongly related to the dimensions of features expected to be visible in the image which in turn depends on focus quality, i.e. on the maximum spatial frequencies present in the image.