Bautista Pinky A, Yagi Yukako
Department of Pathology Harvard Medical School, Boston, MA 02114, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:3669-72. doi: 10.1109/IEMBS.2009.5334529.
In whole slide imaging (WSI) the quality of scanned images is an interplay between the hardware specifications of the scanning device and the condition of the tissue slide itself. Tissue artifacts such as folds and bubbles have been known to affect the efficiency of a whole slide scanning system in selecting the focus points wherein the presence of the said artifacts have been found to produce blur or unfocused images. Thus, for a whole slide scanning device to produce the best image quality, even with the presence of tissue artifacts, information on the location of these artifacts should be known such that they can be avoided in the selection of the focus points. In this paper we introduced an enhancement method to emphasize and detect the location of the tissue folds from whole slide images. Results of the experiments that we conducted on various H&E stained images that were scanned using different scanners show the robustness of the method to detect tissue folds.
在全切片成像（WSI）中，扫描图像的质量是扫描设备的硬件规格与组织切片本身状况之间相互作用的结果。诸如褶皱和气泡等组织伪像已知会影响全切片扫描系统在选择焦点时的效率，在这些伪像存在的情况下会产生模糊或失焦的图像。因此，对于全切片扫描设备而言，即使存在组织伪像，若要产生最佳图像质量，也应了解这些伪像的位置信息，以便在选择焦点时能够避开它们。在本文中，我们介绍了一种增强方法，用于从全切片图像中突出并检测组织褶皱的位置。我们在使用不同扫描仪扫描的各种苏木精-伊红（H&E）染色图像上进行的实验结果表明，该方法在检测组织褶皱方面具有稳健性。
