Segmentation and Classification for fusion HCC Biopsy Images(International Forum on Medical Imaging in Asia 2009 (IFMIA 2009))

概要

論文の詳細を見る
The grading of pathological biopsy is very important in prognosis and treatment planning for hepatocellular carcinoma. Nevertheless, the grading results interpreted by pathologists are very subject to interobserver and intraobserver variability. Therefore, providing a quantitative analysis by machine vision is thus necessary. However, the cells on the biopsy are not all in the some depth of focus under the microscope. The small variances of depth focus cause some of cells in captured images to become a blur. These cells may not be segmented from image or segmented with error shape by the machine and thus affect the grading results. Consequently, "an all-in-focus image" is very useful to the HCC grading performed by the machine. In this paper, we proposed an approach to fusion two images with different depth focus into one image, which contains much more in-depth focus cells. In our experiments, we demonstrate that the fusion images not only have clear appearance of cells but also provide higher accuracy of grading than original images.
社団法人電子情報通信学会の論文
2009-01-12