成果報告書詳細
管理番号20120000001178
タイトル*平成23年度中間年報 「がん超早期診断・治療機器の総合研究開発/超早期高精度診断システムの研究開発:病理画像等認識技術の研究開発/病理画像等認識基礎技術の研究開発(定量的病理診断を可能とする病理画像認識技術)」
公開日2012/12/19
報告書年度2011-2011
委託先名学校法人埼玉医科大学
プロジェクト番号P10003
部署名バイオテクノロジー・医療技術部
和文要約和文要約等以下本編抜粋:
肝臓癌などの病理組織診断において病理画像を用いた支援装置の開発が求められている。本プロェクトは、がん組織の定量的解析可能な「定量的病理診断」技術の確立を目的としている。
英文要約Title: Research and Development Project for pathological image recognition technology, Research and Development Project to develop basic technologies for recognizing pathology images, Pathological image analysis technology to enable a quantitative pathological diagnosis, (FY2010-FY2012) FY2011 Annual Report
(1) Research and Development of Image Recognition and Quantification Technology for Pathological Images: The development of the computer-aided system for a pathological image-reading is needed in order to support pathologist. The goal of our project is to establish the quantification method for hepatocellular carcinoma. The HE stained image of hepatocellular carcinoma have many features in multiple image resolution levels. Thus the area segmentation preprocessing is effective to analyze images in an appropriate image resolution for each part. In this study, segmentation method for hepatic fat microvesicles using a self-organizing map is developed this fiscal year. Addition to the method, the circularity measurement and the separation technique for combined fat microvesicles were effective to increase accuracy of segmentation. The experimental results show a basic ability for quantification of steatosis areas. The steatosis hepatic quantification program for whole-slide image was also developed. The program can count the all fat microvesicles and calculate their area ratio.
(2) Development of High Quality Image Compression Technology for Pathological Images: Image compression is necessary for pathological images because the raw images of 1G bytes are too large to storage and to analyze. We studied an evaluation method of image compression for pathological image analysis, and developed high quality image compression method using characters of HE stained pathological images this fiscal year. In the first study, we clarify relationships between compressed image quality and color space image processing errors caused by image compression. We also show the tolerance to image compression artifacts on pathological image abstraction using pixel color. As the second theme, we proposed and developed image compression method using color space pre-processing based on localization of color space value in HE stained image. This method has merits to make high compressed image quality and to have compatibility with JPEG and JPEG2000.
ダウンロード成果報告書データベース(ユーザ登録必須)から、ダウンロードしてください。

▲トップに戻る