マルチモダリティ画像を用いた包括的画像処理による肝臓病変の鑑別

概要

論文の詳細を見る
Recently, imaging techniques such as high magnetic field imaging and multidetector-row CT provides remarkable improvement in diagnosis. However, the latest imaging systems easily produce more than a thousand diagnostic images per patient. Image reading of a huge number of multi-modality images by use of a multi-formatted display and/or stack display method would be a hard work for radiologists. Therefore, we have developed a pixel-based comprehensive image processing method for the differential diagnosis of liver diseases by using multi-modality images. In this scheme, the criteria of an attendant radiologist for differential diagnosis for normal liver, cyst, hemangioma, hepatocellular carcinoma, and metastatic cancer on magnetic resonance images with various sequences and computed tomography images with and without contrast enhancement are employed. Total of 40 cases which including 10 cysts, 10 hemangiomas, 10 hepatocellular carcinomas, and 10 metastatic cancers are used in this study. The liver diseases could be correctly detected in all cases. The comprehensive image processing technique could assist radiologists for the differential diagnosis of the liver diseases.
医用画像情報学会の論文