超音波断層像の動画像処理による検査手技支援のための心臓断層面認識(<特集>生体医工学シンポジウム2005)

概要

論文の詳細を見る
Examination by echography greatly depends on the expertise and experience of the operator, though there is no research to assist the handler of the ultrasound probe. If cross sections of internal organs are automatically recognized from the echogram, it is possible to provide a position feedback system for the operator, which may also act as a guidance system for inexperienced operators. We have developed an algorithm to recognize a cross section of the heart from successive echograms. We first divided an echogram into sub-regions and detected the position of the mitral valve by the analyzing brightness variation and the correlation coefficient between sub-regions. We confirmed that recognition of the mitral valve corresponds to the motion of the ultrasound probe with reliable accuracy. Furthermore, combining this technique with an optical flow method, we elucidated the contract velocity of wall motion in eight radial regions by centering the mitral valve. Finally, we recognized a short-axis view of the heart by comparing the correlation of the contraction velocity between specified regions.
社団法人日本生体医工学会の論文
2006-03-10