eduzhai > Applied Sciences > Engineering >

Perfusion Quantification from Endoscopic Videos Learning to Read Tumor Signatures

  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: Intra-operative identification of malignant versus benign or healthy tissueis a major challenge in fluorescence guided cancer surgery. We propose aperfusion quantification method for computer-aided interpretation of subtledifferences in dynamic perfusion patterns which can be used to distinguishbetween normal tissue and benign or malignant tumors intra-operatively inreal-time by using multispectral endoscopic videos. The method exploits thefact that vasculature arising from cancer angiogenesis gives tumors differingperfusion patterns from the surrounding tissue, and defines a signature oftumor which could be used to differentiate tumors from normal tissues.Experimental evaluation of our method on a cohort of colorectal cancer surgeryendoscopic videos suggests that the proposed tumor signature is able tosuccessfully discriminate between healthy, cancerous and benign tissue with 95 accuracy.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...