Syntactic analysis and languages of shape feature description in computer-aided diagnosis and recognition of cancerous and inflammatory lesions of organs in selected x-ray images

We present new algorithms for the recognition of morphologic changes and sh ape feature analysis, which have been proposed to be used in a diagnosis of pathologic symptoms characteristic of cancerous and inflammatory lesions, These methods have been used so far for early detection and diagnosis of ne oplastic changes in pancreas and chronic pancreatitis based on x-ray images acquired by endoscopic retrograde cholangiopancreatography (ERCP). Prelimi nary processing of x-ray images involves binarization, and, subsequently, p ancreatic ducts shown in the pictures are subjected to the straightening tr ansformation, which enables obtaining two-dimensional width graphs that sho w contours of objects with their morphologic changes. Recognition of such c hanges was performed using attributed context-free grammars. Correct descri ption and diagnosis of some symptoms leg, large cavitary projections) requi red two-dimensional analysis of width graphs. In such cases, languages of s hape feature description with special multidirectional sin-quad distributio n were additionally applied. Copyright (C) 1999 by W.B. Saunders Company.