Active contour for overlap resolution using watershed based initialization (acorew): Applications to histopathology. Sahirzeeshan Ali and Anant Madabhushi.The segmentation accuracy is compared to that of Geodesic active contours, based on the ground truth generated by expert pathologist. The study performed over the Benign and Malignant tissue images from BreakHis dataset has shown the efficacy of the methodology in terms of object detection accuracy and overlap resolution. The result of watershed transformation is used compute the centroid of nuclei to serve the initialization of the contour and the proposed gradient to drive the same efficiently. An Expectation Maximization based morphologically precomputed shape prior is used to extract the foreground markers, which controls the watershed transformation. In this research, a novel approach of driving the contours of distance regularized level sets using an improved watershed transformation, has been presented. With the advent of various imaging studies over a digitized Histopathological image, Active contour based segmentation approaches are considered to be much potential scheme in detecting the nuclei within occlusions and extracting their irregular boundaries. The change in shape and size of the nuclei objects (nuclear pleomorphism) contributes much significantly in grading the cancer.
The microscopic observation of H&E stained histopathological slides involves the study of various tissue objects and their significant traits influencing the cancer grading. Detection of significant biomarker has been a major issue in the pathological study of cancerous tissue.
0 kommentar(er)
