Image Segmentation by Multi-shape GC-OAAM

Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. The liver image is segmented by using confusion algorithm. The performance is improved by the implementation of multiple MTANN. The MTANN supervised filter was effective for enhancement in medical images and is useful for improving the sensitivity and specificity. Multi-shape GC – OAAM segmentation methods have implemented on abdomen MRI and edge detection on liver image. It improves the object delineation time than the existing method. This approach for segmentation of medical images can help in the proper detection of the region of interest and also can be very helpful for doctor’s diagnoses, medical teaching, learning and research. The salient feature of the algorithm is that it can automatically choose an optimal shape prior from among multiple priors at each voxel by minimizing the proposed sub-modular energy function. The minimization is per-formed in a sequential manner by the fusion move algorithm that uses the QPBO min-cut algorithm. Multi-shape GCs are proven to be more beneficial than single-shape GCs. Hence, the segmentation methods are validated by calculating statistical measures. The false positive (FP) is reduced and sensitivity and specificity improved by multiple MTANN. The comparative performance analysis is done between GC-OAAM and MTANN outputs. The performance of the MTANN is directly applied to the false positives. The multi resolution decomposition/composition techniques with two down/up-sampling steps allowed MTANNs to support a 28.8-by-28.8 mm square region.