Adaptive-sized residual fusion network-based segmentation of biomedical images

Medical imaging is crucial in examinations and for providing appropriate patient care. Medical images are used to diagnose and identify specific conditions. However, the diagnostic procedures are confounded by the complexity of these images, which have several overlapping characteristics. Various techniques have enhanced biomedical image segmentation, and strategies to improve the contrast and accuracy of medical images have been presented in the literature. This article presents a recurrent grasshopper herd-based optimized histogram-based contrast enhancement technique, in which sharp-edge morphological characteristics can be enhanced using inclusive Laplacian fractional order Savitzky-Golay differentiation. An adaptive-sized residual fusion network approach is used to isolate the target tissue in the biomedical image. The effectiveness of the proposed system is verified using different medical data sets and a high level of accuracy is achieved. The proposed method outperforms other state-of-the-art methodologies in terms of the scale, shape and morphological attributes of the medical image.