• Prof.Dr.Ramana (Naik) Banothu
• Dr A ArunKumar

Abstract: One of the most essential technologies for computed tomography is medical image segmentation. As a result, image segmentation is critical in image-guided surgery, both in terms of benefits and drawbacks. Traditional machine learning methods have aided in the segmentation of medical images, but they suffer from limitations such as low classification accuracy and robustness. Medical image segmentation problems are solved anew using deep learning theory because of its good generalizability and ability to extract features. To solve these challenges, we adapt a normal neural network to medical imaging properties by adding cross-layer connections to a standard CNN. In addition, a better version of the CNN is being developed. Medical images can be segmented using data from two scales at the same time by optimising a CNN model. A new approach for medical picture segmentation is proposed that uses an optimised CNN and an adjustable dropout depth computation. The kernel approach was created by support vector machines (SVMs), and it has since received a lot of attention. We describe a spatially contextualised kernel-based approach for clustering image data. This approach improves the objective function in the traditional fuzzy c-means algorithm by utilising a kernel-induced distance metric and a spatial penalty term that accounts for the influence of the surrounding pixels on the centre pixel. The study reported in this article attempts to look at medical image segmentation.

Kernel method; CNN; multi-hyperbolic tangent function; Segmentation; fuzzy; multi-modality fusion.

"INTEGRATION OF DIFFERENT KERNELS FOR NEURO FUZZY BASED CONCEPT USING FOR MRI MEDICAL IMAGE SEGMENTATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 12, page no.f132-f141, December-2021, Available :http://www.jetir.org/papers/JETIR2112516.pdf

"INTEGRATION OF DIFFERENT KERNELS FOR NEURO FUZZY BASED CONCEPT USING FOR MRI MEDICAL IMAGE SEGMENTATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 12, page no. ppf132-f141, December-2021, Available at : http://www.jetir.org/papers/JETIR2112516.pdf