Interactive Medical Image Segmentation Using Deep Learning with Image-Specific Fine Tuning

Abstract:

           DEEP learning with convolution neural networks (CNNs) has achieved state-of-the-art performance for automated medical image segmentation. However, automatic segmentation methods have not demonstrated sufficiently accurate and robust results for clinical use due to the inherent challenges of medical images, such as poor image quality, different imaging and segmentation protocols and variations among patients. Interactive segmentation often requires image specific learning to deal with large context variations among different images but current CNNs are not adaptive to different test images, as parameters of the model are learned from training images and then fixed in the testing stage without image specific adaptation. The Proposed system focus on interactive tumor segmentation of medical image sequences using deep neural network. The proposed work utilizes pattern based classification using neural network function. Adaptive Hirerical motion segmentation is designed in the proposed area.

Proposed System:

             The Proposed system focus on interactive tumor segmentation of medical image sequences using deep neural network. The proposed work utilizes pattern based classification using neural network function. Adaptive Hirerical motion segmentation is designed in the proposed area. The term adaptive means that the threshold required for segmenting adjust itself according to the segmented area and position.