Publications by authors named "Durgansh Sharma"

Article Synopsis
  • Medical image segmentation is more challenging than regular image segmentation due to the complexity of medical images and the difficulty in distinguishing between tumorous and non-tumorous cells.
  • The proposed solution is a deep convolutional generative adversarial network designed specifically for tumor segmentation in brain MRI images, featuring a generator and a discriminator to enhance local information extraction.
  • Experimental results show significant improvements in segmentation accuracy, achieving a 97% accuracy rate and low loss, indicating the model's effectiveness in distinguishing between tumorous and benign tissues.
View Article and Find Full Text PDF