A fuzzified model for soft tissue prediction using a knowledge-based deep learning approach

Abstract

Medical image analysis gains huge advancements with deep learning approaches which boosts the computational capability and accurate prediction. An expert in the field analyzes the feature representation, and an intelligent model helps to categorize and forecast diseases. The MRI images from cancer imaging archives are used to give a novel learning approach for soft tissue diagnosis. This work suggests a Type-2 fuzzy model that chooses local and maximum absolute value to handle the data. According to the experimental investigation, the predicted model works better than several current strategies. Deep convolutional neural networks built on the VGG-16 architecture and the Adam optimizers are used to pre-train the proposed model. The classification accuracy is anticipated based on the experimentation, demonstrating the need for complementary information for learning systems. The goal is to forecast the depth of knowledge extraction by boosting pre-trained CNN’s ability to be fine-tuned by improving the accuracy of soft tissue classification. The proposed model improves performance and validates the significance of the network model by categorizing the tissues as benign or cancerous. The proposed model attains 96.8% accuracy and 9% for depths of 5 and 8 mm and 93% for 10 mm. Similarly, the model attains 96.8% without inclusion, 100% with inclusion and an average outcome of 99%.