A System for Prediction and Analysis of Cancer Disease Using DL Algo

The accurate prediction and analysis of cancer disease plays a crucial role in improving patient outcomes and treatment planning. In this dissertation, the model for the prediction and analysis of cancer using deep learning algorithms, specifically Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN), with the utilization of PET/CT images. The system aims to enhance the accuracy and efficiency of cancer diagnosis and provides valuable insights for decisions regarding treatment. The system leverages the power of deep learning models which are known to provide valuable information about cancer metabolism and anatomical structures. By training CNN models on a large dataset of annotated PET/CT images, the system can learn to recognize patterns and characteristics indicative of cancerous regions. To evaluate the accuracy of the system, performance metrics such as Intersection over Union (IoU) and F-measure are employed. IoU measures the overlap between the predicted cancer regions and ground truth annotations, while F-measure assesses the balance between precision and recall of the predictions. These metrics provide quantitative measures of the system's performance.

Autorentext

O Prof. Prathamesh S. Birajdar trabalha como professor assistente no Departamento de CSE da SSWCOE, Solapur, e tem um total de 4 anos de experiência. Dr. Somnath B. Thigale tem mais de 17 anos de experiência e trabalha atualmente como Professor e Chefe do Departamento de AI&DS da FTC COER, Sangola. O Dr. Tukaram A. Chavan tem mais de 25 anos de experiência como professor e diretor da SSWCOE, Solapur.