Affiliations: [a]
Department of CSE, FEAT, Annamalai University, Chidamabaram, Tamilnadu, India
| [b]
Department of IT, Perunthalaivar Kamarajar Institute of Engineering and Technology, Karaikal, Tamilnadu, India
Correspondence:
[*]
Corresponding author. Ajanthaa Lakkshmanan, Department of CSE, FEAT, Annamalai University, Chidamabaram, Tamilnadu, India E-mail: [email protected].
Abstract: Pancreatic tumor is the deadliest disease which needs earlier identification to reduce the mortality rate. With this motivation, this study introduces a Multi-Objective Metaheuristics with Intelligent Deep Learning Model for Pancreatic Tumor Diagnosis (MOM-IDL) model. The proposed MOM-IDL technique encompasses an adaptive Weiner filter based pre-processing technique to enhance the image quality and get rid of the noise. In addition, multi-level thresholding based segmentation using Kapur’s entropy is employed where the threshold values are optimally chosen by the barnacles mating optimizer (BMO). Besides, densely connected network (DenseNet-169) is employed as a feature extractor and fuzzy support vector machine (FSVM) is utilized as a classifier. For improving the classification performance, the BMO technique was implemented for fine-tuning the parameters of the FSVM model. The design of MOBMO algorithm for threshold selection and parameter optimization processes shows the novelty of the work. A wide range of simulations take place on the benchmark dataset and the experimental results highlighted the enhanced performance of the MOM-IDL technique over the recent state of art techniques.
