CTVR-EHO TDA-IPH Topological Optimized Convolutional Visual Recurrent Network for Brain Tumor Segmentation and Classification

Abstract

In today's world of healthcare, brain tumor (BT) detection has become increasingly prevalent. However, the manual BT classification of BTs is a time-consuming process. Consequently, deep convolutional neural network is used by many researchers in the medical field for making accurate diagnoses and aiding in patient's treatment. The traditional techniques have problems such as overfitting and the inability to extract necessary features. To address these issues, we developed the topological data analysis based improved persistent homology (TDA-IPH) and convolutional transfer learning and visual recurrent learning with elephant herding optimization hyperparameter tuning (CTVR-EHO) models for BT segmentation and classification. Initially, the TDA-IPH is designed to segment the BT image. Then, from the segmented image, features are extracted using transfer learning via the AlexNet model and bidirectional visual long short-term memory (Bi-VLSTM). Next, elephant herding optimization is used to tune the hyperparameters of both networks to get an optimal result. Finally, extracted features are concatenated and classified using the softmax activation layer. The simulation results of these proposed CTVR-EHO and TDA-IPH methods are analyzed based on precision, accuracy, recall, loss, and F score metrics. Compared to other existing BT segmentation and classification models, the proposed CTVR-EHO and TDA-IPH approaches show high accuracy (99.8%), high recall (99.23%), high precision (99.67%), and high F score (99.59%).

Received: 30 June 2024 | Revised: 18 November 2024 | Accepted: 20 December 2024

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The brain tumor (BT) data that support the findings of this study are openly available in figshare at https://doi.org/10.6084/m9. figshare.1512427.v5.

Author Contribution Statement

Dhananjay Joshi: Conceptualization, Methodology, Software, Validation, Writing – original draft. Bhupesh Kumar Singh: Methodology, Validation, Writing – review & editing. Kapil Kumar Nagwanshi: Methodology, Validation, Writing – review & editing. Nitin Surajkishor Choubey: Methodology, Validation, Writing – review & editing.