ItemArticle

Hybrid Mobile-Spinalnet with feature extraction for brain tumor detection using MRI images

Title
Hybrid Mobile-Spinalnet with feature extraction for brain tumor detection using MRI images
Creator
Vadivu, P. Balashanmuga; Prabhakar, Telagarapu; Mandala, Jyothi; Chandra Sekhar, Kattamuri Venkata
Description
Brain tumors are deadly and can hinder the normal functioning of the human body. Generally, surgical methods are preferred for treating brain tumors. Early and accurate detection remains a problem, due to the complexity of tumor shapes and poor generalization to diverse tumor types. To address this, a hybrid Mobile-SpinalNet is established in this paper for the detection of brain tumors with Magnetic Resonance Imaging (MRI) images. This system involves seven stages, including input image acquisition, image preprocessing, skill stripping, tumor segmentation, data augmentation, feature extraction, and brain tumor detection. Initially, image acquisition is carried out, and then the input image is preprocessed by using a Mean filter. Subsequently, the skull stripping is performed using Fuzzy C-Means (FCM). After that, by using the TransUNet, the tumor region is isolated in the segmentation module. Furthermore, the data augmentation is carried out, and then the feature mining takes place in the feature extraction phase to excerpt features such as Speeded Up Robust Features (SURF), Oriented Fast and Rotated BRIEF (ORB), Fuzzy Local Binary Pattern (FLBP) and statistical features. At last, the brain tumor is identified by employing a hybrid Mobile-SpinalNet. This framework fuses the MobileNet and SpinalNet depending on regression modeling with applied Fractional Calculus (FC). The Mobile-SpinalNet is validated for its efficacy by comparing it to other techniques, and it showed better performance with a precision of 0.953, accuracy of 0.943, and recall of 0.970. 2025 Elsevier Ltd
Source
Biomedical Signal Processing and Control;Volume;112;Issue;;Article No.;108571;
Date
01-01-2026
Publisher
Elsevier Ltd
Subject
Brain tumor; Fractional Calculus; Fuzzy C-Means; Hybrid model; MobileNet; SpinalNet; TransUNet
Coverage
Vadivu P.B., Department of ECE, Mahendra Engineering College, Tamil Nadu, Namakkal, India; Prabhakar T., Department of ECE, GMR Institute of Technology, GMR Nagar, Andhra Pradesh, Rajam, India; Mandala J., Department of Computer science and engineering, CHRIST (Deemed to be University), Banglore, India; Chandra Sekhar K.V., Department of Artificial Intelligence & Machine Learning, Aditya Institute of Technology and Management, Srikakulam, Tekkali, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 17468094;
Format
online
Language
English
Type
Article

Citation

Vadivu, P. Balashanmuga; Prabhakar, Telagarapu; Mandala, Jyothi; Chandra Sekhar, Kattamuri Venkata, “Hybrid Mobile-Spinalnet with feature extraction for brain tumor detection using MRI images,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/22207.

Output Formats