A Secure IoT-Enabled Machine Learning Framework for Brain Tumor Classification and Prediction Using MR Image Data

Aug 4, 2026

Brain tumor identification and classification benefit from rapid advances in medical imaging and machine learning technology. This paper proposes two connected directions for secure image handling in the Internet of Things (IoT): an IoT-based prediction and classification pipeline powered by advanced models, and an encryption/decryption security design using an AES-ECC hybrid model within the MQTT protocol for MRI image data. A heterogeneous Kaggle dataset covering four MRI scan types from 2870 patients is used, with CNN, DenseNet, ResNet, and G-Net for learning and interpretation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Secure IoT-enabled workflow

Machine learning for healthcare applications

A Secure IoT-Enabled Machine Learning Framework for Brain Tumor Classification and Prediction Using MR Image Data Satyaprakash Swain1,*, Mihir Narayan Mohanty2, Binod Kumar Pattanayak3,*, Puspanjali Mallik4, Kumar Janardan Patra5,*, Chittaranjan Panda6 1,3,4 Department of Computer Science & Engineering, Institute of Technical Education & Research(ITER), Siksha ‘O’ Anusandhan (Deemed to be University), Bhubaneswar, Odisha, India 2 Department of Electronics and Communication Engineering, Institute of Technical Education & Research(ITER), Siksha ‘O’Anusandhan (Deemed to be University), Bhubaneswar, Odisha, India 5Department of Computer Science & Engineering, Institute of Management and Information Technology, Cuttack, BPUT, Odisha, India 6Mavenir Systems, Bangalore, India 1,*[satyaimit@gmail.com](satyaimit@gmail.com), [2](2 mihirmohanty@soa.ac.in)[ mihirmohanty@soa.ac.in](2 mihirmohanty@soa.ac.in),3,*[binodpattanayak@soa.ac.in](binodpattanayak@soa.ac.in), [4](4 mallickpuspa@gmail.com)[ mallickpuspa@gmail.com](4 mallickpuspa@gmail.com), 5,*[janardanpatra1997@gmail.com](janardanpatra1997@gmail.com),[6](6 chittaranjan.panda@mavenir.com)[ chittaranjan.panda@mavenir.com](6 chittaranjan.panda@mavenir.com) *Corresponding Author Abstract—Brain tumor identification and classification have improved due to the quick development of medical imaging and machine learning technology. This paper presents two approaches to secure image transmission in the Internet of Things (IoT): a comprehensive approach for brain tumor prediction and classification using a strong IoT infrastructure with cutting-edge machine learning models and a security approach with the implementation of the AES-ECC hybrid model in the MQTT communication protocol for image data encryption and decryption. We make use of a heterogeneous dataset that we sourced from the Kaggle Dataset platform, which includes four different types of MRI scans of brain tumors from 2870 patients. Our proposed methodology starts with the safe acquisition and transfer of MRI images through an IoT protocol infrastructure to a cloud-based platform. CNN, DenseNet, ResNet and G-Net are some of the sophisticated machine learning models that are used to interpret and analyse these pictures. The computer is trained to identify photos of brain tumors into the appropriate groups using all above four models. According to the data, our suggested CNN model performs better than the others, obtaining an amazing 89% accuracy rate. Nonetheless, we want to achieve even greater improvement in forecast precision by utilising ensemble boosting methodologies. Boosting the CNN model with Ada-Boost, Gradient Boost, XG Boost and Cat Boost algorithms aims to maximize prediction performance. We find that the CNN algorithm combined with XG Boost outperforms all other ensemble methods with an amazing accuracy rate of 97% . This encouraging result highlights how combining cutting-edge machine learning algorithms with IoT infrastructure can lead to better brain tumor classification and prognosis. The creation of more precise and effective diagnostic instruments for the identification of brain tumors is one of our study's many implications, one that will ultimately improve patient outcomes and the healthcare industry. Keywords-IoT, AES, ECC, ML, MRI, Voting Model, Boosting Model I. INTRODUCTION The emergence of the Internet of Things (IoT) has created new opportunities for the healthcare industry by providing creative solutions to the pressing problem of brain tumor prediction and categorization. Because of their intricacy and potentially serious implications, brain tumors require early and precise detection. This picture is set to change as a result of the integration of advanced machine learning models with IoT infrastructure[18-20] . The integration will provide simplified data collecting, secure transfer and improved diagnostic capabilities. Machine learning is one of the key hidden insights t

FAQs

What secure IoT approach is used for MRI image transmission?

The framework uses MQTT as the communication protocol and applies an AES-ECC hybrid encryption model for securing image data during encryption and decryption.

Which machine learning models are employed for brain tumor classification and prediction?

The work uses CNN, DenseNet, ResNet, and G-Net to interpret and analyze MRI scans and to classify images into appropriate groups.

How is model performance evaluated and improved?

A CNN-based approach is reported to achieve about 89% accuracy, and ensemble boosting is further explored using Ada-Boost, Gradient Boost, XG Boost, and Cat Boost to improve prediction precision.

Aug 4, 2026

Upload by Emma Wilson