A secure two-qubit quantum model for segmentation and classification of brain tumor using MRI images based on blockchain

The size of the medical imaging data is increasing day by day which requires improved tools/applications to perform accurate and efficient diagnoses. Another important concern is to secure the patient's personal information. Therefore, this research work focuses on a novel secure framework for...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications Vol. 34; no. 20; pp. 17315 - 17328
Main Authors: Amin, Javaria, Anjum, Muhammad Almas, Gul, Nadia, Sharif, Muhammad
Format: Journal Article
Language:English
Published: London Springer London 01.10.2022
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Brain
Brain cancer
Brain research
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Cryptography
Data Mining and Knowledge Discovery
Image classification
Image Processing and Computer Vision
Image segmentation
Magnetic resonance imaging
Medical imaging
Original Article
Probability and Statistics in Computer Science
Qubits (quantum computing)
Tumors
Brain tumor
J. Quantum
Semantic segmentation
J. SegCNN
Blockchain
ISSN:0941-0643, 1433-3058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The size of the medical imaging data is increasing day by day which requires improved tools/applications to perform accurate and efficient diagnoses. Another important concern is to secure the patient's personal information. Therefore, this research work focuses on a novel secure framework for brain tumor diagnosis. The proposed methodology comprises three main core steps. Initially, the patient's MRI data are encrypted and decrypted using the SHA-256 algorithm to secure the brain data. The decrypted images are supplied to the 2-qubit quantum model named Javeria (J). Quantum model for tumor classification, which comprises three layers as two dense layers and one Keras layer with a softmax activation unit. The classified tumor images are input to the semantic segmentation model named J. SegCNN for tumor segmentation. The proposed J. SegCNN model contains 11 layers that are trained on selected batch-size and Adam optimizer solver. The proposed model provides a 98% dice similarity coefficient (DSC) which is far better as compared to the latest research works.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-022-07388-x