Detection of brain cancer using quantum-classical CNN-based method

Sriya Bada; Sreeraj Rajan Warrier; Jayasri Dontabhaktuni

doi:10.1117/12.2650132

8 March 2023 Detection of brain cancer using quantum-classical CNN-based method

Sriya Bada, Sreeraj Rajan Warrier, Jayasri Dontabhaktuni

Proceedings Volume 12446, Quantum Computing, Communication, and Simulation III; 1244616 (2023) https://doi.org/10.1117/12.2650132
Event: SPIE Quantum West, 2023, San Francisco, California, United States

Conference Poster

Abstract

Classification of MRI images of brain cancer using deep learning methods such as CNN’s is an increasingly popular method to detect cancer and its spread. In the present work, we perform a competitive analysis of hybrid quantum CNN based methods to classify the MRI images of brain cancer into three different classes using quantum simulators. The quantum image processing is done via three encoding schemes, viz. QCNN, FRQI and NEQR. We see that QCNN has higher accuracy of 87% with a precision of 81%. The NEQR and FRQI encoding schemes have an accuracy of 79% and 75%, respectively. The computational time for QCNN, FRQI and NEQR are considerably less than the conventional CNN method, which was tested by running the same dataset through DenseNet121 Keras architecture.

Citation Download Citation

Sriya Bada, Sreeraj Rajan Warrier, and Jayasri Dontabhaktuni "Detection of brain cancer using quantum-classical CNN-based method", Proc. SPIE 12446, Quantum Computing, Communication, and Simulation III, 1244616 (8 March 2023); https://doi.org/10.1117/12.2650132

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available