Student: “Nikolaos Charisis”

Program: “Data Science and Information Technologies”

Title: “A Comparative Analysis of Classical Machine Learning Methods and
Variational Quantum Methods for Breast Tumor Classification”

Abstract:
“Breast cancer accounts for 36% of female oncological cases, necessitating
high-precision prognostic tools. While traditional machine learning is the
standard, this study explores the efficacy of Variational Quantum
Classifiers (VQCs) using breast tumor data from fine-needle aspirates. By
integrating Principal Component Analysis (PCA), we managed the tradeoff
between explained variance and the dimensions of the Hilbert space
traversed by the quantum processor. The findings reveal that a 4-qubit
configuration utilizing 16 principal components captured nearly 99% of
data variance, consistently achieving classification scores above 90%.
This performance demonstrates that even small-scale quantum circuits can
remain competitive with sophisticated classical methods like Logistic
Regression. Ultimately, the study highlights how hybrid quantum-classical
pipelines with a small number of qubits can leverage quantum advantages to
provide robust, scalable solutions for complex medical diagnostics.”

Date and time of presentation: Monday, March 2, 5.00 p.m.

Examination Comitee:
”
Dr.   Aikaterini Mandilara
Prof. Dimitrios Gunopulos
Prof. Dimitrios Syvridis
”

Meeting Link:
https://meet.google.com/ukg-bowy-ejb