PhD Thesis Defense by Alexia Tzalavra titled "Development and Use of Multiple Discriminative Analysis and Fuzzy Logic Methodologies for the Assisted Diagnosis of Breast Cancer from Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI)"

On Thursday 14.09.2023 Alexia Tzalavra successfully defended her PhD Thesis titled "Development and Use of Multiple Discriminative Analysis and Fuzzy Logic Methodologies for the Assisted Diagnosis of Breast Cancer from Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI)".

Abstract: The present thesis aims at the design, development, and evaluation of machine learning techniques to support the computer aided diagnosis of breast cancer. Breast cancer is one of the most common causes of death for women worldwide. This fact places the early detection of the disease as one of the major challenges addressed by researchers working in the field. Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) is nowadays an area of intense research efforts, as it is a diagnostic method with high sensitivity that allows the study of the tumor’s morphology.

First, preprocessing of breast DCE-MRI images is carried out focusing on the enhancement of the image quality. As part of the image preprocessing, tumor segmentation from the original images has been performed with the help of experienced breast radiologist. The goal is the identification of the most important breast anatomical differences as well as the isolation of the regions of interest from the background.

Methodologies of multiscale analysis are further developed to quantitatively study the segmented regions (tumors), based on the extraction of texture features which are of major importance for breast cancer detection. Feature selection methods for the discrimination between benign and malignant findings are also utilized.

Furthermore, a hybrid classifier combining the features of an Adaptive Neuro-Fuzzy Inference System (ANFIS) with the Particle Swarm Optimization (PSO) algorithm is developed. The goal is the automatic discrimination between malignant and benign tumors with the best possible accuracy. A comparative assessment of the developed methodologies for the analysis and classification of breast DCE-MRI images is also carried out, aiming at the evaluation of the potential of each of these methods in the classification accuracy for benign and malignant tumors in daily clinical practice. More specifically, the studied methodologies are evaluated in real patient data that were used for research purposes. Breast DCE – MRI images were used from a total of 44 patients (23 with malignant tumors and 23 with benign tumors) collected from the Penn Medicine, Radiology department of the University of Pennsylvania in USA. The features extracted by each methodology are fed to various known classifiers. In terms of classification accuracy, the three-level Stationary Wavelet Transform (SWT) with sym9 as the mother wavelet function outperforms (91% accuracy) the Discrete Wavelet Transform (DWT) when the extracted texture features are fed in a Linear Discriminant Analysis (LDA) classifier in a leave-one-out cross validation scheme. In addition, the four-level fast discrete curve transform (FDCT) achieves the maximum classification accuracy (93.18%) when the extracted features feed the same classifier. Furthermore, the classification accuracy of the developed hybrid classifier is evaluated against known classifiers. The investigated classifiers are based on ensembles of neural networks trained with the bagging method, ensembles of feedforward neural networks of different number of hidden neurons and layers, classifiers based on binary logistic regression, Bayesian approach, and decision trees. The findings indicate that the proposed hybrid ANFIS-PSO classifier when fed with texture features extracted by the FDCT methodology using four levels of decomposition, outperforms all the investigated breast tumor classification schemes in terms of classification accuracy (94%), as well as the area under the Receiver Operating Characteristic (ROC) curve.