Biomedical Engineering and Bioengineering Commons^™

Longitudinal Case-Control Study Of Mammographic Breast Tissue Subtypes, Kendra Batchelder

Electronic Theses and Dissertations

Breast density is a known risk factor for breast cancer. However, there has been limited research on potential subtypes of mammographic dense breast tissue to identify areas of active dense tissue that is structurally reorganizing and links to cancer dynamics, versus areas of passive dense tissue which remains organized. We hypothesize that the amounts of subtypes of mammographic dense tissue and the associated rate of change through time could provide insights into breast cancer risk. A retrospective study was conducted to investigate breast cancer using longitudinal screening mammograms and accompanying pathology reports collected in 2015. Patients were matched by age …

Hybrid Power Spectral And Wavelet Image Roughness Analysis, Basel White

Electronic Theses and Dissertations

The Two-Dimensional Wavelet Transform Modulus Maxima (2D WTMM) sliding window methodology has proven to be a robust approach, in particular for the extraction of the Hurst (H) roughness exponent from grayscale mammograms. The power spectrum is a computational analysis based on the Fourier transform that can be used to estimate the roughness of a scale-invariant image or region via the calculation of H. We aim to examine how the calculation of H in fractional Brownian motion (fBm) images and mammograms can be improved. fBm images are generated for H ∈ [0.00,1.00] for testing through the previous 2D …

Using Feature Extraction From Deep Convolutional Neural Networks For Pathological Image Analysis And Its Visual Interpretability, Wei-Wen Hsu

Electrical & Computer Engineering Theses & Dissertations

This dissertation presents a computer-aided diagnosis (CAD) system using deep learning approaches for lesion detection and classification on whole-slide images (WSIs) with breast cancer. The deep features being distinguishing in classification from the convolutional neural networks (CNN) are demonstrated in this study to provide comprehensive interpretability for the proposed CAD system using the domain knowledge in pathology. In the experiment, a total of 186 slides of WSIs were collected and classified into three categories: Non-Carcinoma, Ductal Carcinoma in Situ (DCIS), and Invasive Ductal Carcinoma (IDC). Instead of conducting pixel-wise classification (segmentation) into three classes directly, a hierarchical framework with the …

Metabolism-Driven High-Throughput Cancer Identification With Glut5-Specific Molecular Probes, Srinivas Kannan, Vagarshak Begoyan, Joseph Fedie, Shuai Xia, Łukasz J. Weseliński, Marina Tanasova, Smitha Rao

Michigan Tech Publications

Point-of-care applications rely on biomedical sensors to enable rapid detection with high sensitivity and selectivity. Despite advances in sensor development, there are challenges in cancer diagnostics. Detection of biomarkers, cell receptors, circulating tumor cells, gene identification, and fluorescent tagging are time-consuming due to the sample preparation and response time involved. Here, we present a novel approach to target the enhanced metabolism in breast cancers for rapid detection using fluorescent imaging. Fluorescent analogs of fructose target the fructose-specific transporter GLUT5 in breast cancers and have limited to no response from normal cells. These analogs demonstrate a marked difference in adenocarcinoma and …

Modular Machine Learning Methods For Computer-Aided Diagnosis Of Breast Cancer, Mia Kathleen Markey '94

Doctoral Dissertations

The purpose of this study was to improve breast cancer diagnosis by reducing the number of benign biopsies performed. To this end, we investigated modular and ensemble systems of machine learning methods for computer-aided diagnosis (CAD) of breast cancer. A modular system partitions the input space into smaller domains, each of which is handled by a local model. An ensemble system uses multiple models for the same cases and combines the models' predictions.

Five supervised machine learning techniques (LDA, SVM, BP-ANN, CBR, CART) were trained to predict the biopsy outcome from mammographic findings (BIRADS™) and patient age based on a …