Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Engineering
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 …
Investigation Of Acute Radiation-Induced Changes In Oxygenation In A Murine Breast Tumor Model, Alaa Abdelgawad
Investigation Of Acute Radiation-Induced Changes In Oxygenation In A Murine Breast Tumor Model, Alaa Abdelgawad
Biomedical Engineering Undergraduate Honors Theses
Around 50-60% of all cancer patients undergo radiation therapy. Although some patients show complete response with no recurrence, a significant proportion of the population still develop radiation resistance. It is important to identify tumor resistance at early stages of therapy in order to adjust treatment protocol and avoid extra exposure to radiation. Current methods to assess treatment response are only limited to anatomical measurements of tumor volume after therapy. Novel approaches that shed the light on any functional information during the course of radiotherapy could significantly improve our ability to identify patients who do not respond to radiation therapy. Diffuse …
Utilizing Immunopet To Measure Tumor Response To Treatment In Breast Cancer, Brooke Mcknight
Utilizing Immunopet To Measure Tumor Response To Treatment In Breast Cancer, Brooke Mcknight
Wayne State University Dissertations
With a broad spectrum of therapies available for treating breast cancer, the need for personalized medicine tailoring the cure according to phenotype is evident. Such an approach may be fully realized with the development of quantitative imaging technologies for disease detection, staging and diagnosis, without increasing patient burden. Immuno-positron emission tomography (PET) combines the targeted specificity of antibodies with the sensitivity of PET for whole body imaging by targeting molecular features amplified in lesions. ImmunoPET probes targeting different antigens and their utility to measure response to treatment were explored. 89Zr-trastuzumab was employed as a surrogate readout of Src inhibition after …