Medicine and Health Sciences Commons^™

Cancer Detection In Radical Prostatectomy Histology Using Convolutional Neural Networks, Laurie Huang

Electronic Thesis and Dissertation Repository

Radical prostatectomy (RP) is a common treatment for prostate cancer. We used RP whole-mount tissue samples from 68 patients stained with haematoxylin and eosin to create cancer maps using four pretrained networks: AlexNet, NASNet, VGG16 and Xception, to classify regions of interest (ROIs) as cancer or non-cancer. Models were trained on either raw images or as tissue component maps (TCMs) containing nuclei, lumina and stroma/other components generated from a trained U-Net.

All models performed similarly; however, VGG16 trained on raw images performed with the highest area under the receiver operating characteristic curve (AUC) of 0.994 (95% confidence interval 0.992-0.996). Ensemble …

Ambient Ionization - Mass Spectrometry: Advances Toward Intrasurgical Cancer Detection, Alan Keith Jarmusch

Open Access Dissertations

My dissertation research has focused on the development of ambient ionization – mass spectrometry (MS) for clinical measurements, specifically intrasurgical cancer detection. The molecular differences between normal and cancerous tissue were detected via direct tissue analysis in vitro by touch spray ionization (TS) or by analyzing sectioned or smeared tissue using desorption electrospray ionization (DESI). The physical form of the tissue, e.g. in vitro sampling, sectioned, or smeared, was inconsequential in differentiating normal from cancerous tissue; however, the spectra acquired by TS and DESI differed due to differences in ionization processes. We envision that TS-MS and DESI-MS could impact diagnostic …