Translational Medical Research 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 …

Applying Knowledge Translation In Rehabilitation: An Exploration Of What It Means To Change Clinical Practice, Stacey D. Guy

Electronic Thesis and Dissertation Repository

Health care providers are often required to implement evidence-based recommendations into the care they deliver. Resources that support health care providers’ efforts are a useful knowledge translation strategy. This thesis describes the development and usability evaluation of an evidence-informed clinical practice implementation toolkit to support implementation efforts. Two studies were undertaken to provide insight into what was needed to support health care providers, and to inform the development of the toolkit. A retrospective evaluation analyzed the performance of a team implementing a pressure ulcer risk assessment for patients with spinal cord injury. The rates of adherence to the risk assessment …

The Symbiome Project: An Exploratory Investigation Of The Biological, Psychological, And Social Mechanisms That Contribute To The Transition From Acute To Chronic Musculoskeletal Pain, Joshua Y. Lee

Electronic Thesis and Dissertation Repository

This dissertation presents the initial findings of the SYMBIOME project; which attempts to combine the objective and subjective aspects of musculoskeletal pain to develop a prognostic clinical phenotype. Chapter 2 presents a moderator analysis of functional outcomes (pain interference and pain severity). Psychosocial moderators can affect the relationship between biomarkers and pain. For pain severity, TNF-α, TGF-β1, and CRP were moderated by employment status, pre-existing psychopathology, and sex. For pain interference, IL-1β, cortisol, TGF-β1, CRP, and IL-6 were moderated by pre-existing pain, peri-traumatic fear, region of injury, and peri-traumatic stress. Chapter 3 presents a latent growth curve analysis in determining …