Date of Award
Colorectal Cancer, Convolutional Neural Network, Deep Learning, Omics
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Colorectal cancer is one of the most common cancers and is a leading cause of death worldwide. It starts in the colon or the rectum, and they are often grouped together because they have many features in common. It has been noticed that colorectal cancer attacks young-onset patients who are less than 50 years of age in increasing rates lately. Rapid developments in omics technologies have led them to be highly regarded in the field of biomedical research for the early detection of cancer. Omics data revealed how different molecules and clinical features work together in the disease progression. However, Omics data sources are variants in nature and require careful preprocessing to be integrated. A convolutional neural network is a class of deep neural networks, commonly applied to analyze visual imagery. In this thesis, we propose a model that converts one-dimensional vectors of omics into RGB images to be integrated into the hidden layers of the convolutional neural network. The prediction model will allow all different omics to contribute to the decision making based on extracting the hidden interactions among these omics. These subsets of interacted omics can serve as potential biomarkers for young-onset colorectal cancer.
Kammonah, Noor, "A Deep Learning Approach for Multi-Omics Data Integration to Diagnose Early-Onset Colorectal Cancer" (2021). Electronic Theses and Dissertations. 8558.