This item is available under a Creative Commons License for non-commercial use only
1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences, Information Science
Cancer detection has been a great topic of research for a long time, as early detection of cancer can help in increasing the survival rate of patients by providing on time better treatment. A robust system is required in order to detect early-stage cancer as its difficult to identify early-stage cancer from the normal clinical process. The computer vision techniques provide a new way to understand the challenges related to the medical image analysis. This thesis presents the medical image analysis using a combination of Convolutional Neural Network and Hyperspectral Images of cancer patient's tissues. The idea behind choosing the CNN is it has been doing really well in image processing and outperformed the other traditional techniques. An attempt is made to distinguish between Normal Tissues, Premature Tissues and Oesophageal adenocarcinoma (OAC) tissues. The dataset used here posses many challenges like less number of instances and most importantly imbalanced data, which means some instances are very few in comparison to others. This thesis focuses on improving the F1 Score of the CNN classifier and the performance is measured after fine-tuning the baseline model. The experiment result shows that fine-tuning the CNN algorithm help in improving the F1 Score a bit though haven't achieved great result due to the limitation of imbalanced data. This work is a contribution towards detection of early-stage cancer through images, which clinical processes are unable to detect.
Jain, P. (2018). Use of Hyperspectral Images (HSI) and Convolutional Neural Network (CNN) To Identify Normal, Precancerous and Cancerous Tissues. M.Sc. Dissertation in Computing (Data Analytics), September 2018.