Classification Of Ovarian Tumor Using Histopathological Images

Tikone, Minakshi Goraksh (2022) Classification Of Ovarian Tumor Using Histopathological Images. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Histopathology and allied sciences such as cytology have gained new perspectives as a result of the rise of digital pathology. Computer algorithms, specifically artificial-intelligence algorithms, can work on digitized slides to aid pathologists with theranostic and diagnostic duties. In recent years, machine learning has come a long way. Machine learning approaches such as segmentation and classifications have apparent advantage of doing pathological image analysis. In this research, I provide the findings of a search of the world’s biggest public archive ([TCGA]The Cancer Genome Atlas program run by the National Cancer Institute in the United States) of entire slide pictures of over 50 individuals with ovarian tumor cells. I successfully indexed and searched around high-resolution digital slides totaling 8 giga bytes of data composed of 8000 x 8500 pixels picture patches for the first time. This study demonstrate a pretained DCNN architecture -VGG16 which consist of 16 layers. The model was trained with 46 images, achieved an accuracy score of 44% due to the limitation issue. The proposed study is to use VGG16 model to classify the ovarian tumor using histopathological images.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Histopathology; machine learning; DCNN; pre-trained model; VGG16
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RB Pathology R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	14 Mar 2023 10:01
Last Modified:	14 Mar 2023 10:01
URI:	https://norma.ncirl.ie/id/eprint/6327

Actions (login required)

View Item