Tools
Tools
Maitra, Souvik (2022) Prediction of Non-Alcoholic Fatty Liver Disease Stages Through CT-Scan And Sonography Using Neural Network. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Cirrhosis which is the last and fourth stage of NAFLD caused in the liver is one of the major diseases of concern in the world with cases rising every year.Fatty liver diseases such as non-alcoholic fatty liver diseases (NAFLD) generally don’t cause many problems for the patients as such but it does have the possibility to progress into a more dangerous disease of Liver Cirrhosis. Identification of such progression beforehand can be very beneficial for the patients as well as the doctors.For the patients, it can save their lives as well as money that may be required for screening and operations.Doctors can make use of this information to direct the treatment in the proper direction to help patients.Hence a system for early detection of fatty liver disease into liver cirrhosis is a need in modern medicine healthcare infrastructure. This research has been focused on the early detection of the disease.The study implemented four distinct models of machine learning for predictions viz.Recurrent Neural Network, Deep Recurrent Neural Network, Support Vector Machines, and Random Forest.Our proposed research method is superior at identifying the stages using the Deep Neural Network with balanced accuracy of 96.7%.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RB Pathology |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 22 Feb 2023 17:19 |
| Last Modified: | 22 Feb 2023 17:19 |
| URI: | https://norma.ncirl.ie/id/eprint/6219 |
Actions (login required)
 |
View Item |