Tools
Tools
Hiremath, Nivedita Vishwanath (2022) Breast Cancer Detection and Classification using EfficientNet B0 and EfficientNet B0-HSV. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (10MB) | Preview |
Preview |
PDF (Configuration manual)
Download (911kB) | Preview |
Abstract
Breast cancer is a critical health issue, and it is the leading cause of cancer deaths in women worldwide. Early detection can considerably improve the chances of survival. To establish the tumor’s malignancy at the cellular level, a histological imaging evaluation is required. Manual examination of these slides takes time and is difficult and susceptible to human error. Due to the diversity in its properties in heterogeneity large size automated classification of histopathological images has been a serious issue. In this research work, histopathological images are gathered from Kaggle. This project implementation is based on transfer learning classification using EfficientNet B0 and EfficientNet B0 with HSV in pre processing step. Transfer learning uses a feature vectors model trained on ImageNet .This experiment compares EfficientNet B0 and EfficientNet B0-HSV on various magnification levels. From the experiment, it was observed that using EfficientNet B0-HSV at 100X and 200X magnification levels gave a better result in terms of precision. However, EfficientNet B0-HSV failed to minimise false negative values compared to EfficientNet B0.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Life sciences > Medical sciences > Pathology > Tumors > Cancer H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 26 Jan 2023 16:01 |
| Last Modified: | 26 Jan 2023 16:01 |
| URI: | https://norma.ncirl.ie/id/eprint/6135 |
Actions (login required)
 |
View Item |