OncoFusion: Multi-Model Approach for Generalized and Ovarian Cancer Detection with Stacked Ensembles
Cancer detection is a critical task in the medical field, where accurate and early diagnosis can save lives. However, current research faces challenges such as high false positive rates, difficulty in generalizing models across diverse datasets, and inconsistent accuracy in real- world scenarios. Ma...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | EPJ Web of Conferences |
| Online Access: | https://www.epj-conferences.org/articles/epjconf/pdf/2025/13/epjconf_icetsf2025_01045.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Cancer detection is a critical task in the medical field, where accurate and early diagnosis can save lives. However, current research faces challenges such as high false positive rates, difficulty in generalizing models across diverse datasets, and inconsistent accuracy in real- world scenarios. Many models perform well on specific datasets but struggle to maintain accuracy across different populations and imaging techniques. Our research focuses on using machine learning (ML) techniques to detect cancer from histopathological images. We investigated Convolutional Neural Networks (CNN) as well as more conventional machine learning models like Random Forests and XGBoost for the analyzing images. The datasets offer a solid foundation for testing and training. Our goal is to create a cancer detection system that is accurate, scalable, and greatly enhances diagnostic capabilities. We also use data augmentation for improved generalization, hyperparameter tuning to increase accuracy and transfer learning to improve model performance. |
|---|---|
| ISSN: | 2100-014X |