Related Experiment Video
Updated: Aug 6, 2026
10:25
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
Published on: November 11, 2022
8.9K
Ensembles of Convolutional Neural Networks and Transformers for Polyp Segmentation
Loris Nanni1, Carlo Fantozzi1, Andrea Loreggia2
1Department of Information Engineering, University of Padova, 35122 Padova, Italy.
Sensors (Basel, Switzerland)
|July 11, 2023
Summary
This study reviews deep ensemble learning for polyp segmentation, developing novel ensembles that outperform existing methods. Averaging intermediate masks significantly improves performance in medical image analysis.
Area of Science:
- Computer Vision
- Medical Image Analysis
- Deep Learning
Background:
- Semantic segmentation classifies each pixel in an image, crucial for tasks like medical diagnostics.
- Accurate polyp segmentation aids in early disease detection, reducing potential health consequences.
- Deep ensemble learning models offer a promising approach to enhance segmentation accuracy.
Conclusions:
- Deep ensemble learning, particularly with diverse components and novel mask averaging, significantly advances polyp segmentation.
- The developed ensembles represent a state-of-the-art solution for medical image segmentation tasks.
- This work provides a strong foundation for future research in automated medical diagnostics using computer vision.
