EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vezakis, Ioannis A., Georgas, Konstantinos, Fotiadis, Dimitrios, Matsopoulos, George K.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913442166734848
author Vezakis, Ioannis A.
Georgas, Konstantinos
Fotiadis, Dimitrios
Matsopoulos, George K.
author_facet Vezakis, Ioannis A.
Georgas, Konstantinos
Fotiadis, Dimitrios
Matsopoulos, George K.
contents This work introduces EffiSegNet, a novel segmentation framework leveraging transfer learning with a pre-trained Convolutional Neural Network (CNN) classifier as its backbone. Deviating from traditional architectures with a symmetric U-shape, EffiSegNet simplifies the decoder and utilizes full-scale feature fusion to minimize computational cost and the number of parameters. We evaluated our model on the gastrointestinal polyp segmentation task using the publicly available Kvasir-SEG dataset, achieving state-of-the-art results. Specifically, the EffiSegNet-B4 network variant achieved an F1 score of 0.9552, mean Dice (mDice) 0.9483, mean Intersection over Union (mIoU) 0.9056, Precision 0.9679, and Recall 0.9429 with a pre-trained backbone - to the best of our knowledge, the highest reported scores in the literature for this dataset. Additional training from scratch also demonstrated exceptional performance compared to previous work, achieving an F1 score of 0.9286, mDice 0.9207, mIoU 0.8668, Precision 0.9311 and Recall 0.9262. These results underscore the importance of a well-designed encoder in image segmentation networks and the effectiveness of transfer learning approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16298
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder
Vezakis, Ioannis A.
Georgas, Konstantinos
Fotiadis, Dimitrios
Matsopoulos, George K.
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
This work introduces EffiSegNet, a novel segmentation framework leveraging transfer learning with a pre-trained Convolutional Neural Network (CNN) classifier as its backbone. Deviating from traditional architectures with a symmetric U-shape, EffiSegNet simplifies the decoder and utilizes full-scale feature fusion to minimize computational cost and the number of parameters. We evaluated our model on the gastrointestinal polyp segmentation task using the publicly available Kvasir-SEG dataset, achieving state-of-the-art results. Specifically, the EffiSegNet-B4 network variant achieved an F1 score of 0.9552, mean Dice (mDice) 0.9483, mean Intersection over Union (mIoU) 0.9056, Precision 0.9679, and Recall 0.9429 with a pre-trained backbone - to the best of our knowledge, the highest reported scores in the literature for this dataset. Additional training from scratch also demonstrated exceptional performance compared to previous work, achieving an F1 score of 0.9286, mDice 0.9207, mIoU 0.8668, Precision 0.9311 and Recall 0.9262. These results underscore the importance of a well-designed encoder in image segmentation networks and the effectiveness of transfer learning approaches.
title EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.16298