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

TL;DR

EffiSegNet is a simplified, efficient neural network architecture leveraging transfer learning with a pre-trained backbone for gastrointestinal polyp segmentation, achieving state-of-the-art results with fewer parameters and lower computational cost.

Contribution

This paper introduces EffiSegNet, a novel, simplified segmentation framework that uses a pre-trained CNN backbone and full-scale feature fusion, outperforming existing methods on the Kvasir-SEG dataset.

Findings

Achieved state-of-the-art F1 score of 0.9552 on Kvasir-SEG

Demonstrated high accuracy with a simplified decoder architecture

Validated effectiveness of transfer learning in medical image segmentation

Abstract

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.