PAAN: Pyramid Attention Augmented Network for polyp segmentation

Sida Yi, Yuesheng Zhu, Guibo Luo
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1823-1840, 2024.

Abstract

Polyp segmentation is a task of segmenting polyp lesion regions from normal tissues in medical images, which is crucial for medical diagnosis and treatment planning. However, existing methods still suffer from low accuracy in polyp boundary delineation and insufficient suppression of irrelevant background due to the blur boundaries and textures of polyps. To overcome these limitations, in this paper a Pyramid Attention Augmented Network (PAAN) is proposed, in which a pyramid feature diversion structure with spatial attention mechanism is developed so that good feature representation with low information loss can be achieved by conducting channel attention-based feature diversion and inter-layer fusion, while reducing computational complexity. Also, our framework includes an Enhanced Spatial Attention module (ESA), which can improve the quality of initial polyp segmentation predictions through spatial self-attention mechanism and multi-scale feature fusion. Our approach is evaluated on five challenging polyp datasets— Kvasir, CVC-ClinicDB, CVC-300, ETIS, and CVC-colonDB and achieves excellent results. In particular, we achieve 94.2% Dice and 89.7% IoU on Kvasir, outperforming other state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-yi24a, title = {PAAN: Pyramid Attention Augmented Network for polyp segmentation}, author = {Yi, Sida and Zhu, Yuesheng and Luo, Guibo}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1823--1840}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/yi24a/yi24a.pdf}, url = {https://proceedings.mlr.press/v250/yi24a.html}, abstract = {Polyp segmentation is a task of segmenting polyp lesion regions from normal tissues in medical images, which is crucial for medical diagnosis and treatment planning. However, existing methods still suffer from low accuracy in polyp boundary delineation and insufficient suppression of irrelevant background due to the blur boundaries and textures of polyps. To overcome these limitations, in this paper a Pyramid Attention Augmented Network (PAAN) is proposed, in which a pyramid feature diversion structure with spatial attention mechanism is developed so that good feature representation with low information loss can be achieved by conducting channel attention-based feature diversion and inter-layer fusion, while reducing computational complexity. Also, our framework includes an Enhanced Spatial Attention module (ESA), which can improve the quality of initial polyp segmentation predictions through spatial self-attention mechanism and multi-scale feature fusion. Our approach is evaluated on five challenging polyp datasets— Kvasir, CVC-ClinicDB, CVC-300, ETIS, and CVC-colonDB and achieves excellent results. In particular, we achieve 94.2% Dice and 89.7% IoU on Kvasir, outperforming other state-of-the-art methods.} }
Endnote
%0 Conference Paper %T PAAN: Pyramid Attention Augmented Network for polyp segmentation %A Sida Yi %A Yuesheng Zhu %A Guibo Luo %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-yi24a %I PMLR %P 1823--1840 %U https://proceedings.mlr.press/v250/yi24a.html %V 250 %X Polyp segmentation is a task of segmenting polyp lesion regions from normal tissues in medical images, which is crucial for medical diagnosis and treatment planning. However, existing methods still suffer from low accuracy in polyp boundary delineation and insufficient suppression of irrelevant background due to the blur boundaries and textures of polyps. To overcome these limitations, in this paper a Pyramid Attention Augmented Network (PAAN) is proposed, in which a pyramid feature diversion structure with spatial attention mechanism is developed so that good feature representation with low information loss can be achieved by conducting channel attention-based feature diversion and inter-layer fusion, while reducing computational complexity. Also, our framework includes an Enhanced Spatial Attention module (ESA), which can improve the quality of initial polyp segmentation predictions through spatial self-attention mechanism and multi-scale feature fusion. Our approach is evaluated on five challenging polyp datasets— Kvasir, CVC-ClinicDB, CVC-300, ETIS, and CVC-colonDB and achieves excellent results. In particular, we achieve 94.2% Dice and 89.7% IoU on Kvasir, outperforming other state-of-the-art methods.
APA
Yi, S., Zhu, Y. & Luo, G.. (2024). PAAN: Pyramid Attention Augmented Network for polyp segmentation. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1823-1840 Available from https://proceedings.mlr.press/v250/yi24a.html.

Related Material