MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation
The colonoscopy procedure heavily relies on the operator’s expertise, underscoring the importance of automated polyp segmentation techniques in enhancing the efficiency and accuracy of colorectal cancer diagnosis. Nevertheless, achieving precise segmentation remains a significant challenge due to th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/1/42 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589374571675648 |
|---|---|
| author | Botao Liu Changqi Shi Ming Zhao |
| author_facet | Botao Liu Changqi Shi Ming Zhao |
| author_sort | Botao Liu |
| collection | DOAJ |
| description | The colonoscopy procedure heavily relies on the operator’s expertise, underscoring the importance of automated polyp segmentation techniques in enhancing the efficiency and accuracy of colorectal cancer diagnosis. Nevertheless, achieving precise segmentation remains a significant challenge due to the high visual similarity between polyps and their backgrounds, blurred boundaries, and complex localization. To address these challenges, a Multi-scale Selective Edge-Aware Network has been proposed to facilitate polyp segmentation. The model consists of three key components: (1) an Edge Feature Extractor (EFE) that captures polyp edge features with precision during the initial encoding phase, (2) the Cross-layer Context Fusion (CCF) block designed to extract and integrate multi-scale contextual information from diverse receptive fields, and (3) the Selective Edge Aware (SEA) module that enhances sensitivity to high-frequency edge details during the decoding phase, thereby improving edge preservation and segmentation accuracy. The effectiveness of our model has been rigorously validated on the Kvasir-SEG, Kvasir-Sessile, and BKAI datasets, achieving mean Dice scores of 91.92%, 82.10%, and 92.24%, respectively, on the test sets. |
| format | Article |
| id | doaj-art-0495d76bfc8542e3ba14eb2865aa2fed |
| institution | Kabale University |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-0495d76bfc8542e3ba14eb2865aa2fed2025-01-24T13:17:35ZengMDPI AGAlgorithms1999-48932025-01-011814210.3390/a18010042MSEANet: Multi-Scale Selective Edge Aware Network for Polyp SegmentationBotao Liu0Changqi Shi1Ming Zhao2School of Computer Science, Yangtze University, Jingzhou 434023, ChinaSchool of Computer Science, Yangtze University, Jingzhou 434023, ChinaSchool of Internet of Things Engineering, Wuxi University, Wuxi 214105, ChinaThe colonoscopy procedure heavily relies on the operator’s expertise, underscoring the importance of automated polyp segmentation techniques in enhancing the efficiency and accuracy of colorectal cancer diagnosis. Nevertheless, achieving precise segmentation remains a significant challenge due to the high visual similarity between polyps and their backgrounds, blurred boundaries, and complex localization. To address these challenges, a Multi-scale Selective Edge-Aware Network has been proposed to facilitate polyp segmentation. The model consists of three key components: (1) an Edge Feature Extractor (EFE) that captures polyp edge features with precision during the initial encoding phase, (2) the Cross-layer Context Fusion (CCF) block designed to extract and integrate multi-scale contextual information from diverse receptive fields, and (3) the Selective Edge Aware (SEA) module that enhances sensitivity to high-frequency edge details during the decoding phase, thereby improving edge preservation and segmentation accuracy. The effectiveness of our model has been rigorously validated on the Kvasir-SEG, Kvasir-Sessile, and BKAI datasets, achieving mean Dice scores of 91.92%, 82.10%, and 92.24%, respectively, on the test sets.https://www.mdpi.com/1999-4893/18/1/42polyp segmentationcontext fusionedge awarehigh-frequency informationdeep learning |
| spellingShingle | Botao Liu Changqi Shi Ming Zhao MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation Algorithms polyp segmentation context fusion edge aware high-frequency information deep learning |
| title | MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation |
| title_full | MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation |
| title_fullStr | MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation |
| title_full_unstemmed | MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation |
| title_short | MSEANet: Multi-Scale Selective Edge Aware Network for Polyp Segmentation |
| title_sort | mseanet multi scale selective edge aware network for polyp segmentation |
| topic | polyp segmentation context fusion edge aware high-frequency information deep learning |
| url | https://www.mdpi.com/1999-4893/18/1/42 |
| work_keys_str_mv | AT botaoliu mseanetmultiscaleselectiveedgeawarenetworkforpolypsegmentation AT changqishi mseanetmultiscaleselectiveedgeawarenetworkforpolypsegmentation AT mingzhao mseanetmultiscaleselectiveedgeawarenetworkforpolypsegmentation |