EFCNet enhances the efficiency of segmenting clinically significant small medical objects
Abstract Efficient segmentation of small hyperreflective dots, key biomarkers for diseases like macular edema, is critical for diagnosis and treatment monitoring.However, existing models, including Convolutional Neural Networks (CNNs) and Transformers, struggle with these minute structures due to in...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-93171-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156591329837056 |
|---|---|
| author | Lingjie Kong Qiaoling Wei Chengming Xu Xiaofeng Ye Wei Liu Min Wang Yanwei Fu Han Chen |
| author_facet | Lingjie Kong Qiaoling Wei Chengming Xu Xiaofeng Ye Wei Liu Min Wang Yanwei Fu Han Chen |
| author_sort | Lingjie Kong |
| collection | DOAJ |
| description | Abstract Efficient segmentation of small hyperreflective dots, key biomarkers for diseases like macular edema, is critical for diagnosis and treatment monitoring.However, existing models, including Convolutional Neural Networks (CNNs) and Transformers, struggle with these minute structures due to information loss.To address this, we introduce EFCNet, which integrates the Cross-Stage Axial Attention (CSAA) module for enhanced feature fusion and the Multi-Precision Supervision (MPS) module for improved hierarchical guidance. We evaluated EFCNet on two datasets: S-HRD, comprising 313 retinal OCT scans from patients with macular edema, and S-Polyp, a 229-image subset of the publicly available CVC-ClinicDB colonoscopy dataset. EFCNet outperformed state-of-the-art models, achieving average Dice Similarity Coefficient (DSC) gains of 4.88% on S-HRD and 3.49% on S-Polyp, alongside Intersection over Union (IoU) improvements of 3.77% and 3.25%, respectively. Notably, smaller objects benefit most, highlighting EFCNet’s effectiveness where conventional models underperform. Unlike U-Net-Large, which offers marginal gains with increased scale, EFCNet’s superior performance is driven by its novel design. These findings demonstrate its effectiveness and potential utility in clinical practice. |
| format | Article |
| id | doaj-art-933779ae35dc4b0aa0b63b40d8eca296 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-933779ae35dc4b0aa0b63b40d8eca2962025-08-20T02:24:29ZengNature PortfolioScientific Reports2045-23222025-04-0115111110.1038/s41598-025-93171-6EFCNet enhances the efficiency of segmenting clinically significant small medical objectsLingjie Kong0Qiaoling Wei1Chengming Xu2Xiaofeng Ye3Wei Liu4Min Wang5Yanwei Fu6Han Chen7School of Data Science, Fudan UniversityEye Institute, Department of Ophthalmology, Eye & ENT Hospital, Fudan UniversitySchool of Data Science, Fudan UniversityEye Institute, Department of Ophthalmology, Eye & ENT Hospital, Fudan UniversityEye Institute, Department of Ophthalmology, Eye & ENT Hospital, Fudan UniversityEye Institute, Department of Ophthalmology, Eye & ENT Hospital, Fudan UniversitySchool of Data Science, Fudan UniversityEye Institute, Department of Ophthalmology, Eye & ENT Hospital, Fudan UniversityAbstract Efficient segmentation of small hyperreflective dots, key biomarkers for diseases like macular edema, is critical for diagnosis and treatment monitoring.However, existing models, including Convolutional Neural Networks (CNNs) and Transformers, struggle with these minute structures due to information loss.To address this, we introduce EFCNet, which integrates the Cross-Stage Axial Attention (CSAA) module for enhanced feature fusion and the Multi-Precision Supervision (MPS) module for improved hierarchical guidance. We evaluated EFCNet on two datasets: S-HRD, comprising 313 retinal OCT scans from patients with macular edema, and S-Polyp, a 229-image subset of the publicly available CVC-ClinicDB colonoscopy dataset. EFCNet outperformed state-of-the-art models, achieving average Dice Similarity Coefficient (DSC) gains of 4.88% on S-HRD and 3.49% on S-Polyp, alongside Intersection over Union (IoU) improvements of 3.77% and 3.25%, respectively. Notably, smaller objects benefit most, highlighting EFCNet’s effectiveness where conventional models underperform. Unlike U-Net-Large, which offers marginal gains with increased scale, EFCNet’s superior performance is driven by its novel design. These findings demonstrate its effectiveness and potential utility in clinical practice.https://doi.org/10.1038/s41598-025-93171-6Medical image segmentationSmall object detectionConvolutional neural networksAxial attention mechanismsMulti-precision supervisionOptical coherence tomography |
| spellingShingle | Lingjie Kong Qiaoling Wei Chengming Xu Xiaofeng Ye Wei Liu Min Wang Yanwei Fu Han Chen EFCNet enhances the efficiency of segmenting clinically significant small medical objects Scientific Reports Medical image segmentation Small object detection Convolutional neural networks Axial attention mechanisms Multi-precision supervision Optical coherence tomography |
| title | EFCNet enhances the efficiency of segmenting clinically significant small medical objects |
| title_full | EFCNet enhances the efficiency of segmenting clinically significant small medical objects |
| title_fullStr | EFCNet enhances the efficiency of segmenting clinically significant small medical objects |
| title_full_unstemmed | EFCNet enhances the efficiency of segmenting clinically significant small medical objects |
| title_short | EFCNet enhances the efficiency of segmenting clinically significant small medical objects |
| title_sort | efcnet enhances the efficiency of segmenting clinically significant small medical objects |
| topic | Medical image segmentation Small object detection Convolutional neural networks Axial attention mechanisms Multi-precision supervision Optical coherence tomography |
| url | https://doi.org/10.1038/s41598-025-93171-6 |
| work_keys_str_mv | AT lingjiekong efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT qiaolingwei efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT chengmingxu efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT xiaofengye efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT weiliu efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT minwang efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT yanweifu efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects AT hanchen efcnetenhancestheefficiencyofsegmentingclinicallysignificantsmallmedicalobjects |