PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images
Abstract Retinal microaneurysm (MA) is a definite earliest clinical sigh of diabetic retinopathy (DR). Its automatic segmentation is key to realizing intelligent screening for early DR, which can significantly reduce the risk of visual impairment in patients. However, the minute scale and subtle con...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.13275 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850118429518856192 |
|---|---|
| author | Jiaxin Lu Beiji Zou Xiaoxia Xiao Qinghua Peng Junfeng Yan Wensheng Zhang Kejuan Yue |
| author_facet | Jiaxin Lu Beiji Zou Xiaoxia Xiao Qinghua Peng Junfeng Yan Wensheng Zhang Kejuan Yue |
| author_sort | Jiaxin Lu |
| collection | DOAJ |
| description | Abstract Retinal microaneurysm (MA) is a definite earliest clinical sigh of diabetic retinopathy (DR). Its automatic segmentation is key to realizing intelligent screening for early DR, which can significantly reduce the risk of visual impairment in patients. However, the minute scale and subtle contrast of MAs against the background pose challenges for segmentation. This paper focuses on automatic MA segmentation in fundus images. A novel pyramid feature fusion network (PFFNet) that progressively develops and fuses rich contextual information by integrating two pyramid modules is proposed. Multiple global pyramid scene parsing (GPSP) modules are introduced between the encoder and decoder to provide diverse global contextual information for the decoder through reconstructing skip connections. Additionally, a spatial scale‐aware pyramid (SSAP) module is introduced to dynamically fuse multi‐scale contextual information. This rich contextual information will help to identify MAs from low‐contrast background. Furthermore, to mitigate issue related to category imbalance, a combo loss function is introduced. Finally, to validate the effectiveness of the proposed method, experiments are conducted on two publicly available datasets, IDRiD and DDR, and PFFNet is compared with several state‐of‐the‐art models. The experimental results demonstrate the superiority of our PFFNet in the MA segmentation task. |
| format | Article |
| id | doaj-art-81ec0772bf1b4692bb77e2c86254a720 |
| institution | OA Journals |
| issn | 1751-9659 1751-9667 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj-art-81ec0772bf1b4692bb77e2c86254a7202025-08-20T02:35:53ZengWileyIET Image Processing1751-96591751-96672024-12-0118144653466510.1049/ipr2.13275PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus imagesJiaxin Lu0Beiji Zou1Xiaoxia Xiao2Qinghua Peng3Junfeng Yan4Wensheng Zhang5Kejuan Yue6School of Informatics Hunan University of Chinese Medicine Changsha Hunan Province ChinaSchool of Informatics Hunan University of Chinese Medicine Changsha Hunan Province ChinaSchool of Informatics Hunan University of Chinese Medicine Changsha Hunan Province ChinaAI TCM Lab Hunan Hunan University of Chinese Medicine Changsha Hunan Province ChinaSchool of Informatics Hunan University of Chinese Medicine Changsha Hunan Province ChinaSchool of Informatics Hunan University of Chinese Medicine Changsha Hunan Province ChinaSchool of Computer Science Hunan First Normal University Changsha Hunan Province ChinaAbstract Retinal microaneurysm (MA) is a definite earliest clinical sigh of diabetic retinopathy (DR). Its automatic segmentation is key to realizing intelligent screening for early DR, which can significantly reduce the risk of visual impairment in patients. However, the minute scale and subtle contrast of MAs against the background pose challenges for segmentation. This paper focuses on automatic MA segmentation in fundus images. A novel pyramid feature fusion network (PFFNet) that progressively develops and fuses rich contextual information by integrating two pyramid modules is proposed. Multiple global pyramid scene parsing (GPSP) modules are introduced between the encoder and decoder to provide diverse global contextual information for the decoder through reconstructing skip connections. Additionally, a spatial scale‐aware pyramid (SSAP) module is introduced to dynamically fuse multi‐scale contextual information. This rich contextual information will help to identify MAs from low‐contrast background. Furthermore, to mitigate issue related to category imbalance, a combo loss function is introduced. Finally, to validate the effectiveness of the proposed method, experiments are conducted on two publicly available datasets, IDRiD and DDR, and PFFNet is compared with several state‐of‐the‐art models. The experimental results demonstrate the superiority of our PFFNet in the MA segmentation task.https://doi.org/10.1049/ipr2.13275CADdiseasesfeature extractionimage processingimage segmentationmedical image processing |
| spellingShingle | Jiaxin Lu Beiji Zou Xiaoxia Xiao Qinghua Peng Junfeng Yan Wensheng Zhang Kejuan Yue PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images IET Image Processing CAD diseases feature extraction image processing image segmentation medical image processing |
| title | PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images |
| title_full | PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images |
| title_fullStr | PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images |
| title_full_unstemmed | PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images |
| title_short | PFFNet: A pyramid feature fusion network for microaneurysm segmentation in fundus images |
| title_sort | pffnet a pyramid feature fusion network for microaneurysm segmentation in fundus images |
| topic | CAD diseases feature extraction image processing image segmentation medical image processing |
| url | https://doi.org/10.1049/ipr2.13275 |
| work_keys_str_mv | AT jiaxinlu pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages AT beijizou pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages AT xiaoxiaxiao pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages AT qinghuapeng pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages AT junfengyan pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages AT wenshengzhang pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages AT kejuanyue pffnetapyramidfeaturefusionnetworkformicroaneurysmsegmentationinfundusimages |