FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
Open Access
- 22 September 2024
- journal article
- research article
- Published by MDPI AG in Bioengineering
- Vol. 11 (9) , 950
Abstract
The segmentation of fundus tumors is critical for ophthalmic diagnosis and treatment, yet it presents unique challenges due to the variability in lesion size and shape. Our study introduces Fundus Tumor Segmentation Network (FTSNet), a novel segmentation network designed to address these challenges by leveraging classification results and prompt learning. Our key innovation is the multiscale feature extractor and the dynamic prompt head. Multiscale feature extractors are proficient in eliciting a spectrum of feature information from the original image across disparate scales. This proficiency is fundamental for deciphering the subtle details and patterns embedded in the image at multiple levels of granularity. Meanwhile, a dynamic prompt head is engineered to engender bespoke segmentation heads for each image, customizing the segmentation process to align with the distinctive attributes of the image under consideration. We also present the Fundus Tumor Segmentation (FTS) dataset, comprising 254 pairs of fundus images with tumor lesions and reference segmentations. Experiments demonstrate FTSNet’s superior performance over existing methods, achieving a mean Intersection over Union (mIoU) of 0.8254 and mean Dice (mDice) of 0.9042. The results highlight the potential of our approach in advancing the accuracy and efficiency of fundus tumor segmentation.Keywords
Funding Information
- Science and Technology Innovation Committee of Shenzhen-Platform and Carrier (International Science and Technology Information Center) (KCXFZ20211020163813019, 82000916, 2024-4-20510)
- Shenzhen Bay Lab (KCXFZ20211020163813019, 82000916, 2024-4-20510)
- Shenzhen Science and Technology Innovation Committee (KCXFZ20211020163813019, 82000916, 2024-4-20510)
- National Natural Science Foundation of China (KCXFZ20211020163813019, 82000916, 2024-4-20510)
- Capital Health Research and Development of Special (KCXFZ20211020163813019, 82000916, 2024-4-20510)
This publication has 26 references indexed in Scilit:
- Trends in application of fundus fluorescein angiography in fundus diseases during a recent ten-year periodPhotodiagnosis and Photodynamic Therapy, 2024
- Fundus photograph-based cataract evaluation network using deep learningFrontiers in Physics, 2024
- Semi-supervised segmentation of retinoblastoma tumors in fundus imagesScientific Reports, 2023
- RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical BenchmarkIEEE Journal of Biomedical and Health Informatics, 2022
- Fundus image segmentation via hierarchical feature learningComputers in Biology and Medicine, 2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed dataISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Uveal melanomaCancer Treatment Reviews, 2012
- Uveal Melanoma: Trends in Incidence, Treatment, and SurvivalOphthalmology, 2011
- Incidence of uveal melanoma in the United States: 1973–1997Ophthalmology, 2003