FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Shurui Bai, Zhuo Deng, Jingyan Yang, Zheng Gong, Weihao Gao, Lei Shao, Fang Li, Wenbin Wei, Lan Ma
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/11/9/950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258388394442752
author Shurui Bai
Zhuo Deng
Jingyan Yang
Zheng Gong
Weihao Gao
Lei Shao
Fang Li
Wenbin Wei
Lan Ma
author_facet Shurui Bai
Zhuo Deng
Jingyan Yang
Zheng Gong
Weihao Gao
Lei Shao
Fang Li
Wenbin Wei
Lan Ma
author_sort Shurui Bai
collection DOAJ
description 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.
format Article
id doaj-art-e6032b636aff4740ae44573f11be3d09
institution OA Journals
issn 2306-5354
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-e6032b636aff4740ae44573f11be3d092025-08-20T01:56:10ZengMDPI AGBioengineering2306-53542024-09-0111995010.3390/bioengineering11090950FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and PromptsShurui Bai0Zhuo Deng1Jingyan Yang2Zheng Gong3Weihao Gao4Lei Shao5Fang Li6Wenbin Wei7Lan Ma8Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaInstitute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaBeijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaInstitute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaInstitute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaBeijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaInstitute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaBeijing Tongren Hospital, Capital Medical University, Beijing 100730, ChinaInstitute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaThe 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.https://www.mdpi.com/2306-5354/11/9/950fundus tumorsegmentationdeep learning
spellingShingle Shurui Bai
Zhuo Deng
Jingyan Yang
Zheng Gong
Weihao Gao
Lei Shao
Fang Li
Wenbin Wei
Lan Ma
FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
Bioengineering
fundus tumor
segmentation
deep learning
title FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
title_full FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
title_fullStr FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
title_full_unstemmed FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
title_short FTSNet: Fundus Tumor Segmentation Network on Multiple Scales Guided by Classification Results and Prompts
title_sort ftsnet fundus tumor segmentation network on multiple scales guided by classification results and prompts
topic fundus tumor
segmentation
deep learning
url https://www.mdpi.com/2306-5354/11/9/950
work_keys_str_mv AT shuruibai ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT zhuodeng ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT jingyanyang ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT zhenggong ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT weihaogao ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT leishao ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT fangli ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT wenbinwei ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts
AT lanma ftsnetfundustumorsegmentationnetworkonmultiplescalesguidedbyclassificationresultsandprompts