Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios

Most existing optic disc (OD) and cup (OC) segmentation models are biased to the dominant size and easy class (normal class), resulting in suboptimal performances on glaucoma-confirmed samples. Thus, these models are not optimal choices for assisting in tracking glaucoma progression and prognosis. M...

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Liu, Jicong Zhang
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7255
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228031825641472
author Kai Liu
Jicong Zhang
author_facet Kai Liu
Jicong Zhang
author_sort Kai Liu
collection DOAJ
description Most existing optic disc (OD) and cup (OC) segmentation models are biased to the dominant size and easy class (normal class), resulting in suboptimal performances on glaucoma-confirmed samples. Thus, these models are not optimal choices for assisting in tracking glaucoma progression and prognosis. Moreover, fully supervised models employing annotated glaucoma samples can achieve superior performances, although restricted by the high cost of collecting and annotating the glaucoma samples. Therefore, in this paper, we are dedicated to developing a glaucoma-specialized model by exploiting low-cost annotated normal fundus images, simultaneously adapting various common scenarios in clinical practice. We employ a contrastive learning and domain adaptation-based model by exploiting shared knowledge from normal samples. To capture glaucoma-related features, we utilize a Gram matrix to encode style information and the domain adaptation strategy to encode domain information, followed by narrowing the style and domain gaps between normal and glaucoma samples by contrastive and adversarial learning, respectively. To validate the efficacy of our proposed model, we conducted experiments utilizing two public datasets to mimic various common scenarios. The results demonstrate the superior performance of our proposed model across multi-scenarios, showcasing its proficiency in both the segmentation- and glaucoma-related metrics. In summary, our study illustrates a concerted effort to target confirmed glaucoma samples, mitigating the inherent bias issue in most existing models. Moreover, we propose an annotation-efficient strategy that exploits low-cost, normal-labeled fundus samples, mitigating the economic- and labor-related burdens by employing a fully supervised strategy. Simultaneously, our approach demonstrates its adaptability across various scenarios, highlighting its potential utility in both assisting in the monitoring of glaucoma progression and assessing glaucoma prognosis.
format Article
id doaj-art-c747aedda284432a8799d69bd26cdbcb
institution OA Journals
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c747aedda284432a8799d69bd26cdbcb2025-08-20T02:04:40ZengMDPI AGSensors1424-82202024-11-012422725510.3390/s24227255Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical ScenariosKai Liu0Jicong Zhang1School of Biological Science and Medical Engineering, Beihang University, Beijing 100083, ChinaSchool of Biological Science and Medical Engineering, Beihang University, Beijing 100083, ChinaMost existing optic disc (OD) and cup (OC) segmentation models are biased to the dominant size and easy class (normal class), resulting in suboptimal performances on glaucoma-confirmed samples. Thus, these models are not optimal choices for assisting in tracking glaucoma progression and prognosis. Moreover, fully supervised models employing annotated glaucoma samples can achieve superior performances, although restricted by the high cost of collecting and annotating the glaucoma samples. Therefore, in this paper, we are dedicated to developing a glaucoma-specialized model by exploiting low-cost annotated normal fundus images, simultaneously adapting various common scenarios in clinical practice. We employ a contrastive learning and domain adaptation-based model by exploiting shared knowledge from normal samples. To capture glaucoma-related features, we utilize a Gram matrix to encode style information and the domain adaptation strategy to encode domain information, followed by narrowing the style and domain gaps between normal and glaucoma samples by contrastive and adversarial learning, respectively. To validate the efficacy of our proposed model, we conducted experiments utilizing two public datasets to mimic various common scenarios. The results demonstrate the superior performance of our proposed model across multi-scenarios, showcasing its proficiency in both the segmentation- and glaucoma-related metrics. In summary, our study illustrates a concerted effort to target confirmed glaucoma samples, mitigating the inherent bias issue in most existing models. Moreover, we propose an annotation-efficient strategy that exploits low-cost, normal-labeled fundus samples, mitigating the economic- and labor-related burdens by employing a fully supervised strategy. Simultaneously, our approach demonstrates its adaptability across various scenarios, highlighting its potential utility in both assisting in the monitoring of glaucoma progression and assessing glaucoma prognosis.https://www.mdpi.com/1424-8220/24/22/7255color fundus imageglaucoma-specialized modelprogression trackingOD/OC segmentationadapted multi-scenarios
spellingShingle Kai Liu
Jicong Zhang
Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios
Sensors
color fundus image
glaucoma-specialized model
progression tracking
OD/OC segmentation
adapted multi-scenarios
title Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios
title_full Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios
title_fullStr Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios
title_full_unstemmed Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios
title_short Development of a Cost-Efficient and Glaucoma-Specialized OD/OC Segmentation Model for Varying Clinical Scenarios
title_sort development of a cost efficient and glaucoma specialized od oc segmentation model for varying clinical scenarios
topic color fundus image
glaucoma-specialized model
progression tracking
OD/OC segmentation
adapted multi-scenarios
url https://www.mdpi.com/1424-8220/24/22/7255
work_keys_str_mv AT kailiu developmentofacostefficientandglaucomaspecializedodocsegmentationmodelforvaryingclinicalscenarios
AT jicongzhang developmentofacostefficientandglaucomaspecializedodocsegmentationmodelforvaryingclinicalscenarios