Pathological myopia(PM)is a severe ocular disease leading to blindness.As a traditional noninvasive diagnostic method,fundus color photography(FCP)is widely used in detecting PM due to its highfidelity and precision.H...Pathological myopia(PM)is a severe ocular disease leading to blindness.As a traditional noninvasive diagnostic method,fundus color photography(FCP)is widely used in detecting PM due to its highfidelity and precision.However,manual examination of fundus photographs for PM is time-consuming and prone to high error rates.Existing automated detection technologies have yet to study the detailed classification in diagnosing different stages of PM lesions.In this paper,we proposed an intelligent system which utilized Resnet101 technology to multi-categorically diagnose PM by classifying FCPs with different stages of lesions.The system subdivided different stages of PM into eight subcategories,aiming to enhance the precision and efficiency of the diagnostic process.It achieved an average accuracy rate of 98.86%in detection of PM,with an area under the curve(AUC)of 98.96%.For the eight subcategories of PM,the detection accuracy reached 99.63%,with an AUC of 99.98%.Compared with other widely used multi-class models such as VGG16,Vision Transformer(VIT),EfficientNet,this system demonstrates higher accuracy and AUC.This artificial intelligence system is designed to be easily integrated into existing clinical diagnostic tools,providing an efficient solution for large-scale PM screening.展开更多
In ophthalmology,the quality of fundus images is critical for accurate diagnosis,both in clinical practice and in artificial intelligence(AI)-assisted diagnostics.Despite the broad view provided by ultrawide-field(UWF...In ophthalmology,the quality of fundus images is critical for accurate diagnosis,both in clinical practice and in artificial intelligence(AI)-assisted diagnostics.Despite the broad view provided by ultrawide-field(UWF)imaging,pseudocolor images may conceal critical lesions necessary for precise diagnosis.To address this,we introduce UWF-Net,a sophisticated image enhancement algorithm that takes disease characteristics into consideration.Using the Fudan University ultra-wide-field image(FDUWI)dataset,which includes 11294 Optos pseudocolor and 2415 Zeiss true-color UWF images,each of which is rigorously annotated,UWF-Net combines global style modeling with feature-level lesion enhancement.Pathological consistency loss is also applied to maintain fundus feature integrity,significantly improving image quality.Quantitative and qualitative evaluations demonstrated that UWF-Net outperforms existing methods such as contrast limited adaptive histogram equalization(CLAHE)and structure and illumination constrained generative adversarial network(StillGAN),delivering superior retinal image quality,higher quality scores,and preserved feature details after enhancement.In disease classification tasks,images enhanced by UWF-Net showed notable improvements when processed with existing classification systems over those enhanced by StillGAN,demonstrating a 4.62%increase in sensitivity(SEN)and a 3.97%increase in accuracy(ACC).In a multicenter clinical setting,UWF-Net-enhanced images were preferred by ophthalmologic technicians and doctors,and yielded a significant reduction in diagnostic time((13.17±8.40)s for UWF-Net enhanced images vs(19.54±12.40)s for original images)and an increase in diagnostic accuracy(87.71%for UWF-Net enhanced images vs 80.40%for original images).Our research verifies that UWF-Net markedly improves the quality of UWF imaging,facilitating better clinical outcomes and more reliable AI-assisted disease classification.The clinical integration of UWF-Net holds great promise for enhancing diagnostic processes and patient care in ophthalmology.展开更多
We perfected the narrow spectral band fundus photographic system using interference filters at the wavelengths of 417, 478, 500, 530, 547, 570, 589, 607, 628 and 648nm. Tests about the light penetration of filters and...We perfected the narrow spectral band fundus photographic system using interference filters at the wavelengths of 417, 478, 500, 530, 547, 570, 589, 607, 628 and 648nm. Tests about the light penetration of filters and exposure of various brand films were made on this system. Studies of the contrast of fundal tissues and structures under the different narrow spectral band light were made on 43 Chinese fellow eyes. The results indicates that the interference filters of 570 nm have the highest light penetr...展开更多
Background:A variety of experimental animal models are used in basic ophthalmological research to elucidate physiological mechanisms of vision and disease pathogenesis.The choice of animal model is based on the measur...Background:A variety of experimental animal models are used in basic ophthalmological research to elucidate physiological mechanisms of vision and disease pathogenesis.The choice of animal model is based on the measurability of specific parameters or structures,the applicability of clinical measurement technologies,and the similarity to human eye function.Studies of eye pathology usually compare optical parameters between a healthy and altered state,so accurate baseline assessments are critical,but few reports have comprehensively examined the normal anatomical structures and physiological functions in these models.Methods:Three cynomolgus monkeys,six New Zealand rabbits,ten Sprague Dawley(SD)rats,and BALB/c mice were examined by fundus photography(FP),fundus fluorescein angiography(FFA),and optical coherence tomography(OCT).Results:Most retinal structures of cynomolgus monkey were anatomically similar to the corresponding human structures as revealed by FP,FFA,and OCT.New Zealand rabbits have large eyeballs,but they have large optic disc and myelinated retinal nerve fibers in their retinas,and the growth pattern of retinal vessels were also different to the human retinas.Unlike monkeys and rabbits,the retinal vessels of SD rats and BALB/c mice were widely distributed and clear.The OCT performance of them were similar with human beings except the macular.Conclusions:Monkey is a good model to study changes in retinal structure associated with fundus disease,rabbits are not suitable for studies on retinal vessel diseases and optic nerve diseases,and rats and mice are good models for retinal vascular diseases.These measures will help guide the choice of model and measurement technology and reduce the number of experimental animals required.展开更多
The eye is an immune-privileged and sensory organ in humans and animals.Anatomical,physiological,and pathobiological features share significant similarities across divergent species(1).Each compartment of the eye has ...The eye is an immune-privileged and sensory organ in humans and animals.Anatomical,physiological,and pathobiological features share significant similarities across divergent species(1).Each compartment of the eye has a unique structure and function.The anterior and posterior compartments of the eye contain endothelium(cornea),epithelium(cornea,ciliary body,iris),muscle(ciliary body),vitreous and neuronal(retina)tissues,which make the eye suitable to evaluate efficacy and safety of tissue specific drugs(2).展开更多
Background： A sensitive method is required to detect retinal hamartomas in patients with tuberous sclerosis complex （TSC）. The aim of the present study was to compare the color fundus photography, infrared imaging ...Background： A sensitive method is required to detect retinal hamartomas in patients with tuberous sclerosis complex （TSC）. The aim of the present study was to compare the color fundus photography, infrared imaging （IFG）, and optical coherence tomography （OCT） in the detection rate of retinal hamartoma in patients with TSC. Methods： This study included 11 patients （22 eyes） with TSC, who underwent color fundus photography, IFG, and spectral-domain OCT to detect retinal hamartomas. TSC1 and TSC2 mutations were tested in eight patients. Results： The mean age of the 11 patients was 8.0 ± 2.1 years. The mean spherical equivalent was -0.55 ±1.42 D by autorefraction with cycloplegia. In 11 patients （22 eyes）, OCT, infrared fundus photography, and color fundus photography revealed 26, 18, and 9 hamartomas, respectively. The predominant hamartoma was type I （55.6%）. All the hamartomas that detected by color fundus photography or IFG can be detected by OCT. Conclusion： Among the methods of color fundus photography, IFG, and OCT, the OCT has higher detection rate for retinal hamartoma in TSC patients; therefore, OCT might be promising for the clinical diagnosis of TSC.展开更多
With the popularity and development of artificial intelligence(AI),disease screening systems based on AI algorithms are gradually emerging in the medical field.Such systems can be used for primary screening of disease...With the popularity and development of artificial intelligence(AI),disease screening systems based on AI algorithms are gradually emerging in the medical field.Such systems can be used for primary screening of diseases to relieve the pressure on primary health care.In recent years,AI algorithms have demonstrated good performance in the analysis and identification of lesion signs in the macular region of fundus color photography,and a screening system for fundus lesion signs applicable to primary screening is bound to emerge in the future.Therefore,to standardize the design and clinical application of macular region lesion sign screening systems based on AI algorithms,the Ocular Fundus Diseases Group of Chinese Ophthalmological Society,in collaboration with relevant experts,developed this guideline after investigating issues,discussing production evidence,and holding guideline workshops.It aimed to establish uniform standards for the definition of the macular region and lesion signs,AI adoption scenarios,algorithm model construction,dataset establishment and labeling,architecture and function design,and image data acquisition for the screening system to guide the implementation of the screening work.展开更多
基金supported by the Natural National Science Foundation of China(62175156)the Science and technology innovation project of Shanghai Science and Technology Commission(22S31903000)Collaborative Innovation Project of Shanghai Institute of Technology(XTCX2022-27)。
文摘Pathological myopia(PM)is a severe ocular disease leading to blindness.As a traditional noninvasive diagnostic method,fundus color photography(FCP)is widely used in detecting PM due to its highfidelity and precision.However,manual examination of fundus photographs for PM is time-consuming and prone to high error rates.Existing automated detection technologies have yet to study the detailed classification in diagnosing different stages of PM lesions.In this paper,we proposed an intelligent system which utilized Resnet101 technology to multi-categorically diagnose PM by classifying FCPs with different stages of lesions.The system subdivided different stages of PM into eight subcategories,aiming to enhance the precision and efficiency of the diagnostic process.It achieved an average accuracy rate of 98.86%in detection of PM,with an area under the curve(AUC)of 98.96%.For the eight subcategories of PM,the detection accuracy reached 99.63%,with an AUC of 99.98%.Compared with other widely used multi-class models such as VGG16,Vision Transformer(VIT),EfficientNet,this system demonstrates higher accuracy and AUC.This artificial intelligence system is designed to be easily integrated into existing clinical diagnostic tools,providing an efficient solution for large-scale PM screening.
基金supported by the National Natural Science Foundation of China(82020108006 and 81730025 to Chen Zhao,U2001209 to Bo Yan)the Excellent Academic Leaders of Shanghai(18XD1401000 to Chen Zhao)the Natural Science Foundation of Shanghai,China(21ZR1406600 to Weimin Tan).
文摘In ophthalmology,the quality of fundus images is critical for accurate diagnosis,both in clinical practice and in artificial intelligence(AI)-assisted diagnostics.Despite the broad view provided by ultrawide-field(UWF)imaging,pseudocolor images may conceal critical lesions necessary for precise diagnosis.To address this,we introduce UWF-Net,a sophisticated image enhancement algorithm that takes disease characteristics into consideration.Using the Fudan University ultra-wide-field image(FDUWI)dataset,which includes 11294 Optos pseudocolor and 2415 Zeiss true-color UWF images,each of which is rigorously annotated,UWF-Net combines global style modeling with feature-level lesion enhancement.Pathological consistency loss is also applied to maintain fundus feature integrity,significantly improving image quality.Quantitative and qualitative evaluations demonstrated that UWF-Net outperforms existing methods such as contrast limited adaptive histogram equalization(CLAHE)and structure and illumination constrained generative adversarial network(StillGAN),delivering superior retinal image quality,higher quality scores,and preserved feature details after enhancement.In disease classification tasks,images enhanced by UWF-Net showed notable improvements when processed with existing classification systems over those enhanced by StillGAN,demonstrating a 4.62%increase in sensitivity(SEN)and a 3.97%increase in accuracy(ACC).In a multicenter clinical setting,UWF-Net-enhanced images were preferred by ophthalmologic technicians and doctors,and yielded a significant reduction in diagnostic time((13.17±8.40)s for UWF-Net enhanced images vs(19.54±12.40)s for original images)and an increase in diagnostic accuracy(87.71%for UWF-Net enhanced images vs 80.40%for original images).Our research verifies that UWF-Net markedly improves the quality of UWF imaging,facilitating better clinical outcomes and more reliable AI-assisted disease classification.The clinical integration of UWF-Net holds great promise for enhancing diagnostic processes and patient care in ophthalmology.
文摘We perfected the narrow spectral band fundus photographic system using interference filters at the wavelengths of 417, 478, 500, 530, 547, 570, 589, 607, 628 and 648nm. Tests about the light penetration of filters and exposure of various brand films were made on this system. Studies of the contrast of fundal tissues and structures under the different narrow spectral band light were made on 43 Chinese fellow eyes. The results indicates that the interference filters of 570 nm have the highest light penetr...
基金This study was funded by Science and Technology Projects of Guangdong Province(Nos.2019A030317002,2017A030303013,2013B060300003).
文摘Background:A variety of experimental animal models are used in basic ophthalmological research to elucidate physiological mechanisms of vision and disease pathogenesis.The choice of animal model is based on the measurability of specific parameters or structures,the applicability of clinical measurement technologies,and the similarity to human eye function.Studies of eye pathology usually compare optical parameters between a healthy and altered state,so accurate baseline assessments are critical,but few reports have comprehensively examined the normal anatomical structures and physiological functions in these models.Methods:Three cynomolgus monkeys,six New Zealand rabbits,ten Sprague Dawley(SD)rats,and BALB/c mice were examined by fundus photography(FP),fundus fluorescein angiography(FFA),and optical coherence tomography(OCT).Results:Most retinal structures of cynomolgus monkey were anatomically similar to the corresponding human structures as revealed by FP,FFA,and OCT.New Zealand rabbits have large eyeballs,but they have large optic disc and myelinated retinal nerve fibers in their retinas,and the growth pattern of retinal vessels were also different to the human retinas.Unlike monkeys and rabbits,the retinal vessels of SD rats and BALB/c mice were widely distributed and clear.The OCT performance of them were similar with human beings except the macular.Conclusions:Monkey is a good model to study changes in retinal structure associated with fundus disease,rabbits are not suitable for studies on retinal vessel diseases and optic nerve diseases,and rats and mice are good models for retinal vascular diseases.These measures will help guide the choice of model and measurement technology and reduce the number of experimental animals required.
文摘The eye is an immune-privileged and sensory organ in humans and animals.Anatomical,physiological,and pathobiological features share significant similarities across divergent species(1).Each compartment of the eye has a unique structure and function.The anterior and posterior compartments of the eye contain endothelium(cornea),epithelium(cornea,ciliary body,iris),muscle(ciliary body),vitreous and neuronal(retina)tissues,which make the eye suitable to evaluate efficacy and safety of tissue specific drugs(2).
文摘Background： A sensitive method is required to detect retinal hamartomas in patients with tuberous sclerosis complex （TSC）. The aim of the present study was to compare the color fundus photography, infrared imaging （IFG）, and optical coherence tomography （OCT） in the detection rate of retinal hamartoma in patients with TSC. Methods： This study included 11 patients （22 eyes） with TSC, who underwent color fundus photography, IFG, and spectral-domain OCT to detect retinal hamartomas. TSC1 and TSC2 mutations were tested in eight patients. Results： The mean age of the 11 patients was 8.0 ± 2.1 years. The mean spherical equivalent was -0.55 ±1.42 D by autorefraction with cycloplegia. In 11 patients （22 eyes）, OCT, infrared fundus photography, and color fundus photography revealed 26, 18, and 9 hamartomas, respectively. The predominant hamartoma was type I （55.6%）. All the hamartomas that detected by color fundus photography or IFG can be detected by OCT. Conclusion： Among the methods of color fundus photography, IFG, and OCT, the OCT has higher detection rate for retinal hamartoma in TSC patients; therefore, OCT might be promising for the clinical diagnosis of TSC.
文摘With the popularity and development of artificial intelligence(AI),disease screening systems based on AI algorithms are gradually emerging in the medical field.Such systems can be used for primary screening of diseases to relieve the pressure on primary health care.In recent years,AI algorithms have demonstrated good performance in the analysis and identification of lesion signs in the macular region of fundus color photography,and a screening system for fundus lesion signs applicable to primary screening is bound to emerge in the future.Therefore,to standardize the design and clinical application of macular region lesion sign screening systems based on AI algorithms,the Ocular Fundus Diseases Group of Chinese Ophthalmological Society,in collaboration with relevant experts,developed this guideline after investigating issues,discussing production evidence,and holding guideline workshops.It aimed to establish uniform standards for the definition of the macular region and lesion signs,AI adoption scenarios,algorithm model construction,dataset establishment and labeling,architecture and function design,and image data acquisition for the screening system to guide the implementation of the screening work.
