Pub Date : 2023-12-20DOI: 10.1101/2023.12.19.23298260
Berkeley K Fahrenthold, Matthew R Cavanaugh, Madhura Tamhankar, Byron L Lam, Steven E Feldon, Brent A Johnson, Krystel R Huxlin
Purpose: Damage to the adult primary visual cortex (V1) causes vision loss in the contralateral hemifield, initiating a process of trans-synaptic retrograde degeneration (TRD). Here, we examined retinal correlates of TRD using a new metric to account for global changes in inner retinal thickness, and asked if perceptual training in the intact or blind field impacts its progression. Methods: We performed a meta-analysis of optical coherence tomography (OCT) data in 48 participants with unilateral V1 stroke and homonymous visual defects, who completed clinical trial NCT03350919. After measuring the thickness of the macular ganglion cell and inner plexiform layers (GCL-IPL), and the peripapillary retinal nerve fiber layer (RNFL), we computed individual laterality indices (LI) at baseline and after ~6 months of daily motion discrimination training in the intact- or blind-field. Increasingly positive LI denoted greater layer thinning in retinal regions affected versus unaffected by the cortical damage. Results: Pre-training, the affected GCL-IPL and RNFL were thinner than their unaffected counterparts, generating LI values positively correlated with time since stroke. Participants trained in their intact-field exhibited increased LIGCL-IPL. Those trained in their blind-field had no significant change in LIGCL-IPL. LIRNFL did not change in either group. Conclusions: Relative shrinkage of the affected versus unaffected macular GCL-IPL can be reliably measured at an individual level and increases with time post-V1 stroke. Relative thinning progressed during intact-field training, but appeared to be halted by training within the blind field, suggesting a potentially neuroprotective effect of this simple behavioral intervention.
{"title":"Training in cortically-blind fields confers patient-specific benefit against retinal thinning after occipital stroke","authors":"Berkeley K Fahrenthold, Matthew R Cavanaugh, Madhura Tamhankar, Byron L Lam, Steven E Feldon, Brent A Johnson, Krystel R Huxlin","doi":"10.1101/2023.12.19.23298260","DOIUrl":"https://doi.org/10.1101/2023.12.19.23298260","url":null,"abstract":"Purpose: Damage to the adult primary visual cortex (V1) causes vision loss in the contralateral hemifield, initiating a process of trans-synaptic retrograde degeneration (TRD). Here, we examined retinal correlates of TRD using a new metric to account for global changes in inner retinal thickness, and asked if perceptual training in the intact or blind field impacts its progression.\u0000Methods: We performed a meta-analysis of optical coherence tomography (OCT) data in 48 participants with unilateral V1 stroke and homonymous visual defects, who completed clinical trial NCT03350919. After measuring the thickness of the macular ganglion cell and inner plexiform layers (GCL-IPL), and the peripapillary retinal nerve fiber layer (RNFL), we computed individual laterality indices (LI) at baseline and after ~6 months of daily motion discrimination training in the intact- or blind-field. Increasingly positive LI denoted greater layer thinning in retinal regions affected versus unaffected by the cortical damage.\u0000Results: Pre-training, the affected GCL-IPL and RNFL were thinner than their unaffected counterparts, generating LI values positively correlated with time since stroke. Participants trained in their intact-field exhibited increased LIGCL-IPL. Those trained in their blind-field had no significant change in LIGCL-IPL. LIRNFL did not change in either group.\u0000Conclusions: Relative shrinkage of the affected versus unaffected macular GCL-IPL can be reliably measured at an individual level and increases with time post-V1 stroke. Relative thinning progressed during intact-field training, but appeared to be halted by training within the blind field, suggesting a potentially neuroprotective effect of this simple behavioral intervention.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138826023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-14DOI: 10.1101/2023.12.13.23299931
Min Shi, Yan Luo, Yu Tian, Lucy Shen, Tobias Elze, Nazlee Zebardast, Mohammad Eslami, Saber Kazeminasab, Michael V. Boland, David S. Friedman, Louis R. Pasquale, Mengyu Wang
Objective To develop an equitable artificial intelligence model for glaucoma screening.
目标 为青光眼筛查开发一个公平的人工智能模型。
{"title":"Equitable Artificial Intelligence for Glaucoma Screening with Fair Identity Normalization","authors":"Min Shi, Yan Luo, Yu Tian, Lucy Shen, Tobias Elze, Nazlee Zebardast, Mohammad Eslami, Saber Kazeminasab, Michael V. Boland, David S. Friedman, Louis R. Pasquale, Mengyu Wang","doi":"10.1101/2023.12.13.23299931","DOIUrl":"https://doi.org/10.1101/2023.12.13.23299931","url":null,"abstract":"<strong>Objective</strong> To develop an equitable artificial intelligence model for glaucoma screening.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138742009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-14DOI: 10.1101/2023.12.12.23299846
Asieh Soltanipour, Roya Arian, Ali Aghababaei, Raheleh Kafieh, Fereshteh Ashtari
Background Our purpose was to investigate the most relevant and discriminating clinical feature set of Scanning laser ophthalmoscopy (SLO) images, which could differentiate multiple sclerosis (MS) and healthy control (HC) patients.
{"title":"Analyzing morphological alternations of vessels in multiple Sclerosis using SLO images of the eyes","authors":"Asieh Soltanipour, Roya Arian, Ali Aghababaei, Raheleh Kafieh, Fereshteh Ashtari","doi":"10.1101/2023.12.12.23299846","DOIUrl":"https://doi.org/10.1101/2023.12.12.23299846","url":null,"abstract":"<strong>Background</strong> Our purpose was to investigate the most relevant and discriminating clinical feature set of Scanning laser ophthalmoscopy (SLO) images, which could differentiate multiple sclerosis (MS) and healthy control (HC) patients.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138717430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose To identify the genetic variants associated with diabetic retinopathy in type 2 patients from the UK Biobank cohort (n = 17,015) and supporting replication cohorts GODARTS (n = 5,013), GOSHARE (n = 1,754), Caucasian Australians (n = 518), FinnGen (n = 206,664) and Chinese (n = 1,007). Methods Totally eleven genome-wide association studies were applied to search for significant genetic variants. Results We found 5 different loci associated with type 2 diabetic retinopathy in or nearest gene EYA2, MPDZ, NTNG1, CTAGE14P and MREGP1. In the primary GWAS, a significant SNP rs6066146 located in gene EYA2 showed a p value of 4.21 x 10-8 and may play a role in the development of the disease, with "spleen" reaching a significant level produced by tissue expression analysis. Corresponding heritability of DR was estimated to be 26.73% by SumHer. Among five genes, we found that genes EYA2, MPDZ, NTNG1 had genetic interactions and may affect the complex development of retinal blood vessels. Conclusion Diabetic retinopathy is a complication of diabetes that affects the eyes. It is highly likely to occur when high blood sugar damages the retinal blood vessels. There is limited awareness regarding the pathogenesis of DR. Our study identified multiple loci associated with diabetic retinopathy, which may lead to personalized treatments to reduce the burden of the disease. Keywords: Diabetic retinopathy; UK Biobank; genome-wide association study; tissue expression analysis; heritability.
{"title":"Multiple genome-wide association studies of type 2 diabetes implicate several genes are associated with diabetic retinopathy based on UK Biobank","authors":"Tengda Cai, Qi Pan, Yiwen Tao, Charvi Nangia, Aravind Lathika Rajendrakumar, Tania Dottorini, Mainul Haque, Colin Palmer, Weihua Meng","doi":"10.1101/2023.12.02.23299320","DOIUrl":"https://doi.org/10.1101/2023.12.02.23299320","url":null,"abstract":"<em>Purpose</em>\u0000To identify the genetic variants associated with diabetic retinopathy in type 2 patients from the UK Biobank cohort (n = 17,015) and supporting replication cohorts GODARTS (n = 5,013), GOSHARE (n = 1,754), Caucasian Australians (n = 518), FinnGen (n = 206,664) and Chinese (n = 1,007). <em>Methods</em>\u0000Totally eleven genome-wide association studies were applied to search for significant genetic variants. <em>Results</em>\u0000We found 5 different loci associated with type 2 diabetic retinopathy in or nearest gene EYA2, MPDZ, NTNG1, CTAGE14P and MREGP1. In the primary GWAS, a significant SNP rs6066146 located in gene EYA2 showed a p value of 4.21 x 10-8 and may play a role in the development of the disease, with \"spleen\" reaching a significant level produced by tissue expression analysis. Corresponding heritability of DR was estimated to be 26.73% by SumHer. Among five genes, we found that genes EYA2, MPDZ, NTNG1 had genetic interactions and may affect the complex development of retinal blood vessels. <em>Conclusion</em>\u0000Diabetic retinopathy is a complication of diabetes that affects the eyes. It is highly likely to occur when high blood sugar damages the retinal blood vessels. There is limited awareness regarding the pathogenesis of DR. Our study identified multiple loci associated with diabetic retinopathy, which may lead to personalized treatments to reduce the burden of the disease.\u0000<strong>Keywords</strong>: Diabetic retinopathy; UK Biobank; genome-wide association study; tissue expression analysis; heritability.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138521641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.1101/2023.11.29.23299210
Neil Dogra, Bryan V. Redmond, Selena Lilley, Brent A. Johnson, Byron L. Lam, Madhura Tamhankar, Steven E. Feldon, Berkeley Fahrenthold, Jingyi Yang, Krystel R. Huxlin, Matthew R. Cavanaugh
Background/Objectives Stroke damage to the primary visual cortex induces large, homonymous visual field defects that impair daily living. Here, we asked if vision-related quality of life (V-QoL) is impacted by time since stroke.
{"title":"The Natural History of Vision-Related Quality of Life after Unilateral Occipital Stroke","authors":"Neil Dogra, Bryan V. Redmond, Selena Lilley, Brent A. Johnson, Byron L. Lam, Madhura Tamhankar, Steven E. Feldon, Berkeley Fahrenthold, Jingyi Yang, Krystel R. Huxlin, Matthew R. Cavanaugh","doi":"10.1101/2023.11.29.23299210","DOIUrl":"https://doi.org/10.1101/2023.11.29.23299210","url":null,"abstract":"<strong>Background/Objectives</strong> Stroke damage to the primary visual cortex induces large, homonymous visual field defects that impair daily living. Here, we asked if vision-related quality of life (V-QoL) is impacted by time since stroke.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138542321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-29DOI: 10.1101/2023.11.28.23299139
Andreas Katsimpris, Sebastian-Edgar Baumeister, Hansjörg Baurecht, Andrew J Tatham, Michael Nolde
The association of central corneal thickness (CCT) with primary open-angle glaucoma (POAG) remains uncertain. Although, several observational studies assessing this relationship, have reported an inverse association between CCT and POAG, this could be the result of collider bias. In this study, we leveraged human genetic data to assess through Mendelian randomization (MR) the effect of CCT on POAG risk, and whether this effect is mediated by intraocular pressure (IOP) changes. We used 24 single-nucleotide polymorphisms (SNPs) associated with CCT (P-value < 5×10-8) from a genome-wide association study (GWAS) (N = 17,803) provided by the International Glaucoma Genetics Consortium and 53 SNPs associated with IOP (P-value < 5×10-8) from a GWAS of UK Biobank (UKBB) (N = 97,653). We related these instruments with POAG using a GWAS meta-analysis of 8,283 POAG cases and 753,827 controls from UKBB and FinnGen. MR analysis suggested a positive association between CCT and POAG (odds ratio of POAG per 50μm increase in CCT: 1.38; 95% confidence interval: 1.18 to 1.61; p-value < 0.01). MR mediation analysis showed that 28.4% of the total effect of CCT on POAG risk was mediated through changes in IOP. The primary results were consistent with estimates of pleiotropy-robust MR methods. In conclusion, contrary to most observational studies, our results support a positive effect of CCT on the risk of POAG.
{"title":"Central corneal thickness and the risk of primary open-angle glaucoma: a Mendelian randomization mediation analysis","authors":"Andreas Katsimpris, Sebastian-Edgar Baumeister, Hansjörg Baurecht, Andrew J Tatham, Michael Nolde","doi":"10.1101/2023.11.28.23299139","DOIUrl":"https://doi.org/10.1101/2023.11.28.23299139","url":null,"abstract":"The association of central corneal thickness (CCT) with primary open-angle glaucoma (POAG) remains uncertain. Although, several observational studies assessing this relationship, have reported an inverse association between CCT and POAG, this could be the result of collider bias. In this study, we leveraged human genetic data to assess through Mendelian randomization (MR) the effect of CCT on POAG risk, and whether this effect is mediated by intraocular pressure (IOP) changes. We used 24 single-nucleotide polymorphisms (SNPs) associated with CCT (P-value < 5×10<sup>-8</sup>) from a genome-wide association study (GWAS) (N = 17,803) provided by the International Glaucoma Genetics Consortium and 53 SNPs associated with IOP (P-value < 5×10<sup>-8</sup>) from a GWAS of UK Biobank (UKBB) (N = 97,653). We related these instruments with POAG using a GWAS meta-analysis of 8,283 POAG cases and 753,827 controls from UKBB and FinnGen. MR analysis suggested a positive association between CCT and POAG (odds ratio of POAG per 50μm increase in CCT: 1.38; 95% confidence interval: 1.18 to 1.61; p-value < 0.01). MR mediation analysis showed that 28.4% of the total effect of CCT on POAG risk was mediated through changes in IOP. The primary results were consistent with estimates of pleiotropy-robust MR methods. In conclusion, contrary to most observational studies, our results support a positive effect of CCT on the risk of POAG.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138521638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Backgrounds: GPT4-V(ision) has generated great interest across various fields, while its performance in ocular multimodal images is still unknown. This study aims to evaluate the capabilities of a GPT-4V-based chatbot in addressing queries related to ocular multimodal images. Methods: A digital ophthalmologist app was built based on GPT-4V. The evaluation dataset comprised various ocular imaging modalities: slit-lamp, scanning laser ophthalmoscopy (SLO), fundus photography of the posterior pole (FPP), optical coherence tomography (OCT), fundus fluorescein angiography (FFA), and ocular ultrasound (OUS). Each modality included images representing 5 common and 5 rare diseases. The chatbot was presented with ten questions per image, focusing on examination identification, lesion detection, diagnosis, decision support, and the repeatability of diagnosis. The responses of GPT-4V were evaluated based on accuracy, usability, and safety. Results: There was a substantial agreement among three ophthalmologists. Out of 600 responses,30.5% were accurate,22.8% of 540 responses were highly usable, and 55.5% of 540 responses were considered safe by ophthalmologists. The chatbot excelled in interpreting slit-lamp images, with 42.0%,42.2%, and 68.5% of the responses being accurate, highly usable, and no harm, respectively. However, its performance was notably weaker in FPP images, with only 13.7%,3.7%, and 38.5% in the same categories. It correctly identified 95.6% of the imaging modalities. For lesion identification, diagnosis, and decision support, the chatbot's accuracy was 25.6%,16.1%, and 24.0%, respectively. The average proportions of correct answers, highly usable, and no harm for GPT-4V in common diseases were 37.9%,30.5%, and 60.1%, respectively. These proportions were all higher compared to those in rare diseases, which were 23.2% (P<0.001),15.2% (P<0.001), and 51.1% (P=0.032), respectively. The overall repeatability of GPT4-V in diagnosing ocular images was 63% (38/60). Conclusion: Currently, GPT-4V lacks the reliability required for clinical decision-making and patient consultation in ophthalmology. Ongoing refinement and testing are essential for improving the efficacy of large language models in medical applications.
{"title":"Evaluation of a digital ophthalmologist app built by GPT4-V(ision)","authors":"Pusheng Xu, Xiaolan Chen, Ziwei Zhao, Yingfeng Zheng, Guangming Jin, Danli Shi, Mingguang He","doi":"10.1101/2023.11.27.23299056","DOIUrl":"https://doi.org/10.1101/2023.11.27.23299056","url":null,"abstract":"Backgrounds: GPT4-V(ision) has generated great interest across various fields, while its performance in ocular multimodal images is still unknown. This study aims to evaluate the capabilities of a GPT-4V-based chatbot in addressing queries related to ocular multimodal images.\u0000Methods: A digital ophthalmologist app was built based on GPT-4V. The evaluation dataset comprised various ocular imaging modalities: slit-lamp, scanning laser ophthalmoscopy (SLO), fundus photography of the posterior pole (FPP), optical coherence tomography (OCT), fundus fluorescein angiography (FFA), and ocular ultrasound (OUS). Each modality included images representing 5 common and 5 rare diseases. The chatbot was presented with ten questions per image, focusing on examination identification, lesion detection, diagnosis, decision support, and the repeatability of diagnosis. The responses of GPT-4V were evaluated based on accuracy, usability, and safety.\u0000Results: There was a substantial agreement among three ophthalmologists. Out of 600 responses,30.5% were accurate,22.8% of 540 responses were highly usable, and 55.5% of 540 responses were considered safe by ophthalmologists. The chatbot excelled in interpreting slit-lamp images, with 42.0%,42.2%, and 68.5% of the responses being accurate, highly usable, and no harm, respectively. However, its performance was notably weaker in FPP images, with only 13.7%,3.7%, and 38.5% in the same categories. It correctly identified 95.6% of the imaging modalities. For lesion identification, diagnosis, and decision support, the chatbot's accuracy was 25.6%,16.1%, and 24.0%, respectively. The average proportions of correct answers, highly usable, and no harm for GPT-4V in common diseases were 37.9%,30.5%, and 60.1%, respectively. These proportions were all higher compared to those in rare diseases, which were 23.2% (P<0.001),15.2% (P<0.001), and 51.1% (P=0.032), respectively. The overall repeatability of GPT4-V in diagnosing ocular images was 63% (38/60). Conclusion: Currently, GPT-4V lacks the reliability required for clinical decision-making and patient consultation in ophthalmology. Ongoing refinement and testing are essential for improving the efficacy of large language models in medical applications.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138521639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-27DOI: 10.1101/2023.11.24.23298953
Vera Sorin, Noa Kapelushnik, Idan Hecht, Ofira Zloto, Benjamin S. Glicksberg, Hila Bufman, Yiftach Barash, Girish N. Nadkarni, Eyal Klang
Objective Recent advancements in GPT-4 have enabled analysis of text with visual data. Diagnosis in ophthalmology is often based on ocular examinations and imaging, alongside the clinical context. The aim of this study was to evaluate the performance of multimodal GPT-4 (GPT-4V) in an integrated analysis of ocular images and clinical text.
{"title":"GPT-4 Multimodal Analysis on Ophthalmology Clinical Cases Including Text and Images","authors":"Vera Sorin, Noa Kapelushnik, Idan Hecht, Ofira Zloto, Benjamin S. Glicksberg, Hila Bufman, Yiftach Barash, Girish N. Nadkarni, Eyal Klang","doi":"10.1101/2023.11.24.23298953","DOIUrl":"https://doi.org/10.1101/2023.11.24.23298953","url":null,"abstract":"<strong>Objective</strong> Recent advancements in GPT-4 have enabled analysis of text with visual data. Diagnosis in ophthalmology is often based on ocular examinations and imaging, alongside the clinical context. The aim of this study was to evaluate the performance of multimodal GPT-4 (GPT-4V) in an integrated analysis of ocular images and clinical text.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138521637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fundus angiography, including fundus fluorescein angiography (FFA) and indocyanine green angiography (ICGA), are essential examination tools for visualizing lesions and changes in retinal and choroidal vasculature. However, the interpretation of angiography images is labor-intensive and time-consuming. In response to this, we are organizing the third APTOS competition for automated and interpretable angiographic report generation. For this purpose, we have released the first angiographic dataset, which includes over 50,000 images labeled by retinal specialists. This dataset covers 24 conditions and provides detailed descriptions of the type, location, shape, size and pattern of abnormal fluorescence to enhance interpretability and accessibility. Additionally, we have implemented two baseline methods that achieve an overall score of 7.966 and 7.947 using the classification method and language generation method in the test set, respectively. We anticipate that this initiative will expedite the application of artificial intelligence in automatic report generation, thereby reducing the workload of clinicians and benefiting patients on a broader scale.
{"title":"Angiographic Report Generation for the 3rd APTOS’s Competition: Dataset and Baseline Methods","authors":"Weiyi Zhang, Peranut Chotcomwongse, Xiaolan Chen, Florence H.T. Chung, Fan Song, Xueli Zhang, Mingguang He, Danli Shi, Paisan Ruamviboonsuk","doi":"10.1101/2023.11.26.23299021","DOIUrl":"https://doi.org/10.1101/2023.11.26.23299021","url":null,"abstract":"Fundus angiography, including fundus fluorescein angiography (FFA) and indocyanine green angiography (ICGA), are essential examination tools for visualizing lesions and changes in retinal and choroidal vasculature. However, the interpretation of angiography images is labor-intensive and time-consuming. In response to this, we are organizing the third APTOS competition for automated and interpretable angiographic report generation. For this purpose, we have released the first angiographic dataset, which includes over 50,000 images labeled by retinal specialists. This dataset covers 24 conditions and provides detailed descriptions of the type, location, shape, size and pattern of abnormal fluorescence to enhance interpretability and accessibility. Additionally, we have implemented two baseline methods that achieve an overall score of 7.966 and 7.947 using the classification method and language generation method in the test set, respectively. We anticipate that this initiative will expedite the application of artificial intelligence in automatic report generation, thereby reducing the workload of clinicians and benefiting patients on a broader scale.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138521640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-23DOI: 10.1101/2023.11.22.23298937
Julian Wolf, Teja Chemudupati, Aarushi Kumar, Joel A. Franco, Artis A. Montague, Charles C. Lin, Wen-Shin Lee, A. Caroline Fisher, Jeffrey L. Goldberg, Prithvi Mruthyunjaya, Robert T. Chang, Vinit B. Mahajan
Purpose Knowing the surgical safety of anterior chamber liquid biopsies will support the increased use of proteomics and other molecular analyses to better understand disease mechanisms and therapeutic responses in patients and clinical trials. Manual review of operative notes from different surgeons and procedures in electronic health records (EHR) is cumbersome, but free-text software tools could facilitate efficient searches.
{"title":"Using electronic health record data to determine the safety of aqueous humor liquid biopsies for molecular analyses","authors":"Julian Wolf, Teja Chemudupati, Aarushi Kumar, Joel A. Franco, Artis A. Montague, Charles C. Lin, Wen-Shin Lee, A. Caroline Fisher, Jeffrey L. Goldberg, Prithvi Mruthyunjaya, Robert T. Chang, Vinit B. Mahajan","doi":"10.1101/2023.11.22.23298937","DOIUrl":"https://doi.org/10.1101/2023.11.22.23298937","url":null,"abstract":"<strong>Purpose</strong> Knowing the surgical safety of anterior chamber liquid biopsies will support the increased use of proteomics and other molecular analyses to better understand disease mechanisms and therapeutic responses in patients and clinical trials. Manual review of operative notes from different surgeons and procedures in electronic health records (EHR) is cumbersome, but free-text software tools could facilitate efficient searches.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138525830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：