Fei-Yan-Qing-Hua decoction exerts an anti-inflammatory role during influenza by inhibiting the infiltration of macrophages and neutrophils through NF-κB and p38 MAPK pathways.

ETHNOPHARMACOLOGICAL RELEVANCE: Fei-Yan-Qing-Hua decoction (FYQHD) is an empirical formula that has shown clinical success in treating community-acquired pneumonia (CAP) for two decades. Influenza viral infection is a significant trigger for severe pneumonia, yet the role of FYQHD in treating influenza remains unclear. AIM OF THE STUDY: This study aimed to assess the potential efficacy of FYQHD in treating influenza viral infection and to elucidate its underlying mechanisms. MATERIALS AND METHODS: The protective effects of FYQHD against influenza were evaluated through survival assessments and pathological analyses. Transcriptomic analysis was performed to identify the genes and pathways influenced by FYQHD in influenza. The anti-inflammatory effects and molecular mechanisms of FYQHD were studied in macrophages stimulated by Toll-like receptor (TLR) 7 ligation in vitro. The key constituents of FYQHD absorbed in mouse sera were identified using untargeted metabolomics, and the anti-inflammatory activity of some of these compounds in macrophages was evaluated using ELISA. RESULTS: Our findings demonstrate that FYQHD enhances survival and reduces lung damage in PR8-infected mice, primarily through its anti-inflammatory properties. Lung indexes and organ damage were significantly lower in the PR8 + OSV + FYQHD group compared to the PR8 + OSV group, indicating a potential complementary therapeutic effect of FYQHD and OSV in treating influenza. FYQHD effectively reduced chemokine expression, thereby decreasing the chemotaxis and infiltration of inflammatory monocytes/macrophages and neutrophils in the lungs. The anti-inflammatory effects of FYQHD in macrophages were achieved through the inhibition of NF-κB activation and p38 phosphorylation. The key constituents of FYQHD absorbed in mouse sera were identified, with some, such as wogonin, luteolin, kaempferol, and isorhamnetin, showing anti-inflammatory effects in primary macrophages. CONCLUSION: FYQHD demonstrates protective efficacy against influenza and shows promise as an adjuvant therapeutic agent, particularly when used in combination with antiviral drugs like OSV. The potent anti-inflammatory components within FYQHD provide a basis for further exploration in drug research and development aimed at combating influenza.

Vessel-promoted OCT to OCTA image translation by heuristic contextual constraints.

Optical Coherence Tomography Angiography (OCTA) is a crucial tool in the clinical screening of retinal diseases, allowing for accurate 3D imaging of blood vessels through non-invasive scanning. However, the hardware-based approach for acquiring OCTA images presents challenges due to the need for specialized sensors and expensive devices. In this paper, we introduce a novel method called TransPro, which can translate the readily available 3D Optical Coherence Tomography (OCT) images into 3D OCTA images without requiring any additional hardware modifications. Our TransPro method is primarily driven by two novel ideas that have been overlooked by prior work. The first idea is derived from a critical observation that the OCTA projection map is generated by averaging pixel values from its corresponding B-scans along the Z-axis. Hence, we introduce a hybrid architecture incorporating a 3D adversarial generative network and a novel Heuristic Contextual Guidance (HCG) module, which effectively maintains the consistency of the generated OCTA images between 3D volumes and projection maps. The second idea is to improve the vessel quality in the translated OCTA projection maps. As a result, we propose a novel Vessel Promoted Guidance (VPG) module to enhance the attention of network on retinal vessels. Experimental results on two datasets demonstrate that our TransPro outperforms state-of-the-art approaches, with relative improvements around 11.4% in MAE, 2.7% in PSNR, 2% in SSIM, 40% in VDE, and 9.1% in VDC compared to the baseline method. The code is available at: https://github.com/ustlsh/TransPro.

Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raters.

In medical image segmentation, it is often necessary to collect opinions from multiple experts to make the final decision. This clinical routine helps to mitigate individual bias. However, when data is annotated by multiple experts, standard deep learning models are often not applicable. In this paper, we propose a novel neural network framework called Multi-rater Prism (MrPrism) to learn medical image segmentation from multiple labels. Inspired by iterative half-quadratic optimization, MrPrism combines the task of assigning multi-rater confidences and calibrated segmentation in a recurrent manner. During this process, MrPrism learns inter-observer variability while taking into account the image's semantic properties and finally converges to a self-calibrated segmentation result reflecting inter-observer agreement. Specifically, we propose Converging Prism (ConP) and Diverging Prism (DivP) to iteratively process the two tasks. ConP learns calibrated segmentation based on multi-rater confidence maps estimated by DivP, and DivP generates multi-rater confidence maps based on segmentation masks estimated by ConP. Experimental results show that the two tasks can mutually improve each other through this recurrent process. The final converged segmentation result of MrPrism outperforms state-of-the-art (SOTA) methods for a wide range of medical image segmentation tasks. The code is available at https://github.com/WuJunde/MrPrism.

Rujin Jiedu decoction protects against influenza virus infection by modulating gut microbiota.

Background: Rujin Jiedu decoction (RJJDD) is a classical prescription of Traditional Chinese Medicine that has long been applied to treat pneumonia caused by external infection, but whether and how it benefits influenza virus therapy remains largely unclear. The aim of this study was to investigate the anti-inflammatory effect of RJJDD on the mouse model of influenza and to explore its potential mechanism. Methods: The mice were mock-infected with PBS or infected with PR8 virus followed by treatment with RJJDD or antiviral oseltamivir. The weight loss and morbidity of mice were monitored daily. Network pharmacology is used to explore the potential pathways that RJJDD may modulate. qRT-PCR and ELISA were performed to assess the expression of inflammatory cytokines in the lung tissue and macrophages. The intestinal feces were collected for 16S rDNA sequencing to assess the changes in gut microbiota. Results: We demonstrate that RJJDD protects against IAV-induced pneumonia. Comprehensive network pharmacology analyses of the Mass Spec-identified components of RJJDD suggest that RJJDD may act through down-regulating key signaling pathways producing inflammatory cytokines, which was experimentally confirmed by cytokine expression analysis in IAV-infected mouse lung tissues and IAV single-strand RNA mimic R837-induced macrophages. Furthermore, gut microbiota analysis indicates that RJJDD prevented IAV-induced dysbiosis of host intestinal flora, thereby offering a mechanistic explanation for RJJDD's efficacy in influenza pneumonia. Conclusion: This study defines a previously uncharacterized role for RJJDD in protecting against influenza likely by maintaining homeostasis of gut microbiota, and provides a new therapeutic option for severe influenza.

Towards Lightweight Super-Resolution with Dual Regression Learning.

Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks by learning a mapping from low-resolution (LR) images to high-resolution (HR) images. However, the SR problem is typically an ill-posed problem and existing methods would come with several limitations. First, the possible mapping space of SR can be extremely large since there may exist many different HR images that can be super-resolved from the same LR image. As a result, it is hard to directly learn a promising SR mapping from such a large space. Second, it is often inevitable to develop very large models with extremely high computational cost to yield promising SR performance. In practice, one can use model compression techniques to obtain compact models by reducing model redundancy. Nevertheless, it is hard for existing model compression methods to accurately identify the redundant components due to the extremely large SR mapping space. To alleviate the first challenge, we propose a dual regression learning scheme to reduce the space of possible SR mappings. Specifically, in addition to the mapping from LR to HR images, we learn an additional dual regression mapping to estimate the downsampling kernel and reconstruct LR images. In this way, the dual mapping acts as a constraint to reduce the space of possible mappings. To address the second challenge, we propose a dual regression compression (DRC) method to reduce model redundancy in both layer-level and channel-level based on channel pruning. Specifically, we first develop a channel number search method that minimizes the dual regression loss to determine the redundancy of each layer. Given the searched channel numbers, we further exploit the dual regression manner to evaluate the importance of channels and prune the redundant ones. Extensive experiments show the effectiveness of our method in obtaining accurate and efficient SR models.

MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images.

This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. While diffusion-based generative models are increasingly used in medical imaging, current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports' abundant information. The radiology reports can enhance the generation process by providing additional guidance and offering fine-grained control over the synthesis of images. Nevertheless, expanding text-guided generation to high-resolution 3D images poses significant memory and anatomical detail-preserving challenges. Addressing the memory issue, we introduce a hierarchical scheme that uses a modified UNet architecture. We start by synthesizing low-resolution images conditioned on the text, serving as a foundation for subsequent generators for complete volumetric data. To ensure the anatomical plausibility of the generated samples, we provide further guidance by generating vascular, airway, and lobular segmentation masks in conjunction with the CT images. The model demonstrates the capability to use textual input and segmentation tasks to generate synthesized images. Algorithmic comparative assessments and blind evaluations conducted by 10 board-certified radiologists indicate that our approach exhibits superior performance compared to the most advanced models based on GAN and diffusion techniques, especially in accurately retaining crucial anatomical features such as fissure lines and airways. This innovation introduces novel possibilities. This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements. The advancements in image generation can be applied to enhance numerous downstream tasks.

Multi-risk factors joint prediction model for risk prediction of retinopathy of prematurity.

Purpose: Retinopathy of prematurity (ROP) is a retinal vascular proliferative disease common in low birth weight and premature infants and is one of the main causes of blindness in children.In the context of predictive, preventive and personalized medicine (PPPM/3PM), early screening, identification and treatment of ROP will directly contribute to improve patients' long-term visual prognosis and reduce the risk of blindness. Thus, our objective is to establish an artificial intelligence (AI) algorithm combined with clinical demographics to create a risk model for ROP including treatment-requiring retinopathy of prematurity (TR-ROP) infants. Methods: A total of 22,569 infants who underwent routine ROP screening in Shenzhen Eye Hospital from March 2003 to September 2023 were collected, including 3335 infants with ROP and 1234 infants with TR-ROP among ROP infants. Two machine learning methods of logistic regression and decision tree and a deep learning method of multi-layer perceptron were trained by using the relevant combination of risk factors such as birth weight (BW), gestational age (GA), gender, whether multiple births (MB) and mode of delivery (MD) to achieve the risk prediction of ROP and TR-ROP. We used five evaluation metrics to evaluate the performance of the risk prediction model. The area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCPR) were the main measurement metrics. Results: In the risk prediction for ROP, the BW + GA demonstrated the optimal performance (mean ± SD, AUCPR: 0.4849 ± 0.0175, AUC: 0.8124 ± 0.0033). In the risk prediction of TR-ROP, reasonable performance can be achieved by using GA + BW + Gender + MD + MB (AUCPR: 0.2713 ± 0.0214, AUC: 0.8328 ± 0.0088). Conclusions: Combining risk factors with AI in screening programs for ROP could achieve risk prediction of ROP and TR-ROP, detect TR-ROP earlier and reduce the number of ROP examinations and unnecessary physiological stress in low-risk infants. Therefore, combining ROP-related biometric information with AI is a cost-effective strategy for predictive diagnostic, targeted prevention, and personalization of medical services in early screening and treatment of ROP.

Bibliometric analysis of hotspots and trends of global myopia research.

AIM: To gain insights into the global research hotspots and trends of myopia. METHODS: Articles were downloaded from January 1, 2013 to December 31, 2022 from the Science Core Database website and were mainly statistically analyzed by bibliometrics software. RESULTS: A total of 444 institutions in 87 countries published 4124 articles. Between 2013 and 2022, China had the highest number of publications (n=1865) and the highest H-index (61). Sun Yat-sen University had the highest number of publications (n=229) and the highest H-index (33). Ophthalmology is the main category in related journals. Citations from 2020 to 2022 highlight keywords of options and reference, child health (pediatrics), myopic traction mechanism, public health, and machine learning, which represent research frontiers. CONCLUSION: Myopia has become a hot research field. China and Chinese institutions have the strongest academic influence in the field from 2013 to 2022. The main driver of myopic research is still medical or ophthalmologists. This study highlights the importance of public health in addressing the global rise in myopia, especially its impact on children's health. At present, a unified theoretical system is still needed. Accurate surgical and therapeutic solutions must be proposed for people with different characteristics to manage and intervene refractive errors. In addition, the benefits of artificial intelligence (AI) models are also reflected in disease monitoring and prediction.

Calibrate the Inter-Observer Segmentation Uncertainty via Diagnosis-First Principle.

Many of the tissues/lesions in the medical images may be ambiguous. Therefore, medical segmentation is typically annotated by a group of clinical experts to mitigate personal bias. A common solution to fuse different annotations is the majority vote, e.g., taking the average of multiple labels. However, such a strategy ignores the difference between the grader expertness. Inspired by the observation that medical image segmentation is usually used to assist the disease diagnosis in clinical practice, we propose the diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis-First segmentation Framework (DiFF) is proposed. Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis-First Ground-truth (DF-GT). Then, the Take and Give Model (T&G Model) to segment DF-GT from the raw image is proposed. With the T&G Model, DiFF can learn the segmentation with the calibrated uncertainty that facilitate the disease diagnosis. We verify the effectiveness of DiFF on three different medical segmentation tasks: optic-disc/optic-cup (OD/OC) segmentation on fundus images, thyroid nodule segmentation on ultrasound images, and skin lesion segmentation on dermoscopic images. Experimental results show that the proposed DiFF can effectively calibrate the segmentation uncertainty, and thus significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods.

Platycodin D facilitates antiviral immunity through inhibiting cytokine storm via targeting K63-linked TRAF6 ubiquitination.

Influenza virus infection is a worldwide challenge that causes heavy burdens on public health. The mortality rate of severe influenza patients is often associated with hyperactive immunological abnormalities characterized by hypercytokinemia. Due to the continuous mutations and the occurrence of drug-resistant influenza virus strains, the development of host-directed immunoregulatory drugs is urgently required. Platycodon grandiflorum is among the top 10 herbs of traditional Chinese medicine used to treat pulmonary diseases. As one of the major terpenoid saponins extracted from Platycodon grandiflorum, Platycodin D (PD) has been reported to play several roles, including anti-inflammation, analgesia, anti-cancer, hepatoprotection, and immunoregulation. However, the therapeutic roles of PD to treat influenza virus infection remains unknown. Here, we show that PD can protect the body weight loss in severely infected influenza mice, alleviate lung damage, and thus improve the survival rate. More specifically, PD protects flu mice via decreasing the immune cell infiltration into lungs and downregulating the overactivated inflammatory response. Western blot and immunofluorescence assays exhibited that PD could inhibit the activation of TAK1/IKK/NF-κB and MAPK pathways. Besides that, CETSA, SPR and immunoprecipitation assays indicated that PD binds with TRAF6 to decrease its K63 ubiquitination after R837 stimulation. Additionally, siRNA interference experiments exhibited that PD could inhibit the secretion of IL-1ß and TNF-α in TRAF6-dependent manner. Altogether, our results suggested that PD is a promising drug candidate for treating influenza. Our study also offered a scientific explanation for the commonly used Platycodon grandiflorum in many anti-epidemic classic formulas. Due to its host-directed regulatory role, PD may serve as an adjuvant therapeutic drug in conjunction with other antiviral drugs to treat the flu.

Predicting Implantable Collamer Lens Vault Using Machine Learning Based on Various Preoperative Biometric Factors.

Purpose: To predict the vault size after Implantable Collamer Lens (ICL) V4c implantation using machine learning methods and to compare the predicted vault with the conventional manufacturer's nomogram. Methods: This study included 707 patients (707 eyes) who underwent ICL V4c implantation at the Department of Ophthalmology, Peking Union Medical College Hospital, from September 2019 to January 2022. Random Forest Regression (RFR), XGBoost, and linear regression (LR) were used to predict the vault size 1 week after ICL V4c implantation. The mean absolute error (MAE), median absolute error (MedAE), root mean square error (RMSE), symmetric mean absolute percentage error (SMAPE), and Bland-Altman plot were utilized to compare the prediction performance of these machine learning methods. Results: The dataset was divided into a training set of 180 patients (180 eyes) and a test set of 527 patients (527 eyes). XGBoost had the lowest prediction error, with mean MAE, RMSE, and SMAPE values of 121.70 µm, 148.87 µm, and 19.13%, respectively. The Bland‒Altman plots of RFR and XGBoost showed better prediction consistency than LR. However, XGBoost showed narrower 95% limits of agreement (LoA) than RFR, ranging from -307.12 to 256.59 µm. Conclusions: XGBoost demonstrated better predictive performance than RFR and LR, as it had the lowest prediction error and the narrowest 95% LoA. Machine learning may be applicable for vault prediction, and it might be helpful for reducing the complications and the secondary surgery rate. Translational Relevance: Using the proposed machine learning model, surgeons can consider the postoperative vault to reduce the surgical complications.

Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation.

Pathologic myopia (PM) is a common blinding retinal degeneration suffered by highly myopic population. Early screening of this condition can reduce the damage caused by the associated fundus lesions and therefore prevent vision loss. Automated diagnostic tools based on artificial intelligence methods can benefit this process by aiding clinicians to identify disease signs or to screen mass populations using color fundus photographs as inputs. This paper provides insights about PALM, our open fundus imaging dataset for pathological myopia recognition and anatomical structure annotation. Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment. In addition, this paper elaborates on other details such as the labeling process used to construct the database, the quality and characteristics of the samples and provides other relevant usage notes.

Crystalline lens nuclear age prediction as a new biomarker of nucleus degeneration.

BACKGROUND: The crystalline lens is a transparent structure of the eye to focus light on the retina. It becomes muddy, hard and dense with increasing age, which makes the crystalline lens gradually lose its function. We aim to develop a nuclear age predictor to reflect the degeneration of the crystalline lens nucleus. METHODS: First we trained and internally validated the nuclear age predictor with a deep-learning algorithm, using 12 904 anterior segment optical coherence tomography (AS-OCT) images from four diverse Asian and American cohorts: Zhongshan Ophthalmic Center with Machine0 (ZOM0), Tomey Corporation (TOMEY), University of California San Francisco and the Chinese University of Hong Kong. External testing was done on three independent datasets: Tokyo University (TU), ZOM1 and Shenzhen People's Hospital (SPH). We also demonstrate the possibility of detecting nuclear cataracts (NCs) from the nuclear age gap. FINDINGS: In the internal validation dataset, the nuclear age could be predicted with a mean absolute error (MAE) of 2.570 years (95% CI 1.886 to 2.863). Across the three external testing datasets, the algorithm achieved MAEs of 4.261 years (95% CI 3.391 to 5.094) in TU, 3.920 years (95% CI 3.332 to 4.637) in ZOM1-NonCata and 4.380 years (95% CI 3.730 to 5.061) in SPH-NonCata. The MAEs for NC eyes were 8.490 years (95% CI 7.219 to 9.766) in ZOM1-NC and 9.998 years (95% CI 5.673 to 14.642) in SPH-NC. The nuclear age gap outperformed both ophthalmologists in detecting NCs, with areas under the receiver operating characteristic curves of 0.853 years (95% CI 0.787 to 0.917) in ZOM1 and 0.909 years (95% CI 0.828 to 0.978) in SPH. INTERPRETATION: The nuclear age predictor shows good performance, validating the feasibility of using AS-OCT images as an effective screening tool for nucleus degeneration. Our work also demonstrates the potential use of the nuclear age gap to detect NCs.

Fei-Yan-Qing-Hua decoction decreases hyperinflammation by inhibiting HMGB1/RAGE signaling and promotes bacterial phagocytosis in the treatment of sepsis.

ETHNOPHARMACOLOGICAL RELEVANCE: Fei-Yan-Qing-Hua decoction (FYQHD), derived from the renowned formula Ma Xing Shi Gan tang documented in Zhang Zhong Jing's "Treatise on Exogenous Febrile Disease" during the Han Dynasty, has demonstrated notable efficacy in the clinical treatment of pneumonia resulting from bacterial infection. However, its molecular mechanisms underlying the therapeutic effects remains elusive. AIM OF THE STUDY: This study aimed to investigate the protective effects of FYQHD against lipopolysaccharide (LPS) and carbapenem-resistant Klebsiella pneumoniae (CRKP)-induced sepsis in mice and to elucidate its specific mechanism of action. MATERIALS AND METHODS: Sepsis models were established in mice through intraperitoneal injection of LPS or CRKP. FYQHD was administered via gavage at low and high doses. Serum cytokines, bacterial load, and pathological damage were assessed using enzyme-linked immunosorbent assay (ELISA), minimal inhibitory concentration (MIC) detection, and hematoxylin and eosin staining (H&E), respectively. In vitro, the immunoregulatory effects of FYQHD on macrophages were investigated through ELISA, MIC, quantitative real-time PCR (Q-PCR), immunofluorescence, Western blot, and a network pharmacological approach. RESULTS: The application of FYQHD in the treatment of LPS or CRKP-induced septic mouse models revealed significant outcomes. FYQHD increased the survival rate of mice exposed to a lethal dose of LPS to 33.3%, prevented hypothermia (with a rise of 3.58 °C), reduced pro-inflammatory variables (including TNF-α, IL-6, and MCP-1), and mitigated tissue damage in LPS or CRKP-induced septic mice. Additionally, FYQHD decreased bacterial load in CRKP-infected mice. In vitro, FYQHD suppressed the expression of inflammatory cytokines in macrophages activated by LPS or HK-CRKP. Mechanistically, FYQHD inhibited the PI3K/AKT/mTOR/4E-BP1 signaling pathway, thereby suppressing the translational level of inflammatory cytokines. Furthermore, it reduced the expression of HMGB1/RAGE, a positive feedback loop in the inflammatory response. Moreover, FYQHD was found to enhance the phagocytic activity of macrophages by upregulating the expression of phagocytic receptors such as CD169 and SR-A1. CONCLUSION: FYQHD provides protection against bacterial sepsis by concurrently inhibiting the inflammatory response and augmenting the phagocytic ability of immune cells.

Deep segmentation of OCTA for evaluation and association of changes of retinal microvasculature with Alzheimer's disease and mild cognitive impairment.

BACKGROUND: Optical coherence tomography angiography (OCTA) enables fast and non-invasive high-resolution imaging of retinal microvasculature and is suggested as a potential tool in the early detection of retinal microvascular changes in Alzheimer's Disease (AD). We developed a standardised OCTA analysis framework and compared their extracted parameters among controls and AD/mild cognitive impairment (MCI) in a cross-section study. METHODS: We defined and extracted geometrical parameters of retinal microvasculature at different retinal layers and in the foveal avascular zone (FAZ) from segmented OCTA images obtained using well-validated state-of-the-art deep learning models. We studied these parameters in 158 subjects (62 healthy control, 55 AD and 41 MCI) using logistic regression to determine their potential in predicting the status of our subjects. RESULTS: In the AD group, there was a significant decrease in vessel area and length densities in the inner vascular complexes (IVC) compared with controls. The number of vascular bifurcations in AD is also significantly lower than that of healthy people. The MCI group demonstrated a decrease in vascular area, length densities, vascular fractal dimension and the number of bifurcations in both the superficial vascular complexes (SVC) and the IVC compared with controls. A larger vascular tortuosity in the IVC, and a larger roundness of FAZ in the SVC, can also be observed in MCI compared with controls. CONCLUSION: Our study demonstrates the applicability of OCTA for the diagnosis of AD and MCI, and provides a standard tool for future clinical service and research. Biomarkers from retinal OCTA images can provide useful information for clinical decision-making and diagnosis of AD and MCI.

GAMMA challenge: Glaucoma grAding from Multi-Modality imAges.

Glaucoma is a chronic neuro-degenerative condition that is one of the world's leading causes of irreversible but preventable blindness. The blindness is generally caused by the lack of timely detection and treatment. Early screening is thus essential for early treatment to preserve vision and maintain life quality. Colour fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both imaging modalities have prominent biomarkers to indicate glaucoma suspects, such as the vertical cup-to-disc ratio (vCDR) on fundus images and retinal nerve fiber layer (RNFL) thickness on OCT volume. In clinical practice, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes for the automated glaucoma detection, there are few methods that leverage both of the modalities to achieve the target. To fulfil the research gap, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA) Challenge to encourage the development of fundus & OCT-based glaucoma grading. The primary task of the challenge is to grade glaucoma from both the 2D fundus images and 3D OCT scanning volumes. As part of GAMMA, we have publicly released a glaucoma annotated dataset with both 2D fundus colour photography and 3D OCT volumes, which is the first multi-modality dataset for machine learning based glaucoma grading. In addition, an evaluation framework is also established to evaluate the performance of the submitted methods. During the challenge, 1272 results were submitted, and finally, ten best performing teams were selected for the final stage. We analyse their results and summarize their methods in the paper. Since all the teams submitted their source code in the challenge, we conducted a detailed ablation study to verify the effectiveness of the particular modules proposed. Finally, we identify the proposed techniques and strategies that could be of practical value for the clinical diagnosis of glaucoma. As the first in-depth study of fundus & OCT multi-modality glaucoma grading, we believe the GAMMA Challenge will serve as an essential guideline and benchmark for future research.

Guidelines on clinical research evaluation of artificial intelligence in ophthalmology (2023).

With the upsurge of artificial intelligence (AI) technology in the medical field, its application in ophthalmology has become a cutting-edge research field. Notably, machine learning techniques have shown remarkable achievements in diagnosing, intervening, and predicting ophthalmic diseases. To meet the requirements of clinical research and fit the actual progress of clinical diagnosis and treatment of ophthalmic AI, the Ophthalmic Imaging and Intelligent Medicine Branch and the Intelligent Medicine Committee of Chinese Medicine Education Association organized experts to integrate recent evaluation reports of clinical AI research at home and abroad and formed a guideline on clinical research evaluation of AI in ophthalmology after several rounds of discussion and modification. The main content includes the background and method of developing this guideline, an introduction to international guidelines on the clinical research evaluation of AI, and the evaluation methods of clinical ophthalmic AI models. This guideline introduces general evaluation methods of clinical ophthalmic AI research, evaluation methods of clinical ophthalmic AI models, and commonly-used indices and formulae for clinical ophthalmic AI model evaluation in detail, and amply elaborates the evaluation methods of clinical ophthalmic AI trials. This guideline aims to provide guidance and norms for clinical researchers of ophthalmic AI, promote the development of regularization and standardization, and further improve the overall level of clinical ophthalmic AI research evaluations.

A generic fundus image enhancement network boosted by frequency self-supervised representation learning.

Fundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on degraded images, high data demands and limited applicability hinder their clinical deployment. To circumvent this bottleneck, a generic fundus image enhancement network (GFE-Net) is developed in this study to robustly correct unknown fundus images without supervised or extra data. Levering image frequency information, self-supervised representation learning is conducted to learn robust structure-aware representations from degraded images. Then with a seamless architecture that couples representation learning and image enhancement, GFE-Net can accurately correct fundus images and meanwhile preserve retinal structures. Comprehensive experiments are implemented to demonstrate the effectiveness and advantages of GFE-Net. Compared with state-of-the-art algorithms, GFE-Net achieves superior performance in data dependency, enhancement performance, deployment efficiency, and scale generalizability. Follow-up fundus image analysis is also facilitated by GFE-Net, whose modules are respectively verified to be effective for image enhancement.