Hasil untuk "Ophthalmology"

C. Walker

W. Reinhart, D. Musch, D. Jacobs et al.

Ankan Deria, Komal Kumar, Adinath Madhavrao Dukre et al.

Multimodal large language models have advanced rapidly, but their adoption in medicine is constrained by limited domain coverage, imperfect modality alignment, and insufficient grounded reasoning. We introduce MedMO, a medical multimodal foundation model built on a general MLLM architecture and trained exclusively on large-scale domain-specific data. MedMO uses a multi-stage training recipe that includes cross-modal pretraining to align heterogeneous visual encoders with a medical language backbone, instruction tuning with multi-task supervision spanning captioning, VQA, report generation, retrieval, and bounding-box disease localization, and reinforcement learning with verifiable rewards that combine factuality checks with a box-level GIoU signal to improve spatial grounding and step-by-step reasoning in challenging clinical settings. Across modalities and tasks, MedMO surpasses strong open-source medical baselines. MedMO-8B-Next achieves consistent gains on VQA benchmarks, improving by 6.6% on average over Fleming-VL-8B, including gains of 6.0% on MMMU-Med, 9.8% on PMC-VQA, and 21.3% on MedXpertQA. On text-based QA, it improves by 14.4% over Fleming-VL-8B, driven by gains of 8.4% on MMLU-Med and 30.1% on MedQA. For medical report generation, it improves by 6.7% on MIMIC-CXR. MedMO-8B-Next also demonstrates strong grounding performance, reaching 56.1 IoU on Bacteria, which is a 47.8 IoU gain over Fleming-VL-8B. At smaller scale, MedMO-4B-Next remains competitive and exceeds Fleming-VL-8B across VQA, QA, and report generation. Evaluations spanning radiology, ophthalmology, and pathology microscopy further confirm broad cross-modality generalization. Project is available at https://genmilab.github.io/MedMO-Page

Jinze Zhang, Jian Zhong, Li Lin et al.

Optical coherence tomography (OCT) has revolutionized retinal disease diagnosis with its high-resolution and three-dimensional imaging nature, yet its full diagnostic automation in clinical practices remains constrained by multi-stage workflows and conventional single-slice single-task AI models. We present Full-process OCT-based Clinical Utility System (FOCUS), a foundation model-driven framework enabling end-to-end automation of 3D OCT retinal disease diagnosis. FOCUS sequentially performs image quality assessment with EfficientNetV2-S, followed by abnormality detection and multi-disease classification using a fine-tuned Vision Foundation Model. Crucially, FOCUS leverages a unified adaptive aggregation method to intelligently integrate 2D slices-level predictions into comprehensive 3D patient-level diagnosis. Trained and tested on 3,300 patients (40,672 slices), and externally validated on 1,345 patients (18,498 slices) across four different-tier centers and diverse OCT devices, FOCUS achieved high F1 scores for quality assessment (99.01%), abnormally detection (97.46%), and patient-level diagnosis (94.39%). Real-world validation across centers also showed stable performance (F1: 90.22%-95.24%). In human-machine comparisons, FOCUS matched expert performance in abnormality detection (F1: 95.47% vs 90.91%) and multi-disease diagnosis (F1: 93.49% vs 91.35%), while demonstrating better efficiency. FOCUS automates the image-to-diagnosis pipeline, representing a critical advance towards unmanned ophthalmology with a validated blueprint for autonomous screening to enhance population scale retinal care accessibility and efficiency.

Laurin Lux, Alexander H. Berger, Maria Romeo Tricas et al.

Interpretability is crucial to enhance trust in machine learning models for medical diagnostics. However, most state-of-the-art image classifiers based on neural networks are not interpretable. As a result, clinicians often resort to known biomarkers for diagnosis, although biomarker-based classification typically performs worse than large neural networks. This work proposes a method that surpasses the performance of established machine learning models while simultaneously improving prediction interpretability for diabetic retinopathy staging from optical coherence tomography angiography (OCTA) images. Our method is based on a novel biology-informed heterogeneous graph representation that models retinal vessel segments, intercapillary areas, and the foveal avascular zone (FAZ) in a human-interpretable way. This graph representation allows us to frame diabetic retinopathy staging as a graph-level classification task, which we solve using an efficient graph neural network. We benchmark our method against well-established baselines, including classical biomarker-based classifiers, convolutional neural networks (CNNs), and vision transformers. Our model outperforms all baselines on two datasets. Crucially, we use our biology-informed graph to provide explanations of unprecedented detail. Our approach surpasses existing methods in precisely localizing and identifying critical vessels or intercapillary areas. In addition, we give informative and human-interpretable attributions to critical characteristics. Our work contributes to the development of clinical decision-support tools in ophthalmology.

Minghan Li, Congcong Wen, Yu Tian et al.

Fairness remains a critical concern in healthcare, where unequal access to services and treatment outcomes can adversely affect patient health. While Federated Learning (FL) presents a collaborative and privacy-preserving approach to model training, ensuring fairness is challenging due to heterogeneous data across institutions, and current research primarily addresses non-medical applications. To fill this gap, we establish the first experimental benchmark for fairness in medical FL, evaluating six representative FL methods across diverse demographic attributes and imaging modalities. We introduce FairFedMed, the first medical FL dataset specifically designed to study group fairness (i.e., demographics). It comprises two parts: FairFedMed-Oph, featuring 2D fundus and 3D OCT ophthalmology samples with six demographic attributes; and FairFedMed-Chest, which simulates real cross-institutional FL using subsets of CheXpert and MIMIC-CXR. Together, they support both simulated and real-world FL across diverse medical modalities and demographic groups. Existing FL models often underperform on medical images and overlook fairness across demographic groups. To address this, we propose FairLoRA, a fairness-aware FL framework based on SVD-based low-rank approximation. It customizes singular value matrices per demographic group while sharing singular vectors, ensuring both fairness and efficiency. Experimental results on the FairFedMed dataset demonstrate that FairLoRA not only achieves state-of-the-art performance in medical image classification but also significantly improves fairness across diverse populations. Our code and dataset can be accessible via link: https://wang.hms.harvard.edu/fairfedmed/.

Daeyoung Kim

Age Related Macular Degeneration(AMD) has been one of the most leading causes of permanent vision impairment in ophthalmology. Though treatments, such as anti VEGF drugs or photodynamic therapies, were developed to slow down the degenerative process of AMD, there is still no specific cure to reverse vision loss caused by AMD. Thus, for AMD, detecting existence of risk factors of AMD or AMD itself within the patient retina in early stages is a crucial task to reduce the possibility of vision impairment. Apart from traditional approaches, deep learning based methods, especially attention mechanism based CNNs and GradCAM based XAI analysis on OCT scans, exhibited successful performance in distinguishing AMD retina from normal retinas, making it possible to use AI driven models to aid medical diagnosis and analysis by ophthalmologists regarding AMD. However, though having significant success, previous works mostly focused on prediction performance itself, not pathologies or underlying causal mechanisms of AMD, which can prohibit intervention analysis on specific factors or even lead to less reliable decisions. Thus, this paper introduces a novel causal AMD analysis model: GCVAMD, which incorporates a modified CausalVAE approach that can extract latent causal factors from only raw OCT images. By considering causality in AMD detection, GCVAMD enables causal inference such as treatment simulation or intervention analysis regarding major risk factors: drusen and neovascularization, while returning informative latent causal features that can enhance downstream tasks. Results show that through GCVAMD, drusen status and neovascularization status can be identified with AMD causal mechanisms in GCVAMD latent spaces, which can in turn be used for various tasks from AMD detection(classification) to intervention analysis.

Sanitha Sathyan

Ahmed Azeez Hasan, Anis Kausar Ghazali, Najib Majdi Yaacob et al.

Objectives This study aimed to validate the psychometric properties of the recently developed knowledge, attitudes, and perceptions questionnaire for community-based surveillance of infectious diseases (KAP-CBS-ID questionnaire), using confirmatory factor analysis (CFA) and item response theory (IRT). Methods A cross-sectional study using multistage sampling recruited 470 schoolteachers from Kelantan, Malaysia. The self-administered KAP-CBS-ID questionnaire consists of 3 domains: knowledge (31 items), attitudes (23 items), and perceptions (21-items). Two-parameter logistic (2-PL) IRT analysis and CFA were performed to validate the knowledge section. For attitudes and perceptions sections, CFA proceeded using a 4-factor model to evaluate both model fit and construct validity. Results Two-PL IRT analysis of the knowledge section resulted in elimination of 14 items due to inadequate discrimination or difficulty parameters. The 3-factor CFA model demonstrated good fit indices for knowledge (root mean square error of approximation [RMSEA], 0.028; comparative fit index [CFI], 0.945; Tucker-Lewis index [TLI], 0.941) without any modifications. The attitudes section required re-specification, ultimately yielding 21 items across 4 factors with acceptable fit indices (standardized root mean square residual [SRMR], 0.067; RMSEA, 0.055; CFI, 0.937; TLI, 0.927). Similarly, the perceptions section was refined to 17 items across 4 factors, showing good model fit (SRMR, 0.055; RMSEA, 0.059; CFI, 0.962; TLI, 0.954). Factor loadings ranged from 0.33 to 0.98, while Raykov’s rho reliability estimates ranged from 0.71 to 0.93. Factor determinacy exceeded 80% for all factors. Conclusion The KAP-CBS-ID is a valid and reliable instrument for assessing community representatives’ knowledge, attitudes, and perceptions regarding community-based surveillance of infectious diseases.

Shengsong Xu, Linling Li, Yingting Zhu et al.

Abstract Background Previous Artificial Intelligence (AI) models are mainly based on hospital data to predict myopia progression in myopic children. However, school-level AI models for predicting myopia onset in non-myopic children are lacking. There is a need for more precise and comprehensive tools for full myopia management, from the onset of myopia to its progression. Methods This study was conducted in 870 centers dispersed across seven cities in China from September 2019 to December 2021, with participants observed for two years. Machine learning models were trained and internally validated on datasets from Shenzhen, and then externally tested from the other six cities. Of 1,123,602 children and adolescents aged 4–18 years old, 1,105,271 individuals were confirmed eligible. After two-year follow-up, 915,991 individuals were included in analysis. Data were analyzed from June 2022 to July 2023. Main outcomes and measures are the occurrence of myopia, and the change of spherical equivalent refraction in 2 years. Results Of 915,991 participants, 405,784 (44.3%) were identified as myopic at baseline. In two years, the occurrence of myopia was 45.5% and the overall myopic shift was − 0.97 ± 1.32D. The optimal machine learning models were established for predicting myopia occurrence in non-myopic individuals; and predicting progression of any amount (defined as an annual progression of < − 0.25D) in myopic individuals. The performance in predicting occurrence (AUC 0.962, 95% CI 0.956–0.968) and progression (AUC 0.923, 95% CI 0.912–0.934) were acceptable in the external test set. The interactions between age and other variables were revealed by the algorithms, and hence the final prediction models were established based on age segmentation. In the external test set, the performance of the models for both 4–11-years (occurrence prediction: AUC 0.978, 95% CI 0.972–0.984; progression prediction: AUC 0.957, 95% CI 0.951–0.963) and 11–18-years age groups (occurrence prediction: AUC 0.966, 95% CI 0.960–0.972; progression prediction: AUC 0.928, 95% CI 0.917–0.939) were improved. Finally, user-friendly software was developed, which makes this model accessible for school use. Conclusions The algorithm developed in the current study for predicting myopia occurrence and progression showed excellent performance in school settings using real-world data, indicating its potential application in school-level myopia management. Trial registration chictr.org Identifier: ChiCTR2200057391.

Yutong Zhang, Yi Pan, Tianyang Zhong et al.

Medical images and radiology reports are crucial for diagnosing medical conditions, highlighting the importance of quantitative analysis for clinical decision-making. However, the diversity and cross-source heterogeneity of these data challenge the generalizability of current data-mining methods. Multimodal large language models (MLLMs) have recently transformed many domains, significantly affecting the medical field. Notably, Gemini-Vision-series (Gemini) and GPT-4-series (GPT-4) models have epitomized a paradigm shift in Artificial General Intelligence (AGI) for computer vision, showcasing their potential in the biomedical domain. In this study, we evaluated the performance of the Gemini, GPT-4, and 4 popular large models for an exhaustive evaluation across 14 medical imaging datasets, including 5 medical imaging categories (dermatology, radiology, dentistry, ophthalmology, and endoscopy), and 3 radiology report datasets. The investigated tasks encompass disease classification, lesion segmentation, anatomical localization, disease diagnosis, report generation, and lesion detection. Our experimental results demonstrated that Gemini-series models excelled in report generation and lesion detection but faces challenges in disease classification and anatomical localization. Conversely, GPT-series models exhibited proficiency in lesion segmentation and anatomical localization but encountered difficulties in disease diagnosis and lesion detection. Additionally, both the Gemini series and GPT series contain models that have demonstrated commendable generation efficiency. While both models hold promise in reducing physician workload, alleviating pressure on limited healthcare resources, and fostering collaboration between clinical practitioners and artificial intelligence technologies, substantial enhancements and comprehensive validations remain imperative before clinical deployment.

Jeremiah Fadugba, Patrick Köhler, Lisa Koch et al.

Retinal blood vessel segmentation can extract clinically relevant information from fundus images. As manual tracing is cumbersome, algorithms based on Convolution Neural Networks have been developed. Such studies have used small publicly available datasets for training and measuring performance, running the risk of overfitting. Here, we provide a rigorous benchmark for various architectural and training choices commonly used in the literature on the largest dataset published to date. We train and evaluate five published models on the publicly available FIVES fundus image dataset, which exceeds previous ones in size and quality and which contains also images from common ophthalmological conditions (diabetic retinopathy, age-related macular degeneration, glaucoma). We compare the performance of different model architectures across different loss functions, levels of image qualitiy and ophthalmological conditions and assess their ability to perform well in the face of disease-induced domain shifts. Given sufficient training data, basic architectures such as U-Net perform just as well as more advanced ones, and transfer across disease-induced domain shifts typically works well for most architectures. However, we find that image quality is a key factor determining segmentation outcomes. When optimizing for segmentation performance, investing into a well curated dataset to train a standard architecture yields better results than tuning a sophisticated architecture on a smaller dataset or one with lower image quality. We distilled the utility of architectural advances in terms of their clinical relevance therefore providing practical guidance for model choices depending on the circumstances of the clinical setting

Hongqiu Wang, Zhaohu Xing, Weitong Wu et al.

Fundus imaging is a pivotal tool in ophthalmology, and different imaging modalities are characterized by their specific advantages. For example, Fundus Fluorescein Angiography (FFA) uniquely provides detailed insights into retinal vascular dynamics and pathology, surpassing Color Fundus Photographs (CFP) in detecting microvascular abnormalities and perfusion status. However, the conventional invasive FFA involves discomfort and risks due to fluorescein dye injection, and it is meaningful but challenging to synthesize FFA images from non-invasive CFP. Previous studies primarily focused on FFA synthesis in a single disease category. In this work, we explore FFA synthesis in multiple diseases by devising a Diffusion-guided generative adversarial network, which introduces an adaptive and dynamic diffusion forward process into the discriminator and adds a category-aware representation enhancer. Moreover, to facilitate this research, we collect the first multi-disease CFP and FFA paired dataset, named the Multi-disease Paired Ocular Synthesis (MPOS) dataset, with four different fundus diseases. Experimental results show that our FFA synthesis network can generate better FFA images compared to state-of-the-art methods. Furthermore, we introduce a paired-modal diagnostic network to validate the effectiveness of synthetic FFA images in the diagnosis of multiple fundus diseases, and the results show that our synthesized FFA images with the real CFP images have higher diagnosis accuracy than that of the compared FFA synthesizing methods. Our research bridges the gap between non-invasive imaging and FFA, thereby offering promising prospects to enhance ophthalmic diagnosis and patient care, with a focus on reducing harm to patients through non-invasive procedures. Our dataset and code will be released to support further research in this field (https://github.com/whq-xxh/FFA-Synthesis).

Jamie Burke, Justin Engelmann, Samuel Gibbon et al.

Optical coherence tomography (OCT) and scanning laser ophthalmoscopy (SLO) of the eye has become essential to ophthalmology and the emerging field of oculomics, thus requiring a need for transparent, reproducible, and rapid analysis of this data for clinical research and the wider research community. Here, we introduce OCTolyzer, the first open-source toolkit for retinochoroidal analysis in OCT/SLO data. It features two analysis suites for OCT and SLO data, facilitating deep learning-based anatomical segmentation and feature extraction of the cross-sectional retinal and choroidal layers and en face retinal vessels. We describe OCTolyzer and evaluate the reproducibility of its OCT choroid analysis. At the population level, metrics for choroid region thickness were highly reproducible, with a mean absolute error (MAE)/Pearson correlation for macular volume choroid thickness (CT) of 6.7$μ$m/0.99, macular B-scan CT of 11.6$μ$m/0.99, and peripapillary CT of 5.0$μ$m/0.99. Macular choroid vascular index (CVI) also showed strong reproducibility, with MAE/Pearson for volume CVI yielding 0.0271/0.97 and B-scan CVI 0.0130/0.91. At the eye level, measurement noise for regional and vessel metrics was below 5% and 20% of the population's variability, respectively. Outliers were caused by poor-quality B-scans with thick choroids and invisible choroid-sclera boundary. Processing times on a laptop CPU were under three seconds for macular/peripapillary B-scans and 85 seconds for volume scans. OCTolyzer can convert OCT/SLO data into reproducible and clinically meaningful retinochoroidal features and will improve the standardisation of ocular measurements in OCT/SLO image analysis, requiring no specialised training or proprietary software to be used. OCTolyzer is freely available here: https://github.com/jaburke166/OCTolyzer.

Yan Ning Neo, Marketa Cilkova, Alfonso Vasquez Perez

Xudong Wen, Pan Long, Pan Long

Nchongmaje Ndipenoch, Alina Miron, Zidong Wang et al.

Retinal Optical Coherence Tomography (OCT), a noninvasive cross-sectional scan of the eye with qualitative 3D visualization of the retinal anatomy is use to study the retinal structure and the presence of pathogens. The advent of the retinal OCT has transformed ophthalmology and it is currently paramount for the diagnosis, monitoring and treatment of many eye pathogens including Macular Edema which impairs vision severely or Glaucoma that can cause irreversible blindness. However the quality of retinal OCT images varies among device manufacturers. Deep Learning methods have had their success in the medical image segmentation community but it is still not clear if the level of success can be generalised across OCT images collected from different device vendors. In this work we propose two variants of the nnUNet [8]. The standard nnUNet and an enhanced vision call nnUnet_RASPP (nnU-Net with residual and Atrous Spatial Pyramid Pooling) both of which are robust and generalise with consistent high performance across images from multiple device vendors. The algorithm was validated on the MICCAI 2017 RETOUCH challenge dataset [1] acquired from 3 device vendors across 3 medical centers from patients suffering from 2 retinal disease types. Experimental results show that our algorithms outperform the current state-of-the-arts algorithms by a clear margin for segmentation obtaining a mean Dice Score (DS) of 82.3% for the 3 retinal fluids scoring 84.0%, 80.0%, 83.0% for Intraretinal Fluid (IRF), Subretinal Fluid (SRF), and Pigment Epithelium Detachments (PED) respectively on the testing dataset. Also we obtained a perfect Area Under the Curve (AUC) score of 100% for the detection of the presence of fluid for all 3 fluid classes on the testing dataset.

C. Malhotra, A. Jain

The amniotic membrane (AM) is the inner layer of the fetal membranes and consist of 3 different layers: the epithelium, basement membrane and stroma which further consists of three contiguous but distinct layers: the inner compact layer, middle fibroblast layer and the outermost spongy layer. The AM has been shown to have anti-inflammatory, anti-fibrotic, anti-angiogenic as well as anti-microbial properties. Also because of its transparent structure, lack of immunogenicity and the ability to provide an excellent substrate for growth, migration and adhesion of epithelial corneal and conjunctival cells, it is being used increasingly for ocular surface reconstruction in a variety of ocular pathologies including corneal disorders associated with limbal stem cell deficiency, surgeries for conjunctival reconstruction, as a carrier for ex vivo expansion of limbal epithelial cells, glaucoma surgeries and sceral melts and perforations. However indiscriminate use of human AM needs to be discouraged as complications though infrequent can occur. These include risk of transmission of bacterial, viral or fungal infections to the recipient if the donors are not adequately screened for communicable diseases, if the membrane is not processed under sterile conditions or if storage is improper. Optimal outcomes can be achieved only with meticulous case selection. This review explores the ever expanding ophthalmological indications for the use of human AM.

Stefan Ploner, Siyu Chen, Jungeun Won et al.

Optical coherence tomography (OCT) is a micrometer-scale, volumetric imaging modality that has become a clinical standard in ophthalmology. OCT instruments image by raster-scanning a focused light spot across the retina, acquiring sequential cross-sectional images to generate volumetric data. Patient eye motion during the acquisition poses unique challenges: Non-rigid, discontinuous distortions can occur, leading to gaps in data and distorted topographic measurements. We present a new distortion model and a corresponding fully-automatic, reference-free optimization strategy for computational motion correction in orthogonally raster-scanned, retinal OCT volumes. Using a novel, domain-specific spatiotemporal parametrization of forward-warping displacements, eye motion can be corrected continuously for the first time. Parameter estimation with temporal regularization improves robustness and accuracy over previous spatial approaches. We correct each A-scan individually in 3D in a single mapping, including repeated acquisitions used in OCT angiography protocols. Specialized 3D forward image warping reduces median runtime to < 9 s, fast enough for clinical use. We present a quantitative evaluation on 18 subjects with ocular pathology and demonstrate accurate correction during microsaccades. Transverse correction is limited only by ocular tremor, whereas submicron repeatability is achieved axially (0.51 um median of medians), representing a dramatic improvement over previous work. This allows assessing longitudinal changes in focal retinal pathologies as a marker of disease progression or treatment response, and promises to enable multiple new capabilities such as supersampled/super-resolution volume reconstruction and analysis of pathological eye motion occuring in neurological diseases.

Alexandre H. Thiery, Fabian Braeu, Tin A. Tun et al.

Purpose: (1) To assess the performance of geometric deep learning (PointNet) in diagnosing glaucoma from a single optical coherence tomography (OCT) 3D scan of the optic nerve head (ONH); (2) To compare its performance to that obtained with a standard 3D convolutional neural network (CNN), and with a gold-standard glaucoma parameter, i.e. retinal nerve fiber layer (RNFL) thickness. Methods: 3D raster scans of the ONH were acquired with Spectralis OCT for 477 glaucoma and 2,296 non-glaucoma subjects at the Singapore National Eye Centre. All volumes were automatically segmented using deep learning to identify 7 major neural and connective tissues including the RNFL, the prelamina, and the lamina cribrosa (LC). Each ONH was then represented as a 3D point cloud with 1,000 points chosen randomly from all tissue boundaries. To simplify the problem, all ONH point clouds were aligned with respect to the plane and center of Bruch's membrane opening. Geometric deep learning (PointNet) was then used to provide a glaucoma diagnosis from a single OCT point cloud. The performance of our approach was compared to that obtained with a 3D CNN, and with RNFL thickness. Results: PointNet was able to provide a robust glaucoma diagnosis solely from the ONH represented as a 3D point cloud (AUC=95%). The performance of PointNet was superior to that obtained with a standard 3D CNN (AUC=87%) and with that obtained from RNFL thickness alone (AUC=80%). Discussion: We provide a proof-of-principle for the application of geometric deep learning in the field of glaucoma. Our technique requires significantly less information as input to perform better than a 3D CNN, and with an AUC superior to that obtained from RNFL thickness alone. Geometric deep learning may have wide applicability in the field of Ophthalmology.