ABSTRACT
Primary diabetes care and diabetic retinopathy (DR) screening persist as major public health challenges due to a shortage of trained primary care physicians (PCPs), particularly in low-resource settings. Here, to bridge the gaps, we developed an integrated image-language system (DeepDR-LLM), combining a large language model (LLM module) and image-based deep learning (DeepDR-Transformer), to provide individualized diabetes management recommendations to PCPs. In a retrospective evaluation, the LLM module demonstrated comparable performance to PCPs and endocrinology residents when tested in English and outperformed PCPs and had comparable performance to endocrinology residents in Chinese. For identifying referable DR, the average PCP's accuracy was 81.0% unassisted and 92.3% assisted by DeepDR-Transformer. Furthermore, we performed a single-center real-world prospective study, deploying DeepDR-LLM. We compared diabetes management adherence of patients under the unassisted PCP arm (n = 397) with those under the PCP+DeepDR-LLM arm (n = 372). Patients with newly diagnosed diabetes in the PCP+DeepDR-LLM arm showed better self-management behaviors throughout follow-up (P < 0.05). For patients with referral DR, those in the PCP+DeepDR-LLM arm were more likely to adhere to DR referrals (P < 0.01). Additionally, DeepDR-LLM deployment improved the quality and empathy level of management recommendations. Given its multifaceted performance, DeepDR-LLM holds promise as a digital solution for enhancing primary diabetes care and DR screening.
ABSTRACT
BACKGROUND: Large language models (LLMs) demonstrated advanced performance in processing clinical information. However, commercially available LLMs lack specialized medical knowledge and remain susceptible to generating inaccurate information. Given the need for self-management in diabetes, patients commonly seek information online. We introduce the RISE framework and evaluate its performance in enhancing LLMs to provide accurate responses to diabetes-related inquiries. OBJECTIVE: This study aimed to evaluate the potential of RISE framework, an information retrieval and augmentation tool, to improve the LLM's performance to accurately and safely respond to diabetes-related inquiries. METHODS: The RISE, an innovative retrieval augmentation framework, comprises four steps: Rewriting Query, Information Retrieval, Summarization, and Execution. Using a set of 43 common diabetes-related questions, we evaluated three base LLMs (GPT-4, Anthropic Claude 2, Google Bard) and their RISE-enhanced versions. Assessments were conducted by clinicians for accuracy and comprehensiveness, and by patients for understandability. RESULTS: The integration of RISE significantly improved the accuracy and comprehensiveness of responses from all three based LLMs. On average, the percentage of accurate responses increased by 12% (122 - 107/129) with RISE. Specifically, the rates of accurate responses increased by 7% (42 - 39/43) for GPT-4, 19% (39 - 31/43) for Claude 2, and 9% (41 - 37/43) for Google Bard. The framework also enhanced response comprehensiveness, with mean scores improving by 0.44. Understandability was also enhanced by 0.19 on average. Data collection was conducted from Sept. 30, 2023, to Feb. 05, 2024. CONCLUSIONS: RISE significantly improves LLMs' performance in responding to diabetes-related inquiries, enhancing accuracy, comprehensiveness, and understandability. These improvements have crucial implications for RISE's future role in patient education and chronic illness self-management, which contributes to relieving medical resource pressures and raising public awareness of medical knowledge.
ABSTRACT
Purpose: The purpose of this study was to develop and validate prediction model for myopic macular degeneration (MMD) progression in patients with high myopia. Methods: The Zhongshan High Myopia Cohort for model development included 660 patients aged 7 to 70 years with a bilateral sphere of ≤-6.00 diopters (D). Two hundred twelve participants with an axial length (AL) ≥25.5 mm from the Chinese Ocular Imaging Project were used for external validation. Thirty-four clinical variables, including demographics, lifestyle, myopia history, and swept source optical coherence tomography data, were analyzed. Sequential forward selection was used for predictor selection, and binary classification models were created using five machine learning algorithms to forecast the risk of MMD progression over 10 years. Results: Over a median follow-up of 10.9 years, 133 patients (20.2%) showed MMD progression in the development cohort. Among them, 69 (51.9%) developed newly-onset MMD, 11 (8.3%) developed patchy atrophy from diffuse atrophy, 54 (40.6%) showed an enlargement of lesions, and 9 (6.8%) developed plus signs. Top six predictors for MMD progression included thinner subfoveal choroidal thickness, longer AL, worse best-corrected visual acuity, older age, female gender, and shallower anterior chamber depth. The eXtreme Gradient Boosting algorithm yielded the best discriminative performance (area under the receiver operating characteristic curve [AUROC] = 0.87 ± 0.02) with good calibration in the training cohort. In a less myopic external validation group (median -5.38 D), 48 patients (22.6%) developed MMD progression over 4 years, with the model's AUROC validated at 0.80 ± 0.008. Conclusions: Machine learning model effectively predicts MMD progression a decade ahead using clinical and imaging indicators. This tool shows promise for identifying "at-risk" high myopes for timely intervention and vision protection.
Subject(s)
Algorithms , Disease Progression , Machine Learning , Macular Degeneration , Myopia, Degenerative , Tomography, Optical Coherence , Humans , Male , Female , Middle Aged , Adult , Tomography, Optical Coherence/methods , Aged , Adolescent , Child , Young Adult , Macular Degeneration/diagnosis , Myopia, Degenerative/diagnosis , Follow-Up Studies , Risk Factors , Forecasting , Risk Assessment/methods , Visual AcuityABSTRACT
Fundus fluorescein angiography (FFA) is a crucial diagnostic tool for chorioretinal diseases, but its interpretation requires significant expertise and time. Prior studies have used Artificial Intelligence (AI)-based systems to assist FFA interpretation, but these systems lack user interaction and comprehensive evaluation by ophthalmologists. Here, we used large language models (LLMs) to develop an automated interpretation pipeline for both report generation and medical question-answering (QA) for FFA images. The pipeline comprises two parts: an image-text alignment module (Bootstrapping Language-Image Pre-training) for report generation and an LLM (Llama 2) for interactive QA. The model was developed using 654,343 FFA images with 9392 reports. It was evaluated both automatically, using language-based and classification-based metrics, and manually by three experienced ophthalmologists. The automatic evaluation of the generated reports demonstrated that the system can generate coherent and comprehensible free-text reports, achieving a BERTScore of 0.70 and F1 scores ranging from 0.64 to 0.82 for detecting top-5 retinal conditions. The manual evaluation revealed acceptable accuracy (68.3%, Kappa 0.746) and completeness (62.3%, Kappa 0.739) of the generated reports. The generated free-form answers were evaluated manually, with the majority meeting the ophthalmologists' criteria (error-free: 70.7%, complete: 84.0%, harmless: 93.7%, satisfied: 65.3%, Kappa: 0.762-0.834). This study introduces an innovative framework that combines multi-modal transformers and LLMs, enhancing ophthalmic image interpretation, and facilitating interactive communications during medical consultation.
ABSTRACT
MOTIVATION: The quality scores data (QSD) account for 70% in compressed FastQ files obtained from the short and long reads sequencing technologies. Designing effective compressors for QSD that counterbalance compression ratio, time cost, and memory consumption is essential in scenarios such as large-scale genomics data sharing and long-term data backup. This study presents a novel parallel lossless QSD-dedicated compression algorithm named PQSDC, which fulfills the above requirements well. PQSDC is based on two core components: a parallel sequences-partition model designed to reduce peak memory consumption and time cost during compression and decompression processes, as well as a parallel four-level run-length prediction mapping model to enhance compression ratio. Besides, the PQSDC algorithm is also designed to be highly concurrent using multicore CPU clusters. RESULTS: We evaluate PQSDC and four state-of-the-art compression algorithms on 27 real-world datasets, including 61.857 billion QSD characters and 632.908 million QSD sequences. (1) For short reads, compared to baselines, the maximum improvement of PQSDC reaches 7.06% in average compression ratio, and 8.01% in weighted average compression ratio. During compression and decompression, the maximum total time savings of PQSDC are 79.96% and 84.56%, respectively; the maximum average memory savings are 68.34% and 77.63%, respectively. (2) For long reads, the maximum improvement of PQSDC reaches 12.51% and 13.42% in average and weighted average compression ratio, respectively. The maximum total time savings during compression and decompression are 53.51% and 72.53%, respectively; the maximum average memory savings are 19.44% and 17.42%, respectively. (3) Furthermore, PQSDC ranks second in compression robustness among the tested algorithms, indicating that it is less affected by the probability distribution of the QSD collections. Overall, our work provides a promising solution for QSD parallel compression, which balances storage cost, time consumption, and memory occupation primely. AVAILABILITY AND IMPLEMENTATION: The proposed PQSDC compressor can be downloaded from https://github.com/fahaihi/PQSDC.
Subject(s)
Algorithms , Data Compression , Data Compression/methods , Genomics/methods , High-Throughput Nucleotide Sequencing/methods , Sequence Analysis, DNA/methods , Software , HumansABSTRACT
Virus-like particles (VLP) are a promising tool for intracellular gene delivery, yet their potential in ocular gene therapy remains underexplored. In this study, we bridged this knowledge gap by demonstrating the successful generation and application of vesicular stomatitis virus glycoprotein (VSVG)-pseudotyped mouse PEG10 (MmPEG10)-VLP for intraocular mRNA delivery. Our findings revealed that PEG10-VLP can efficiently deliver GFP mRNA to adult retinal pigment epithelial cell line-19 (ARPE-19) cells, leading to transient expression. Moreover, we showed that MmPEG10-VLP can transfer SMAD7 to inhibit epithelial-mesenchymal transition (EMT) in RPE cells effectively. In vivo experiments further substantiated the potential of these vectors, as subretinal delivery into adult mice resulted in efficient transduction of retinal pigment epithelial (RPE) cells and GFP reporter gene expression without significant immune response. However, intravitreal injection did not yield efficient ocular expression. We also evaluated the transduction characteristics of MmPEG10-VLP following intracameral delivery, revealing transient GFP protein expression in corneal endothelial cells without significant immunotoxicities. In summary, our study established that VSVG pseudotyped MmPEG10-based VLP can transduce mitotically inactive RPE cells and corneal endothelial cells in vivo without triggering an inflammatory response, underscoring their potential utility in ocular gene therapy.
Subject(s)
Gene Transfer Techniques , RNA, Messenger , Retinal Pigment Epithelium , Animals , Mice , Retinal Pigment Epithelium/metabolism , RNA, Messenger/genetics , Genetic Therapy/methods , Genetic Vectors , Mice, Inbred C57BL , Humans , Green Fluorescent Proteins/genetics , Epithelial-Mesenchymal Transition , Membrane Glycoproteins/genetics , Membrane Glycoproteins/metabolismABSTRACT
BACKGROUND: Indocyanine green angiography (ICGA) is vital for diagnosing chorioretinal diseases, but its interpretation and patient communication require extensive expertise and time-consuming efforts. We aim to develop a bilingual ICGA report generation and question-answering (QA) system. METHODS: Our dataset comprised 213 129 ICGA images from 2919 participants. The system comprised two stages: image-text alignment for report generation by a multimodal transformer architecture, and large language model (LLM)-based QA with ICGA text reports and human-input questions. Performance was assessed using both qualitative metrics (including Bilingual Evaluation Understudy (BLEU), Consensus-based Image Description Evaluation (CIDEr), Recall-Oriented Understudy for Gisting Evaluation-Longest Common Subsequence (ROUGE-L), Semantic Propositional Image Caption Evaluation (SPICE), accuracy, sensitivity, specificity, precision and F1 score) and subjective evaluation by three experienced ophthalmologists using 5-point scales (5 refers to high quality). RESULTS: We produced 8757 ICGA reports covering 39 disease-related conditions after bilingual translation (66.7% English, 33.3% Chinese). The ICGA-GPT model's report generation performance was evaluated with BLEU scores (1-4) of 0.48, 0.44, 0.40 and 0.37; CIDEr of 0.82; ROUGE of 0.41 and SPICE of 0.18. For disease-based metrics, the average specificity, accuracy, precision, sensitivity and F1 score were 0.98, 0.94, 0.70, 0.68 and 0.64, respectively. Assessing the quality of 50 images (100 reports), three ophthalmologists achieved substantial agreement (kappa=0.723 for completeness, kappa=0.738 for accuracy), yielding scores from 3.20 to 3.55. In an interactive QA scenario involving 100 generated answers, the ophthalmologists provided scores of 4.24, 4.22 and 4.10, displaying good consistency (kappa=0.779). CONCLUSION: This pioneering study introduces the ICGA-GPT model for report generation and interactive QA for the first time, underscoring the potential of LLMs in assisting with automated ICGA image interpretation.
ABSTRACT
Age-related macular degeneration (AMD) is the leading cause of central vision impairment among the elderly. Effective and accurate AMD screening tools are urgently needed. Indocyanine green angiography (ICGA) is a well-established technique for detecting chorioretinal diseases, but its invasive nature and potential risks impede its routine clinical application. Here, we innovatively developed a deep-learning model capable of generating realistic ICGA images from color fundus photography (CF) using generative adversarial networks (GANs) and evaluated its performance in AMD classification. The model was developed with 99,002 CF-ICGA pairs from a tertiary center. The quality of the generated ICGA images underwent objective evaluation using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity measures (SSIM), etc., and subjective evaluation by two experienced ophthalmologists. The model generated realistic early, mid and late-phase ICGA images, with SSIM spanned from 0.57 to 0.65. The subjective quality scores ranged from 1.46 to 2.74 on the five-point scale (1 refers to the real ICGA image quality, Kappa 0.79-0.84). Moreover, we assessed the application of translated ICGA images in AMD screening on an external dataset (n = 13887) by calculating area under the ROC curve (AUC) in classifying AMD. Combining generated ICGA with real CF images improved the accuracy of AMD classification with AUC increased from 0.93 to 0.97 (P < 0.001). These results suggested that CF-to-ICGA translation can serve as a cross-modal data augmentation method to address the data hunger often encountered in deep-learning research, and as a promising add-on for population-based AMD screening. Real-world validation is warranted before clinical usage.
ABSTRACT
Purpose: We aim to use fundus fluorescein angiography (FFA) to label the capillaries on color fundus (CF) photographs and train a deep learning model to quantify retinal capillaries noninvasively from CF and apply it to cardiovascular disease (CVD) risk assessment. Design: Cross-sectional and longitudinal study. Participants: A total of 90732 pairs of CF-FFA images from 3893 participants for segmentation model development, and 49229 participants in the UK Biobank for association analysis. Methods: We matched the vessels extracted from FFA and CF, and used vessels from FFA as labels to train a deep learning model (RMHAS-FA) to segment retinal capillaries using CF. We tested the model's accuracy on a manually labeled internal test set (FundusCapi). For external validation, we tested the segmentation model on 7 vessel segmentation datasets, and investigated the clinical value of the segmented vessels in predicting CVD events in the UK Biobank. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity for segmentation. Hazard ratio (HR; 95% confidence interval [CI]) for Cox regression analysis. Results: On the FundusCapi dataset, the segmentation performance was AUC = 0.95, accuracy = 0.94, sensitivity = 0.90, and specificity = 0.93. Smaller vessel skeleton density had a stronger correlation with CVD risk factors and incidence (P < 0.01). Reduced density of small vessel skeletons was strongly associated with an increased risk of CVD incidence and mortality for women (HR [95% CI] = 0.91 [0.84-0.98] and 0.68 [0.54-0.86], respectively). Conclusions: Using paired CF-FFA images, we automated the laborious manual labeling process and enabled noninvasive capillary quantification from CF, supporting its potential as a sensitive screening method for identifying individuals at high risk of future CVD events. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
ABSTRACT
Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. The risk of DR progression is highly variable among different individuals, making it difficult to predict risk and personalize screening intervals. We developed and validated a deep learning system (DeepDR Plus) to predict time to DR progression within 5 years solely from fundus images. First, we used 717,308 fundus images from 179,327 participants with diabetes to pretrain the system. Subsequently, we trained and validated the system with a multiethnic dataset comprising 118,868 images from 29,868 participants with diabetes. For predicting time to DR progression, the system achieved concordance indexes of 0.754-0.846 and integrated Brier scores of 0.153-0.241 for all times up to 5 years. Furthermore, we validated the system in real-world cohorts of participants with diabetes. The integration with clinical workflow could potentially extend the mean screening interval from 12 months to 31.97 months, and the percentage of participants recommended to be screened at 1-5 years was 30.62%, 20.00%, 19.63%, 11.85% and 17.89%, respectively, while delayed detection of progression to vision-threatening DR was 0.18%. Altogether, the DeepDR Plus system could predict individualized risk and time to DR progression over 5 years, potentially allowing personalized screening intervals.
Subject(s)
Deep Learning , Diabetes Mellitus , Diabetic Retinopathy , Humans , Diabetic Retinopathy/diagnosis , BlindnessABSTRACT
Importance: Identifying primary angle closure suspect (PACS) eyes at risk of angle closure is crucial for its management. However, the risk of progression and its prediction are still understudied in long-term longitudinal studies about PACS. Objective: To explore baseline predictors and develop prediction models for the 14-year risk of progression from PACS to primary angle closure (PAC). Design, Setting, and Participants: This cohort study involved participants from the Zhongshan Angle Closure Prevention trial who had untreated eyes with PACS. Baseline examinations included tonometry, ultrasound A-scan biometry, and anterior segment optical coherence tomography (AS-OCT) under both light and dark conditions. Primary angle closure was defined as peripheral anterior synechiae in 1 or more clock hours, intraocular pressure (IOP) greater than 24 mm Hg, or acute angle closure. Based on baseline covariates, logistic regression models were built to predict the risk of progression from PACS to PAC during 14 years of follow-up. Results: The analysis included 377 eyes from 377 patients (mean [SD] patient age at baseline, 58.28 [4.71] years; 317 females [84%]). By the 14-year follow-up visit, 93 eyes (25%) had progressed from PACS to PAC. In multivariable models, higher IOP (odds ratio [OR], 1.14 [95% CI, 1.04-1.25] per 1-mm Hg increase), shallower central anterior chamber depth (ACD; OR, 0.81 [95% CI, 0.67-0.97] per 0.1-mm increase), and shallower limbal ACD (OR, 0.96 [95% CI, 0.93-0.99] per 0.01 increase in peripheral corneal thickness) at baseline were associated with an increased 14-year risk of progression from PACS to PAC. As for AS-OCT measurements, smaller light-room trabecular-iris space area (TISA) at 500 µm from the scleral spur (OR, 0.86 [95% CI, 0.77-0.96] per 0.01-mm2 increase), smaller light-room angle recess area (ARA) at 750 µm from the scleral spur (OR, 0.93 [95% CI, 0.88-0.98] per 0.01-mm2 increase), and smaller dark-room TISA at 500 µm (OR, 0.89 [95% CI, 0.80-0.98] per 0.01-mm2 increase) at baseline were identified as predictors for the 14-year risk of progression. The prediction models based on IOP and central and limbal ACDs showed moderate performance (area under the receiver operating characteristic curve, 0.69; 95% CI, 0.63-0.75) in predicting progression from PACS to PAC, and inclusion of AS-OCT metrics did not improve the model's performance. Conclusions and Relevance: This cohort study suggests that higher IOP, shallower central and limbal ACDs, and smaller TISA at 500 µm and light-room ARA at 750 µm may serve as baseline predictors for progression to PAC in PACS eyes. Evaluating these factors can aid in customizing PACS management.
Subject(s)
Glaucoma, Angle-Closure , Iridectomy , Female , Humans , Child, Preschool , Cohort Studies , Glaucoma, Angle-Closure/diagnosis , Glaucoma, Angle-Closure/surgery , Iris , Intraocular Pressure , Tomography, Optical Coherence/methodsABSTRACT
Importance: Understanding the long-term axial elongation trajectory in high myopia is important to prevent blindness. Objective: To evaluate axial elongation trajectories and related visual outcomes in children and adults with high myopia. Design, Setting, and Participants: In this cohort study, participants in the Zhongshan Ophthalmic Centre-Brien Holden Vision Institute high myopia cohort were followed up every other year for 8 years. Participants with axial length measurements at baseline (2011 or 2012) and at least 1 follow-up visit were included. Participants were grouped according to baseline age as children and adolescents (7 to <18 years), young adults (18 to <40 years), and older adults (≥40 to 70 years). Data were analyzed from November 1, 2022, to June 1, 2023. Exposure: High myopia (spherical power ≤-6.00 diopters). Main Outcomes and Measures: Longitudinal axial elongation trajectories were identified by cluster analysis. Axial elongation rates were calculated by linear mixed-effects models. A 2-sided P < .05 was defined as statistically significant. Results: A total of 793 participants (median [range] age, 17.8 [6.8-69.7] years; 418 females [52.7%]) and 1586 eyes were included in the analyses. Mean axial elongation rates were 0.46 mm/y (95% CI, 0.44-0.48 mm/y) for children and adolescents, 0.07 mm/y (95% CI, 0.06-0.09 mm/y) for young adults, and 0.13 mm/y (95% CI, 0.07-0.19 mm/y) for older adults. Cluster analysis identified 3 axial elongation trajectories, with the stable, moderate, and rapid progression trajectories having mean axial elongation rates of 0.02 mm/y (95% CI, 0.01-0.02 mm/y), 0.12 mm/y (95% CI, 0.11-0.13 mm/y), and 0.38 mm/y (95% CI, 0.35-0.42 mm/y), respectively. At 8 years of follow-up, compared with the stable progression trajectory, the rapid progression trajectory was associated with a 6.92 times higher risk of developing pathological myopic macular degeneration (defined as diffuse or patchy chorioretinal atrophy or macular atrophy; odds ratio, 6.92 [95% CI, 1.07-44.60]; P = .04), and it was associated with a 0.032 logMAR decrease in best-corrected visual acuity (ß = 0.032 [95% CI, 0.001-0.063]; P = .04). Conclusions and Relevance: The findings of this 8-year follow-up study suggest that axial length in high myopia continues to increase from childhood to late adulthood following 3 distinct trajectories. At 8 years of follow-up, the rapid progression trajectory was associated with a higher risk of developing pathological myopic macular degeneration and poorer best-corrected visual acuity compared with the stable progression trajectory. These distinct axial elongation trajectories could prove valuable for early identification and intervention for high-risk individuals.
Subject(s)
Macular Degeneration , Myopia, Degenerative , Child , Female , Adolescent , Young Adult , Humans , Aged , Adult , Cohort Studies , Follow-Up Studies , Visual Acuity , Myopia, Degenerative/diagnosis , Myopia, Degenerative/complications , Macular Degeneration/complications , China/epidemiology , Atrophy/complicationsABSTRACT
BACKGROUND: Arthroscopic surgery has been established as an efficacious intervention for the treatment of rotator cuff tears. The primary aim of this study was to analyze the modifications in the lateral acromial angle (LAA) subsequent to rotator cuff repair surgery using single-row rivet fixation and double-row rivet fixation techniques. Furthermore, we sought to investigate the influence of LAA on the prognosis of rotator cuff repair surgery. METHOD: This observational study retrospectively enrolled 105 patients diagnosed with degenerative rotator cuff tears who underwent arthroscopic rotator cuff repair between 2016 and 2019. Following the exclusion of two patients with subscapularis or superior labrum anterior and posterior (SLAP) tears, as well as three patients who were lost to follow-up, a cohort of 100 patients was included for clinical and imaging evaluation. Among these individuals, 50 were assigned to the double-row repair group, whereas the remaining 50 comprised the single-row repair group. Bilateral shoulder magnetic resonance imaging (MRI) scans were conducted no less than 24 months post-surgery. Experienced arthroscopic surgeons, blinded to the LAA measurements, assessed the rotator interval (RI) using a control MRI. Functional assessment was performed using the University of California, Los Angeles (UCLA) quick disability of the shoulder and arm, shoulder and hand (qDASH) score. The Wilcoxon signed-rank test for dependent samples was employed to compare data between the pre- and post-intervention groups. Pearson correlation coefficients were calculated to evaluate the relationship between different parameters. RESULTS: The study population consisted of 73 female patients and 27 male patients, with a mean age of 58.32 ± 5.29 years and a mean follow-up duration of 25.88 ± 8.11 months. Preoperatively, the mean LAA was 75.81° ± 11.28°, RI was 4.78 ± 0.62, UCLA score was 17.54 ± 2.44, and qDASH score was 2.45 ± 0.25. The average tear size was 8.95 ± 2.11 mm. A statistically significant difference in LAA was observed between the preoperative and postoperative measurements, with the double-row repair group exhibiting a greater LAA than the single-row repair group. Finally, a significant correlation was identified between LAA, RI, and qDASH scores after a 24-month follow-up period. CONCLUSION: According to our findings, the utilization of double-row rivet fixation has a greater LAA angle than single-row rivet fixation. Moreover, this preservation of LAA is significantly associated with the functional recovery of the shoulder joint.
Subject(s)
Rotator Cuff Injuries , Humans , Male , Female , Middle Aged , Rotator Cuff Injuries/diagnostic imaging , Rotator Cuff Injuries/surgery , Acromion/diagnostic imaging , Acromion/surgery , Retrospective Studies , Rotator Cuff/diagnostic imaging , Rotator Cuff/surgery , Shoulder , Arthroscopy/methods , Magnetic Resonance Imaging , Treatment OutcomeABSTRACT
Background: Fundus Autofluorescence (FAF) is a valuable imaging technique used to assess metabolic alterations in the retinal pigment epithelium (RPE) associated with various age-related and disease-related changes. The practical uses of FAF are ever-growing. This study aimed to evaluate the effectiveness of a generative deep learning (DL) model in translating color fundus (CF) images into synthetic FAF images and explore its potential for enhancing screening of age-related macular degeneration (AMD). Methods: A generative adversarial network (GAN) model was trained on pairs of CF and FAF images to generate synthetic FAF images. The quality of synthesized FAF images was assessed objectively by common generation metrics. Additionally, the clinical effectiveness of the generated FAF images in AMD classification was evaluated by measuring the area under the curve (AUC), using the LabelMe dataset. Results: A total of 8410 FAF images from 2586 patients were analyzed. The synthesized FAF images exhibited an impressive objectively assessed quality, achieving a multi-scale structural similarity index (MS-SSIM) of 0.67. When evaluated on the LabelMe dataset, the combination of generated FAF images and CF images resulted in a noteworthy improvement in AMD classification accuracy, with the AUC increasing from 0.931 to 0.968. Conclusions: This study presents the first attempt to use a generative deep learning model to create authentic and high-quality FAF images from CF images. The incorporation of the translated FAF images on top of CF images improved the accuracy of AMD classification. Overall, this study presents a promising approach to enhance large-scale AMD screening.
ABSTRACT
The advent of generative artificial intelligence and large language models has ushered in transformative applications within medicine. Specifically in ophthalmology, large language models offer unique opportunities to revolutionise digital eye care, address clinical workflow inefficiencies, and enhance patient experiences across diverse global eye care landscapes. Yet alongside these prospects lie tangible and ethical challenges, encompassing data privacy, security, and the intricacies of embedding large language models into clinical routines. This Viewpoint highlights the promising applications of large language models in ophthalmology, while weighing up the practical and ethical barriers towards their real-world implementation. This Viewpoint seeks to stimulate broader discourse on the potential of large language models in ophthalmology and to galvanise both clinicians and researchers into tackling the prevailing challenges and optimising the benefits of large language models while curtailing the associated risks.
Subject(s)
Medicine , Ophthalmology , Humans , Artificial Intelligence , Language , PrivacyABSTRACT
BACKGROUND: Genomic sequencing reads compressors are essential for balancing high-throughput sequencing short reads generation speed, large-scale genomic data sharing, and infrastructure storage expenditure. However, most existing short reads compressors rarely utilize big-memory systems and duplicative information between diverse sequencing files to achieve a higher compression ratio for conserving reads data storage space. RESULTS: We employ compression ratio as the optimization objective and propose a large-scale genomic sequencing short reads data compression optimizer, named PMFFRC, through novelty memory modeling and redundant reads clustering technologies. By cascading PMFFRC, in 982 GB fastq format sequencing data, with 274 GB and 3.3 billion short reads, the state-of-the-art and reference-free compressors HARC, SPRING, Mstcom, and FastqCLS achieve 77.89%, 77.56%, 73.51%, and 29.36% average maximum compression ratio gains, respectively. PMFFRC saves 39.41%, 41.62%, 40.99%, and 20.19% of storage space sizes compared with the four unoptimized compressors. CONCLUSIONS: PMFFRC rational usage big-memory of compression server, effectively saving the sequencing reads data storage space sizes, which relieves the basic storage facilities costs and community sharing transmitting overhead. Our work furnishes a novel solution for improving sequencing reads compression and saving storage space. The proposed PMFFRC algorithm is packaged in a same-name Linux toolkit, available un-limited at https://github.com/fahaihi/PMFFRC .
Subject(s)
Data Compression , Software , Algorithms , Genomics , High-Throughput Nucleotide Sequencing , Cluster Analysis , Sequence Analysis, DNAABSTRACT
Purpose: To develop and validate a deep learning model that can transform color fundus (CF) photography into corresponding venous and late-phase fundus fluorescein angiography (FFA) images. Design: Cross-sectional study. Participants: We included 51 370 CF-venous FFA pairs and 14 644 CF-late FFA pairs from 4438 patients for model development. External testing involved 50 eyes with CF-FFA pairs and 2 public datasets for diabetic retinopathy (DR) classification, with 86 952 CF from EyePACs, and 1744 CF from MESSIDOR2. Methods: We trained a deep-learning model to transform CF into corresponding venous and late-phase FFA images. The translated FFA images' quality was evaluated quantitatively on the internal test set and subjectively on 100 eyes with CF-FFA paired images (50 from external), based on the realisticity of the global image, anatomical landmarks (macula, optic disc, and vessels), and lesions. Moreover, we validated the clinical utility of the translated FFA for classifying 5-class DR and diabetic macular edema (DME) in the EyePACs and MESSIDOR2 datasets. Main Outcome Measures: Image generation was quantitatively assessed by structural similarity measures (SSIM), and subjectively by 2 clinical experts on a 5-point scale (1 refers real FFA); intragrader agreement was assessed by kappa. The DR classification accuracy was assessed by area under the receiver operating characteristic curve. Results: The SSIM of the translated FFA images were > 0.6, and the subjective quality scores ranged from 1.37 to 2.60. Both experts reported similar quality scores with substantial agreement (all kappas > 0.8). Adding the generated FFA on top of CF improved DR classification in the EyePACs and MESSIDOR2 datasets, with the area under the receiver operating characteristic curve increased from 0.912 to 0.939 on the EyePACs dataset and from 0.952 to 0.972 on the MESSIDOR2 dataset. The DME area under the receiver operating characteristic curve also increased from 0.927 to 0.974 in the MESSIDOR2 dataset. Conclusions: Our CF-to-FFA framework produced realistic FFA images. Moreover, adding the translated FFA images on top of CF improved the accuracy of DR screening. These results suggest that CF-to-FFA translation could be used as a surrogate method when FFA examination is not feasible and as a simple add-on to improve DR screening. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
ABSTRACT
OBJECTIVES: To evaluate the feasibility and accuracy of a portable, self-imaging optical coherence tomography (OCT) for measuring central subfield thickness (CST) and achieving diagnostic concordance for retinal lesions compared with clinic-based spectral-domain OCT (SD-OCT). METHODS: This comparative, cross-sectional study was conducted between August 2020 and February 2021. Two groups of adult participants were recruited: (1) a selected cohort of 160 participants with confirmed diagnosis and (2) a consecutive cohort of 315 participants recruited randomly. All participants underwent self-imaging OCT examination, as well as standard OCT examination. CST was automatically calculated for comparisons between the two OCT devices. Diagnostic concordance for retinal lesions and the success rate of self-imaging were assessed within the consecutive cohort. RESULTS: In the selected cohort, self-imaging OCT images yielded consistent CST with SD-OCT, with a mean difference of 0.1±7.7 µm for normal eyes, 4.9±10.6 µm for macular oedema, -1.3±9.5 µm for choroidal neovascularisation, 5.0±7.8 µm for epiretinal membrane. The self-imaging OCT also demonstrated good repeatability, with a mean test-retest difference in CST of 0.7±3.9 µm and limits of agreement ranging from -6.9 to 8.3 µm. Additionally, within the consecutive cohort, interdevice κ values ranged for detecting various retinal lesions ranged from 0.8 to 1.0, except in the cases of retinal detachment (κ=0.5). All eyes (100%) in the selected cohort and 242 eyes (76.8%) in the consecutive cohort successfully completed self-imaging. Participants spent less time on self-imaging compared with SD-OCT operated by a technician (66.7±20.1 vs 73.3±32.5, p<0.01). A majority of participants (90%) found the self-imaging process 'easy' and 'comfortable'. CONCLUSIONS AND RELEVANCE: This study demonstrates that our self-imaging OCT and clinical-used SD-OCT are highly consistent not only in measuring the CST but also in identifying most retinal lesions.
ABSTRACT
Behect's disease is a chronic vasculitis characterized by complex multi-organ immune aberrations. However, a comprehensive understanding of the gene-regulatory profile of peripheral autoimmunity and the diverse immune responses across distinct cell types in Behcet's disease (BD) is still lacking. Here, we present a multi-omic single-cell study of 424,817 cells in BD patients and non-BD individuals. This study maps chromatin accessibility and gene expression in the same biological samples, unraveling vast cellular heterogeneity. We identify widespread cell-type-specific, disease-associated active and pro-inflammatory immunity in both transcript and epigenomic aspects. Notably, integrative multi-omic analysis reveals putative TF regulators that might contribute to chromatin accessibility and gene expression in BD. Moreover, we predicted gene-regulatory networks within nominated TF activators, including AP-1, NF-kB, and ETS transcript factor families, which may regulate cellular interaction and govern inflammation. Our study illustrates the epigenetic and transcriptional landscape in BD peripheral blood and expands understanding of potential epigenomic immunopathology in this disease.