Performance of Artificial Intelligence in Detecting Diabetic Macular Edema From Fundus Photography and Optical Coherence Tomography Images: A Systematic Review and Meta-analysis.

BACKGROUND: Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography (FP) and optical coherence tomography (OCT) images allows prompt detection and intervention. PURPOSE: To evaluate the performance of AI in detecting DME from FP or OCT images and identify potential factors affecting model performances. DATA SOURCES: We searched seven electronic libraries up to 12 February 2023. STUDY SELECTION: We included studies using AI to detect DME from FP or OCT images. DATA EXTRACTION: We extracted study characteristics and performance parameters. DATA SYNTHESIS: Fifty-three studies were included in the meta-analysis. FP-based algorithms of 25 studies yielded pooled area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of 0.964, 92.6%, and 91.1%, respectively. OCT-based algorithms of 28 studies yielded pooled AUROC, sensitivity, and specificity of 0.985, 95.9%, and 97.9%, respectively. Potential factors improving model performance included deep learning techniques, larger size, and more diversity in training data sets. Models demonstrated better performance when validated internally than externally, and those trained with multiple data sets showed better results upon external validation. LIMITATIONS: Analyses were limited by unstandardized algorithm outcomes and insufficient data in patient demographics, OCT volumetric scans, and external validation. CONCLUSIONS: This meta-analysis demonstrates satisfactory performance of AI in detecting DME from FP or OCT images. External validation is warranted for future studies to evaluate model generalizability. Further investigations may estimate optimal sample size, effect of class balance, patient demographics, and additional benefits of OCT volumetric scans.

Research on the Communication Path of Traditional Chinese Medicine Culture from the Perspective of Industry-University-Research Collaborative Innovation / 中国医学伦理学

Traditional Chinese Medicine (TCM) is an indispensable carrier of traditional culture for China to embrace the world. During the 14th Five-Year Plan period, the state proposed to "comprehensively promote the building of a healthy China, attach equal importance to TCM and western medicine, and vigorously develop the cultural industry of TCM". Promoting the development of TCM cultural industry needs scientific and innovative approaches. This paper explored how to realize the communication path of TCM culture from the perspective of "Industry-University-Research". Based on the analysis of the current situation of TCM culture communication, taking Shandong University of Traditional Chinese Medicine as an example, this paper integrated technology, human resources, resources, environment and information and other collaborative innovation elements to effectively gather, and explored a new way for the collaborative development of TCM communication with enterprises, schools, scientific research institutions and et al, aiming to further help TCM culture go abroad.

Large language models and their impact in ophthalmology.

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.

Developing a privacy-preserving deep learning model for glaucoma detection: a multicentre study with federated learning.

BACKGROUND: Deep learning (DL) is promising to detect glaucoma. However, patients' privacy and data security are major concerns when pooling all data for model development. We developed a privacy-preserving DL model using the federated learning (FL) paradigm to detect glaucoma from optical coherence tomography (OCT) images. METHODS: This is a multicentre study. The FL paradigm consisted of a 'central server' and seven eye centres in Hong Kong, the USA and Singapore. Each centre first trained a model locally with its own OCT optic disc volumetric dataset and then uploaded its model parameters to the central server. The central server used FedProx algorithm to aggregate all centres' model parameters. Subsequently, the aggregated parameters are redistributed to each centre for its local model optimisation. We experimented with three three-dimensional (3D) networks to evaluate the stabilities of the FL paradigm. Lastly, we tested the FL model on two prospectively collected unseen datasets. RESULTS: We used 9326 volumetric OCT scans from 2785 subjects. The FL model performed consistently well with different networks in 7 centres (accuracies 78.3%-98.5%, 75.9%-97.0%, and 78.3%-97.5%, respectively) and stably in the 2 unseen datasets (accuracies 84.8%-87.7%, 81.3%-84.8%, and 86.0%-87.8%, respectively). The FL model achieved non-inferior performance in classifying glaucoma compared with the traditional model and significantly outperformed the individual models. CONCLUSION: The 3D FL model could leverage all the datasets and achieve generalisable performance, without data exchange across centres. This study demonstrated an OCT-based FL paradigm for glaucoma identification with ensured patient privacy and data security, charting another course toward the real-world transition of artificial intelligence in ophthalmology.

What can GPT-4 do for Diagnosing Rare Eye Diseases? A Pilot Study.

INTRODUCTION: Generative pretrained transformer-4 (GPT-4) has gained widespread attention from society, and its potential has been extensively evaluated in many areas. However, investigation of GPT-4's use in medicine, especially in the ophthalmology field, is still limited. This study aims to evaluate GPT-4's capability to identify rare ophthalmic diseases in three simulated scenarios for different end-users, including patients, family physicians, and junior ophthalmologists. METHODS: We selected ten treatable rare ophthalmic disease cases from the publicly available EyeRounds service. We gradually increased the amount of information fed into GPT-4 to simulate the scenarios of patient, family physician, and junior ophthalmologist using GPT-4. GPT-4's responses were evaluated from two aspects: suitability (appropriate or inappropriate) and accuracy (right or wrong) by senior ophthalmologists (> 10 years' experiences). RESULTS: Among the 30 responses, 83.3% were considered "appropriate" by senior ophthalmologists. In the scenarios of simulated patient, family physician, and junior ophthalmologist, seven (70%), ten (100%), and eight (80%) responses were graded as "appropriate" by senior ophthalmologists. However, compared to the ground truth, GPT-4 could only output several possible diseases generally without "right" responses in the simulated patient scenarios. In contrast, in the simulated family physician scenario, 50% of GPT-4's responses were "right," and in the simulated junior ophthalmologist scenario, the model achieved a higher "right" rate of 90%. CONCLUSION: To our knowledge, this is the first proof-of-concept study that evaluates GPT-4's capacity to identify rare eye diseases in simulated scenarios involving patients, family physicians, and junior ophthalmologists. The results indicate that GPT-4 has the potential to serve as a consultation assisting tool for patients and family physicians to receive referral suggestions and an assisting tool for junior ophthalmologists to diagnose rare eye diseases. However, it is important to approach GPT-4 with caution and acknowledge the need for verification and careful referrals in clinical settings.

High Myopia Normative Database of Peripapillary Retinal Nerve Fiber Layer Thickness to Detect Myopic Glaucoma in a Chinese Population.

PURPOSE: To develop and validate the performance of a high myopia (HM)-specific normative database of peripapillary retinal nerve fiber layer (pRNFL) thickness in differentiating HM from highly myopic glaucoma (HMG). DESIGN: Cross-sectional multicenter study. PARTICIPANTS: A total of 1367 Chinese participants (2325 eyes) with nonpathologic HM or HMG were included from 4 centers. After quality control, 1108 eyes from 694 participants with HM were included in the normative database; 459 eyes from 408 participants (323 eyes with HM and 136 eyes with HMG) and 322 eyes from 197 participants (131 eyes with HM and 191 eyes with HMG) were included in the internal and external validation sets, respectively. Only HMG eyes with an intraocular pressure > 21 mmHg were included. METHODS: The pRNFL thickness was measured with swept-source (SS) OCT. Four strategies of pRNFL-specified values were examined, including global and quadrantic pRNFL thickness below the lowest fifth or the lowest first percentile of the normative database. MAIN OUTCOMES MEASURES: The accuracy, sensitivity, and specificity of the HM-specific normative database for detecting HMG. RESULTS: Setting the fifth percentile of the global pRNFL thickness as the threshold, using the HM-specific normative database, we achieved an accuracy of 0.93 (95% confidence interval [CI], 0.90-0.95) and 0.85 (95% CI, 0.81-0.89), and, using the first percentile as the threshold, we acheived an accuracy of 0.85 (95% CI, 0.81-0.88) and 0.70 (95% CI, 0.65-0.75) in detecting HMG in the internal and external validation sets, respectively. The fifth percentile of the global pRNFL thickness achieved high sensitivities of 0.75 (95% CI, 0.67-0.82) and 0.75 (95% CI, 0.68-0.81) and specificities of 1.00 (95% CI, 0.99-1.00) and 1.00 (95% CI, 0.97-1.00) in the internal and external validation datasets, respectively. Compared with the built-in database of the OCT device, the HM-specific normative database showed a higher sensitivity and specificity than the corresponding pRNFL thickness below the fifth or first percentile (P < 0.001 for all). CONCLUSIONS: The HM-specific normative database is more capable of detecting HMG eyes than the SS OCT built-in database, which may be an effective tool for differential diagnosis between HMG and HM. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Deep Reinforcement Learning-Based Retinal Imaging in Alzheimer's Disease: Potential and Perspectives.

Alzheimer's disease (AD) remains a global health challenge in the 21st century due to its increasing prevalence as the major cause of dementia. State-of-the-art artificial intelligence (AI)-based tests could potentially improve population-based strategies to detect and manage AD. Current retinal imaging demonstrates immense potential as a non-invasive screening measure for AD, by studying qualitative and quantitative changes in the neuronal and vascular structures of the retina that are often associated with degenerative changes in the brain. On the other hand, the tremendous success of AI, especially deep learning, in recent years has encouraged its incorporation with retinal imaging for predicting systemic diseases. Further development in deep reinforcement learning (DRL), defined as a subfield of machine learning that combines deep learning and reinforcement learning, also prompts the question of how it can work hand in hand with retinal imaging as a viable tool for automated prediction of AD. This review aims to discuss potential applications of DRL in using retinal imaging to study AD, and their synergistic application to unlock other possibilities, such as AD detection and prediction of AD progression. Challenges and future directions, such as the use of inverse DRL in defining reward function, lack of standardization in retinal imaging, and data availability, will also be addressed to bridge gaps for its transition into clinical use.

Deep learning in optical coherence tomography: Where are the gaps?

Optical coherence tomography (OCT) is a non-invasive optical imaging modality, which provides rapid, high-resolution and cross-sectional morphology of macular area and optic nerve head for diagnosis and managing of different eye diseases. However, interpreting OCT images requires experts in both OCT images and eye diseases since many factors such as artefacts and concomitant diseases can affect the accuracy of quantitative measurements made by post-processing algorithms. Currently, there is a growing interest in applying deep learning (DL) methods to analyse OCT images automatically. This review summarises the trends in DL-based OCT image analysis in ophthalmology, discusses the current gaps, and provides potential research directions. DL in OCT analysis shows promising performance in several tasks: (1) layers and features segmentation and quantification; (2) disease classification; (3) disease progression and prognosis; and (4) referral triage level prediction. Different studies and trends in the development of DL-based OCT image analysis are described and the following challenges are identified and described: (1) public OCT data are scarce and scattered; (2) models show performance discrepancies in real-world settings; (3) models lack of transparency; (4) there is a lack of societal acceptance and regulatory standards; and (5) OCT is still not widely available in underprivileged areas. More work is needed to tackle the challenges and gaps, before DL is further applied in OCT image analysis for clinical use.

Applications of Artificial Intelligence and Deep Learning in Glaucoma.

Diagnosis and detection of progression of glaucoma remains challenging. Artificial intelligence-based tools have the potential to improve and standardize the assessment of glaucoma but development of these algorithms is difficult given the multimodal and variable nature of the diagnosis. Currently, most algorithms are focused on a single imaging modality, specifically screening and diagnosis based on fundus photos or optical coherence tomography images. Use of anterior segment optical coherence tomography and goniophotographs is limited. The majority of algorithms designed for disease progression prediction are based on visual fields. No studies in our literature search assessed the use of artificial intelligence for treatment response prediction and no studies conducted prospective testing of their algorithms. Additional challenges to the development of artificial intelligence-based tools include scarcity of data and a lack of consensus in diagnostic criteria. Although research in the use of artificial intelligence for glaucoma is promising, additional work is needed to develop clinically usable tools.

Deep Learning in Optical Coherence Tomography Angiography: Current Progress, Challenges, and Future Directions.

Optical coherence tomography angiography (OCT-A) provides depth-resolved visualization of the retinal microvasculature without intravenous dye injection. It facilitates investigations of various retinal vascular diseases and glaucoma by assessment of qualitative and quantitative microvascular changes in the different retinal layers and radial peripapillary layer non-invasively, individually, and efficiently. Deep learning (DL), a subset of artificial intelligence (AI) based on deep neural networks, has been applied in OCT-A image analysis in recent years and achieved good performance for different tasks, such as image quality control, segmentation, and classification. DL technologies have further facilitated the potential implementation of OCT-A in eye clinics in an automated and efficient manner and enhanced its clinical values for detecting and evaluating various vascular retinopathies. Nevertheless, the deployment of this combination in real-world clinics is still in the "proof-of-concept" stage due to several limitations, such as small training sample size, lack of standardized data preprocessing, insufficient testing in external datasets, and absence of standardized results interpretation. In this review, we introduce the existing applications of DL in OCT-A, summarize the potential challenges of the clinical deployment, and discuss future research directions.

Clinically relevant factors associated with a binary outcome of diabetic macular ischaemia: an OCTA study.

AIMS: We investigated the demographic, ocular, diabetes-related and systemic factors associated with a binary outcome of diabetic macular ischaemia (DMI) as assessed by optical coherence tomography angiography (OCTA) evaluation of non-perfusion at the level of the superficial capillary plexus (SCP) and deep capillary plexus (DCP) in a cohort of patients with diabetes mellitus (DM). MATERIALS AND METHODS: 617 patients with DM were recruited from July 2015 to December 2020 at the Chinese University of Hong Kong Eye Centre. Image quality assessment (gradable or ungradable for assessing DMI) and DMI evaluation (presence or absence of DMI) were assessed at the level of the SCP and DCP by OCTA. RESULTS: 1107 eyes from 593 subjects were included in the final analysis. 560 (50.59%) eyes had DMI at the level of SCP, and 647 (58.45%) eyes had DMI at the level of DCP. Among eyes without diabetic retinopathy (DR), DMI was observed in 19.40% and 24.13% of eyes at SCP and DCP, respectively. In the multivariable logistic regression models, older age, poorer visual acuity, thinner ganglion cell-inner plexiform layer thickness, worsened DR severity, higher haemoglobin A1c level, lower estimated glomerular filtration rate and higher low-density lipoprotein cholesterol level were associated with SCP-DMI. In addition to the aforementioned factors, presence of diabetic macular oedema and shorter axial length were associated with DCP-DMI. CONCLUSION: We reported a series of associated factors of SCP-DMI and DCP-DMI. The binary outcome of DMI might promote a simplified OCTA-based DMI evaluation before subsequent quantitative analysis for assessing DMI extent and fulfil the urge for an updating diabetic retinal disease staging to be implemented with OCTA.

Frailty as tested by the Liver Frailty Index in out-patient patients with cirrhosis in China: a cross-sectional study.

BACKGROUND: Early identification and prevention of frailty are very important for patients with cirrhosis. METHODS: The study was the first to use Liver Frailty Index in out-patient patients with cirrhosis in China, and to analyze the influencing factors. RESULT: This study included 387 patients with cirrhosis. Frailty was diagnosed using the Liver Frailty Index. Multiple Logistic regression model were used to analyze influencing factors of frailty in out-patient patients with cirrhosis. Frailty was diagnosed in 9.6% of patients and prefrailty was diagnosed in 54.8% of patients. Age, sex, BMI, education level, monthly economic income, number of unplanned hospital admissions in the past year, cause of cirrhosis, Child-Pugh classification of cirrhosis, nutritional risk, physical activity, gait speed and Activity of Daily Living (ADL) Scale in the frailty, prefrailty and no frailty of groups were statistically significant. Age (OR, 1.103; CI, 0.064-0.132), BMI (OR, 0.817; CI, -0.302 to -0.104), education level (OR, 4.321; CI, 0.754-2.173), physical activity (OR, 3.580; CI, 0.534-2.016) and gait speed (OR, 0.001; CI, -8.188 to -4.972) were influential factors of frailty in out-patient patients with cirrhosis. CONCLUSION: Out-patient patients with cirrhosis have a high incidence of frailty and prefrailty. Elderly, reduced gait speed, no physical activity and low culture level are risk factors for frailty and prefrailty, and we should be identification and intervention early.

Genomic epitopes of Xinjiang hemorrhagic fever virus and the evaluation of its laboratory testing value / 中华检验医学杂志

Objective:To grasp the distribution of fine antigenic epitope profiles of nucleoprotein (NP) and glycoprotein (GP) fragments of Crimean-Congo hemorrhagic fever virus (CCHFV) and to clarify the value of dominant antigenic epitopes in laboratory testing of Crimean-Congo hemorrhagic fever (CCHF).Methods:In a minimal synthetic short peptide consisting of 8 amino acids was segmentally expressed by CCHFV YL04057 strain using a modified bio-peptide synthesis method from 2014 to 2021 in the laboratory of Xinjiang University, College of Life Sciences. Using CCHFV polyclonal antibody or monoclonal antibody 14B7 (IgM) or CCHFV-positive sheep serum as antibodies, the minimal antigenic epitopes (BCEs) with antigenic activity on NP and GP fragments were identified by immunoblotting, and the obtained BCEs with sequence polymorphism were spatially clustered with CCHFV from different regions using the neighbor-joining method to determine the combination mode of BCEs with geographical correlation of regional distribution, to explore its application in establishing serological diagnosis. A prokaryotic expression plasmid (pET-32a), an E. coli expression plasmid (pGEX-KG) and a prokaryotic expression plasmid with an incomplete glutathione (GST188) tag (pXXGST-ST-1) were used to construct and express six dominant antigenic epitopes of different peptide lengths on NP fragments, and an indirect Enzyme-linked immunosorbent assay (ELISA) was established. CCHF sheep serum identified by immunofluorescence assay (IFA) was used as a control, and the specificity, sensitivity and overall compliance of the recombinant proteins with different peptide lengths of antigenic epitopes with IFA assay results were statistically analyzed. Results:CCHFV, NP and GP fragments had a total of 30 antigenically active BCEs, among which the core intermediate fragment NP2 (aa 170 th-305 th), which had a concentration of antigenic epitopes in the NP fragment, has 6 BCEs, and the NP1 (aa 1 st-200 th) and NP3 (aa 286 th-482 nd) at both ends have 9 BCEs; the Gc (aa 1 st-558 th) and Gn (aa 533 th-708 th) fragments of the GP fragment have 14 BCEs and a long antigenic peptide (AP) containing 15 amino acids, and the amino acid sequence homology of the NP fragment BCEs was 97.1% and that of the GP fragment BCEs was 89.1%. There was a significant difference ( P=0.0281, P<0.05). Among the 9 BCEs with sequence polymorphism in the GP fragment, 6 combined BCEs from GnEc1, GnE2, GnE4, GcE3, GcE6 and GcAP-4 (Ap) could cluster 15 CCHFV strains from different regions of the world into 5 geographical taxa, AsiaⅠ, AsiaⅡ, AficaⅠ, AficaⅡ and Europe. The constructs expressing PET-32a-NP (full length), PGEX-KG-NP2 (aa 170 th-305 th), pGEX-KG-NP2-1 (aa 235 th-275 th), PGEX-KG-NP2-1-1 (aa 237 th-256 th), pXXGST-1-NP2-1-2 (aa 250 th-265 th) and PGEX KG-NP2-1-3 (aa 260 th-276 th), six recombinant proteins CCHFV NP rabbit polyclonal antiserum (pAb) Western Blotting reaction positive, 33 sheep sera tested by IFA XHF as a reference, the sensitivity of the assay established by indirect ELISA using the recombinant proteins constructed from two fragments of NP2 and NP2-1 as antigens. The sensitivity, specificity and overall compliance were the best, with 73.4% (11/15) and 66.7% (10/15) for sensitivity, 100% (18/18) and 94.4% (17/18) for specificity, and 87.9% (29/33) and 81.8% (27/33) for overall compliance. Conclusion:CCHFV NP and GP are distributed with a high number of BCEs with antigenic immunoreactivity, among which the dominant antigenic epitopes are of high value in the laboratory serological diagnosis of CCHF.

Clinical observation of venetoclax-based treatment regimens for acute myeloid leukemia / 白血病·淋巴瘤

Objective:To investigate clinical efficacy and safety of venetoclax (VEN)-based regimens in the treatment of acute myeloid leukemia (AML).Methods:The clinical data of 41 AML patients treated with venetoclax-based regimens from January 2021 to December 2021 in Ruijin Hospital North of Shanghai Jiao Tong University School of Medicine were retrospectively analyzed. The treatment regimens included VEN+demethylating drugs ± gene mutation inhibitors or VEN+chemotherapy with a median number of 2 courses (1- 5 courses).Results:The median age of all patients was 60 years (18-73 years), and there were 24 males and 17 females. After 1 course of VEN-based therapy, 22 (53.7%) patients achieved complete remission (CR) or morphological complete remission without complete blood count recovery (CRi), including 5 patients achieving minimal residual disease (MRD) negative. After 2 courses of treatment, of 17 patients available for efficacy evaluation, 7 patients achieved MRD negative. Among 20 relapsed/refractory AML patients, 9 cases achieved CR/CRi after 1 course of treatment, of which 1 patient had MRD negative. Among 21 patients initially treated and re-treated, 13 cases achieved CR/CRi and 1 case achieved partial remission after 1 course of treatment, of which 4 cases had MRD negative.Conclusions:VEN-based treatment regimens for AML have a high remission rate and tolerable adverse effects.

Subcutaneous Streptococcus dysgalactiae GAPDH vaccine in mice induces a proficient innate immune response

Background@#Glyceraldehyde-3-phosphate dehydrogenase (GAPDH) on the surface of Streptococcus dysgalactiae, coded with gapC, is a glycolytic enzyme that was reported to be a moonlighting protein and virulence factor. @*Objective@#This study assessed GAPDH as a potential immunization candidate protein to prevent streptococcus infections. @*Methods@#Mice were vaccinated subcutaneously with recombinant GAPDH and challenged with S. dysgalactiae in vivo. They were then evaluated using histological methods. rGAPDH of mouse bone marrow-derived dendritic cells (BMDCs) was evaluated using immunoblotting, reverse transcription quantitative polymerase chain reaction, and enzyme-linked immunosorbent assay methods. @*Results@#Vaccination with rGAPDH improved the survival rates and decreased the bacterial burdens in the mammary glands compared to the control group. The mechanism by which rGAPDH vaccination protects against S. dysgalactiae was investigated. In vitro experiments showed that rGAPDH boosted the generation of interleukin-10 and tumor necrosis factor-α. Treatment of BMDCs with TAK-242, a toll-like receptor 4 inhibitor, or C29, a toll-like receptor 2 inhibitor, reduced cytokines substantially, suggesting that rGAPDH may be a potential ligand for both TLR2 and TLR4. Subsequent investigations showed that rGAPDH may activate the phosphorylation of MAPKs and nuclear factor-κB. @*Conclusions@#GAPDH is a promising immunization candidate protein for targeting virulence and enhancing immune-mediated protection. Further investigations are warranted to understand the mechanisms underlying the activation of BMDCs by rGAPDH in a TLR2- and TLR4-dependent manner and the regulation of inflammatory cytokines contributing to mastitis pathogenesis.

Clinicopathological analysis of benign mammary ductal cystic papillomatosis with loss of myoepithelial cells / 中华病理学杂志

Objective: To investigate the histopathological and immunohistochemical characteristics of benign apocrine cystic papillary hyperplasia of the breast with loss of myoepithelial cell layer. Methods: The clinical data, histopathological features and immunohistochemical profile of patients with benign apocrine cystic papillary hyperplasia of breast with loss of myoepithelial cell layer from January 2016 to December 2021 were examined, in which six patients were identified. Results: All six patients were female, aged 36-61 years (median 46 years), who presented with a breast mass; three cases were from the left breast and three cases were from the right breast. Microscopic examination of all cases showed breast hyperplasia with apocrine cysts, accompanied by different degrees of micropapillary and papillary hyperplasia of apocrine cells. One case was associated with lobular carcinoma in situ, and one case was associated with apocrine ductal carcinoma in situ with intraductal dissemination in adenosis. Immunohistochemical staining of CK5/6, p63, SMA, SMMHC, Calponin and CD10 showed complete absence of myoepithelial cell layer surrounding ducts in apocrine cystic papillary hyperplasia. Conclusions: The myoepithelial cells of apocrine cystic papillary hyperplasia of the breast may undergo abnormal changes and may even be completely lost. The diagnosis should be comprehensively considered along with cytomorphological and histological features to avoid overdiagnosis.

Federated Learning in Ocular Imaging: Current Progress and Future Direction.

Advances in artificial intelligence deep learning (DL) have made tremendous impacts on the field of ocular imaging over the last few years. Specifically, DL has been utilised to detect and classify various ocular diseases on retinal photographs, optical coherence tomography (OCT) images, and OCT-angiography images. In order to achieve good robustness and generalisability of model performance, DL training strategies traditionally require extensive and diverse training datasets from various sites to be transferred and pooled into a "centralised location". However, such a data transferring process could raise practical concerns related to data security and patient privacy. Federated learning (FL) is a distributed collaborative learning paradigm which enables the coordination of multiple collaborators without the need for sharing confidential data. This distributed training approach has great potential to ensure data privacy among different institutions and reduce the potential risk of data leakage from data pooling or centralisation. This review article aims to introduce the concept of FL, provide current evidence of FL in ocular imaging, and discuss potential challenges as well as future applications.

A deep learning model for detection of Alzheimer's disease based on retinal photographs: a retrospective, multicentre case-control study.

BACKGROUND: There is no simple model to screen for Alzheimer's disease, partly because the diagnosis of Alzheimer's disease itself is complex-typically involving expensive and sometimes invasive tests not commonly available outside highly specialised clinical settings. We aimed to develop a deep learning algorithm that could use retinal photographs alone, which is the most common method of non-invasive imaging the retina to detect Alzheimer's disease-dementia. METHODS: In this retrospective, multicentre case-control study, we trained, validated, and tested a deep learning algorithm to detect Alzheimer's disease-dementia from retinal photographs using retrospectively collected data from 11 studies that recruited patients with Alzheimer's disease-dementia and people without disease from different countries. Our main aim was to develop a bilateral model to detect Alzheimer's disease-dementia from retinal photographs alone. We designed and internally validated the bilateral deep learning model using retinal photographs from six studies. We used the EfficientNet-b2 network as the backbone of the model to extract features from the images. Integrated features from four retinal photographs (optic nerve head-centred and macula-centred fields from both eyes) for each individual were used to develop supervised deep learning models and equip the network with unsupervised domain adaptation technique, to address dataset discrepancy between the different studies. We tested the trained model using five other studies, three of which used PET as a biomarker of significant amyloid ß burden (testing the deep learning model between amyloid ß positive vs amyloid ß negative). FINDINGS: 12 949 retinal photographs from 648 patients with Alzheimer's disease and 3240 people without the disease were used to train, validate, and test the deep learning model. In the internal validation dataset, the deep learning model had 83·6% (SD 2·5) accuracy, 93·2% (SD 2·2) sensitivity, 82·0% (SD 3·1) specificity, and an area under the receiver operating characteristic curve (AUROC) of 0·93 (0·01) for detecting Alzheimer's disease-dementia. In the testing datasets, the bilateral deep learning model had accuracies ranging from 79·6% (SD 15·5) to 92·1% (11·4) and AUROCs ranging from 0·73 (SD 0·24) to 0·91 (0·10). In the datasets with data on PET, the model was able to differentiate between participants who were amyloid ß positive and those who were amyloid ß negative: accuracies ranged from 80·6 (SD 13·4%) to 89·3 (13·7%) and AUROC ranged from 0·68 (SD 0·24) to 0·86 (0·16). In subgroup analyses, the discriminative performance of the model was improved in patients with eye disease (accuracy 89·6% [SD 12·5%]) versus those without eye disease (71·7% [11·6%]) and patients with diabetes (81·9% [SD 20·3%]) versus those without the disease (72·4% [11·7%]). INTERPRETATION: A retinal photograph-based deep learning algorithm can detect Alzheimer's disease with good accuracy, showing its potential for screening Alzheimer's disease in a community setting. FUNDING: BrightFocus Foundation.

Effect of Text Messaging Parents of School-Aged Children on Outdoor Time to Control Myopia: A Randomized Clinical Trial.

Importance: Myopia in school-aged children is a public health issue worldwide; consequently, effective interventions to prevent onset and progression are required. Objective: To investigate whether SMS text messages to parents increase light exposure and time outdoors in school-aged children and provide effective myopia control. Design, Setting, and Participants: This randomized clinical trial was conducted in China from May 2017 to May 2018, with participants observed for 3 years. Of 528 965 primary school-aged children from Anyang, 3113 were randomly selected. Of these, 268 grade 2 schoolchildren were selected and randomly assigned to SMS and control groups. Data were analyzed from June to December 2021. Interventions: Parents of children in the SMS group were sent text messages twice daily for 1 year to take their children outdoors. All children wore portable light meters to record light exposure on 3 randomly selected days (2 weekdays and 1 weekend day) before and after the intervention. Main Outcomes and Measures: The co-primary outcomes were change in axial length (axial elongation) and change in spherical equivalent refraction (myopic shift) from baseline as measured at the end of the intervention and 3 years later. A secondary outcome was myopia prevalence. Results: Of 268 grade 2 schoolchildren, 121 (45.1%) were girls, and the mean (SD) age was 8.4 (0.3) years. Compared with the control group, the SMS intervention group demonstrated greater light exposure and higher time outdoors during weekends, and the intervention had significant effect on axial elongation (coefficient, 0.09; 95% CI, 0.02-0.17; P = .01). Axial elongation was lower in the SMS group than in the control group during the intervention (0.27 mm [95% CI, 0.24-0.30] vs 0.31 mm [95% CI, 0.29-0.34]; P = .03) and at year 2 (0.39 mm [95% CI, 0.35-0.42] vs 0.46 mm [95% CI, 0.42-0.50]; P = .009) and year 3 (0.30 mm [95% CI, 0.27-0.33] vs 0.35 mm [95% CI, 0.33-0.37]; P = .005) after the intervention. Myopic shift was lower in the SMS group than in the control group at year 2 (-0.69 diopters [D] [95% CI, -0.78 to -0.60] vs -0.82 D [95% CI, -0.91 to -0.73]; P = .04) and year 3 (-0.47 D [95% CI, -0.54 to -0.39] vs -0.60 D [95% CI, -0.67 to -0.53]; P = .01) after the intervention, as was myopia prevalence (year 2: 38.3% [51 of 133] vs 51.1% [68 of 133]; year 3: 46.6% [62 of 133] vs 65.4% [87 of 133]). Conclusions and Relevance: In this randomized clinical trial, SMS text messages to parents resulted in lower axial elongation and myopia progression in schoolchildren over 3 years, possibly through increased outdoor time and light exposure, showing promise for reducing myopia prevalence. Trial Registration: Chinese Clinical Trial Registry Identifier: ChiCTR-IOC-17010525.

Imprinted SARS-CoV-2 humoral immunity induces converging Omicron RBD evolution

Continuous evolution of Omicron has led to a rapid and simultaneous emergence of numerous variants that display growth advantages over BA. 5. Despite their divergent evolutionary courses, mutations on their receptor-binding domain (RBD) converge on several hotspots. The driving force and destination of such convergent evolution and its impact on humoral immunity remain unclear. Here, we demonstrate that these convergent mutations can cause striking evasion of neutralizing antibody (NAb) drugs and convalescent plasma, including those from BA.5 breakthrough infection, while maintaining sufficient ACE2 binding capability. BQ.1.1.10, BA.4.6.3, XBB, and CH. 1.1 are the most antibody-evasive strain tested, even exceeding SARS-CoV-1 level. To delineate the origin of the convergent evolution, we determined the escape mutation profiles and neutralization activity of monoclonal antibodies (mAbs) isolated from BA.2 and BA.5 breakthrough-infection convalescents. Importantly, due to humoral immune imprinting, BA.2 and especially BA.5 breakthrough infection caused significant reductions in the epitope diversity of NAbs and increased proportion of non-neutralizing mAbs, which in turn concentrated humoral immune pressure and promoted convergent evolution. Moreover, we showed that the convergent RBD mutations could be accurately inferred by integrated deep mutational scanning (DMS) profiles, and the evolution trends of BA.2.75/BA.5 subvariants could be well-simulated through constructed convergent pseudovirus mutants. Together, our results suggest current herd immunity and BA.5 vaccine boosters may not provide good protection against infection. Broad-spectrum SARS-CoV-2 vaccines and NAb drugs development should be highly prioritized, and the constructed mutants could help to examine their effectiveness in advance.