An Shao's research while affiliated with Zhejiang University and other places

As an indispensable part of the human sensory system, visual acuity may be impaired and even develop into irreversible blindness due to various ocular pathologies. Among ocular diseases, fundus neovascularization diseases (FNDs) are prominent etiologies of visual impairment worldwide. Intravitreal injection of anti‐vascular endothelial growth factor drugs remains the primary therapy but is hurdled by common complications and incomplete potency. To renovate the current therapeutic modalities, nanomedicine emerged as the times required, which has been endowed with advanced capabilities, able to fulfill the effective ocular fundus drug delivery and achieve precise drug release control, thus further improving the therapeutic effect. This review provides a comprehensive summary of advances in nanomedicine for FND management from state‐of‐the‐art studies. Firstly, we thoroughly introduce the current therapeutic modalities for FNDs, focusing on the key challenges of ocular fundus drug delivery. Secondly, we comprehensively reviewed nanocarriers for ocular posterior drug delivery based on the nanostructures: polymer‐based nanocarriers, lipid‐based nanocarriers, and inorganic nanoparticles. Thirdly, we elaborate on the characteristics of the fundus microenvironment, their pathological changes during FNDs, and corresponding strategies for constructing smart nanocarriers. Furthermore, the challenges and prospects of nanomedicine for FND management are thoroughly discussed. This article is protected by copyright. All rights reserved

Retinal organoid (RO) is the three-dimensional (3D) retinal culture derived from pluripotent or embryonic stem cells which recapitulates organ functions, which was a revolutionary milestone in stem cell technology. The purpose of this study is to explore the hotspots and future directions on ROs, as well as to better understand the fields of greatest research opportunities. Eligible publications related to RO from 2011 to 2022 were acquired from the Web of Science (WoS) Core Collection database. Bibliometric analysis was performed by using software including VOSviewer, CiteSpace, and ArcGIS. A total of 520 articles were included, and the number of annual publications showed a rapid increase with an average rate of 40.86%. The United States published the most articles (241/520, 46.35%) with highest total citation frequencies (5,344). University College London (UK) contributed the largest publication output (40/520, 7.69%) and received highest total citation frequencies. Investigative Ophthalmology & Visual Science was the most productive journal with 129 articles. Majlinda Lako contributed the most research with 32 articles, while Olivier Goureau has the strongest collaboration work. Research could be subdivided into four keyword clusters: “culture and differentiation,” “morphogenesis and modeling,” “gene therapy,” and “transplantation and visual restoration,” and evolution of keywords was identified. Last decade has witnessed the huge progress in the field of RO, which is a young and promising research area with extensive and in-depth studies. More attention should be paid to RO-related models and therapies based on specific retinal diseases, especially inherited retinopathies.

Background Benefiting from rich knowledge and the exceptional ability to understand text, large language models like ChatGPT have shown great potential in English clinical environments. However, the performance of ChatGPT in non-English clinical settings, as well as its reasoning, have not been explored in depth. Objective This study aimed to evaluate ChatGPT’s diagnostic performance and inference abilities for retinal vascular diseases in a non-English clinical environment. Methods In this cross-sectional study, we collected 1226 fundus fluorescein angiography reports and corresponding diagnoses written in Chinese and tested ChatGPT with 4 prompting strategies (direct diagnosis or diagnosis with a step-by-step reasoning process and in Chinese or English). Results Compared with ChatGPT using Chinese prompts for direct diagnosis that achieved an F1-score of 70.47%, ChatGPT using English prompts for direct diagnosis achieved the best diagnostic performance (80.05%), which was inferior to ophthalmologists (89.35%) but close to ophthalmologist interns (82.69%). As for its inference abilities, although ChatGPT can derive a reasoning process with a low error rate (0.4 per report) for both Chinese and English prompts, ophthalmologists identified that the latter brought more reasoning steps with less incompleteness (44.31%), misinformation (1.96%), and hallucinations (0.59%) (all P<.001). Also, analysis of the robustness of ChatGPT with different language prompts indicated significant differences in the recall (P=.03) and F1-score (P=.04) between Chinese and English prompts. In short, when prompted in English, ChatGPT exhibited enhanced diagnostic and inference capabilities for retinal vascular disease classification based on Chinese fundus fluorescein angiography reports. Conclusions ChatGPT can serve as a helpful medical assistant to provide diagnosis in non-English clinical environments, but there are still performance gaps, language disparities, and errors compared to professionals, which demonstrate the potential limitations and the need to continually explore more robust large language models in ophthalmology practice.

BACKGROUND Benefiting from the exceptional ability of text understanding and rich knowledge, large language models (LLMs) like ChatGPT, have shown great potential in English clinical environments. However, the performance of ChatGPT in non-English clinical settings, as well as its reasoning, have not been explored in-depth. OBJECTIVE To evaluate ChatGPT’s diagnostic performance and inference abilities for retinal vascular diseases in a non-English clinical environment. METHODS In this cross-sectional study, we collected 1226 fundus fluorescein angiography reports and corresponding diagnosis written in Chinese, and tested ChatGPT with four prompting strategies (direct diagnosis or diagnosis with explanation and in Chinese or English). RESULTS ChatGPT using English prompt for direct diagnosis achieved the best performance, with F1-score of 80.05%, which was inferior to ophthalmologists (89.35%) but close to ophthalmologist interns (82.69%). Although ChatGPT can derive reasoning process with a low error rate, mistakes such as misinformation (1.96%), and hallucination (0.59%) still exist. CONCLUSIONS ChatGPT can serve as a helpful medical assistant to provide diagnosis under non-English clinical environments, but there are still performance gaps, language disparity, and errors compared to professionals, which demonstrates the potential limitations and the desiration to continually explore more robust LLMs in ophthalmology practice. CLINICALTRIAL ClinicalTrials.gov NCT04718532

Objective: To evaluate the effectiveness and reasoning ability of ChatGPT in diagnosing retinal vascular diseases in the Chinese clinical environment. Materials and Methods: We collected 1226 fundus fluorescein angiography reports and corresponding diagnosis written in Chinese, and tested ChatGPT with four prompting strategies (direct diagnosis or diagnosis with explanation and in Chinese or English). Results: ChatGPT using English prompt for direct diagnosis achieved the best performance, with F1-score of 80.05%, which was inferior to ophthalmologists (89.35%) but close to ophthalmologist interns (82.69%). Although ChatGPT can derive reasoning process with a low error rate, mistakes such as misinformation (1.96%), and hallucination (0.59%) still exist. Discussion and Conclusions: ChatGPT can serve as a helpful medical assistant to provide diagnosis under non-English clinical environments, but there are still performance gaps, language disparity, and errors compared to professionals, which demonstrates the potential limitations and the desiration to continually explore more robust LLMs in ophthalmology practice.

Basal cell carcinoma (BCC) and squamous cell carcinoma (SCC) are the two most common skin cancer and impose a huge medical burden on society. Histopathological examination based on whole-slide images (WSIs) remains to be the confirmatory diagnostic method for skin tumors. Accurate segmentation of tumor tissue in WSIs by deep-learning (DL) models can reduce the workload of pathologists and help surgeons ensure the complete removal of tumors. To accurately segment the tumor areas in WSIs of BCC, SCC and squamous cell papilloma (SCP, homologous to SCC) with robust models. We established a data set (ZJU-NMSC) containing 151 WSIs of BCC, SCC and SCP in total. Seven models were utilized to segment WSIs, including the state-of-the-art model, models proposed by us and other models. Dice score, intersection over union, accuracy, sensitivity and specificity were used to evaluate and compare the performance of different models. Heatmaps and tumor tissue masks were generated to reflect the results of the segmentation. The processing times of models are also recorded and compared. While the dice score of most models is higher than 0.85, deeplab v3+ has the best performance and the corresponding tumor tissue mask is more consistent with the ground truth tumor areas even with complex and small lobular lesions. This study broadens the use of DL-based segmentation models in WSIs of skin tumors in terms of tumor types and computational approaches. Segmenting tumor areas can simplify the process of histopathological inspection and benefit the diagnosis and following management of the diseases in practice.

Objective: To investigate the histopathological classification of orbital space-occupying lesions. Methods: This is a retrospective case series study. The clinical and pathological data of 1 913 tissue specimens from 1 913 patients with space-occupying lesions of the orbit which were examined in the Second Affiliated Hospital, Zhejiang University School of Medicine from January 2000 to December 2021 were collected. The mass lesions were classified based on histogenesis, pathological nature and age. Results: There were 913 males (47.7%) and 1 000 females (52.3%). The lesions were benign in 1 489 patients (77.8%) and malignant in 424 patients (22.2%). Based on histogenesis, there were 521 vasculogenic lesions (27.2%), which rancked first, 407 cystoid lesions (21.3%), 277 lymphoproliferative lesions (14.5%), 182 lacrimal gland lesions (9.5%) and 121 inflammatory lesions (6.3%). By pathological nature, there were 1 489 benign lesions, including cavernous hemangioma (275, 14.4%), dermoid cyst (225, 11.8%), other hemangiomas (199, 10.4%), epidermoid cyst (136, 7.1%) and benign mixed tumor of the lacrimal gland (134, 7.0%), and 257 malignant lesions, including lymphoma (210, 11.0%) and sebaceous gland carcinoma (47, 2.5%). The age of all patients ranged from 0 to 90 years, while 247 lesions (12.9%) occurred in patients aged 0 to18 years, 1 270 lesions (66.4%) in patients aged 19 to 59 years, and 396 lesions (20.7%) in patients aged 60 to 90 years. Conclusions: In 22 years, almost 2/3 benign orbital lesions in the Second Affiliated Hospital, Zhejiang University School of Medicine occurred in young and middle-aged patients, and males were fewer than females. The most common benign orbital tumors was cavernous hemangioma, followed by dermoid cyst and epidermoid cyst. And the most common malignant orbital tumor was lymphoma, which occurred more frequently in older patients.

Purpose To comprehensively analyze and discuss the publications on machine learning (ML) in diabetic retinopathy (DR) following a bibliometric approach. Methods The global publications on ML in DR from 2011 to 2021 were retrieved from the Web of Science Core Collection (WoSCC) database. We analyzed the publication and citation trend over time and identified highly-cited articles, prolific countries, institutions, journals and the most relevant research domains. VOSviewer and Wordcloud are used to visualize the mainstream research topics and evolution of subtopics in the form of co-occurrence maps of keywords. Results By analyzing a total of 1147 relevant publications, this study found a rapid increase in the number of annual publications, with an average growth rate of 42.68%. India and China were the most productive countries. IEEE Access was the most productive journal in this field. In addition, some notable common points were found in the highly-cited articles. The keywords analysis showed that “diabetic retinopathy”, “classification”, and “fundus images” were the most frequent keywords for the entire period, as automatic diagnosis of DR was always the mainstream topic in the relevant field. The evolution of keywords highlighted some breakthroughs, including “deep learning” and “optical coherence tomography”, indicating the advance in technologies and changes in the research attention. Conclusions As new research topics have emerged and evolved, studies are becoming increasingly diverse and extensive. Multiple modalities of medical data, new ML techniques and constantly optimized algorithms are the future trends in this multidisciplinary field.

PurposeThe lack of finely annotated pathologic data has limited the application of deep learning systems (DLS) to the automated interpretation of pathologic slides. Therefore, this study develops a robust self-supervised learning (SSL) pathology diagnostic system to automatically detect malignant melanoma (MM) in the eyelid with limited annotation.DesignDevelopment of a self-supervised diagnosis pipeline based on a public dataset, then refined and tested on a private, real-world clinical dataset.SubjectsA. Patchcamelyon (PCam)-a publicly accessible dataset for the classification task of patch-level histopathologic images. B. The Second Affiliated Hospital, Zhejiang University School of Medicine (ZJU-2) dataset – 524,307 patches (small sections cut from pathologic slide images) from 192 H&E-stained whole-slide-images (WSIs); only 72 WSIs were labeled by pathologists.Methods Patchcamelyon was used to select a convolutional neural network (CNN) as the backbone for our SSL-based model. This model was further developed in the ZJU-2 dataset for patch-level classification with both labeled and unlabeled images to test its diagnosis ability. Then the algorithm retrieved information based on patch-level prediction to generate WSI-level classification results using random forest. A heatmap was computed for visualizing the decision-making process.Main outcome measure(s)The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to evaluate the performance of the algorithm in identifying MM.ResultsResNet50 was selected as the backbone of the SSL-based model using the PCam dataset. This algorithm then achieved an AUC of 0.981 with an accuracy, sensitivity, and specificity of 90.9, 85.2, and 96.3% for the patch-level classification of the ZJU-2 dataset. For WSI-level diagnosis, the AUC, accuracy, sensitivity, and specificity were 0.974, 93.8%, 75.0%, and 100%, separately. For every WSI, a heatmap was generated based on the malignancy probability.Conclusion Our diagnostic system, which is based on SSL and trained with a dataset of limited annotation, can automatically identify MM in pathologic slides and highlight MM areas in WSIs by a probabilistic heatmap. In addition, this labor-saving and cost-efficient model has the potential to be refined to help diagnose other ophthalmic and non-ophthalmic malignancies.