A5101604630- Retinal Imaging and Analysis
- Retinal and Optic Conditions
- Cutaneous Melanoma Detection and Management
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- Nonmelanoma Skin Cancer Studies
- Retinal Diseases and Treatments
- Digital Media Forensic Detection
- Retinal Development and Disorders
- Acute Ischemic Stroke Management
- Tracheal and airway disorders
- Nanoplatforms for cancer theranostics
- Corneal Surgery and Treatments
- Ocular Oncology and Treatments
- Cancer and Skin Lesions
- Soft tissue tumor case studies
- Ocular Diseases and Behçet’s Syndrome
- Retinal and Macular Surgery
- Advanced Nanomaterials in Catalysis
- Neuroinflammation and Neurodegeneration Mechanisms
- Airway Management and Intubation Techniques
- Voice and Speech Disorders
- COVID-19 diagnosis using AI
- Clinical Reasoning and Diagnostic Skills
- Chaos-based Image/Signal Encryption
Second Affiliated Hospital of Zhejiang University
2022-2025
Jiangsu University
2025
Affiliated Hospital of Jiangsu University
2025
University of California, San Francisco
2022
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, performance of non-English settings, as well its reasoning, not been explored depth.
Abstract Age‐related macular degeneration (AMD), characterized by choroidal neovascularization (CNV), is the global leading cause of irreversible blindness. Current first‐line therapeutics, vascular endothelial growth factor (VEGF) antagonists, often yield incomplete and suboptimal vision improvement, necessitating exploration novel efficacious therapeutic approaches. Herein, a supramolecular engineering strategy to construct moringin (MOR) loaded α‐cyclodextrin (α‐CD) coated nanoceria...
Sublobar surgeries involving the left anterior segment of lung can be challenging due to its central location within upper lobe (LUL) and among multi-segments. However, there have been no reports specifically analysing anatomical patterns this segment. Therefore, study aimed comprehensively investigate subsegmental bronchovascular relationship between variations surgical strategies. The branching bronchi pulmonary vessels were assessed retrospectively categorised using three-dimensional...
Purpose To comprehensively analyze and discuss the publications on machine learning (ML) in diabetic retinopathy (DR) following a bibliometric approach. Methods The global ML DR from 2011 to 2021 were retrieved Web of Science Core Collection (WoSCC) database. We analyzed publication citation trend over time identified highly-cited articles, prolific countries, institutions, journals most relevant research domains. VOSviewer Wordcloud are used visualize mainstream topics evolution subtopics...
Abstract Objective To evaluate the effectiveness and reasoning ability of ChatGPT in diagnosing retinal vascular diseases Chinese clinical environment. Materials Methods We collected 1226 fundus fluorescein angiography reports corresponding diagnosis written Chinese, tested with four prompting strategies (direct or explanation English). Results using English prompt for direct achieved best performance, F1-score 80.05%, which was inferior to ophthalmologists (89.35%) but close ophthalmologist...
The lack of finely annotated pathologic data has limited the application deep learning systems (DLS) to automated interpretation slides. Therefore, this study develops a robust self-supervised (SSL) pathology diagnostic system automatically detect malignant melanoma (MM) in eyelid with annotation. Development diagnosis pipeline based on public dataset, then refined and tested private, real-world clinical dataset. A. Patchcamelyon (PCam)-a publicly accessible dataset for classification task...
Basal cell carcinoma (BCC) and squamous (SCC) are the two most common skin cancer impose a huge medical burden on society. Histopathological examination based whole-slide images (WSIs) remains to be confirmatory diagnostic method for tumors. Accurate segmentation of tumor tissue in WSIs by deep-learning (DL) models can reduce workload pathologists help surgeons ensure complete removal To accurately segment areas BCC, SCC papilloma (SCP, homologous SCC) with robust models. We established data...
Objective: To investigate the histopathological classification of orbital space-occupying lesions. Methods: This is a retrospective case series study. The clinical and pathological data 1 913 tissue specimens from patients with lesions orbit which were examined in Second Affiliated Hospital, Zhejiang University School Medicine January 2000 to December 2021 collected. mass classified based on histogenesis, nature age. Results: There males (47.7%) 000 females (52.3%). benign 489 (77.8%)...
Retinal organoid (RO) is the three-dimensional (3D) retinal culture derived from pluripotent or embryonic stem cells which recapitulates organ functions, was a revolutionary milestone in cell technology. The purpose of this study to explore hotspots and future directions on ROs, as well better understand fields greatest research opportunities. Eligible publications related RO 2011 2022 were acquired Web Science (WoS) Core Collection database. Bibliometric analysis performed by using software...
Abstract The intricate anatomy of the eyelid, and subspecialization trend in pathology made it more difficult for general surgical pathologists to maintain high accuracy across entire range diverse eyelid lesions. A lack access subspecialty expertise, misalignment diagnosis eye can slow diagnostic speed, resulting intraorbital intracranial extension and/or systemic spread which could threaten vision life. Here, we developed a robust deep learning system (DLS) detect tumors using digital...
<sec> <title>BACKGROUND</title> 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, performance of non-English settings, as well its reasoning, not been explored depth. </sec> <title>OBJECTIVE</title> This study aimed evaluate ChatGPT’s diagnostic inference abilities for retinal vascular diseases a environment. <title>METHODS</title> In this cross-sectional...