A5016183535- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Retinal and Optic Conditions
- Glaucoma and retinal disorders
- Nanoparticle-Based Drug Delivery
- Hepatocellular Carcinoma Treatment and Prognosis
- Artificial Intelligence in Healthcare and Education
- Nanoplatforms for cancer theranostics
- Ocular Surface and Contact Lens
- Liver Disease Diagnosis and Treatment
- Digital Imaging for Blood Diseases
- AI in cancer detection
- Cancer, Hypoxia, and Metabolism
- Optical Coherence Tomography Applications
- Corneal Surgery and Treatments
- Advanced Optical Sensing Technologies
- Retinal Development and Disorders
- Ocular Disorders and Treatments
- MRI in cancer diagnosis
- Computational Physics and Python Applications
- Medical Image Segmentation Techniques
- Retinal and Macular Surgery
- Ophthalmology and Visual Health Research
- Advanced Vision and Imaging
- Advanced Fiber Laser Technologies
Second Affiliated Hospital of Zhejiang University
2016-2025
Zhejiang University
2015-2025
Sinopec (China)
2025
Eye Center
2024-2025
Shanghai Clinical Research Center
2025
Fudan University
2013-2024
Zhongshan Hospital
2016-2024
Tongji University
2024
Huadong Hospital
2022-2024
Guilin University of Technology
2024
Many common eye diseases and cardiovascular can be diagnosed through retinal imaging. However, due to uneven illumination, image blurring, low contrast, images with poor quality are not useful for diagnosis, especially in automated analyzing systems. Here, we propose a new enhancement method improve color luminosity contrast.A luminance gain matrix, which is obtained by gamma correction of the value channel HSV (hue, saturation, value) space, used enhance R, G, B (red, green blue) channels,...
Abstract Purpose This study aimed to determine the efficacy of a multimodal deep learning (DL) model using optical coherence tomography (OCT) and angiography (OCTA) images for assessment choroidal neovascularization (CNV) in neovascular age‐related macular degeneration (AMD). Methods retrospective cross‐sectional was performed at multicentre, inclusion criteria were age >50 years diagnosis typical AMD. The OCT OCTA data an internal set two external sets collected. A DL developed with...
Abstract Retinal vasculature provides an opportunity for direct observation of vessel morphology, which is linked to multiple clinical conditions. However, objective and quantitative interpretation the retinal relies on precise segmentation, time consuming labor intensive. Artificial intelligence (AI) has demonstrated great promise in segmentation. The development evaluation AI-based models require large numbers annotated images. public datasets that are usable this task scarce. In paper, we...
Background/aims Fundus fluorescein angiography (FFA) is an important technique to evaluate diabetic retinopathy (DR) and other retinal diseases. The interpretation of FFA images complex time-consuming, the ability diagnosis uneven among different ophthalmologists. aim study develop a clinically usable multilevel classification deep learning model for images, including prediagnosis assessment lesion classification. Methods A total 15 599 1558 eyes from 845 patients diagnosed with DR were...
Recently, biomimetic nanoparticles, especially cell membrane-cloaked have attracted increasing attention in biomedical applications, including antitumor therapy, detoxification, and immune modulation, by imitating the structure function of biological systems such as long circulation life blood. However, time nanoparticles is far less than that original cells, greatly limiting their while underlying reasons are seldom demonstrated. In this study, influence particle size on biodistribution red...
Telemedicine and the medical "big data" era in ophthalmology highlight use of non-mydriatic ocular fundus photography, which has given rise to indispensable applications portable cameras. However, case image quality is more vulnerable distortions, such as uneven illumination, color distortion, blur, low contrast. Such distortions are called generic distortions. This paper proposes an algorithm capable selecting images fair that would be especially useful assist inexperienced individuals...
Glioblastoma is one of the most challenging and intractable tumors with difficult treatment poor prognosis. Unsatisfactory traditional systemic chemotherapies for glioblastoma are mainly attributed to insufficient nonspecific drug delivery into brain as well incomplete release at tumor sites. Inspired by facts that angiopep-2 peptide an acknowledged dual-targeting moiety tumor-targeting high-intensity focused ultrasound (HIFU) ideal trigger ultrahigh energy millimeter-sized focus ability, in...
Previous works suggested that neutralizing intratumoral lactic acidosis combined with glucose deprivation may deliver an effective approach to control tumor. We did a pilot clinical investigation, including nonrandomized (57 patients large HCC) and randomized controlled (20 study.The were treated transarterial chemoembolization (TACE) or without bicarbonate local infusion into tumor.In the study, geometric mean of viable tumor residues (VTR) in TACE was 6.4-fold lower than (7.1% [95% CI:...
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.
Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due lacking reliable and interpretable analysis methods. Thus, this study aimed develop two-stage deep learning (DL) system named iERM provide accurate automatic of clinical practice. Methods: The was trained human segmentation key features improve classification...
Image quality assessment (IQA) is significant for current techniques of image-based computer-aided diagnosis, and fundus imaging the chief modality screening diagnosing ophthalmic diseases. However, most existing IQA datasets are single-center datasets, disregarding type device, eye condition, environment. In this paper, we collected a multi-source heterogeneous (MSHF) database. The MSHF dataset consisted 1302 high-resolution normal pathologic images from color photography (CFP), healthy...
The blood-brain barrier is a formidable obstacle for glioma chemotherapy due to its compact structure and drug efflux ability. In this study, dual-targeting delivery system involving Angiopep-2-conjugated biodegradable polymersomes loaded with doxorubicin (Ang-PS-DOX) was developed exploit transport by the low-density lipoprotein receptor-related protein 1 (LRP1), which overexpressed in both cells. (PS) were prepared using thin-film hydration method. PS pH gradient method (Ang-PS-DOX)....
We modified and reconstructed a high image quality portable non-mydriatic fundus camera compared it with the tabletop to evaluate efficacy of new in detecting retinal diseases. designed built novel handheld telemedicine system. The cameras was that existing commercial by taking photographs 364 eyes from 254 patients. In all 800 images taken two types, 400 per camera, were graded four clarity classifications. Using 63% (252/400) as excellent overall quality, 20.5% (82/400) good, 11.75%...
The integration of artificial intelligence (AI) in ophthalmology has promoted the development discipline, offering opportunities for enhancing diagnostic accuracy, patient care, and treatment outcomes. This paper aims to provide a foundational understanding AI applications ophthalmology, with focus on interpreting studies related AI-driven diagnostics. core our discussion is explore various methods, including deep learning (DL) frameworks detecting quantifying ophthalmic features imaging...