Zongyuan Ge
YOU?
Author Swipe
View article: Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook
Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook Open
Learning from noisy labels remains a major challenge in medical image analysis, where annotation demands expert knowledge and substantial inter-observer variability often leads to inconsistent or erroneous labels. Despite extensive researc…
View article: Multi-Aspect Knowledge-Enhanced Medical Vision-Language Pretraining with Multi-Agent Data Generation
Multi-Aspect Knowledge-Enhanced Medical Vision-Language Pretraining with Multi-Agent Data Generation Open
Vision-language pretraining (VLP) has emerged as a powerful paradigm in medical image analysis, enabling representation learning from large-scale image-text pairs without relying on expensive manual annotations. However, existing methods o…
View article: Automated triage of cancer-suspicious skin lesions with 3D total-body photography
Automated triage of cancer-suspicious skin lesions with 3D total-body photography Open
View article: RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation
RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation Open
In this paper, we propose RoomPlanner, the first fully automatic 3D room generation framework for painlessly creating realistic indoor scenes with only short text as input. Without any manual layout design or panoramic image guidance, our …
View article: Artificial Intelligence Prediction of Postoperative Rotation Stability After Toric Implantable Collamer Lens Implantation
Artificial Intelligence Prediction of Postoperative Rotation Stability After Toric Implantable Collamer Lens Implantation Open
This study investigated the quantitative relationship between rotation, astigmatism, and vision, bridging the gap between artificial intelligence and optical theory.
View article: Using deep learning systems for diagnosing common skin lesions in sexual health
Using deep learning systems for diagnosing common skin lesions in sexual health Open
Background Early identification and treatment of sexually transmitted infections (STIs) prevents complications and improves STI control. However, there are obstacles to delivering accessible care, particularly for genital conditions. Metho…
View article: Enhancing AI-based diabetic retinopathy diagnosis through universal cross-camera image adaptation
Enhancing AI-based diabetic retinopathy diagnosis through universal cross-camera image adaptation Open
Objective To evaluate the effectiveness of a deep learning-based style adaptation strategy in improving the diagnostic accuracy and cross-camera generalisability of artificial intelligence (AI) for detecting diabetic retinopathy (DR). Meth…
View article: Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective Open
Generalized Category Discovery (GCD) aims to leverage labeled samples from known categories to cluster unlabeled data that may include both known and unknown categories. While existing methods have achieved impressive results under standar…
View article: Correction: Radiomics analysis for the early diagnosis of common sexually transmitted infections and skin lesions
Correction: Radiomics analysis for the early diagnosis of common sexually transmitted infections and skin lesions Open
[This corrects the article DOI: 10.1371/journal.pdig.0000926.].
View article: Special Issue on Artificial Intelligence in Dermatology: A Call for Collaborative Innovation
Special Issue on Artificial Intelligence in Dermatology: A Call for Collaborative Innovation Open
View article: ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model Open
View article: Development and validation of clinico‐imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy
Development and validation of clinico‐imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy Open
Objective Antiseizure medications (ASMs) are the first‐line treatment for epilepsy, yet they are ineffective in controlling seizures in about 40% of patients with unpredictable individual response to treatment. This study aimed to develop …
View article: AI-assisted anti-seizure medication selection? A qualitative study of the views of neurologists and epilepsy patients
AI-assisted anti-seizure medication selection? A qualitative study of the views of neurologists and epilepsy patients Open
PWE and neurologists were supportive of the prospects for MLCDS systems to improve ASM selection for people with epilepsy. However, their support was not unqualified and was often predicated on claims about the nature and role of these sys…
View article: A Systematic Review of Vision and Vision-Language Foundation Models in Ophthalmology
A Systematic Review of Vision and Vision-Language Foundation Models in Ophthalmology Open
View article: WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification
WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification Open
Multimodal Large Language Models (MLLMs) have shown promise in visual-textual reasoning, with Multimodal Chain-of-Thought (MCoT) prompting significantly enhancing interpretability. However, existing MCoT methods rely on rationale-rich data…
View article: Qualitative study on teachers’ psychological experience and coping styles regarding adolescents with non-suicidal self-injury behavior
Qualitative study on teachers’ psychological experience and coping styles regarding adolescents with non-suicidal self-injury behavior Open
Adolescent NSSI requires widespread attention. Key strategies include enhancing parental education, providing comprehensive support, and raising societal awareness. Teachers must receive specialized training to manage self-injury incidents…
View article: A deep learning algorithm based on fundus photographs to measure retinal vascular parameters and their additional value beyond the CAIDE risk score for predicting 14-year dementia risk
A deep learning algorithm based on fundus photographs to measure retinal vascular parameters and their additional value beyond the CAIDE risk score for predicting 14-year dementia risk Open
Summary Background Retinal photography is a valuable non-invasive tool for assessing the nature of vessel changes. It is of interest whether retinal vascular parameters can improve the ability to predict dementia risk of the widely used Ca…
View article: Forecasting the diabetic retinopathy progression using generative adversarial networks
Forecasting the diabetic retinopathy progression using generative adversarial networks Open
View article: Adapting Biomedical Foundation Models for Predicting Outcomes of Anti Seizure Medications
Adapting Biomedical Foundation Models for Predicting Outcomes of Anti Seizure Medications Open
Epilepsy affects over 50 million people worldwide, with anti-seizure medications (ASMs) as the primary treatment for seizure control. However, ASM selection remains a “trial and error” process due to the lack of reliable predictors of effe…
View article: The association of retinal age gap with schizophrenia: a cross-sectional analysis
The association of retinal age gap with schizophrenia: a cross-sectional analysis Open
Schizophrenia, a chronic neuropsychiatric disorder increasingly recognized as a multisystemic disease, is associated with accelerated brain ageing. Using deep learning, we investigated the retina, as a window into the central nervous syste…
View article: Radiomics analysis for the early diagnosis of common sexually transmitted infections and skin lesions
Radiomics analysis for the early diagnosis of common sexually transmitted infections and skin lesions Open
Early identification of sexually transmitted infection (STI) symptoms can prevent subsequent complications and improve STI control. We analysed 597 images from STIAtlas and categorised the images into four typical STIs and two skin lesions…
View article: Corrigendum to: Development and Validation of an Algorithm Model for Predicting Heat Sink Effects during Pulmonary Thermal Ablation
Corrigendum to: Development and Validation of an Algorithm Model for Predicting Heat Sink Effects during Pulmonary Thermal Ablation Open
The publisher regrets that an error has been identified in the published version of the article entitled “Development and Validation of an Algorithm Model for Predicting Heat Sink Effects during Pulmonary Thermal Ablation”, published in th…
View article: Prospective pragmatic trial of automated retinal photography and AI glaucoma screening in Australian primary care
Prospective pragmatic trial of automated retinal photography and AI glaucoma screening in Australian primary care Open
View article: Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis
Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis Open
To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information Pursuit (V-IP) offers an interpretable-by-design framework by sequentially querying input …
View article: A multimodal vision foundation model for clinical dermatology
A multimodal vision foundation model for clinical dermatology Open
View article: Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models
Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models Open
Concept Bottleneck Models (CBMs) decompose image classification into a process governed by interpretable, human-readable concepts. Recent advances in CBMs have used Large Language Models (LLMs) to generate candidate concepts. However, a cr…
View article: Interictal Epileptiform Discharge Detection Using Probabilistic Diffusion Models and AUPRC Maximization
Interictal Epileptiform Discharge Detection Using Probabilistic Diffusion Models and AUPRC Maximization Open
Recently, automated Interictal Epileptiform Discharge (IED) detection has attracted significant attention as a challenging predictive data analysis task aimed at improving early epilepsy diagnosis. Automated IED detection simplifies visual…
View article: MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment
MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment Open
Dermatological diagnosis represents a complex multimodal challenge that requires integrating visual features with specialized clinical knowledge. While vision-language pretraining (VLP) has advanced medical AI, its effectiveness in dermato…
View article: Towards Realistic Semi-supervised Medical Image Classification
Towards Realistic Semi-supervised Medical Image Classification Open
Existing semi-supervised learning (SSL) approaches follow the idealized closed-world assumption, neglecting the challenges present in realistic medical scenarios, such as open-set distribution and imbalanced class distribution. Although so…
View article: A web-based tool for predicting gastric ulcers in Chinese elderly adults based on machine learning algorithms and noninvasive predictors: A national cross-sectional and cohort study
A web-based tool for predicting gastric ulcers in Chinese elderly adults based on machine learning algorithms and noninvasive predictors: A national cross-sectional and cohort study Open
Background As the Chinese population continues to age, the prevalence of gastric ulcers, a common nutrition and diet-related disorder, is rising among the elderly. Gastric ulcers pose a significant public health challenge in China, yet the…