Jinqian Pan
YOU?
Author Swipe
View article: Multimodal Prediction of Renal Tumor Malignancy from Radiology Reports and Structured Electronic Health Records: Retrospective Cohort Study (Preprint)
Multimodal Prediction of Renal Tumor Malignancy from Radiology Reports and Structured Electronic Health Records: Retrospective Cohort Study (Preprint) Open
BACKGROUND Accurate preoperative prediction of renal tumor malignancy is essential but remains challenging. While radiology and structured electronic health record (EHR) data are widely used for tumor evaluation, radiology reports—though …
View article: COMPAC: COMputable Phenotype for Asthma in Children
COMPAC: COMputable Phenotype for Asthma in Children Open
View article: Natural Language Generation in Healthcare: A Review of Methods and Applications
Natural Language Generation in Healthcare: A Review of Methods and Applications Open
Natural language generation (NLG) is the key technology to achieve generative artificial intelligence (AI). With the breakthroughs in large language models (LLMs), NLG has been widely used in various medical applications, demonstrating the…
View article: Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities
Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities Open
Training deep Convolutional Neural Networks (CNNs) presents unique challenges, including the pervasive issue of elimination singularities—consistent deactivation of nodes leading to degenerate manifolds within the loss landscape. These sin…
View article: BGDB: Bernoulli-Gaussian Decision Block with Improved Denoising Diffusion Probabilistic Models
BGDB: Bernoulli-Gaussian Decision Block with Improved Denoising Diffusion Probabilistic Models Open
Generative models can enhance discriminative classifiers by constructing complex feature spaces, thereby improving performance on intricate datasets. Conventional methods typically augment datasets with more detailed feature representation…
View article: Federated learning with multi‐cohort real‐world data for predicting the progression from mild cognitive impairment to Alzheimer's disease
Federated learning with multi‐cohort real‐world data for predicting the progression from mild cognitive impairment to Alzheimer's disease Open
INTRODUCTION Leveraging routinely collected electronic health records (EHRs) from multiple health‐care institutions, this approach aims to assess the feasibility of using federated learning (FL) to predict the progression from mild cogniti…
View article: From Image to Report: Automating Lung Cancer Screening Interpretation and Reporting with Vision-Language Models
From Image to Report: Automating Lung Cancer Screening Interpretation and Reporting with Vision-Language Models Open
View article: MRISeqClassifier: A Deep Learning Toolkit for Precise MRI Sequence Classification
MRISeqClassifier: A Deep Learning Toolkit for Precise MRI Sequence Classification Open
Magnetic Resonance Imaging (MRI) is a crucial diagnostic tool in medicine, widely used to detect and assess various health conditions. Different MRI sequences, such as T1-weighted, T2-weighted, and FLAIR, serve distinct roles by highlighti…
View article: Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities
Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities Open
Training deep Convolutional Neural Networks (CNNs) presents unique challenges, including the pervasive issue of elimination singularities, consistent deactivation of nodes leading to degenerate manifolds within the loss landscape. These si…
View article: BGDB: Bernoulli-Gaussian Decision Block with Improved Denoising Diffusion Probabilistic Models
BGDB: Bernoulli-Gaussian Decision Block with Improved Denoising Diffusion Probabilistic Models Open
Generative models can enhance discriminative classifiers by constructing complex feature spaces, thereby improving performance on intricate datasets. Conventional methods typically augment datasets with more detailed feature representation…
View article: Combining Federated Machine Learning and Qualitative Methods to Investigate Novel Pediatric Asthma Subtypes: Protocol for a Mixed Methods Study
Combining Federated Machine Learning and Qualitative Methods to Investigate Novel Pediatric Asthma Subtypes: Protocol for a Mixed Methods Study Open
Background Pediatric asthma is a heterogeneous disease; however, current characterizations of its subtypes are limited. Machine learning (ML) methods are well-suited for identifying subtypes. In particular, deep neural networks can learn p…
View article: Shifting to machine supervision: annotation-efficient semi and self-supervised learning for automatic medical image segmentation and classification
Shifting to machine supervision: annotation-efficient semi and self-supervised learning for automatic medical image segmentation and classification Open
View article: Combining Federated Machine Learning and Qualitative Methods to Investigate Novel Pediatric Asthma Subtypes: Protocol for a Mixed Methods Study (Preprint)
Combining Federated Machine Learning and Qualitative Methods to Investigate Novel Pediatric Asthma Subtypes: Protocol for a Mixed Methods Study (Preprint) Open
BACKGROUND Pediatric asthma is a heterogeneous disease; however, current characterizations of its subtypes are limited. Machine learning (ML) methods are well-suited for identifying subtypes. In particular, deep neural networks can learn …
View article: Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification
Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification Open
Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands subst…
View article: Enhancing Medical Image Segmentation: Optimizing Cross-Entropy Weights and Post-Processing with Autoencoders
Enhancing Medical Image Segmentation: Optimizing Cross-Entropy Weights and Post-Processing with Autoencoders Open
The task of medical image segmentation presents unique challenges, necessitating both localized and holistic semantic understanding to accurately delineate areas of interest, such as critical tissues or aberrant features. This complexity i…
View article: Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond
Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond Open
This paper presents a comprehensive survey of low-light image and video enhancement, addressing two primary challenges in the field. The first challenge is the prevalence of mixed over-/under-exposed images, which are not adequately addres…
View article: PointNorm: Dual Normalization is All You Need for Point Cloud Analysis
PointNorm: Dual Normalization is All You Need for Point Cloud Analysis Open
Point cloud analysis is challenging due to the irregularity of the point cloud data structure. Existing works typically employ the ad-hoc sampling-grouping operation of PointNet++, followed by sophisticated local and/or global feature extr…