Author name cluster

Lili Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

JBHI Journal 2026 Journal Article

Classifying Post-COVID “Brain Fog” Patients and Identifying Key ROIs via Graph Neural Network Model

Yuzhe Li
Yubo Zhang
Zhaomin Dong
Li Ma
Yonggui Yuan
Lili Chen

Brain fog has raised significant public health concerns as a common neurocognitive impairment in the post-COVID-19 condition, involving memory loss, poor concentration, and language difficulties. However, their neural mechanisms remain unclear, and objective resting-state fMRI–based diagnostic tools are still lacking. To address these challenges, we first recruited 72 patients who experienced persistent brain fog symptoms following COVID-19 infection, along with 68 post-COVID participants without brain fog (PC-noBF), and collected resting-state functional magnetic resonance imaging (rs-fMRI) data from all participants. The interpretable graph neural network model BrainGNN was employed to model and classify individual brain networks, utilizing functional connectivity graphs constructed from the Automated Anatomical Labeling (AAL) atlas. Using out-of-fold predictions from 5-fold cross-validation, BrainGNN achieved an accuracy of 75. 71% (Bootstrap 95% CI: 68. 57%–82. 86%) and an area under the ROC curve (AUC) of 76. 07% (Bootstrap 95% CI: 73. 93%–88. 48%). Furthermore, on an independent test set, BrainGNN outperformed traditional machine learning methods and other GNN models, achieving an accuracy of 82. 14% and an AUC of 82. 82% (classification threshold: 0. 5). Moreover, the model identified several key brain regions—bilateral insula, bilateral Heschl's gyri, and the left superior temporal gyrus—as potential neurobiological markers. Notably, in post-hoc analyses, the ALFF and ReHo values of the left insula were significantly associated with scores related to language and memory symptoms. These findings collectively underscore the effectiveness and interpretability of the proposed approach in identifying functional markers of brain fog. This study not only demonstrates the potential of individual-level identification of brain fog using resting-state fMRI empowered by interpretable GNN, but also reveals its capacity to provide novel insights into the neurobiological mechanisms underlying COVID-19-related cognitive impairment.

Details DOI

JBHI Journal 2022 Journal Article

S2Q-Net: Mining the High-Pass Filtered Phase Data in Susceptibility Weighted Imaging for Quantitative Susceptibility Mapping

Zhiyang Lu
Jun Li
Chaoyue Wang
Rongjun Ge
Lili Chen
Hongjian He
Jun Shi

Susceptibility weighted imaging (SWI) is a routine magnetic resonance imaging (MRI) sequence that combines the magnitude and high-pass filtered phase images to qualitatively enhance the image contrasts related to tissue susceptibility. Tremendous amounts of the high-pass filtered phase data with low signal to noise ratio and incomplete background field removal have thus been collected under default clinical settings. Since SWI cannot quantitatively estimate the susceptibility, it is thus non-trivial to derive quantitative susceptibility mapping (QSM) directly from these redundant phase data, which effectively promotes the mining of the SWI data collected previously. To this end, a novel deep learning based SWI-to-QSM-Net (S2Q-Net) is proposed for QSM reconstruction from SWI high-pass filtered phase data. S2Q-Net firstly estimates the edge maps of QSM to integrate edge prior into features, which benefits the network to reconstruct QSM with realistic and clear tissue boundaries. Furthermore, a novel Second-order Cross Dense Block is proposed in S2Q-Net, which can capture rich inter-region interactions to provide more non-local phase information related to local tissue susceptibility. Experimental results on both simulated and in-vivo data indicate its superiority over all the compared deep learning based QSM reconstruction methods.

Details DOI

NeurIPS Conference 2021 Conference Paper

Decision Transformer: Reinforcement Learning via Sequence Modeling

Lili Chen
Kevin Lu
Aravind Rajeswaran
Kimin Lee
Aditya Grover
Misha Laskin
Pieter Abbeel
Aravind Srinivas

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired return (reward), past states, and actions, our Decision Transformer model can generate future actions that achieve the desired return. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.

PDF Details

NeurIPS Conference 2021 Conference Paper

Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings

Lili Chen
Kimin Lee
Aravind Srinivas
Pieter Abbeel

Recent advances in off-policy deep reinforcement learning (RL) have led to impressive success in complex tasks from visual observations. Experience replay improves sample-efficiency by reusing experiences from the past, and convolutional neural networks (CNNs) process high-dimensional inputs effectively. However, such techniques demand high memory and computational bandwidth. In this paper, we present Stored Embeddings for Efficient Reinforcement Learning (SEER), a simple modification of existing off-policy RL methods, to address these computational and memory requirements. To reduce the computational overhead of gradient updates in CNNs, we freeze the lower layers of CNN encoders early in training due to early convergence of their parameters. Additionally, we reduce memory requirements by storing the low-dimensional latent vectors for experience replay instead of high-dimensional images, enabling an adaptive increase in the replay buffer capacity, a useful technique in constrained-memory settings. In our experiments, we show that SEER does not degrade the performance of RL agents while significantly saving computation and memory across a diverse set of DeepMind Control environments and Atari games.

PDF Details

ICML Conference 2021 Conference Paper

State Entropy Maximization with Random Encoders for Efficient Exploration

Younggyo Seo
Lili Chen
Jinwoo Shin
Honglak Lee
Pieter Abbeel
Kimin Lee

Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL). However, efficient exploration in high-dimensional observation spaces still remains a challenge. This paper presents Random Encoders for Efficient Exploration (RE3), an exploration method that utilizes state entropy as an intrinsic reward. In order to estimate state entropy in environments with high-dimensional observations, we utilize a k-nearest neighbor entropy estimator in the low-dimensional representation space of a convolutional encoder. In particular, we find that the state entropy can be estimated in a stable and compute-efficient manner by utilizing a randomly initialized encoder, which is fixed throughout training. Our experiments show that RE3 significantly improves the sample-efficiency of both model-free and model-based RL methods on locomotion and navigation tasks from DeepMind Control Suite and MiniGrid benchmarks. We also show that RE3 allows learning diverse behaviors without extrinsic rewards, effectively improving sample-efficiency in downstream tasks.

Details

ICRA Conference 2020 Conference Paper

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

Liang Du 0004
Jingang Tan
Xiangyang Xue 0001
Lili Chen
Hongkai Wen 0001
Jianfeng Feng
Jiamao Li
Xiaolin Zhang

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost. Codes are available at: https://github.com/Biotan/3DCFS.

Details

AIIM Journal 2020 Journal Article

Deep neural network for semi-automatic classification of term and preterm uterine recordings

Lili Chen
Huoyao Xu

Pregnancy is a complex process, and the prediction of premature birth is uncertain. Many researchers are exploring non-invasive approaches to enhance its predictability. Currently, the ElectroHysteroGram (EHG) and Tocography (TOCO) signal are a real-time and non-invasive technology which can be employed to predict preterm birth. For this purpose, sparse autoencoder (SAE) based deep neural network (SAE-based DNN) is developed. The deep neural network has three layers including a stacked sparse autoencoder (SSAE) network with two hidden layers and one final softmax layer. To this end, the bursts of all 26 recordings of the publicly available TPEHGT DS database corresponding to uterine contraction intervals and non-contraction intervals (dummy intervals) were manually segmented. 20 features were extracted by two feature extraction algorithms including sample entropy and wavelet entropy. Afterwards, the SSAE network is adopted to learn high-level features from raw features by unsupervised learning. The softmax layer is added at the top of the SSAE network for classification. In order to verify the effectiveness of the proposed method, this study used 10-fold cross-validation and four indicators to evaluate classification performance. Experimental research results display that the performance of deep neural network can achieve Sensitivity of 98. 2%, Specificity of 97. 74%, and Accuracy of 97. 9% in the publicly TPEHGT DS database. The performance of deep neural network outperforms the comparison models including deep belief networks (DBN) and hierarchical extreme learning machine (H-ELM). Finally, experimental research results reveal that the proposed method could be valid applied to semi-automatic identification of term and preterm uterine recordings.

Details DOI

ICRA Conference 2013 Conference Paper

Global optimal data association for multiple people tracking

Lili Chen
Wei Wang 0058
Alois C. Knoll

Multiple people tracking is an important component for different tasks such as video surveillance and human-robot interaction. In this paper, a global optimization approach is proposed for long-term tracking of an a priori unknown number of targets, particularly aim to improve the robustness in case of complex interaction and mutual occlusion. With a state-space discretization scheme, the multiple object tracking problem is formulated with a grid-based network flow model, resulting in a convex problem that can be casted into an Integer Linear Programming (ILP), then solved through relaxation. In order to allow recovery from misdetections, common heuristics such as non-maxima suppression is eschewed within observations. In addition, we show that how behavior cue can be integrated into the association affinity model, providing discriminative hints for resolving ambiguities between crossing trajectories. The validity of the proposed method is demonstrated through experiments on multiple challenging video sequences, using a calibrated multi-camera setup.

Details