Chentao Li

Chentao Li

Auto-generated profile, based on publicly available information

Chentao Li

Fu Foundation School of Engineering and Applied Science, Columbia University, New York, NY, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
Pan HuangPan Huang
Pan Huang
HXHualiang Xiao
Hualiang Xiao
PHPeng He
Peng He
CLChentao Li
Chentao Li
XGXiaodong Guo
Xiaodong Guo
Jing QinJing Qin
Jing Qin
Grading laryngeal squamous cell carcinoma (LSCC) based on histopathological images is a clinically significant yet challenging task. However, more low-effect background semantic information appeared in the feature maps, feature channels, and class activation maps, which caused a serious impact on the accuracy and interpretability of LSCC grading. While the traditional transformer block makes extensive use of parameter attention, the model overlearns the low-effect background semantic information, resulting in ineffectively reducing the proportion of background semantics. Therefore, we propose an end-to-end network with transformers constrained by learned-parameter-free attention (LA-ViT), which improve the ability to learn high-effect target semantic information and reduce the proportion of background semantics. Firstly, according to generalized linear model and probabilistic, we demonstrate that learned-parameter-free attention (LA) has a stronger ability to learn highly effective target semantic information than parameter attention. Secondly, the first-type LA transformer block of LA-ViT utilizes the feature map position subspace to realize the query. Then, it uses the feature channel subspace to realize the key, and adopts the average convergence to obtain a value. And those construct the LA mechanism. Thus, it reduces the proportion of background semantics in the feature maps and feature channels. Thirdly, the second-type LA transformer block of LA-ViT uses the model probability matrix information and decision level weight information to realize key and query, respectively. And those realize the LA mechanism. So, it reduces the proportion of background semantics in class activation maps. Finally, we build a new complex semantic LSCC pathology image dataset to address the problem, which is less research on LSCC grading models because of lacking clinically meaningful datasets. After extensive experiments, the whole metrics of LA-ViT outperform those of other state-of-the-art methods, and the visualization maps match better with the regions of interest in the pathologists' decision-making. Moreover, the experimental results conducted on a public LSCC pathology image dataset show that LA-ViT has superior generalization performance to that of other state-of-the-art methods.

1 April 2026 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
CLChentao Li
Chentao Li
Pan HuangPan Huang
Pan Huang
Jing QinJing Qin
Jing Qin
XWXin DI WU
Xin DI WU
Pathological grading of laryngeal squamous cell carcinoma (LSCC) based on whole-slide image (WSI) is crucial for the diagnosis, treatment and prognosis. According to pathologists' knowledge, tumor regions are highly associated with grading. However, existing multiple instance learning (MIL) methods tend to overrepresent weakly relevant non-tumor regions and irrelevant background, leading to poor grading performance and interpretability. Motivated by the above problems, we propose an end-to-end knowledge-driven MIL network with hierarchical cluster-incorporated aware filtering, i.e. HCF-MIL. Firstly, we develop the tumor-guiding cluster filtering for feature representation, which awarely filters out irrelevant instance-level information and adaptively assigns learnable weights to tumor and non-tumor instances. Secondly, conventional mean-based and max-based aggregation primarily capture the overall patterns, neglecting the contributions of the most representative individual instances. Therefore, we propose a novel enhanced filtering aggregation learning strategy to strengthen hierarchical tumor-related feature representation. Through end-to-end optimization, HCF-MIL reduces model's entropy value and facilitates better alignment between decision-making process and diagnostic behaviors of pathologists. Experiments on larynx and multicentre datasets show that HCF-MIL significantly improves both pathological grading performance and interpretability, providing a strong foundation for reliable clinical deployment. The dataset and code will be available at https://github.com/Prince-Lee-PathAI/HCF-MIL.

1 January 2026 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
FMFuhan Meng
Fuhan Meng
XDXixiang Deng
Xixiang Deng
YQYingbo Qu
Yingbo Qu
CLChentao Li
Chentao Li
QMQiang Ma
Qiang Ma
PFPeng Feng
Peng Feng
Segmenting programmed cell death-ligand 1 (PD-L1) expression regions in lung squamous cell carcinoma from pathological H&E images represents a challenging pixel-level prediction task, attributed to the morphological heterogeneity and size discrepancies of expression areas. Although hybrid architectures of CNN and Transformer can extract local features and capture long-range dependencies, they inadequately address information interaction and redundant information elimination during the fusion process, adversely impacting PD-L1 segmentation accuracy. To address this, we propose a W-shaped dual-encoder network (DEW-Net) with novel attention fusion mechanisms. First, a CNN encoder and a Swin Transformer encoder are connected in parallel to extract multi-layer local and global features from pathological images, respectively. Second, a Cross-Attention Fusion (CAF) module is proposed to strengthen information interaction and semantic feature fusion. Additionally, a Channel Attention (CA) is introduced in skip connections to enhance the channel-wise information of shallow features, while a Bilateral-voting Position Attention (BPA) module is further proposed to eliminate positional noise in same-scale shallow features and reinforce position-wise information. We conducted extensive experiments on four datasets. On the PD-L1 segmentation dataset, DEW-Net achieved superior performance, with DSC and IoU reaching 79.93% and 71.27%, respectively. These results demonstrate its strong performance and generalization capability compared to other state-of-the-art (SOTA) methods.

4 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
CLChentao Li
Chentao Li
BBBehzad Bozorgtabar
Behzad Bozorgtabar
YPYi-Fang Ping
Yi-Fang Ping
Pan HuangPan Huang
Pan Huang
Jing QinJing Qin
Jing Qin
Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit its representation and interpretability. To address these challenges, we propose a latent factor grouping-boosted cluster-reasoning instance disentangled learning framework for whole-slide image (WSI) interpretable representation in three phases. First, we introduce a novel positive semi-definite latent factor grouping that maps instances into a latent subspace, effectively mitigating spatial entanglement in MIL. To alleviate semantic entanglement, we employs instance probability counterfactual inference and optimization via cluster-reasoning instance disentangling. Finally, we employ a generalized linear weighted decision via instance effect re-weighting to address decision entanglement. Extensive experiments on multicentre datasets demonstrate that our model outperforms all state-of-the-art models. Moreover, it attains pathologist-aligned interpretability through disentangled representations and a transparent decision-making process.