Quan Tang

Quan Tang

Auto-generated profile, based on publicly available information

Quan Tang

China West Normal University, Nanchong, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
14 June 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
LXLiming Xu
Liming Xu
QTQuan Tang
Quan Tang
ZBZheng Bochuan
Zheng Bochuan
JLJiancheng Lv
Jiancheng Lv
WLWeisheng Li
Weisheng Li
XZXianhua Zeng
Xianhua Zeng
Medical report generation, as a cross-modal automatic text generation task, can be highly significant both in research and clinical fields. The core is to generate diagnosis reports in clinical language from medical images. However, several limitations persist, including a lack of global information, inadequate cross-modal fusion capabilities, and high computational demands. To address these issues, we propose cross-modal global feature fusion Transformer (CGFTrans) to extract global information meanwhile reduce computational strain. Firstly, we introduce mesh recurrent network to capture inter-layer information at different levels to address the absence of global features. Then, we design feature fusion decoder and define ‘mid-fusion’ strategy to separately fuse visual and global features with medical report embeddings, which enhances the ability of the cross-modal joint learning. Finally, we integrate shifted window attention into Transformer encoder to alleviate computational pressure and capture pathological information at multiple scales. Extensive experiments conducted on three datasets demonstrate that the proposed method achieves average increments of 2.9%, 1.5%, and 0.7% in terms of the BLEU-1, METEOR and ROUGE-L metrics, respectively. Besides, it achieves average increments −22.4% and 17.3% training time and images throughput, respectively.

22 May 2025 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
LXLiming Xu
Liming Xu
YWYongheng Wang
Yongheng Wang
Chunlin HeChunlin He
Chunlin He
QTQuan Tang
Quan Tang
XZXianhua Zeng
Xianhua Zeng
JLJiancheng Lv
Jiancheng Lv
Medical report generation which extracts pathological information within medical images and subsequently produces diagnostic text autonomously aims to alleviate the workload of medical experts and offers auxiliary support in diagnoses. Despite some preliminary progress have been made, several limitations still persist, including lack of specificity in extracted visual features, insufficient consideration of cross-modal alignment and extensive preparatory work required for prior knowledge. To address these issues, we, in this article, propose a novel deep label-guided graph convolutional network for medical report generation which utilizes disease label to guide to extract pathological information from medical images. To be specific, we first construct graph convolutional network to guide the model to extract the specific visual features based on disease labels, which allowing us to selectively extract disease specificity information resided in medical images. Then, we develop cross-modal alignment module to guide the alignment across medical image, diagnose report and disease label, which enables more accurate generation with more precise description. Besides, we build pre-constructed relational matrix to guide report generation model to learn the relationship between visual features and disease types with minimal additional workload to further reduce intensive workload. Extensive experiments on three benchmark datasets, i.e., IU X-ray, MIMIC-CXR, and COV-CTR, demonstrate that the proposed method outperforms the recent state-of-the-art medical report generation methods. Ours shows a 9.2% improvement in BLEU-4 score on the IU X-ray dataset, and both BLEU-4 and CIDEr scores improve by 6.31% on the MIMIC-CXR dataset. Additionally, the results show that it can be easily to applied and extended to medical image report generation with different modalities.

24 December 2021
Verified
Conference Paper
Open access
PDF file
QTQuan Tang
Quan Tang
TLTingjun Li
Tingjun Li
JFJunyan Fang
Junyan Fang
This electronic document is a “live” template. In the current research of cognitive psychology, the field of embodied cognition has become an important part of cognitive science. The introduction of the body-specific hypothesis adds important pieces to the puzzle of the theoretical structure of embodied cognition. The body-specific hypothesis (Casasanto, 2009) suggests that the content of our mind depends to a great extent on our body structure. In this article, we reviewed studies for neurological and brain imaging and behavioral evidence to support the body-specific hypothesis based on the hands and other body parts including foot laterality, general fluency and pain perception. In terms of handedness, we mainly focused on the perspective of action verbs, action and emotion valence, approach motivation and motor control, visuospatial attention and metaphor explanation. In terms of some studies, though did not mention the body specific theory explicitly, they provided supportive results towards the theory. For evidence of other parts of the body, we try to find the relationship between metaphors and other body experiences other than handedness, so as to expand the boundaries of the body specificity hypothesis. While providing evidence for the body specificity hypothesis (BSH), we also try to prove that the body experience influences human cognition through the above content, that is, cognition is embodied. Additionally, we also offered possible research directions for the further exploration and application of the hypothesis, including cross-cultural examination, motivational or emotional factors, and the effect of neuro abnormality.