Kun Yuan

Kun Yuan

Auto-generated profile, based on publicly available information

Kun Yuan

Technical University of Munich, Arcisstraße 21, Munich, 80333, Germany; University of Strasbourg & IHU Strasbourg, 36 Boulevard de la Victoire, Strasbourg, 67000, France

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
4 June 2025 in Medical Image Analysis
Verified
Journal Article
Open access
KYKun Yuan
Kun Yuan
VSVinkle Srivastav
Vinkle Srivastav
TYTong Yu
Tong Yu
JLJoël L. Lavanchy
Joël L. Lavanchy
Jacques MarescauxJacques Marescaux
Jacques Marescaux
NPNicolas Padoy
Nicolas Padoy
Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their design. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals for multi-modal representation learning without relying on manual annotations. We address the surgery-specific linguistic challenges present in surgical video lectures by employing multiple complementary automatic speech recognition systems to generate text transcriptions. We then present a novel method, SurgVLP - Surgical Vision Language Pre-training, for multi-modal representation learning. SurgVLP constructs a new contrastive learning objective to align video clip embeddings with the corresponding multiple text embeddings by bringing them together within a joint latent space. To effectively demonstrate the representational capability of the learned joint latent space, we introduce several vision-and-language surgical tasks and evaluate various vision-only tasks specific to surgery, e.g., surgical tool, phase, and triplet recognition. Extensive experiments across diverse surgical procedures and tasks demonstrate that the multi-modal representations learned by SurgVLP exhibit strong transferability and adaptability in surgical video analysis. Furthermore, our zero-shot evaluations highlight SurgVLP's potential as a general-purpose foundation model for surgical workflow analysis, reducing the reliance on extensive manual annotations for downstream tasks, and facilitating adaptation methods such as few-shot learning to build a scalable and data-efficient solution for various downstream surgical applications. The code is available at https://github.com/CAMMA-public/SurgVLP.

31 August 2025 in Medical Image Analysis
Verified
Journal Article
Open access
GWGuankun Wang
Guankun Wang
LBLong Bai
Long Bai
JWJunyi Wang
Junyi Wang
KYKun Yuan
Kun Yuan
ZLZhen Li
Zhen Li
Hongliang RenHongliang Ren
Hongliang Ren
Recently, Multimodal Large Language Models (MLLMs) have demonstrated their immense potential in computer-aided diagnosis and decision-making. In the context of robotic-assisted surgery, MLLMs can serve as effective tools for surgical training and guidance. However, there is still a deficiency of MLLMs specialized for surgical scene understanding in endoscopic procedures. To this end, we present EndoChat, an MLLM tailored to address various dialogue paradigms and subtasks in understanding endoscopic procedures. To train our EndoChat, we construct the Surg-396K dataset through a novel pipeline that systematically extracts surgical information and generates structured annotations based on large-scale endoscopic surgery datasets. Furthermore, we introduce a multi-scale visual token interaction mechanism and a visual contrast-based reasoning mechanism to enhance the model's representation learning and reasoning capabilities. Our model achieves state-of-the-art performance across five dialogue paradigms and seven surgical scene understanding tasks. Additionally, we conduct evaluations with professional surgeons, who provide positive feedback on the majority of conversation cases generated by EndoChat. Overall, these results demonstrate that EndoChat has the potential to advance training and automation in robotic-assisted surgery. Our dataset and model are publicly available at https://github.com/gkw0010/EndoChat.

22 July 2025 in Medical Image Analysis
Verified
Journal Article
Open access
SZShifang Zhao
Shifang Zhao
LBLong Bai
Long Bai
KYKun Yuan
Kun Yuan
FLFeng Li
Feng Li
JYJieming Yu
Jieming Yu
Hongliang RenHongliang Ren
Hongliang Ren
In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as they are unable to effectively learn such incremental tasks and suffer from catastrophic forgetting. When learning new data, the model experiences a sharp performance drop on previously learned data. Although several continual learning methods have been proposed for incremental understanding tasks in surgical scenarios, the issue of data imbalance often leads to a strong bias in the segmentation head, resulting in poor performance. Data imbalance can occur in two forms: (i) class imbalance between new and old data, and (ii) class imbalance within the same time point of data. Such imbalances often cause the dominant classes to take over the training process of continual semantic segmentation (CSS). To address this issue, we propose SurgCSS, a novel plug-and-play CSS framework for surgical instrument segmentation under data imbalance. Specifically, we generate realistic surgical backgrounds through inpainting and blend instrument foregrounds with the generated backgrounds in a class-aware manner to balance the data distribution in various scenarios. We further propose the Class Desensitization Loss by employing contrastive learning to correct edge biases caused by data imbalance. Moreover, we dynamically fuse the weight parameters of the old and new models to achieve a better trade-off between the biased and unbiased model weights. To investigate the data imbalance problem in surgical scenarios, we construct a new benchmark for surgical instrument CSS by integrating four public datasets: EndoVis 2017, EndoVis 2018, CholecSeg8k, and SAR-RAPR50. Extensive experiments demonstrate the effectiveness of the proposed framework, achieving significant performance improvement against existing baselines. Our method demonstrates excellent potential for clinical applications. The code is publicly available at github.com/Zzsf11/SurgCSS.

21 September 2025
Verified
Book Chapter
Closed access
PDF file
YHYiming Huang
Yiming Huang
LBLong Bai
Long Bai
BCBeilei Cui
Beilei Cui
KYKun Yuan
Kun Yuan
GWGuankun Wang
Guankun Wang
Hongliang RenHongliang Ren
Hongliang Ren

20 September 2025
Verified
Book Chapter
Closed access
PDF file
BBBritty Baby
Britty Baby
VSVinkle Srivastav
Vinkle Srivastav
PJPooja P. Jain
Pooja P. Jain
KYKun Yuan
Kun Yuan
PMPietro Mascagni
Pietro Mascagni
NPNicolas Padoy
Nicolas Padoy

14 June 2026 in International Journal of Computer Assisted Radiology and Surgery
Verified
Journal Article
Closed access
KYKun Yuan
Kun Yuan
YCYutong Cao
Yutong Cao
YTYunxi Tang
Yunxi Tang
NPNicolas Padoy
Nicolas Padoy
XCXiangyu Chu
Xiangyu Chu