Yani Zhang

Dr. Yani Zhang

orcid

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 May 2024 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
QLQiankun Li
Qiankun Li
YWYimou Wang
Yimou Wang
YZYani Zhang
Yani Zhang
ZZZhaoyu Zuo
Zhaoyu Zuo
Junxin ChenJunxin Chen
Junxin Chen
WWWei Wang
Wei Wang
The surge in visual general big data has notably advanced data-driven deep learning-based computer vision technologies. Transformer-based methods shine in this era of big data because of their attention mechanism architecture and demand for massive data. However, the difficulty of obtaining medical images has caused the field to continue facing the limited-data challenge. In this paper, we propose a novel deep neuro-fuzzy system named Fuzzy-ViT, which synergistically integrates fuzzy logic with the Vision Transformer (ViT) for cross-domain transfer learning from large-scale general data to medical image domain. Specifically, Fuzzy-ViT utilizes a ViT backbone pre-trained on extensive general datasets such as ImageNet-21K, LAION-400M, and LAION-2B to extract rich general features. Then, a Fuzzy Attention Cross-Domain Module (FACM) is presented to transfer general features to medical features, thereby enhancing the medical image analysis. Thanks to the Fuzzy System Transitioner (FST) in FACM, fuzzy and uninterpretable general domain features can be effectively converted into those needed in the medical domain. In addition, the Attention Mechanism Smoother (AMS) in FACM smoothes the conversion outcomes, ensuring a harmonious integration of the fuzzy system with the neural network architecture. Experimental results demonstrate that the proposed Fuzzy-ViT achieves state-of-the-art and satisfactory performance on popular medical image benchmarks (BreakHis and HCRF) with 93.37% and 97.22% F1 scores. Detailed ablation analysis demonstrates that the effectiveness of our method for bridging large general visual and medical images.

5 December 2023
Verified
Conference Paper
Closed access
QLQiankun Li
Qiankun Li
XHXiaolong Huang
Xiaolong Huang
BFBo Fang
Bo Fang
YZYani Zhang
Yani Zhang
YCYongyong Chen
Yongyong Chen
Junxin ChenJunxin Chen
Junxin Chen
In recent years, 3D volumetric medical images have been widely used in clinical diagnosis, however, the popular 2D networks were reported unsuitable for segmenting them. In this direction, we propose a plug-and-play (PnP-AE) module to improve the performance of using 2D network for 3D medical image segmentation. Our method takes advantage of the intrinsic correlation between adjacent slices, by multiple encoders and fusion components to decouple plane feature extraction and depth information integration. In addition, the proposed weight sharing and feature storage strategies make PnP-AE extremely efficient. Our method is able to conveniently incorporate with mainstream 2D networks to segment 3D volumetric medical images. Experimental results demonstrate the excellent performance of our method. The source code is available at https://github.com/qklee-lz/PnP-AE.

2 January 2026 in Pattern Recognition
Verified
Journal Article
Closed access
QLQiankun Li
Qiankun Li
XHXiaolong Huang
Xiaolong Huang
YZYani Zhang
Yani Zhang
BFBo Fang
Bo Fang
DHDuo Hong
Duo Hong
Junxin ChenJunxin Chen
Junxin Chen

11 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
QLQiankun Li
Qiankun Li
JMJunyuan Mao
Junyuan Mao
JLJinyue Li
Jinyue Li
RHRui Hao
Rui Hao
HCHuabao Chen
Huabao Chen
Nan LiuNan Liu
Nan Liu
The integration of Multimodal Large Language Models (MLLMs) into healthcare has the potential to drive a considerable advancement toward many AI use cases in medicine, offering transformative capabilities across hierarchical levels of clinical granularity, ranging from microscopic tissue analysis over organ level imaging and individual patient modeling to population-level health surveillance. However, such integration into clinical practice is constrained by a multifaceted “trustworthiness gap”: the mismatch between the raw capabilities demonstrated by Medical MLLMs in controlled experiments and their reliability, fairness, safety, privacy protection, explainability, and regulatory accountability required for clinical deployment in the real world. This gap requires systematic examination of both model behavior and clinical risk across the full lifecycle of Medical MLLM development and use. In this paper, we survey the existing literature on methods, evaluation, and benchmarks of trustworthiness research in Medical MLLMs. We first establish a multi-scale clinical landscape across tissue, organ, individual, and population levels to categorize current models, providing critical insights into the interplay between data heterogeneity and clinical task requirements. Subsequently, we propose a holistic, six-dimensional taxonomy of trustworthiness, comprising truthfulness, robustness, fairness, safety, privacy, and explainability. Using this taxonomy, we critically analyze existing literature to elicit recurring Medical MLLM trustworthiness failure modes and suggest appropriate remediation strategies. Furthermore, our survey enumerates open challenges in evaluating trustworthiness by means of traditional automated metrics, frontier “LLM-as-a-Judge” methods and expert-centric assessment protocols. As a response to these challenges we identify emerging research directions including dynamic and workflow-oriented evaluations for interactive Medical MLLMs. We aim for this work to serve as a systematic guide for researchers and practitioners aiming to develop the next generation of trustworthy medical AI by achieving clinically acceptable reliability through technological innovations. Project Link: https://github.com/junyuanM/Trustworthy-Medical-MLLMs-Survey.

29 March 2026 in Information Fusion
Verified
Journal Article
Closed access
JLJinyue Li
Jinyue Li
YYYuzhou Yu
Yuzhou Yu
JYJingjing Yang
Jingjing Yang
MFMeng Fu
Meng Fu
YZYani Zhang
Yani Zhang
QLQiankun Li
Qiankun Li

24 June 2021
Verified
Conference Paper
Closed access
PDF file
GDGuiBao Dai
GuiBao Dai
QPQing Pan
Qing Pan
JLJianRu Li
JianRu Li
YZYani Zhang
Yani Zhang
Ying LiuYing Liu
Ying Liu
The use of quantum key distribution for encryption to realize the secure transmission of information is a research hotspot in the field of secure communication. In theory, it has a high degree of security with quantum mechanics as a guarantee. In particular, continuous variable quantum key distribution has the advantages of simple quantum state preparation, relatively high key rate and low detector cost, so it has attracted wide attention from all over the world. However, the continuous variable quantum key distribution will be affected by factors such as fiber type and fiber attenuation when it is transmitted in the fiber channel. Therefore, a large number of experimental tests must be carried out in the fiber channel before the quantum key distribution device is connected to the optical network. Therefore, this paper conducted continuous quantum key distribution experiments in different lengths of terrestrial optical fiber G.652D and submarine optical fiber G.654D. Among them, the quantum key generation rate reaches an average of 10kbit/s, and the quantum error rate is within 10%. As the distance increases, the variance of the transmission coefficient and the shot noise becomes smaller and the amplitude of the excess noise fluctuation becomes larger. The negotiation efficiency is above 92.44%. The experimental results show that continuous quantum key distribution has good compatibility in both G.652D and G.654D fibers. The experimental data provides a large amount of data support for subsequent research on the access of quantum key distribution equipment to optical networks.