Xiaojian Li

Xiaojian Li

Auto-generated profile, based on publicly available information

Xiaojian Li

School of Management, Hefei University of Technology, Hefei, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
20 June 2018 in Science Robotics
Verified
Journal Article
Closed access
PDF file
Junyang LiJunyang Li
Junyang Li
XLXiaojian Li
Xiaojian Li
TLTao Luo
Tao Luo
RWRan Wang
Ran Wang
CLChichi Liu
Chichi Liu
DSDong Sun
Dong Sun
A three-dimensional magnetically driven microrobot can carry and deliver cells to targeted areas in vivo.

21 July 2020 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
LLLing Li
Ling Li
XLXiaojian Li
Xiaojian Li
SYShanlin Yang
Shanlin Yang
Shuai DingShuai Ding
Shuai Ding
AJAlireza Jolfaei
Alireza Jolfaei
Xi ZhengXi Zheng
Xi Zheng
Virtual reality technology has been applied in minimally invasive surgery to provide doctors with a more immersive surgical experience. The key to build the virtual reality model is estimation of depth and motion . In this study, a fully unsupervised learning method for depth and motion estimation with the continuous monocular endoscopic video is proposed. After highlighted region detection, EndoMotionNet and EndoDepthNet are designed to estimate ego-motion and depth simultaneously. The timing information between consecutive frames are considered with a long short-term memory layer by EndoMotionNet to enhance the accuracy of ego-motion estimation. The estimated depth of the previous frame is used to estimate the depth of the next frame in EndoDepthNet with a multi-mode fusion mechanism. The custom loss function is designed to improve the accuracy of the unsupervised learning method. Experiments verify that the proposed method can effectively improve the accuracy of depth and motion estimation.

22 July 2019 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
DLDongfang Li
Dongfang Li
Fuzhou NiuFuzhou Niu
Fuzhou Niu
Junyang LiJunyang Li
Junyang Li
XLXiaojian Li
Xiaojian Li
DSDong Sun
Dong Sun
Electromagnetic-based actuation is receiving increasing attention for driving microparticles, particularly for in vivo biomedical applications. This study presents a core shape design for electromagnetic coils to develop a magnetic gradient field-based actuation system that can enable microrobotic manipulation. Based on mathematical model using the finite element method, the shape of the iron core and the size of the probe are optimized aiming to increase the gradient at the focused area. A thin disc is also attached to the end of the iron core for reducing the waste of magnetic field energy. Through this design, the magnetic field generated by the electromagnetic actuation system can be considerably enhanced to propel microrobots in the in vivo environments. The designed system is tested in different in vitro environments, including pure water, artificial cerebrospinal fluid, mouse blood, and a special environment with an extremely high viscosity coefficient. The system is also tested for driving microrobots in an in vivo environment, namely, zebrafish yolk. Experimental results effectively demonstrate the capacity of the designed platform in manipulating microrobots for in vitro and in vivo applications.

2 April 2021 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
LLLing Li
Ling Li
XLXiaojian Li
Xiaojian Li
BOBo Ouyang
Bo Ouyang
Shuai DingShuai Ding
Shuai Ding
SYShanlin Yang
Shanlin Yang
YQYanwei Qu
Yanwei Qu
The robot-held laparoscope efficiently maintains the stability of the surgical screen in comparison with the laparoscope held by the assistant. The collaboration between the robot-held laparoscope and the surgeon is achieved without the artificial manipulation by tracking surgical instruments automatically. In this article, a visual tracking space vector method is proposed to autonomously control the field of view by tracking multiple surgical instruments. In the proposed method, a visual tracking space vector is introduced to track the motion of multiple instruments, and a constraint vector is defined to ensure that the laparoscope is always within the safe working space. In addition, a modified YOLOv3 algorithm is proposed to robustly detect and classify the surgical instruments. The proposed method automatically adapts to the changes in the number of surgical instruments, as compared to other visual servoing methods for tracking surgical instruments. The proposed method does not require the depth information of the tracked surgical instruments. Experimental and simulation results verify that the proposed method accurately and efficiently controls the robot-held laparoscope to track the motion of multiple surgical instruments and ensure safe tracking movement.

10 August 2023 in Acta Biomaterialia
Verified
Journal Article
Open access
SZShilu Zhu
Shilu Zhu
YCYifan Cheng
Yifan Cheng
JWJian Wang
Jian Wang
GLGuangli Liu
Guangli Liu
TLTingting Luo
Tingting Luo
Runhuai YangRunhuai Yang
Runhuai Yang
Biohybrid magnetic microrobots (BMMs) have emerged as an exciting class of microrobots and have been considered as a promising platform in biomedicine. Many microorganisms and body's own cells show intriguing properties, such as morphological characteristics, biosafety, and taxis abilities (e.g., chemotaxis, aerotaxis), which have made them attractive for the fabrication of microrobots. For remote controllability and sustainable actuation, magnetic components are usually incorporated onto these biological entities, and other functionalized non-biological components (e.g., therapeutic agents) are also included for specific applications. This review highlights the latest developments in BMMs with a focus on their biomedical applications. It starts by introducing the fundamental understanding of the propulsion system at the microscale in a magnetically driven manner, followed by a summary of diverse BMMs based on different microorganisms and body's own cells along with their relevant applications. Finally, the review discusses how BMMs contribute to the advancements of microrobots, the current challenges of using BMMs in practical clinical settings, and the future perspectives of this exciting field. STATEMENT OF SIGNIFICANCE: Biohybrid magnetic microrobots (BMMs), composed of biological entities and functional parts, hold great potential and serve as a novel and promising platform for biomedical applications such as targeted drug delivery. This review comprehensively summarizes the recent advancements in BMMs for biomedical applications, mainly focused on the representative propulsion modalities in a magnetically propelled manner and diverse designs of BMMs based on different biological entities, including microorganisms and body's own cells. We hope this review can provide ideas for the future design, development, and innovation of micro/nanorobots in the field of biomedicine.

8 March 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ZYZijie Yue
Zijie Yue
Shuai DingShuai Ding
Shuai Ding
XLXiaojian Li
Xiaojian Li
SYShanlin Yang
Shanlin Yang
YZYoutao Zhang
Youtao Zhang
Automatic acetowhite lesion segmentation in colposcopy images (cervigrams) is essential in assisting gynecologists for the diagnosis of cervical intraepithelial neoplasia grades and cervical cancer. It can also help gynecologists determine the correct lesion areas for further pathological examination. Existing computer-aided diagnosis algorithms show poor segmentation performance because of specular reflections, insufficient training data and the inability to focus on semantically meaningful lesion parts. In this paper, a novel computer-aided diagnosis algorithm is proposed to segment acetowhite lesions in cervigrams automatically. To reduce the interference of specularities on segmentation performance, a specular reflection removal mechanism is presented to detect and inpaint these areas with precision. Moreover, we design a cervigram image classification network to classify pathology results and generate lesion attention maps, which are subsequently leveraged to guide a more accurate lesion segmentation task by the proposed lesion-aware convolutional neural network. We conducted comprehensive experiments to evaluate the proposed approaches on 3045 clinical cervigrams. Our results show that our method outperforms state-of-the-art approaches and achieves better Dice similarity coefficient and Hausdorff Distance values in acetowhite legion segmentation.