Author: hxwu

On the Info Day for Undergraduate Admissions 2024, we were thrilled to see a big crowd of visitors joining the admission talk and special event “𝐖𝐞𝐥𝐥-𝐑𝐨𝐮𝐧𝐝𝐞𝐝 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫 𝐈𝐧𝐜𝐮𝐛𝐚𝐭𝐢𝐨𝐧 𝐒𝐡𝐨𝐰𝐫𝐨𝐨𝐦” to learn the experience in developing APP / Products / Services.

Our lab member, Sishen YUAN, along with others, showcased our progress in augmented reality for neuro-interventional head-mounted robotics (SkullBot), attracting a lot of interest from the visitors and sparking engaging conversations about the future of surgical technology.

Thank you to everyone who joined us and showed interest in our work. We look forward to more opportunities to share our passion and advancements with the surgical robotics community!

We’re delighted to share that 6 papers from our lab have been accepted at IEEE ROBIO 2024 (https://lnkd.in/gXQYD7By)!

Our team has made significant contributions to the field of robotic surgery, with a diverse range of research topics

including:

– Neural Rendering

– Gaussian Splatting

– Registration and Reconstruction

– Augmented Reality for surgical planning and training

– Soft Continuum Robots

– Vision-guided surgery

Get a sneak peek at our digest figures below. We’ll be sharing more details soon! If you’re attending #ROBIO2024 in Bangkok,

we’d love to connect and discuss potential collaborations!

Let’s build connections and drive innovation together!

Our paper entitled “LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion”, led by our former lab member Tong Chen, Qingcheng Lyu, and our PhD student Long Bai, has been awarded the 🎊MICCAI 2024 Best Paper Runner-Up!🎊

This is a collaborative work between the lab of Prof Luping Zhou from The University of Sydney, our #LabREN (http://www.labren.org/mm/), and Qilu Hospital of Shandong University. Congrats to all coauthors!!!

We have also ranked #2nd in the very competitive BraTS Challenge on Sub-Sahara-Africa Adult Glioma (BraTS-SSA)! Our methodology is so-called “Transferring Knowledge from High-Quality to Low-Quality MRI for Adult Glioma Diagnosis”. Stay tuned for more updates!

Congrats to Team members: Yanguang Zhao, Long Bai, Zhaoxi Zhang, and Prof Hongliang Ren from #LabREN at The Chinese University of Hong Kong, Dr. Yanan Wu from China Medical University, and Dr. Mobarakol Islam from University College London.

Robotic endoscopes play a crucial role in diagnosing gastrointestinal disease and performing tumor resections. While current research primarily focuses on autonomously controlling rigid robots, establishing control models for flexible robots remains challenging. To address this, model-free deep reinforcement learning (DRL) presents a promising approach for enabling agents to make decisions under uncertainty.

In this paper, we investigate the control policy of a flexible endoscope using Simulation Open Framework Architecture (SOFA) platform. We design a flexible tendon-driven robotic endoscope (TDRE) and develop a custom simulation environment within SOFA to train DRL agents. Our approach involves implementing the Proximal Policy Optimization (PPO) algorithm to approximate an optimal policy for trajectory planning. The optimal policy facilitates trajectory tracking tasks for the TDRE’s end-effector, such as circle trajectories and action disturbances, without requiring fine-tuning policy network parameters. Experimental results demonstrate that our approach achieves near real-time performance (30 FPS). The feedforward neural network of the policy provides feedback, enabling closed-loop control of TDRE. Furthermore, our experiments show that the navigation success rate of TDRE exceeds 90% within a tolerant error of 3 mm in free space. Notably, compared to direct training with contact, navigation tasks with contact retrained by a pre-trained policy in free space exhibit enhanced navigation capabilities.

Paper link: https://lnkd.in/gDH5xYA5

Co-authors: Chi Kit Ng; Huxin Gao; Tian-Ao Ren; Sam, Jiewen Lai; Hongliang Ren

We are thrilled to share that our latest research paper “Enhancing Anti-interference of Magnetic Tracking: A MagRobustNet-based Framework with Self-supervised Anomaly Detection and Measurements Recovery” has been accepted by IEEE Transactions on Industrial Informatics!

Magnetic tracking technology often suffers from diverse and unpredictable interferences in practical applications, such as hard-/soft-iron interferences and sensor saturation, leading to reduced localization accuracy or even tracking failure.

To address these issues, we propose a MagRobustNet-based framework with anomaly detection and measurement recovery. In the first step, disjoint mask sets are used in conjunction with MagRobustNet to detect anomalous measurements subject to disturbances. In the second step, the interfered regions are masked, and MagRobustNet is applied again to recover their expected measurements from neighboring normal data.

Our proposed method not only enhances the tracking system’s anti-interference capability, but also indicates the interfered regions, offering a new potential diagnostic method for localizing ingested foreign bodies in clinical practice.

Check out our video demonstration at https://lnkd.in/g9TNnsA4

Stay tuned for the paper publication!

Congrats to all co-authors: Shijian Su, Huxin Gao, and Hongliang Ren from the Department of Electronic Engineering, The Chinese University of Hong Kong; Hai Lan and Houde Dai from Quanzhou Institute of Equipment Manufacturing, Haixi Institute, CAS.