Tag: CUHK

๐ŸŽŠ Exciting News!!!๐ŸŽŠ

  By

We will present 4 main conference papers and 4 workshop/challenge papers in #MICCAI2024, Marrakesh, Morocco. These cover interesting topics such as #DDPM, Low-light Image Enhancement, #GaussianSplatting, Depth Reconstruction, Data Robustness, and Medical Image Segmentation. Congrates to all of our awesome collaborators! Do drop by our poster and oral sessions if you are interested in our work!

Main Conference 1: EndoUIC: Promptable Diffusion Transformer for Unified Illumination Correction in Capsule Endoscopy

Long Bai, Oct 08, Poster Session 3, 10:30 – 11:30

Poster ID: T-AM-091

Paper: https://lnkd.in/gV5MzKct

Code: https://lnkd.in/ghYauAGM

Main Conference 2: Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting

YIMING HUANG, Oct 08, Poster Session 4, 15:00 – 16:30 

Post ID: T-PM-074

Paper: https://lnkd.in/gtDwbyWg

Code: https://lnkd.in/ggaDgVxW

Main Conference 3: EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

Beilei Cui, Oct 08, Poster Session 4, 15:00 – 16:30

Poster ID: T-PM-076

Paper: https://lnkd.in/gQgpFFpq

Code: https://lnkd.in/g_bfk56S

Main Conference 4: LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion

Tong Chen, Oct 09, Oral Session 16, 13:30 – 15:00, Poster Session 6, 15:00 – 16:30

Poster ID: W-PM-154

Paper: https://lnkd.in/gybFHPmu

Code: https://lnkd.in/gmmWXCnd

Workshop 1: A Review of 3D Reconstruction Techniques for Deformable Tissues in Robotic Surgery

Long Bai, Oct 06, Oral & Poster

Embodied AI and Robotics for HealTHcare (EARTH) Workshop

Paper: https://lnkd.in/gD6juYyV

Code: https://lnkd.in/gnwhzrQn

Workshop 2: Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data

Beilei Cui, Oct 10, Poster, 15:10 – 16:05

9th International Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI)

Paper: https://lnkd.in/gnWtK37B

Code: https://lnkd.in/gjc2FBWT

Challenge 1: Transferring Knowledge from High-Quality to Low-Quality CT for Adult Glioma Diagnosis

Long Bai, Oct 06, Oral (Top-performing Team)

BraTS Challenge on Sub-Sahara-Africa Adult Glioma (BraTS-SSA)

Challenge 2: Ensembling Multi-scale Networks for Accurate Adult Glioma Diagnosis

Long Bai, Oct 06, Poster

BraTS Adult Glioma Post Treatment Challenge (BraTS-GLI)

We are thrilled to share our journal paper titled โ€œPatient-mounted NeuroOCT for Targeted Minimally-invasive Micro-resolution Volumetric Imaging in Brain In Vivoโ€ accepted to Advanced Intelligent Systems! In this paper, we introduce an innovative โœจ wearable neuro optical coherence tomography (neuroOCT) โœจ system, featuring a lightweight hydraulic 5-DoF skullbot combined with a neuroendoscope approximately 0.6 mm in diameter.

  By

This system facilitates targeted, minimally invasive neuroimaging with an axial resolution of about 2.4 ฮผm and a transverse resolution of around 4.5 ฮผm in the deep brain in vivo. The skullbot enables precise deployment of the neuroendoscope with a targeting accuracy of ยฑ1.5 mm transversely and ยฑ0.25 mm longitudinally, confirmed through optical phantom studies. The skullbot can be securely attached to the head, allowing for motion-insensitive stereotactic imaging within the brain.

We validated the system’s capabilities by demonstrating targeted imaging of a tumor in a brain phantom and conducting in vivo micro-resolution volumetric neuroimaging of fine structures within a mouse brain. This advanced device offers in situ disease evaluation at a micro- resolution level and serves as a promising intraoperative imaging tool, complementing existing4 clinical whole-brain imaging modalities such as MRI.

Our findings suggest that the neuroOCT system can significantly advance minimally invasive high-resolution targeted neuroendoscopy, thereby improving patient safety during neurosurgical procedures.

The paper will be available at https://lnkd.in/gFREQFbS

Stay tuned!

This is a collabrative work between CUHK ABI Lab (https://lnkd.in/gUuzQqDt) and REN Lab (http://www.labren.org/mm/).

Congrates to authors: Chao Xu+, Zhiwei Fang+, Huxin Gao, Tinghua Zhang, Tao Zhang, Peng Liu, Hongliang Ren*, and Wu ‘Scott’ YUAN*

No alternative text description for this image
No alternative text description for this image
No alternative text description for this image

We are excited to share our latest research entitled โ€œDisentangling Contact Location for Stretchable Tactile Sensors from Soft Waveguide Ultrasonic Scatter Signalsโ€ collaborated by Zhiheng Li and Yuan Lin, has been accepted by Advanced Intelligent Systems!

  By

Flexible tactile sensors have garnered significant attention due to their flexible, lightweight, and comfortable nature, catering to the growing demands in various applications such as human-machine interfaces, healthcare, and robotics. However, it remains a challenge to achieve precise contact location sensing that is decoupled from sensor strain and touching forces. Thus, this paper proposes a novel data-driven approach for force contact location sensing (FCLS), based on scatter signals (SS) of the ultrasonic waveguide, with the influence of sensor strain and forces. This method utilizes deep CNNs to fuse local and global features of the soft waveguide ultrasonic SS and an MLP to perform regression modeling on the fused features and FCL, thereby obtaining FCL information. The experimental results indicate that the accuracy of the proposed FCLS method has an MAE loss of 0.627 mm and an MRE loss of 3.19%.

The full paper will be available at: https://lnkd.in/gKr22Uvi

Co-Authors: Zhiheng Li (CUHK), Yuan Lin (SJTU), Peter B. Shull (SJTU) and Hongliang Ren (CUHK). The first two authors contributed equally to this work.

diagram

Our latest research work titled โ€œA Real-Time Self-Sensing Approach to Sensor Array Configuration Fusing Prior Knowledge for Reconfigurable Magnetic Tracking Systemsโ€ has been accepted by IEEE/ASME Transactions on Mechatronics!

  By

Impact:

The reconfigurability of magnetic tracking systems (MTSs) allows for its application in workspaces of different sizes. For instance, with appropriate configuration adjustments, it can be utilized for tasks such as tongue tracking in the head, tracheal intubation navigation in the neck, and even muscle tracking in the legs and arms. However, the dynamic changes in sensor array configuration, known as deformation, caused by posture changes during long-duration examinations, impose significant challenges on MTSs that heavily rely on magnetometer poses.

Here we propose a real-time self-sensing method based on the sensor array structural model and magnetic dipole model, which simultaneously estimates the magnet pose and the hinge angles on the sensor array. The self-sensing capability opens up a new way for perceiving the morphology of origami robots and measuring the curvature of flexible catheters

Paper: https://lnkd.in/dnmcvusm

Authors: Shijian Su; Xindi Yang; Zhen Li; Hongliang Ren

No alternative text description for this image
No alternative text description for this image

We are excited to share our paper “OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgery” which has been accepted for IEEE International Conference on Robotics and Automation (ICRA) 2024!

  By

In this work, we tackle the challenge of open-set recognition in surgical robotics. Our novel OSSAR framework improves the ability to classify known surgical activities while also detecting unknown activities that weren’t seen during training.

Key contributions:

โ€ข A hyperspherical reciprocal point strategy to better separate known and unknown classes

โ€ข A calibration technique to reduce overconfident misclassifications 

โ€ข New open-set benchmarks on the JIGSAWS dataset and our novel DREAMS dataset for endoscopic procedures

โ€ข State-of-the-art performance on open-set surgical activity recognition tasks

This research takes an important step towards more robust and generalizable AI systems for surgical robots. We hope it will help pave the way for safer and more capable robot-assisted surgeries.

Thank all the amazing co-authors Long Bai, Guankun Wang, Jie Wang, Xiaoxiao Yang, Huxin Gao, Xin Liang, An Wang, Mobarakol Islam, and Hongliang Ren

and our institutions (The Chinese University of Hong Kong, Beijing Institute of Technology, Qilu Hospital of Shandong University, Tongji University, University College London, National University of Singapore) for their support.

You can find more details in our paper https://lnkd.in/gDsjVDSP

No alternative text description for this image
No alternative text description for this image
No alternative text description for this image
No alternative text description for this image

We are happy to share our journal paper titled โ€œAMagPoseNet: Real-Time 6-DoF Magnet Pose Estimation by Dual-Domain Few-Shot Learning from Prior Modelโ€ published in IEEE Transactions on Industrial Informatics!

  By

Impact: Traditional magnetic tracking approaches based on mathematical models and optimization algorithms are computationally intensive, depend on initial guesses, and do not guarantee convergence to a global optimum. Here we propose an annular magnet pose estimation network (called AMagPoseNet) based on dual-domain few-shot learning from a prior mathematical model, featuring the following advantages:

1) Higher localization accuracy (1.87ยฑ1.14 mm, 1.89ยฑ0.81ยฐ), especially in the near field;

2) Enhanced robustness, as AMagPoseNet is just a single feed-forward neural network that does not rely on initial guesses and avoids the risk of falling into local optima;

3) Lower computational latency (2.08ยฑ0.02 ms) since the magnet pose is directly regressed from a single feed-forward network rather than iterative optimization;

4) Real-time estimation of 6-DoF pose if discriminative magnetic field features are provided.

Paper: https://lnkd.in/gXBSQ-hG

Dataset: https://lnkd.in/gXEFfwfA

Authors: Shijian Su; Sishen YUAN; Mengya Xu; Huxin Gao; Xiaoxiao Yang; and Prof Hongliang Ren

No alternative text description for this image
No alternative text description for this image

Excited to share our journal paper entitled โ€œMagnetic Tracking With Real-Time Geomagnetic Vector Separation for Robotic Dockable Chargingโ€ published in IEEE Transactions on Intelligent Transportation Systems! ๐ŸŽ‰

  By

Great collaboration between the Chinese University of Hong Kong and the Quanzhou Institute of Equipment Manufacturing, Haixi Institutes, Chinese Academy of Sciences. ๐Ÿค

The superposition of the geomagnetic vector and the magnetic field vector generated by the permanent magnet (PM) leads to the degrading of magnetic tracking performance. Here we present a real-time geomagnetic-vector-separation method to estimate the PM pose and geomagnetic vector simultaneously. This advancement promises to revolutionize autonomous robotic operations, offering a robust solution for seamless and reliable self-charging mechanisms, with far-reaching implications for various industries.

Paper: https://lnkd.in/gAbr82Dp

Authors: Shijian Su; Houde Dai; Yuanchao Zhang; Sishen YUAN; Prof Shuang Song and Prof Hongliang Ren.

No alternative text description for this image
No alternative text description for this image

Our latest research work titled โ€œA Wearable, Reconfigurable, and Modular Magnetic Tracking System for Wireless Capsule Robotsโ€ has been accepted by IEEE Transactions on Industrial Informatics! ๐ŸŽ‰

  By

Existing wearable MTSs are fixed in size and cannot accommodate patients with diverse abdominal circumferences. Here we propose a wearable and reconfigurable MTS. First, we design a reconfigurable sensor array inspired by the structure of bamboo slips, allowing it to conform to the abdominal surface and accommodate individuals with different abdominal circumferences. Next, we formulate a magnetic tracking optimization problem based on the magnetic dipole model and our established kinematic model of the reconfigurable sensor array.

Our proposed system is portable, reconfigurable and adaptable to different abdominal circumferences, offering valuable technological means for diagnosing and treating gastrointestinal disorders.

Paper: https://lnkd.in/g7HqPARr

Authors: Shijian Su; Sishen YUAN; Zhen Li; Yan Ma; Miaomiao Ma and Prof Hongliang Ren

No alternative text description for this image
No alternative text description for this image

We are happy to share our work entitled โ€œChained Flexible Capsule Endoscope: Unraveling the Conundrum of Size Limitations and Functional Integration for Gastrointestinal Transitivityโ€, will be presented in 2024 IEEE International Conference on Robotics and Automation (ICRA2024).

  By

Capsule endoscopes, predominantly serving diagnostic functions, provide lucid internal imagery but are devoid of surgical or therapeutic capabilities. Consequently, despite lesion detection, physicians frequently resort to traditional endoscopic or open surgical procedures for treatment, resulting in more complex, potentially risky interventions.

To surmount these limitations, this study introduces a chained flexible capsule endoscope (FCE) design concept, specifically conceived to navigate the inherent volume constraints of capsule endoscopes whilst augmenting their therapeutic functionalities. The FCEโ€™s distinctive flexibility originates from a conventional rotating joint design and the incision pattern in the flexible material. In vitro experiments validated the passive navigation ability of the FCE in rugged intestinal tracts. Further, the FCE demonstrates consistent reptile-like peristalsis under the influence of an external magnetic field, and possesses the capability for film expansion and disintegration under high-frequency electromagnetic stimulation. These findings illuminate a promising path toward amplifying the therapeutic capacities of capsule endoscopes without necessitating a size compromise.

Author team: Sishen YUAN, Guang Li, Baijia Liang, Lailu Li, Qingzhuo Zheng, and Prof Hongliang Ren from the Chinese University of Hong Kong, Prof Shuang Song from Harbin Institute of Technology, Shenzhen, and Dr Zhen Li from Qilu Hospital of Shandong University.

For details, please check the paper at https://lnkd.in/gcq2HB9H

diagram

We are excited to share our recent work by Sishen Yuan et al., entitled โ€œMagnetic-Guided Flexible Origami Robot toward Long-Term Phototherapy of H. pylori in the Stomachโ€ presented in 2024 IEEE International Conference on Robotics and Automation (ICRA2024).

  By

Helicobacter pylori, a pervasive bacterial infection associated with gastrointestinal disorders such as gastritis, peptic ulcer disease, and gastric cancer, impacts approximately 50% of the global population. The efficacy of standard clinical eradication therapies is diminishing due to the rise of antibiotic-resistant strains, necessitating alternative treatment strategies. Photodynamic therapy (PDT) emerges as a promising prospect in this context.

This study presents the development and implementation of a magnetically-guided origami robot, incorporating flexible printed circuit units for sustained and stable phototherapy of Helicobacter pylori. Each integrated unit is equipped with wireless charging capabilities, producing an optimal power output that can concurrently illuminate up to 15 LEDs at their maximum intensity. Crucially, these units can be remotely manipulated via a magnetic field, facilitating both translational and rotational movements.

We propose an open-loop manual control sequence that allows the formation of a stable, compliant triangular structure through the interaction of internal magnets. This adaptable configuration is uniquely designed to withstand the dynamic squeezing environment prevalent in real-world gastric applications. The research herein represents a significant stride in leveraging technology for innovative medical solutions, particularly in the management of antibiotic-resistant Helicobacter pylori infections.

This is a collabrative work by Sishen YUAN, Baijia Liang, Po Wa Wong, Mingjing Xu, Chi Hsuan Li and Prof Hongliang Ren from The Chinese University of Hong Kong, and Dr. Zhen Li from Qilu Hospital of Shandong University.

For details, please check the paper at https://lnkd.in/g3VGZaA3

diagram