In this work, through incorporating a set of learnable parameters to prompt the learning targets, the diffusion model can effectively address the unified illumination correction challenge in capsule endoscopy. We also propose a new capsule endoscopy dataset including underexposed and overexposed images, as well as the ground truth.
Thanks to all of our collaborators from multiple institutions: Long Bai, Qiaozhi Tan, Zhicheng He, Sishen YUAN, Prof. Hongliang Ren from CUHK & SZRI, Tong Chen from USYD, Wan Jun Nah from Universiti Malaya, Yanheng Li from CityU HK, Prof. Zhen CHEN, Prof. Jinlin Wu, Prof. Hongbin Liu from CAIR HK, Dr. Mobarakol Islam from WEISS, UCL, and Dr. Zhen Li from Qilu Hospital of SDU.
We’re excited to share our latest research on the Segment Anything Model (SAM) 2. This empirical evaluation uncovers SAM 2’s robustness and generalization capabilities in surgical image/video segmentation, a critical component for enhancing precision and safety in the operating room.
๐ฌ **Key Findings**:
– In general, SAM 2 outperforms its predecessor in instrument segmentation, showing a much improved zero-shot generalization capability to the surgical domain.
– Utilizing bounding box prompts, SAM 2 achieves remarkable results, setting a new benchmark in the surgical image segmentation.
– With a single point as the prompt on the first frame, SAM 2 demonstrates substantial improvements on video segmentation over SAM, which requires point prompts on every frames. This suggests great potential in addressing video-based surgical tasks.
– Resilience Under Common Corruptions: SAM 2 shows impressive robustness against real-world image corruption, maintaining performance under various challenges such as compression, noise, and blur.
๐ง **Practical Implications**:
– With faster inference speeds, SAM 2 is poised to provide quick, accurate segmentation, making it a valuable asset in the clinical setting.
๐ **Learn More**:
For those interested in the technical depth, our paper is available on [arXiv](https://lnkd.in/gHfdrvj3).
We’re eager to engage with the community and explore how SAM 2 can revolutionize surgical applications.
In our recent work, “Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery”, which was published in IEEE Transactions on Medical Imaging, we propose a state-of-the-art framework for continual semantic segmentation in robotic surgery. This breakthrough addresses catastrophic forgetting in DNNs, enhancing surgical precision without compromising patient privacy.
๐ Privacy-First Synthetic Data: We’ve crafted a solution that blends open-source instrument data with synthesized backgrounds, ensuring real patient data remains confidential.
๐ก Innovative Features:
– Class-Aware Temperature Normalization (CAT) to prevent forgetting of previously learned tasks.
– Multi-Scale Shifted-Feature Distillation (SD) to preserve spatial relationships for robust feature learning.
Check the paper at https://lnkd.in/eTy8KAC5
Code is also available at https://lnkd.in/eMzNs2Be
Join us in the breathtaking landscapes of ๐๐ก๐๐ง๐ ๐ฒ๐, China for the ๐๐๐๐ ๐๐ง๐ญ๐๐ซ๐ง๐๐ญ๐ข๐จ๐ง๐๐ฅ ๐๐จ๐ง๐๐๐ซ๐๐ง๐๐ ๐จ๐ง ๐๐ข๐จ๐ฆ๐ข๐ฆ๐๐ญ๐ข๐ ๐๐ง๐ญ๐๐ฅ๐ฅ๐ข๐ ๐๐ง๐๐ ๐๐ง๐ ๐๐จ๐๐จ๐ญ๐ข๐๐ฌ (๐๐๐๐๐), an affiliated event of the ๐๐ Elsevier journal ๐๐ข๐จ๐ฆ๐ข๐ฆ๐๐ญ๐ข๐ ๐๐ง๐ญ๐๐ฅ๐ฅ๐ข๐ ๐๐ง๐๐ ๐๐ง๐ ๐๐จ๐๐จ๐ญ๐ข๐๐ฌ (IF 5.4).
We welcome original contributions covering: โข Biomimetic design, materials & actuation โข Bio-inspired sensing, perception & navigation โข Learning-based control & embodied AI โข Soft & adaptive robotics โข Novel real-world applications integrating theory and practice
All accepted papers will be published by Elsevier and indexed in EI & Scopus. Top-ranked submissions will earn best-paper awards and invitations to submit expanded versions to Biomimetic Intelligence and Robotics and other leading journals.
๐๐๐ฒ ๐๐๐ญ๐๐ฌ
โข Full-Paper (or Short Abstract) submissions due โ July 20, 2025
โข Acceptance notifications โ August 1, 2025
โข Registration & final manuscript โ August 10, 2025
Congratulations to the following members (Long, Beilei, Yiming) for the papers accepted and to be presented by MICCAI2024 (accepted 858 out of 2771 papers this year, reaching an acceptance rate of 31%):
Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting
EndoUIC: Promptable Diffusion Transformer for Unified Illumination Correction in Capsule Endoscopy
LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion
EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera
Congratulations to Beilei and Mobarakl for the paper “Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery, (Beilei Cui, Mobarakol Islam, Long Bai, Hongliang Ren) Shortlisted for competing for the IPCAI2024 Best Paper Award and long presentation at IPCAI2024 Barcelona, Spain.
The International Conference on Information Processing in Computer-Assisted Interventions (IPCAI) is one of the most important venues for disseminating innovative peer-reviewed research in computer-assisted surgery and minimally invasive interventions. Now in its 15th year, IPCAI is an interdisciplinary conference that attracts clinicians, engineers and computer science researchers from various backgrounds, including machine learning, robotics, computer vision, medical imaging, data science, and sensing technologies. IPCAI fosters connections and showcases high-quality research in a unique and focused two-day event. The conference is formatted specifically to actively engage the attendees.
The IPCAI was held between June 18-19 2024 in conjunction with the Computer-Assisted Radiology and Surgery (CARS) Conference in Barcelona, Spain.
Dr. Ren won the Young Researcher Award 2024, CUHK, Congratulations!
The Young Researcher Award is nominated annually by each Faculty to recognize young
academic staff with exemplary research achievements. The Award consists of a plaque and
an amount of HK$ I 00,000 in the form of a research grant.
Chi Kit received the Most Creativity Award at the CUHK Capstone Project Presentation Competition 2024 for his FYP work on enhancing autonomy in robotic surgery. Congratulations!
