Surgical navigation techniques enable accurate, safe and minimally invasive treatments for patients in modern operating rooms, through robust medical devices/robots and together with automatic algorithms.
The typical procedures in surgical navigation normally go in a certain way. Before surgery, patients undergo MRI or CT scans for disease diagnosis and surgical planning. Accurate disease diagnosis takes up much time for the radiologists. During surgery, surgeons will conduct the operations with or without the help of robots whose design, modelling and control are essential for the robot-assisted surgical system. The surgical planning is done in the image space while the surgical operation is conducted in the patient space. Thus, the two spaces have to be rigidly aligned for orthopaedic surgery or non-rigidly aligned for a liver or prostate surgery, in a fast and accurate manner. The modalities in a surgical navigation system will inevitably own localisation error, which requires the system to have the ability to predict the error magnitudes and spatial distributions, in order to help the surgeons or medical robots make decisions interventionally. Besides, automatic surgical instrument segmentation is a prerequisite for an intelligent robotic surgical system. We believe both the system designs and algorithmic developments will be crucial for a successful surgical procedure.
Researchers have investigated all aspects around the concept of surgical navigation, towards an intelligent, accurate and robust surgical system. Recently, deep-learning techniques have demonstrated good performances for tasks in intelligent operating rooms, such as medical image segmentation/registration, surgical instrument segmentation, surgical phase recognition, etc. Beyond that, artificial intelligence has also brought tremendous change to the research fields of design, control, modelling of typical medical robots.
Topics aimed at presenting the latest developments and advances in the intelligent modern surgical system, including both theoretical/algorithmic contributions and practical solutions, would be welcome in this Research Topic.
In this Research Topic, we welcome original research articles and review articles focusing on the latest developments in all aspects of surgical navigation and medical robotics.
All articles, either introducing a new medical robotic system or describing novel clinically-relevant AI/conventional algorithms for surgical navigation or disease diagnosis, are to be welcomed.
Topics of interest include and not limited to:
- Medical robotics (e.g., flexible robotics, continuum robots);
- Surgical navigation, image-guided surgery and robot-assisted surgical system;
- Mono/multi-modality medical image registration;
- Image-to-patient registration algorithms (i.e., point cloud registration);
- Medical image segmentation methods (i.e., organs, lesions);
- Computer-assisted diagnosis;
- Uncertainty propagation/estimation/analysis in surgical navigation;
- Interventional organ motion modelling;
- Automatic surgical instrument segmentation in endoscopic images;
- Design, modelling and controlling methods for medical robots;
- Machine learning and AI for surgical data science.
Surgical navigation techniques enable accurate, safe and minimally invasive treatments for patients in modern operating rooms, through robust medical devices/robots and together with automatic algorithms.
The typical procedures in surgical navigation normally go in a certain way. Before surgery, patients undergo MRI or CT scans for disease diagnosis and surgical planning. Accurate disease diagnosis takes up much time for the radiologists. During surgery, surgeons will conduct the operations with or without the help of robots whose design, modelling and control are essential for the robot-assisted surgical system. The surgical planning is done in the image space while the surgical operation is conducted in the patient space. Thus, the two spaces have to be rigidly aligned for orthopaedic surgery or non-rigidly aligned for a liver or prostate surgery, in a fast and accurate manner. The modalities in a surgical navigation system will inevitably own localisation error, which requires the system to have the ability to predict the error magnitudes and spatial distributions, in order to help the surgeons or medical robots make decisions interventionally. Besides, automatic surgical instrument segmentation is a prerequisite for an intelligent robotic surgical system. We believe both the system designs and algorithmic developments will be crucial for a successful surgical procedure.
Researchers have investigated all aspects around the concept of surgical navigation, towards an intelligent, accurate and robust surgical system. Recently, deep-learning techniques have demonstrated good performances for tasks in intelligent operating rooms, such as medical image segmentation/registration, surgical instrument segmentation, surgical phase recognition, etc. Beyond that, artificial intelligence has also brought tremendous change to the research fields of design, control, modelling of typical medical robots.
Topics aimed at presenting the latest developments and advances in the intelligent modern surgical system, including both theoretical/algorithmic contributions and practical solutions, would be welcome in this Research Topic.
In this Research Topic, we welcome original research articles and review articles focusing on the latest developments in all aspects of surgical navigation and medical robotics.
All articles, either introducing a new medical robotic system or describing novel clinically-relevant AI/conventional algorithms for surgical navigation or disease diagnosis, are to be welcomed.
Topics of interest include and not limited to:
- Medical robotics (e.g., flexible robotics, continuum robots);
- Surgical navigation, image-guided surgery and robot-assisted surgical system;
- Mono/multi-modality medical image registration;
- Image-to-patient registration algorithms (i.e., point cloud registration);
- Medical image segmentation methods (i.e., organs, lesions);
- Computer-assisted diagnosis;
- Uncertainty propagation/estimation/analysis in surgical navigation;
- Interventional organ motion modelling;
- Automatic surgical instrument segmentation in endoscopic images;
- Design, modelling and controlling methods for medical robots;
- Machine learning and AI for surgical data science.