Dénes Ákos Nagy

A Framework for Semi-automatic Fiducial Localization in Volumetric Images

Fiducial localization in volumetric images is a common task performed by image-guided navigation and augmented reality systems. These systems often rely on fiducials for image-space to physical-space registration, or as easily identifiable structures for registration validation purposes. Automated methods for fiducial localization in volumetric images are available. Unfortunately, these methods are not generalizable as they explicitly utilize strong a priori knowledge, such as fiducial intensity values in CT, or known spatial configurations as part of the algorithm. Thus, manual localization has remained the most general approach, readily applicable across fiducial types and imaging modalities. The main drawbacks of manual localization are the variability and accuracy errors associated with visual localization. We describe a semi-automatic fiducial localization approach that combines the strengths of the human operator and an underlying computational system. The operator identifies the rough location of the fiducial, and the computational system accurately localizes it via intensity based registration, using the mutual information similarity measure. This approach is generic, implicitly accommodating for all fiducial types and imaging modalities. The framework was evaluated using five fiducial types and three imaging modalities. We obtained a maximal localization accuracy error of 0.35 mm, with a maximal precision variability of 0.5 mm.

Recent trends in automating robotic surgery

Eversince computer technology entered the operating room (OR), surgery has gone through one of the greatest changes in the history of medicine, and now we are foreseeing the age of the digital OR. The range of the novel applications spans from intra-operative navigation to the development of autonomous suturing tools. More recently, after 20 years of experience with pre-programmed, image-guided and teleoperational surgical robots, a new trend is emerging: to create autonomous, or partially autonomous surgical robots. These advanced systems are intended to fit into the surgical workflow, and to help the surgeon in the least intrusive way possible. It is only the recent development of surgical-digital applications which can overcome a the barrier of the cognitive load on surgeons, to become able to completely control of the operating field. Three major trends have been identified in current products and advanced research prototypes: 1) aiming to improve camera handling 2) Sub-task automation 3) complete automation.

Surgical robotics — Born in space

With the introduction of telerobotic systems, it has become possible for surgeons to perform medical operations at greater physical distances from their patients. Whether in an adjacent room or on another continent, these systems enable greater flexibility in mitigating adverse surgical conditions. These ideas originally came from the space research, where further needs emerged to advance robots that could resolve surgical cases previously not treatable. The concept of providing surgical aid to astronauts in outer space yielded to telerobotic surgical care on Earth, benefiting around 1 million patients per year. As the field continues to develop and becomes more prevalent, it is worth looking back to the origins of the technology and the early days of robotic telesurgery. While many of the early prototypes and technologies never reached patients, their engineering components and innovative concepts directly lead to the birth of modern surgical robots.

CogInfoCom-Driven Surgical Skill Training and Assessment: Developing a Novel Anatomical Phantom and Performance Assessment Method for Laparoscopic Prostatectomy Training

The systematic assessment and development of human learning capabilities is one of the biggest challenges in applied sciences. It can be observed within the medical domain how evidence-based paradigms are gradually gaining space. In this chapter, the development process of a laparoscopic box trainer is introduced. A simulator including a phantom for prostatectomy is described, which feeds into medical staff training and skill assessment. An overview of laparoscopic surgical simulators is provided. Based on the state of the art and our previous experience, a clear need was formulated to develop a partially physical, partially computer-integrated simulator. To gain a better understanding of the cognitive load and physical stress, force measurement was used in the test environment. The force and time data were used to evaluate the performance of the participant. A new assessment method was described, which can be used to point out the weak aspects of surgical technique, and the participants can do this on their own. Computer-integrated assistive technologies for surgical education are believed to rapidly become the gold standard on a global scale.

Ontology-Based Surgical Subtask Automation, Automating Blunt Dissection

Automation of surgical processes (SPs) is an utterly complex, yet highly demanded feature by medical experts. Currently, surgical tools with advanced sensory and diagnostic capabilities are only av...

Joint Platforms and Community Efforts in Surgical Robotics Research

Abstract In modern medical research and development, the variety of research tools has extended in the previous years. Exploiting the benefits of shared hardware platforms and software frameworks is crucial to keep up with the technological development rate. Sharing knowledge in terms of algorithms, applications and instruments allows researchers to help each other’s work effectively. Community workshops and publications provide a throughout overview of system design, capabilities, know-how sharing and limitations. This paper provides sneak peek into the emerging collaborative platforms, focusing on available open-source research kits, software frameworks, cloud applications, teleoperation training environments and shared domain ontologies.