Summary Introduction The increasing use of cardiac catheterisation procedures has raised concerns about occupational radiation exposure and its associated health risks for clinicians. Radiation exposure can lead to deterministic and stochastic effects, including cataract and various cancers. To minimise these risks, the ALARA (As Low As Reasonably Achievable) principle must be followed in the clinical setting by applying the available measures. Radiation protection consists of passive and active measures. Passive protection includes architectural shielding, stationary shielding, and personal protective equipment, while active protection focuses on minimising radiation during interventions, employing adjustable lead screens, modifying imaging techniques and provide feedback to improve the usage of these measures. However, current methods for measuring and providing feedback on radiation exposure are insufficient. The primary goal of this research is to find a comprehensive and improved approach to guidance and implementation of protective measures, to ensure the safety and well-being of healthcare workers who face radiation exposure in their daily practice. An integral component of achieving this goal is to create a model that calculates radiation exposure for clinicians in the cathlab with the use of a lead screen. This research aims to determine the feasibility of using dose rate data from measurements without a lead screen to estimate the dose rate in an environment where a lead screen is employed. Moreover, potential methods for communicating dose rate data to clinicians during a procedure will be explored, aiming to increase their awareness of radiation exposure and encourage the adoption of appropriate protective measures without distracting them from the procedure itself. Method Data collection is necessary to construct a model that can predict the radiation scattering. Measurements in the catheterisation laboratory were performed by placing Philips DoseAware Detectors (PDDs) at various locations and heights. Combinations of fluoroscopy or acquisition mode, anteroposterior (AP) view or a 40° tilted view of the C- arm, and the presence or absence of a lead screen, resulted in eight different setups, with each 168 measurements. In the programming process careful consideration has been given to the ease of refining and improving the model afterwards. Three potential source options for the radiation were considered: the centre of the phantom, a point where 50% of the scattering has occurred, and a 3D representation of the entire phantom. The modelled lead screen together with the source was used to create an attenuation grid, which will be used for the estimation of the effect of the lead screen. The adequacy of the estimated dose rates with the lead screen was evaluated using boxplots and counting the number of correctly estimated points. Then, the data was interpolated using Kriging. The interpolated data was visualised, and the radiation doses for the assistant and cardiologist were calculated at the chest and head levels. The exposure calculation was performed for three lead screen positions and a scenario without the lead screen. The placements considered were close to the clinician, close to the phantom, and at the edge of the phantom. To explore radiation feedback preferences, a literature review and a questionnaire for interventional cardiologists were conducted. Results Measurements were taken for eight different setups, each with 168 measurements, including the combinations of fluoroscopy or acquisition mode, anteroposterior (AP) view or a 40° tilted view of the C-arm, and the presence or absence of a lead screen. The interpolated data revealed that the dose rate is higher when the acquisition mode is used, and radiation levels are higher when the C-arm is rotated. Three different source types were incorporated into the measurements, and the accuracy of the estimations was evaluated based on whether they were within a deviation of 0.1 mSv/h from the actual measurements. The 3D source was found to be the most accurate representation of the source in the model. Visualisation of inaccurately estimated values showed that the model overestimated the amount of radiation blocked in certain cases. The radiation exposure for clinicians increased as the lead shield was positioned closer to the radiation source. A questionnaire was conducted with five interventional cardiologists to investigate their radiation safety practices. The results indicated that radiation safety is deemed important, with an average score of 8/10. The lead screen is an essential shielding component, but its placement varies, and there is uncertainty regarding its optimal positioning. Monthly reports on total radiation dose exposure were provided. The clinicians hardly paid attention to this information, as they believed that any potential harm had already occurred. The highest-rated techniques were advice on optimal lead screen position (displayed on the lead screen) and a visualisation using augmented reality that displays the scatter pattern on the monitor. Discussion and Conclusion This study addresses radiation safety in interventional cardiology by exploring protective measures. A preliminary model was developed to predict radiation exposure based on the location of the lead screen enabling the computation of the radiation dose received by clinicians during a procedure. This dose rate model helps to visualise the impact of lead screen positioning on radiation exposure, which can aid in real-time decision-making during procedures. The model also revealed that placing the lead screen closer to the clinician, rather than closer to the source, could potentially enhance radiation attenuation by a factor of 6.2. This results in a possible dose reduction up to 32.5 times. The most preferred option by the interventional cardiologists was to display the suggestion of the optimal position of the lead screen directly on the shield. A potential addition to the feedback system could be an augmented reality (AR) visualisation of the radiation effect on the monitor, clearly showing safe areas for personnel. The precise feedback mechanism should be piloted and refined to ensure seamless integration into clinical practice without distracting the clinician from the procedure itself. Understanding the limitations of the measurements and the model is crucial for optimising its application in practice and the improve the reliability. The accuracy of measurements obtained with the DoseAware badges, while sufficient for this project, could be improved by using more accurate instruments. The phantom used in the study does not accurately represent real patients, and future research should involve patient- specific inputs and more realistic phantoms. One of the key future objectives include collecting more data in different settings and positions of the C-arm, as well as investigating different positions and orientations of the ceiling-mounted lead screen. The model itself has limitations in its representation of the scattering source and interpolation methods. To improve the model, researchers should account for other sources of scatter, and assess alternative interpolation techniques using more powerful computing resources. Moreover, to calculate the received radiation dose, the model should consider the entire body, accounting for the protection provided by a lead apron and the concept of effective radiation dose. Accomplishing these objectives will allow the model to play an important role in enhancing cathlab radiation safety, benefiting the health and safety of clinicians.

This thesis investigates clinical phase recognition for cardiac catheterization purposes, focusing on coronary angiography (CAG) procedures, in the context of an increasing annual prevalence of coronary artery disease. It applies machine learning to analyze C-arm logs and video recordings, aiming to improve procedural efficiency by recognizing procedural phases. Key findings include a baseline model with 45% accuracy; an 80.73% accurate C-arm model, including predictions only for operative phases; a 63.8% accurate object detection model, effective in initial and final phases but less so in operational stages; a combined data model with 79.46% accuracy, showing enhanced performance; and a reduced granularity model achieving 88.23% accuracy, highlighting a balance between granularity and performance. The combined model promises effective CAG phase recognition, especially with reduced granularity, offering comprehensive coverage and improved accuracy. However, it faces challenges in predicting specific phases accurately. The study recognizes limitations like the random forest model's non-temporal nature and potential information loss from object detection. Future research should expand datasets, explore temporal data models, and optimize the balance between granularity and performance for clinical applicability. In conclusion, the thesis contributes to SPR in cardiac catheterization labs, particularly in CAG, demonstrating the potential of machine learning models using C-arm and video data for phase recognition, which could enhance operational efficiency and patient care quality in cardiovascular interventions. Further research is needed to refine these models for clinical use.

Problem: One of the biggest challenges in hospitals today is improving efficiency, (patient) safety and quality of care while cutting on costs. A current reoccurring challenge in the operation department is the coordination of the components involved in making a surgery successful. One of those components is the set of surgical instruments. They undergo a cyclic process using reprocessing methods during which various challenges arise. A few of these challenges are the complex and time-consuming instrument counts before, during and after surgery. Research question: Various technological aids have been proposed to automate the instrument counts. Previous technologies all showed their own flaws when they were tested in the operation room (OR). A new research field for the purpose of instrument counting is the use of computer vision. Computer vision shows great promise as it is already widely used to detect and recognize objects in digital images. However, before developing an algorithm to be used specifically for surgical instrument counting in and around the OR, the various activities, working methods and environmental factors are investigated first. This is done using the following research question: "What is the feasibility of using a computer vision algorithm to automatically detect and count surgical instruments and what are potential factors that influence the performance and the implementation in the OR?". Methods: The research question is answered using a converting thesis structure. Firstly, the most general steps of the instrument cycle are outlined and a description is given of a SIFT computer vision algorithm. SIFT is the proposed algorithm type for the investigated application. Secondly, the more specific steps of the instrument cycle at the Reinier de Graaf Gasthuis (RdGG) are described. The result of this description are different application options and different design scenarios. Thirdly, one application type and design scenario is selected: instrument counts in the OR. A blueprint is given for testing a SIFT algorithm in the OR. This blueprint could result in numerical results, valuable observations in the OR and staff survey results. Results: A total of 35 surgeries were attended. Only results from observations and the survey are shown as the algorithm itself was not tested yet. The observations showed factors that could negatively influence the algorithm’s performance. The survey results gave valuable insights into personal opinions on the value, use and implementation of the algorithm.  Conclusion: The feasibility of a current SIFT algorithm in a current ORs is low as it will not be able to automatically detect and count all instruments. There are a lot of factors that need to be taken into account to improve performance and possible implementation. They are formulated in 5 design focus points: 1) a line of sight between camera and the instrument(s), 2) dealing with instruments being taken away from and added to the table, 3) controlling the light conditions around the instrument table, 4) recognizing the specific type of some instruments and 5) showing clear feedback.

Laparoscopic suturing is one of the most difficult and time-consuming tasks in laparoscopic surgery. The long instrument shafts, two-dimensional view, and limited space for movement make simple actions, such as grasping and manipulating the needle and thread, difficult in the laparoscopic setting. To simplify the suturing process, the Hornet project was started by DEAM. The company was asked by two gynecologists to create a laparoscopic suturing device that simplifies the closure of the vaginal cuff during a total laparoscopic hysterectomy. The first prototypes that were created had promising design elements, but their suturing techniques proved difficult to execute. The modified sewing machine suturing technique was created to solve these issues, resulting in the aim of this thesis: to develop a laparoscopic suturing instrument that uses the modified sewing machine suturing technique to simplify the closure of the vaginal cuff. A new prototype of the Hornet was designed based on a list of Product Specifications. This instrument, Hornet prototype B3, was built and subsequently tested in a series of design verification tests to determine if the design meets the Product Specifications. Additionally, a series of user tests was executed to verify whether the design simplifies the closure of the vaginal cuff. In the tests, the participants placed sutures with both the Hornet and with the regular suturing method. Participants with different levels of suturing and laparoscopic experience were included to determine the effect of experience on the suturing results with the Hornet. The tests showed that the prototype simplifies the suturing process. All participants were able to place a closed suture with the Hornet, whereas only 43% of the participants placed a closed suture with the regular suturing method. The participants without laparoscopic experience had significantly shorter suturing times with the Hornet compared to regular suturing, indicating that the suturing method with the Hornet is simpler to learn. The participants with laparoscopic experience performed similarly with the Hornet and the regular suturing method, indicating that the first time the Hornet is used gives similar results to experience with regular laparoscopic suturing. From this research, it can be concluded that the Hornet prototype B3 simplifies the closure of the vaginal cuff when compared to regular suturing. To further confirm this claim, additional development and testing of the prototype is needed. Some alterations to the prototype design are required to improve its functioning and to ensure that all the product specifications are met. Additional tests are needed to investigate the extent in which the prototype simplifies the suturing process and to determine the learning curve of the Hornet.

The operating room is one of the most complex and expensive environments in the hospital. Research has been focusing on improving the efficient use of the OR time, for instance by using intraoperative data to update the planning of the OR during the day. This thesis used a deep learning network to automatically recognize surgical tools and pre-defined surgical phases present in the recordings, to ultimately track the progress of the procedure. The aim of this thesis is to assess the performance and applicability of this deep learning method for the use of image recognition in a medical environment. To ultimately predict the remaining surgery duration and improve the efficiency of the OR planning. Two datasets of laparoscopic recordings were used, one containing laparoscopic cholecystectomies and one containing total laparoscopic hysterectomies. The surgical tools and the pre-defined phases of the procedure were annotated in every recording, after which the deep learning network was trained with this data. The performance of the network was tested in multiple experiments. The results showed that the performance of the deep learning network was promising and in line with published literature, but that the results varied between recordings. An experiment using three different sized datasets showed that a larger dataset corresponded with the best results and results that varied the least between recordings. Testing the generalizability of the network showed that a network trained on one type of surgery can also be used to recognize similar tools in a different type of surgery. Important is that the tools have the same design. It was found that the most important resources for a project like this are a dedicated hardware with image recognition software and time. This thesis showed the applicability of a deep learning network to automatically recognize the progress of a surgery and provided insight into the steps that need to be taken to use it on a larger scale.