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.

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.