Karl Storz (Germany)

Minimally invasive surgery (MIS) emerged with the aim of replacing traditional open surgery, reducing blood loss and increasing patient comfort. One of the most common MIS procedures is laparoscopy. These procedures require small incisions, frequently for placing instruments and cameras, which allows the observation of the inside of the abdominal cavity. Currently, several robotic systems hold the camera and are controlled by the surgeon who performs the surgery, however, there is a necessity to automate the process. Aiming to achieve this goal, several studies have been performed in this field on image processing to estimate the ideal position of the camera. However, there is a need to transpose these methods to devices. In this sense, this work presents a proof-of-concept of a robotic system that automatically tracks a specific point during the surgery. An experiment was performed with the aim of having the robot holding the camera follow an auxiliary robot that performed movements on different axis. The results were satisfactory, with a low latency in rotational movements (0.061s in movements on the γ and 0.011s on the β rotations) and it proved to be accurate when performing translations because it has an average error of 1.76mm in 30mm translations. However, we observed a moderate displacement of the trocar point throughout the rotations (5.43mm in γ and 11.55mm in β). The results obtained show the effectiveness of the proposed method for performing a dynamic trocar point. In the future, the method will have to be validated with real-time image tracking methods.

Semantic segmentation of anatomical structures in laparoscopic videos is a crucial task to enable the development of new computer-assisted systems that can assist surgeons during surgery. However, this is a difficult task due to artifacts and similar visual characteristics of anatomical structures on the laparoscopic videos. Recently, deep learning algorithms have been showed promising results on the segmentation of laparoscopic instruments. However, due to the lack of large public datasets for semantic segmentation of anatomical structures, there are only a few studies on this task. In this work, we evaluate the performance of five networks, namely U-Net, U-Net++, DynUNet, UNETR and DeepLabV3+, for segmentation of laparoscopic cholecystectomy images from the recently released CholecSeg8k dataset. To the best of our knowledge, this is the first benchmark performed on this dataset. Training was performed with dice loss. The networks were evaluated on segmentation of 8 anatomical structures and instruments, performance was quantified through the dice coefficient, intersection over union, recall, and precision. Apart from the U-Net, all networks obtained scores similar to each other, with the U-Net++ being the network with the best overall score with a mean Dice value of 0.62. Overall, the results show that there is still room for improvement in the segmentation of anatomical structures from laparoscopic videos. Clinical Relevance- The results of this study show the potential of deep neural networks for the segmentation of anatomical structures in laparoscopic images which can later be incorporated into computer-aided systems for surgeons.

Background: Cytoreductive surgery (CRS) in combination with hyperthermic intraperitoneal chemotherapy (HIPEC) is an option in advanced peritoneal sarcomatosis. Nevertheless, CRS and HIPEC are not successful in all patients. An enhancement of HIPEC using photodynamic therapy might be beneficial. Therefore, a combination of the photosensitizer Hypericin (HYP) with HIPEC was evaluated in an animal model. Procedure: An established HIPEC animal model for rhabdomyosarcoma (NOD/LtSz-scid IL2Rγnullmice, n=80) was used. All groups received HYP (100 µg/200 µl) intraperitoneally with and without cisplatin-based (30 or 60 mg/m2) HIPEC (37 or 42 °C, for 60 min) (five groups, each n=16). Tumor dissemination was documented visually and by using HYP-based fluorescence guidance. HYP-based photodynamic therapy (PDT) of the tumor was performed. Finally, tissue samples were evaluated regarding proliferation (Ki-67) and apoptosis (TUNEL). Results: HYP uptake even in smallest tumor nodes (< 1 mm) was found. HYP-based fluorescence guidance allowed a better tumor detection in comparison to visual inspection. Immunohistochemistry revealed HYP penetration across the tumor surface. HYP-based PDT without HIPEC induced marginal apoptotic effects at the tumor surface. Combining HYP with HIPEC revealed cisplatin concentration dependent decrease in proliferation capacity and induction of apoptosis across determined cell layers of the tumor surfaces. Conclusion: HYP as fluorescent photosensitizer offers an intraoperative diagnostic advantage detecting intraperitoneal tumor dissemination. The combination of HYP and cisplatin-based HIPEC was feasible in vivo showing enhanced effects on tumor proliferation and apoptosis induction across the tumor surface. Further studies combining HYP and HIPEC will follow to establish a clinical application.

To translate recent advances in medical device interoperability research into clinical practice, standards are being developed that specify precise requirements towards the network representation of particular medical devices connecting through ISO/IEEE 11073 SDC. The present contribution supplements this protocol standard with specific models for endoscopic camera systems, light sources, insufflators, and pumps. Through industry consensus, these new standards provide modular means to describe the devices' capabilities and modes of interaction in a service-oriented medical device communication architecture. This enables seamless data exchange and the potential for new assistive systems to support the caregiver.

Laparoscopic surgery has revolutionised state of the art in surgical health care. However, its complexity puts a significant burden on the surgeon's cognitive resources resulting in major biliary injuries. With the increasing number of laparoscopic surgeries, it is crucial to identify surgeons' cognitive loads (CL) and levels of focus in real time to give them unobtrusive feedback when detecting the suboptimal level of attention. Assuming that the experts appear to be more focused on attention, we investigate how the skill level of surgeons during live surgery is reflected through eye metrics. Forty-two laparoscopic surgeries have been conducted with four surgeons who have different expertise levels. Concerning eye metrics, we have used six metrics which belong to fixation and pupillary based metrics. With the use of mean, standard deviation and ANOVA test we have proven three reliable metrics which we can use to differentiate the skill level during live surgeries. In future studies, these three metrics will be used to classify the surgeons' cognitive load and level of focus during the live surgery using machine learning techniques.

Abstract Smoke in laparoscopic videos usually appears due to the use of electrocautery when cutting or coagulating tissues. Therefore, detecting smoke can be used for event-based annotation in laparoscopic surgeries by retrieving the events associated with the electrocauterization. Furthermore, smoke detection can also be used for automatic smoke removal. However, detecting smoke in laparoscopic video is a challenge because of the changeability of smoke patterns, the moving camera and the different lighting conditions. In this paper, we present a video-based smoke detection algorithm to detect smoke of different densities such as fog, low and high density in laparoscopic videos. The proposed method depends on extracting various visual features from the laparoscopic images and providing them to support vector machine (SVM) classifier. Features are based on motion, colour and texture patterns of the smoke. We validated our algorithm using experimental evaluation on four laparoscopic cholecystectomy videos. These four videos were manually annotated by defining every frame as smoke or non-smoke frame. The algorithm was applied to the videos by using different feature combinations for classification. Experimental results show that the combination of all proposed features gives the best classification performance. The overall accuracy (i.e. correctly classified frames) is around 84%, with the sensitivity (i.e. correctly detected smoke frames) and the specificity (i.e. correctly detected non-smoke frames) are 89% and 80%, respectively.

Abstract Video-based smoke detection in laparoscopic surgery has different potential applications, such as the automatic addressing of surgical events associated with the electrocauterization task and the development of automatic smoke removal. In the literature, video-based smoke detection has been studied widely for fire surveillance systems. Nevertheless, the proposed methods are insufficient for smoke detection in laparoscopic videos because they often depend on assumptions which rarely hold in laparoscopic surgery such as static camera. In this paper, ten visual features based on motion, texture and colour of smoke are proposed and evaluated for smoke detection in laparoscopic videos. These features are RGB channels, energy-based feature, texture features based on gray level co-occurrence matrix (GLCM), HSV colour space feature, features based on the detection of moving regions using optical flow and the smoke colour in HSV colour space. These features were tested on four laparoscopic cholecystectomy videos. Experimental observations show that each feature can provide valuable information in performing the smoke detection task. However, each feature has weaknesses to detect the presence of smoke in some cases. By combining all proposed features smoke with high and even low density can be identified robustly and the classification accuracy increases significantly.

Diaphragmatic hernia is a quite uncommon disease, being congenital or posttraumatic. Its diagnosis is frequently accidental. Surgical treatment can be performed through the abdomen as well as through the chest. Laparoscopy and thoracoscopy offer a surgical benefit because of reduced wall trauma and added advantages of minimally invasive surgery. Besides the improved cosmetic result, transumbilical single-incision laparoscopy can add other advantages to minimally invasive surgery like reduced postoperative pain, shorter hospital stay, and improved patient's comfort. The authors describe the technique of transumbilical single-incision laparoscopic suture and mesh reinforcement for a nontraumatic left lateral diaphragmatic hernia, discovered accidentally in a 45-year-old male.

We describe a new technique to achieve permanent umbilical cord occlusion. A 3 mm in diameter bipolar diathermy forceps was built to house a 1.2 mm fetoscope, emerging between the blades of the forceps. The device can be inserted percutaneously through a 10 Fr Trocar into the amniotic cavity under local analgesia and ultrasound guidance. A monochorionic (MC) twin pregnancy with a twin reversed arterial perfusion sequence at 18 weeks of gestation underwent cord occlusion of the acardiac twin using this new device in 2004. The instrument allowed cord coagulation under direct visual control. The pregnancy continued until 33 weeks of gestation when a male infant of 1980 g was delivered by cesarean section following preterm labor. This new instrument might allow easier access to the cord and reduce operation time by direct visualization of the target and, therefore, improve the outcome after the procedure.