Search Results (80)

Background/Objectives: Colorectal anastomotic leak (CAL) is one of the most severe postoperative complications in colorectal surgery, impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative laparoscopic recording of the anastomosis for CAL prediction. Methods: A convolutional neural network (CNN) was trained with annotated frames from colorectal surgery videos across three international high-volume centers (Instituto Português de Oncologia de Lisboa, Hospital das Clínicas de Ribeirão Preto, and Royal Liverpool University Hospital). The dataset included a total of 5356 frames from 26 patients, 2007 with CAL and 3349 showing normal anastomosis. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. The models’ performance was evaluated using their sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key image regions influencing predictions. Results: The best-performing model achieved an accuracy of 99.6%, AUROC of 99.6%, sensitivity of 99.2%, specificity of 100.0%, PPV of 100.0%, and NPV of 98.9%. The model reliably identified CAL-positive frames and provided visual explanations through heatmaps. Conclusions: To our knowledge, this is the first AI model developed to predict CAL using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAL before it occurs, marking a paradigm shift in colorectal surgery. Full article

(1) Medical training is changing, especially for surgeons. Virtual reality simulation is an excellent way to train surgeons safely. Studies show that surgeons who train with simulation have demonstrated improved technical skills in fundamental surgical procedures. The purpose of this study is to determine the overall impact of virtual reality training on laparoscopic cholecystectomy performance and to explore whether specific training protocols or the addition of feedback confer any advantages for future surgeons. (2) MEDLINE (PubMed), Embase (Ovid SP), Web of Science, Google Scholar, and Scopus were searched for the literature related to virtual reality training, immersive simulation, laparoscopic surgical skills training, and medical education. Study quality was assessed using the Cochrane Risk of Bias Tool and NIH Quality Assessment Tool. (3) A total of 55 full-text articles were reviewed. Meta-analysis showed that virtual reality training is an effective method for learning cholecystectomy surgical skills. (4) Conclusions: Performance, measured by objective structured assessments and time to task completion, is improved with virtual reality training compared with no additional training. Positive effects of simulation training were evident in global rating scores and operative time. Continuous feedback on movement parameters during laparoscopic cholecystectomy skills training impacts skills acquisition and long-term retention. Full article

Novel laparoscopic optical forceps (OFs), developed and patented by the University of Bari Aldo Moro (EP4119030, Bari, Italy), were designed to enhance safety and efficiency during laparoscopic ovariectomy in dogs by enabling atraumatic ovarian suspension and surgical maneuvers. This study aimed to describe the design, prototyping, sterilization validation, and preliminary clinical evaluation of this instrument. Prototypes were fabricated using ABS-like Pro resin via LSPc 3D printing. EtOx (ethylene oxide) sterilization proved to be the only effective method ensuring both microbiological safety and material integrity after 25 cycles. A randomized clinical trial involving 36 female dogs compared the OFs with conventional extracorporeal suture (ES) suspension using two-port laparoscopic ovariectomy. Surgical performance was assessed via operative times and complication rates. The OF group demonstrated significantly reduced ovariectomy (7.5 ± 1.6 min vs. 23.7 ± 7.6 min, p < 0.01) and overall surgical (14.2 ± 1.7 min vs. 30.4 ± 7.4 min, p < 0.01) times. No intraoperative complications occurred in the OF group, while the ES group exhibited instances of needle breakage, multiple suture attempts, and increased bleeding. The OFs enabled surgical maneuvers and ovarian suspension without requiring additional incisions or complex techniques, offering ergonomic advantages and compatibility with standard optics. These findings support the OFs as a promising tool to simplify and improve minimally invasive ovariectomy in veterinary surgery. Full article

The most frequent form of ectopic pregnancy, known as tubal pregnancy, leads to a dangerous situation where the fertilized ovum implants inside a fallopian tube, which can result in tubal rupture and severe bleeding. The purpose of this narrative review is to evaluate all existing data regarding epidemiology, risk factors, pathophysiology, clinical presentation, diagnosis, and management of tubal ectopic pregnancy in order to provide a comprehensive understanding of this common yet difficult clinical condition. Prior ectopic pregnancy, together with tubal pathology and assisted reproduction, represent the main risk factors for this condition. The diagnosis relies on serial β-hCG tests combined with transvaginal ultrasonography, but laparoscopy serves as the diagnostic tool for cases with uncertain results. The treatment plan depends on the fallopian tube integrity, along with the patient’s hemodynamic condition. Patients with unruptured pregnancies who are hemodynamically stable receive methotrexate treatment as the preferred option, but surgical intervention with salpingectomy or salpingostomy becomes necessary in case of tubal rupture or when medical treatment fails. The development of laparoscopic procedures has led to better results and improved possibilities for fertility preservation. The psychological effects on patients require both counseling and follow-up care. Early detection, along with personalized management, helps decrease maternal complications and optimize reproductive outcomes. Full article

The integration of Context-Aware Systems (CASs) in Future Operating Rooms (FORs) aims to enhance surgical workflows and outcomes through real-time data analysis. CASs require accurate classification of surgical tools, enabling the understanding of surgical actions. This study proposes a novel deep learning approach for surgical tool classification based on combining convolutional neural networks (CNNs), Feature Fusion Modules (FFMs), Squeeze-and-Excitation (SE) networks, and Bidirectional long-short term memory (BiLSTM) networks to capture both spatial and temporal features in laparoscopic surgical videos. We explored different modeling scenarios with respect to the location and number of SE blocks for multi-label surgical tool classification in the Cholec80 dataset. Furthermore, we analyzed a single-label surgical tool classification model using a simplified and computationally less expensive architecture compared to the multi-label problem setting. The single-label classification model showed an improved overall performance compared to the proposed multi-label classification model due to the increased complexity of identifying multiple tools simultaneously. Nonetheless, our results demonstrated that the proposed CNN-SE-FFM-BiLSTM multi-label model achieved competitive performance to state-of-the-art methods with excellent performance in detecting tools with complex usage patterns and in minority classes. Future work should focus on optimizing models for real-time applications, and broadening dataset evaluations to improve performance in diverse surgical environments. These improvements are crucial for the practical implementation of such models in CASs, ultimately aiming to enhance surgical workflows and patient outcomes in FORs. Full article

Robot-assisted surgery has transformed the landscape of genitourinary cancer treatment, offering enhanced precision, reduced morbidity, and improved recovery compared to open or conventional laparoscopic approaches. As the field matures, a new generation of technological innovations is redefining the boundaries of what robotic systems can achieve. This narrative review explores the integration of artificial intelligence, advanced imaging modalities, augmented reality, and connectivity in robotic urologic oncology. The applications of machine learning in surgical skill evaluation and postoperative outcome predictions are discussed, along with AI-enhanced haptic feedback systems that compensate for the lack of tactile sensation. The role of 3D virtual modeling, intraoperative augmented reality, and fluorescence-guided surgery in improving surgical planning and precision is examined for both kidney and prostate procedures. Emerging tools for real-time tissue recognition, including confocal microscopy and Raman spectroscopy, are evaluated for their potential to optimize margin assessment. This review also addresses the shift toward single-port systems and the rise of telesurgery enabled by 5G connectivity, highlighting global efforts to expand expert surgical care across geographic barriers. Collectively, these innovations represent a paradigm shift in robot-assisted urologic oncology, with the potential to enhance functional outcomes, surgical safety, and access to high-quality care. Full article

Background/Objectives: Colorectal cancer is a significant health problem worldwide. Surgery is the primary curative treatment for most colorectal cancers. Cardiopulmonary exercise testing is now performed widely before surgery, and it is the most objective and precise means of evaluating pre-surgical physical fitness. Also, we can use the 6 min walk test to measure cardiorespiratory fitness before surgery. Methods: We included colorectal patients who were awaiting open abdominal or laparoscopic surgery. After admission to the hospital, patients who signed informed consent forms fulfilled a short questionnaire about health and physical status, preoperative physical activities, and quality of life questionnaire (EORTC QLQ-C30). Patients performed a 6 min walk test (6MWT) 2 days before surgery and 7 days after surgery. 6MWT is a tool for measuring the functional status of fitness. Also, they fulfilled the quality of recovery questionnaire (QoR 15) 7 days after surgery. Results: In a final analysis, we included 72 patients with a mean age of 62.48. We compared the number of steps, walk distance, average and maximal walk speed, and average and maximal heart rate before and after surgery, overall, and by group. Our findings show a statistically significant difference between men and women in the walk distance (F = 4.99, p = 0.02) The number of steps showed a statistically significant difference according to patients’ ages (F = 2.90, p = 0.02). Also, we detected differences in the average and maximum heart rate during walking when comparing body mass index (average heart rate F = 5.72, p = 0.00, maximum heart rate F = 2.52, p = 0.04). Conclusions: Our study provides evidence that average and maximal heart rate during the 6 min walk test was higher in the postoperative period, especially in overweight and obese participants. Full article

Background: Laparoscopic surgery for endometriosis presents unique challenges due to the complexity of and variability in lesion appearances within the abdominal cavity. This study investigates the application of deep learning models for object detection in laparoscopic videos, aiming to assist surgeons in accurately identifying and localizing endometriosis lesions and related anatomical structures. A custom dataset was curated, comprising of 199 video sequences and 205,725 frames. Of these, 17,560 frames were meticulously annotated by medical professionals. The dataset includes object detection annotations for 10 object classes relevant to endometriosis, alongside segmentation masks for some classes. Methods: To address the object detection task, we evaluated the performance of two deep learning models—FasterRCNN and YOLOv9—under both stratified and non-stratified training scenarios. Results: The experimental results demonstrated that stratified training significantly reduced the risk of data leakage and improved model generalization. The best-performing FasterRCNN object detection model achieved a high average test precision of 0.9811 ± 0.0084, recall of 0.7083 ± 0.0807, and mAP50 (mean average precision at 50% overlap) of 0.8185 ± 0.0562 across all presented classes. Despite these successes, the study also highlights the challenges posed by the weak annotations and class imbalances in the dataset, which impacted overall model performances. Conclusions: In conclusion, this study provides valuable insights into the application of deep learning for enhancing laparoscopic surgical precision in endometriosis treatment. The findings underscore the importance of robust dataset curation and advanced training strategies in developing reliable AI-assisted tools for surgical interventions. The latter could potentially improve the guidance of surgical interventions and prevent blind spots occurring in difficult to reach abdominal regions. Future work will focus on refining the dataset and exploring more sophisticated model architectures to further improve detection accuracy. Full article

Artificial intelligence (AI) has shown its potential to advance applications in various medical fields. One such area involves developing integrated AI-based systems to assist in laparoscopic surgery. Surgical tool detection and phase recognition are key components to develop such systems, and therefore, they have been extensively studied in recent years. Despite significant advancements in this field, previous image-based methods still face many challenges that limit their performance due to complex surgical scenes and limited annotated data. This study proposes a novel deep learning approach for classifying and localizing surgical tools in laparoscopic surgeries. The proposed approach uses a self-supervised learning algorithm for surgical tool classification followed by a weakly supervised algorithm for surgical tool localization, eliminating the need for explicit localization annotation. In particular, we leverage the Bidirectional Encoder Representation from Image Transformers (BEiT) model for tool classification and then utilize the heat maps generated from the multi-headed attention layers in the BEiT model for the localizing of these tools. Furthermore, the model incorporates class weights to address the class imbalance issue resulting from different usage frequencies of surgical tools in surgeries. Evaluated on the Cholec80 benchmark dataset, the proposed approach demonstrated high performance in surgical tool classification, surpassing previous works that utilize both spatial and temporal information. Additionally, the proposed weakly supervised learning approach achieved state-of-the-art results for the localization task. Full article

This review aims to place open, laparoscopic, computerized (robotic), and image-guided robotic surgical interventions in the context of complex medical surgeries, taking into account patient well-being, staff effort, and task reliability. It deduces the specificities of each technique and subsequently focuses on image-guided interventions and their practice in staff training, preparation, and implementation of a possible autonomous intervention. These complex interventions are intended to be minimally invasive (MI), precise, and safe therapies. The accuracy of robotic positioning could be improved by reductions in complexity and uncertainty involved in the intervention procedure. These can be achieved by matching the real controlled procedure and its virtual replica. The contribution discusses considerations for staff training and/or the planning of surgical interventions using real and virtual phantoms, and the use of augmented matched digital twins (DTs) for real interventions. This paper successively approaches open, laparoscopic and robotic surgeries, image-guided robotic interventions, the control and DT monitoring of MRI-assisted interventions, MRI field ruling equations and MRI compatibility, DT monitoring involvements in surgical interventions, and it ends with a discussion and main conclusions. The different topics presented in this article, although explicit, are reinforced by examples from the literature to facilitate a deeper understanding. The outcome of this review highlights the importance of robotic imaging-assisted procedures involving MI, nonionizing, and precise interventions. It also illustrates the potential of DTs combined with digital tools to offer an effective solution for the management of these interventions. The exploitation of such a suitable digital environment allows the planning, forecasting, prospecting, training, and execution, with staff in the loop, of surgical activities in general. This methodology allows for the precise consideration of specific anatomies, particularly in microsurgery and neurosurgery. Full article

This study introduces a Neuro-Visual Adaptive Control (NVAC) architecture designed to enhance precision and safety in robot-assisted surgery. The proposed system enables semi-autonomous guidance of the laparoscope based on image input. To achieve this, the architecture integrates the following: (1) a computer vision system based on the YOLO11n model, which detects surgical instruments in real time; (2) a Model Reference Adaptive Control with Proportional–Derivative terms (MRAC-PD), which adjusts the robot’s behavior in response to environmental changes; and (3) Closed-Form Continuous-Time Neural Networks (CfC-mmRNNs), which efficiently model the system’s dynamics. These networks address common deep learning challenges, such as the vanishing gradient problem, and facilitate the generation of smooth control signals that minimize wear on the robot’s actuators. Performance evaluations were conducted in CoppeliaSim, utilizing real cholecystectomy images featuring surgical tools. Experimental results demonstrate that the NVAC achieves maximum tracking errors of 1.80 × 10⁻³ m, 1.08 × 10⁻⁴ m, and 1.90 × 10⁻³ m along the x, y, and z axes, respectively, under highly significant dynamic disturbances. This hybrid approach provides a scalable framework for advancing autonomy in robotic surgery. Full article

Robot-assisted minimally invasive surgery offers advantages over traditional laparoscopic surgery, including precision and improved patient outcomes. However, its complexity requires extensive training, leading to the development of simulators that still face challenges such as limited feedback and lack of realism. This study presents an augmented reality-based surgical simulator tailored for minimally invasive pancreatic surgery, integrating an innovative parallel robot, real-time AI-driven force estimation, and haptic feedback. Using Unity and the HoloLens 2, the simulator offers a realistic augmented environment, enhancing spatial awareness and planning in surgical scenarios. A convolutional neural network (CNN) model predicts forces without physical sensors, achieving a mean absolute error of 0.0244 N. Tests indicate a strong correlation between applied and predicted forces, with a haptic feedback latency of 65 ms, suitable for real-time applications. Its modularity makes the simulator accessible for training and preoperative planning, addressing gaps in current robotic surgery training tools while setting the stage for future improvements and broader integration. Full article

Background/Objectives: Managing ventilatory strategies in patients with obesity under general anesthesia presents significant challenges due to obesity-related pathophysiological changes. Inverse ratio ventilation (IRV) has emerged as a potential strategy to optimize respiratory mechanics during laparoscopic surgery in this population. The primary outcomes were changes in respiratory mechanics, including peak inspiratory pressure (P_Peak), plateau pressure (P_Plat), mean airway pressure (P_Mean), and dynamic compliance (C_Dyn). Secondary outcomes included gas exchange parameters, hemodynamic measures, inflammatory cytokines, and postoperative complications. Methods: A systematic review and meta-analysis were conducted, searching PubMed, Scopus, EMBASE, and PMC Central. Only English-language randomized controlled trials (RCTs) evaluating the impact of IRV in adult surgical patients with obesity were included. The quality and certainty of evidence were assessed using the Risk of Bias 2 (RoB 2) tool and the Grades of Recommendation, Assessment, Development, and Evaluation (GRADE) framework, respectively. Results: Three RCTs including 172 patients met the inclusion criteria. Compared to conventional ventilation without prolonged inspiratory time or IRV, IRV significantly reduced P_Peak (MD [95%CI]: −3.15 [−3.88; −2.42] cmH₂O, p < 0.001) and P_Plat (MD [95%CI]: −3.13 [−3.80; −2.47] cmH₂O, p < 0.001) while increasing P_Mean (MD [95%CI]: 4.17 [3.11; 5.24] cmH₂O, p < 0.001) and C_Dyn (MD [95%CI]: 2.64 [0.95; 4.22] mL/cmH₂O, p = 0.002) during laparoscopy, without significantly affecting gas exchange. IRV significantly reduced mean arterial pressure (MD [95%CI]: −2.93 [−3.95; −1.91] mmHg, p < 0.001) and TNF-α levels (MD [95%CI]: −9.65 [−17.89; −1.40] pg/mL, p = 0.021). Conclusions: IRV optimizes intraoperative respiratory mechanics but has no significant impact on postoperative outcomes, necessitating further research to determine its clinical role. Full article

Background: Artificial Intelligence (AI)-driven training systems are becoming increasingly important in surgical education, particularly in the context of laparoscopic suturing. This systematic review aims to assess the impact of AI on skill acquisition, long-term retention, and clinical performance, with a specific focus on the types of machine learning (ML) techniques applied to laparoscopic suturing training and their associated advantages and limitations. Methods: A comprehensive search was conducted across multiple databases, including PubMed, IEEE Xplore, Cochrane Library, and ScienceDirect, for studies published between 2005 and 2024. Following the PRISMA guidelines, 1200 articles were initially screened, and 33 studies met the inclusion criteria. This review specifically focuses on ML techniques such as deep learning, motion capture, and video segmentation and their application in laparoscopic suturing training. The quality of the included studies was assessed, considering factors such as sample size, follow-up duration, and potential biases. Results: AI-based training systems have shown notable improvements in the laparoscopic suturing process, offering clear advantages over traditional methods. These systems enhance precision, efficiency, and long-term retention of key suturing skills. The use of personalized feedback and real-time performance tracking allows learners to gain proficiency more rapidly and ensures that skills are retained over time. These technologies are particularly beneficial for novice surgeons and provide valuable support in resource-limited settings, where access to expert instructors and advanced equipment may be scarce. Key machine learning techniques, including deep learning, motion capture, and video segmentation, have significantly improved specific suturing tasks, such as needle manipulation, insertion techniques, knot tying, and grip control, all of which are critical to mastering laparoscopic suturing. Conclusions: AI-driven training tools are reshaping laparoscopic suturing education by improving skill acquisition, providing real-time feedback, and enhancing long-term retention. Deep learning, motion capture, and video segmentation techniques have proven most effective in refining suturing tasks such as needle manipulation and knot tying. While AI offers significant advantages, limitations in accuracy, scalability, and integration remain. Further research, particularly large-scale, high-quality studies, is necessary to refine these tools and ensure their effective implementation in real-world clinical settings. Full article

Background: Laparoscopic cholecystectomy for acute cholecystitis carries an increased risk of biliovascular injuries. Fluorescence cholangiography (FC) is a valuable diagnostic tool for identifying extrahepatic bile ducts (EHBD). The objective of this study was to evaluate the efficacy of FC in delineating EHBD anatomy, both before and after dissection, based on the critical view of safety (CVS) principles. Methods: Urgently admitted patients were prospectively stratified into two groups, depending on whether they had mild or moderate acute cholecystitis, in accordance with the 2018 Tokyo guidelines. All patients were scheduled for an early laparoscopic cholecystectomy using FC and were administered a fixed dose of indocyanine green (ICG) intravenously 12 h prior to the surgical procedure. Results: A total of 108 patients—75 patients with mild acute cholecystitis and 33 patients with moderate acute cholecystitis—were included. More than four CVS steps were performed in 101 patients (93.5%). Less than four CVS steps were performed only in seven patients—three (2.5%) patients with mild acute cholecystitis and four (4%) patients with moderate acute cholecystitis. The achievement of the CVS principles and the visualization rate using FC significantly increased in both patient groups, ranging from 3% before CVS to 100% after CVS (p < 0.001). In both groups, the cystic duct was visualized in most patients after CVS and FC, followed by the common bile duct and the common hepatic duct. Conversely, even after using CVS and FC, the visualization of the confluence of the cystic and common hepatic ducts remained less likely and challenging in both groups (57.3% in mild patients vs. 33.3% in moderate patients; p = 0.022). Background liver fluorescence disturbance was observed equally in both patient groups (6–11%), but it did not reach statistical significance. The median operative time was 60 ± 25 min in patients with mild acute cholecystitis compared to 85 ± 37 min in patients suffering from moderate acute cholecystitis (p < 0.001). No postoperative complications or biliovascular injuries were observed. Conclusions: FC is a convenient, safe, and efficacious procedure for attaining CVS principles and identifying the EHBD anatomy in most patients. The procedure showed superior results in mild acute cholecystitis patients in comparison to moderate acute cholecystitis patients. Full article