Surgical data science is devoted to enhancing the quality, safety, and efficacy of interventional healthcare. While the use of powerful machine learning algorithms is becoming the standard approach for surgical data science, the underlying end-to-end task models directly infer high-level concepts (e.g., surgical phase or skill) from low-level observations (e.g., endoscopic video). This end-to-end nature of contemporary approaches makes the models vulnerable to non-causal relationships in the data and requires the re-development of all components if new surgical data science tasks are to be solved. The digital twin (DT) paradigm, an approach to building and maintaining computational representations of real-world scenarios, offers a framework for separating low-level processing from high-level inference. In surgical data science, the DT paradigm would allow for the development of generalist surgical data science approaches on top of the universal DT representation, deferring DT model building to low-level computer vision algorithms. In this latter effort of DT model creation, geometric scene understanding plays a central role in building and updating the digital model. In this work, we visit existing geometric representations, geometric scene understanding tasks, and successful applications for building primitive DT frameworks. Although the development of advanced methods is still hindered in surgical data science by the lack of annotations, the complexity and limited observability of the scene, emerging works on synthetic data generation, sim-to-real generalization, and foundation models offer new directions for overcoming these challenges and advancing the DT paradigm.

Liver parenchymal transection is a challenging step during hepatic resection, particularly when using robotic platforms that require specific skills to optimize this phase. Pedicle division at the beginning of the liver parenchyma helps to better identify the resection plane and minimizes blood loss. The three-dimensional (3D) high-definition vision and the robotic Maryland allow for clear identification of the hepatic pedicles that could be dissected or divided without the need for a laparoscopic ultrasonic dissector. The caudo-peripheral technique, combined with the Maryland bipolar Kelly clamp crushing technique, is a useful approach to complete parenchymal transection and achieve safe anatomical resections in cases of hepatocellular carcinoma (HCC) with multi-pronged bleeding control. This is essential for expediting the procedure, reducing the number of intermittent clamping times, and minimizing the risk of ischemia-reperfusion injury. In this setting, perfect synchronization between the surgeon operating at the console and the bedside assistant is crucial. Advances in artificial intelligence (AI) systems have shown great potential to redefine clinical care management, preoperative planning, and intraoperative decision making for patients with HCC. This paper describes the most relevant details of our technique, its theoretical background, advantages, and limitations. Moreover, minimally invasive surgery offers the opportunity to share surgical experiences and technical progress through multimedia videos. This represents a modern and effective teaching tool to accelerate the learning process and overcome the challenges of the most complex procedures by offering surgeons various solutions to common technical problems.

Ultrasound guidance plays a central role in numerous minimally invasive procedures involving percutaneous needle insertion, ensuring safe and accurate needle placement. However, it encounters two primary challenges: (1) aligning the needle with the ultrasound beam and (2) visualizing the needle even when correctly aligned. In this review, we offer a concise overview of the physics foundation underlying these challenges and explore various approaches addressing specific challenges, with a focus on software-based solutions. We further distinguish between hardware-based and software-based solutions, placing a stronger emphasis on the latter. The incorporation of artificial intelligence into these methods to enhance needle visualization and localization is briefly discussed. We identify state-of-the-art needle detection methods, showcasing submillimeter precision in tip localization and orientation. Additionally, we provide insights into potential future directions, aiming to facilitate the translation of these advanced methods into the clinic. This article serves as a comprehensive guide, offering insights into challenges, evolving solutions, and prospective research directions to effectively address these issues.

Artificial intelligence (AI) is the discipline of computer science dedicated to processing a large amount of throughput data and is based on algorithms that can rationalize increasingly complex tasks and ultimately reproduce human intelligence. It has been speculated for clinical uses in liver transplantation (LT) for several years, but its application remains incipient worldwide. Therefore, the recent advancements of digital and robotic tools in daily medical practice make the modern environment propitious to its proper implementation. Nevertheless, it is noteworthy that this technology has significant limitations: (i) its unconditional dependence on a pre-established reliable and extensive database; (ii) the potential impact on independent medical decision-making; and (iii) a major economic and environmental burden. So, despite its seducing and flawless simplicity features, AI emerges as a new “Pandora’s box” that should be carefully understood and used under the light of ethical principles to improve clinical outcomes, promote medical and para-medical working conditions, and increase patient safety and access to medical care. The present work aims to review literature data supporting AI implementation on this basis.

This review explores the significant advancements in liver surgery and transplantation, particularly focusing on the integration of 3D printing and virtual reality (VR) technologies. The core objective is to enhance preoperative planning, simulation, and intraoperative navigation. The review discusses several studies that underscore the accuracy and utility of 3D printed models derived from medical imaging, which are instrumental in identifying small liver lesions, improving surgical education, and facilitating patient comprehension. Additionally, the role of VR in surgical simulation is examined, highlighting its superiority in tumor identification and its potential in training systems. While clinical outcomes data suggest a need for further randomized trials to establish the impact on surgical efficiency and recovery, the review also touches upon the promising future of augmented reality (AR) for intraoperative guidance and liver segment identification, with prospects of artificial intelligence (AI) integration. The conclusion underscores the importance of continued clinical evidence and technological advancements for wider adoption in liver surgery and transplantation.

Aim: Scale-aware 3D reconstruction of the surgical scene from a monocular endoscope is important for automatic navigation systems in robot-assisted surgery. However, traditional multi-view stereo methods purely utilize monocular images, which can recover 3D structures arbitrarily scaled with the real world. Current deep learning-based approaches rely on large training data for relative depth estimation and further 3D reconstruction with no scale. Inspired by recently proposed neural radiance fields (NeRF), we present a novel pipeline, KV-EndoNeRF, which explores limited multi-modal data (i.e., robot kinematics, and monocular endoscope) for surgical scene reconstruction with absolute scale.

Methods: We first extract scale information from robot kinematics data and then integrate it into sparse depth recovered from structure from motion (SfM). Based on the sparse depth supervision, we adapt a monocular depth estimation network to the current surgical scene to obtain scene-specific coarse depth. After adjusting the scale of coarse depth, we use it to guide the optimization of NeRF, resulting in absolute depth estimation. The 3D models of the tissue surface with real scale are recovered by fusing fine depth maps.

Results: Experimental results on the Stereo Correspondence And Reconstruction of Endoscopic Data (SCARED) demonstrate that KV-EndoNeRF excels in learning an absolute scale from robot kinematics and achieves 3D reconstruction with rich details of surface texture and high accuracy, outperforming other existing reconstruction methods.

Conclusion: Combining multi-modal image data with NeRF-based optimization represents a potential approach to achieve scale-aware 3D reconstruction of monocular endoscopic scenes.

Aim: With the increasing prevalence of knee diseases affecting human health and quality of life, it is essential to explore more advanced surgical assistive technologies to improve the precision, safety, and success rate of unilateral knee replacement surgery. This study aims to conduct a comprehensive bibliometric analysis of robotic-assisted unicompartmental knee arthroplasty (r-UKA) to understand its current status, trends, and future directions.

Methods: Retrieve articles about r-UKA in the Web of Science Core Collection (WOSCC) database. Data from 128 selected articles, including author information, publication details, citations, and evidence level, were analyzed. Statistical analyses and data visualizations explored publication and citation trends, research interests, core author groups, and cooperative networks.

Results: Interest in r-UKA research has grown, particularly after 2013, which is evident from increased publications and citations. The United States is the largest contributor, followed by the United Kingdom, both of which have prominent medical research institutions and universities actively involved in r-UKA research. Frequent keywords such as “alignment”, “accuracy”, “revision”, and “survivorship” highlight the focus on surgical precision, implant longevity, and patient outcomes.

Conclusion: Robotic-assisted unicompartmental knee arthroplasty has gained significant attention, promising improved surgical precision and patient outcomes. Collaboration between researchers and medical institutions globally has driven progress in this field. However, long-term outcomes and clinical efficacy compared to traditional techniques require further investigation. As robotic technology evolves, its application in knee replacement surgery holds potential for better therapeutic effects and advancements toward more accurate, safe, and efficient procedures, benefiting patients and advancing unicompartmental knee arthroplasty (UKA).

Artificial intelligence (AI) is currently utilized across numerous medical disciplines. Nevertheless, despite its promising advancements, AI’s integration in hand surgery remains in its early stages and has not yet been widely implemented, necessitating continued research to validate its efficacy and ensure its safety. Therefore, this review aims to provide an overview of the utilization of AI in hand surgery, emphasizing its current application in clinical practice, along with its potential benefits and associated challenges. A comprehensive literature search was conducted across PubMed, Embase, Medline, and Cochrane libraries, adhering to the Preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. The search focused on identifying articles related to the application of AI in hand surgery, utilizing multiple relevant keywords. Each identified article was assessed based on its title, abstract, and full text. The primary search identified 1,228 articles; after the application of inclusion/exclusion criteria and manual bibliography search of included articles, a total of 98 articles were covered in this review. AI’s primary application in hand and wrist surgery is diagnostic, which includes hand and wrist fracture detection, carpal tunnel syndrome (CTS), avascular necrosis (AVN), and osteoporosis screening. Other applications include residents’ training, patient-doctor communication, surgical assistance, and outcome prediction. Consequently, AI is a very promising tool that has numerous applications in hand and wrist surgery, though further research is necessary to fully integrate it into clinical practice.

Aim: To examine the clinical accuracy and applicability of ChatGPT answers to commonly asked questions from patients considering posterior lumbar decompression (PLD).

Methods: A literature review was conducted to identify 10 questions that encompass some of the most common questions and concerns patients may have regarding lumbar decompression surgery. The selected questions were then posed to ChatGPT. Initial responses were then recorded, and no follow-up or clarifying questions were permitted. Two attending fellowship-trained spine surgeons then graded each response from the chatbot using a modified Global Quality Scale to evaluate ChatGPT’s accuracy and utility. The surgeons then analyzed each question, providing evidence-based justifications for the scores.

Results: Minimum scores across all ten questions would lead to a total score of 20, whereas a maximum score would be 100. ChatGPT’s responses in this analysis earned a score of 59, just under an average score of 3, when evaluated by two attending spine surgeons. A score of 3 denoted a somewhat useful response of moderate quality, with some important information adequately discussed but some poorly discussed.

Conclusion: ChatGPT has the ability to provide broadly useful responses to common preoperative questions that patients may have when considering undergoing PLD. ChatGPT has excellent utility in providing background information to patients and in helping them become more informed about their pathology in general. However, it often lacks the specific patient context necessary to provide patients with personalized, accurate insights into their prognosis and medical options.

Aim: Depth information plays a key role in enhanced perception and interaction in image-guided surgery. However, it is difficult to obtain depth information with monocular endoscopic surgery due to a lack of reliable cues for perceiving depth. Although there are reprojection loss-based self-supervised learning techniques to estimate depth and pose, the temporal information from the adjacent frames is not efficiently utilized to handle occlusion in surgery.

Methods: We design long-term reprojection loss (LT-RL) self-supervised monocular depth estimation techniques by integrating longer temporal sequences into reprojection to learn better perception and to address occlusion artifacts in image-guided laparoscopic and robotic surgery. For this purpose, we exploit four temporally adjacent source frames before and after the target frame, where conventional reprojection loss uses two adjacent frames. The pixels that are visible in the target frame but occluded in the immediate two adjacent frames will produce the inaccurate depth but a higher chance to appear in the four adjacent frames during the calculation of minimum reprojection loss.

Results: We validate LT-RL on the benchmark surgical datasets of Stereo correspondence and reconstruction of endoscopic data (SCARED) and Hamlyn to compare the performance with other state-of-the-art depth estimation methods. The experimental results show that our proposed technique yields 2%-4% better root-mean-squared error (RMSE) over the baselines of vanilla reprojection loss.

Conclusion: Our LT-RL self-supervised depth and pose estimation technique is a simple yet effective method to tackle occlusion artifacts in monocular surgical video. It does not add any training parameters, making it flexible for integration with any network architecture and improving the performance significantly.

Adult spinal deformity (ASD) poses significant challenges in spinal surgery, requiring precise planning and execution for successful correction. Additionally, optimization of outcomes and reducing the high complication rates of ASD surgeries are additional challenges facing spinal deformity surgeons. The advent of machine learning (ML) has revolutionized various aspects of healthcare, including spinal surgery. This review provides a comprehensive overview of the current state of ML applications in spinal deformity corrective surgery, highlighting its potential benefits and challenges.

Aim: The purpose of this study was to elucidate differences in patient perspectives on large language model (LLM) vs. physician-generated responses to frequently asked questions about anterior cervical discectomy and fusion (ACDF) surgery.

Methods: This cross-sectional study had three phases: In phase 1, we generated 10 common questions about ACDF surgery using ChatGPT-3.5, ChatGPT-4.0, and Google search. Phase 2 involved obtaining answers to these questions from two spine surgeons, ChatGPT-3.5, and Gemini. In phase 3, we recruited 5 cervical spine surgery patients and 5 age-matched controls to assess the clarity and completeness of the responses.

Results: LLM-generated responses were significantly shorter, on average, than physician-generated responses (30.0 +/- 23.5 vs. 153.7 +/- 86.7 words, P < 0.001). Study participants were more likely to rate LLM-generated responses with more positive clarity ratings (H = 6.25, P = 0.012), with no significant difference in completeness ratings (H = 0.695, P = 0.404). On an individual question basis, there were no significant differences in ratings given to LLM vs. physician-generated responses. Compared with age-matched controls, cervical spine surgery patients were more likely to rate physician-generated responses as higher in clarity (H = 6.42, P = 0.011) and completeness (H = 7.65, P = 0.006).

Conclusion: Despite a small sample size, our findings indicate that LLMs offer comparable, and occasionally preferred, information in terms of clarity and comprehensiveness of responses to common ACDF questions. It is particularly striking that ratings were similar, considering LLM-generated responses were, on average, 80% shorter than physician responses. Further studies are needed to determine how LLMs can be integrated into spine surgery education in the future.