Endoscopic Sleeve Gastroplasty (ESG) is currently being used successfully in people with obesity. However, potential long-term side effects are still unknown. Computational biomechanics has emerged as a valid tool to improve the intervention effectiveness.The aim of this work is to provide an in silico framework to estimate stomach mechanics, as volumetric capacity, structural stiffness, and wall tissue strain, in response to food intake before and after ESG. A cohort of patients who underwent ESG was studied to rationally analyze the reduction in gastric volume and the changes in structural response and strain distribution. Computational predictions were compared with Magnetic Resonance Imaging (MRI) data from post-operative stomachs, allowing the reliability and reproducibility of the methodology to be assessed. Significant differences in stomach mechanics before and after surgery were observed, considering both structural stiffness and tissue strain distribution. This difference may lead to improper activation of mechanoreceptors and thus to variations in satiety after ESG.The results confirm the suitability of the in silico approach for evaluating bariatric surgery in the short-term, because it shed light on the reduction of stomach capacity and pressurization depending on the amount of food ingested, on the variation of tissue strain distribution, giving to the surgeon information that are currently not available. Leveraging computational modeling may help prevent complications, such as reflux or misplacement of sutures, and enhance outcomes by prescribing gastric-wall loading conditions associated with lower postoperative weight-regain rates.
Stereotactic body radiotherapy (SBRT) relies on precise tumor targeting, enabled by the use of fiducial markers. However, conventional marker placement through multiple rigid needle insertions presents risks and may cause tracking errors. This paper introduces a novel approach that combines a flexible ARC needle capable of on-demand curved trajectories with a custom-designed deployment tool. The tool enables the sequential placement of multiple markers through a single entry point with feasibility demonstrated in phantoms and in an ex vivo swine liver under computed tomography (CT) imaging. In addition, we explore the design of new multimodal fiducial markers with distinct radiographic fingerprints, visible in CT, fluoroscopy, ultrasound, and magnetic resonance imaging (MRI). A wide range of candidate materials and configurations were tested in liver-mimicking phantoms and ex vivo tissues to assess visibility and artifact generation. Our results demonstrate feasibility and outline a path toward next-generation fiducials and workflows that may reduce insertions and support improved marker distribution. Future work will focus on quantifying performance, optimizing biocompatible designs, and evaluating the benefits under clinically realistic protocols.
Surgical outcomes depend not only on patient factors and postoperative care but are also strongly influenced by the quality of the operation itself. Yet, for much of mod-ern surgery, intraoperative quality has been assessed indirectly through outcomes and operative reports. The increase in minimally invasive procedures inherently guided by endoscopic video, together with advances in artificial intelligence, creates an unprecedented opportunity to systematically observe, measure, and improve surgi-cal care. This chapter introduces AI-enabled Surgical Quality Assurance as a frame-work for using surgical data to support continuous assessment and improvement in the operating room. We first review existing approaches to surgical safety, from sys-tem-level interventions to procedure-specific standards. We then describe how AI can transform intraoperative video into clinically meaningful information, including recog-nition of anatomy, instruments, workflow, surgical actions, quality criteria, adverse events, and critical moments. Finally, we outline the major challenges that must be addressed before these systems can deliver routine clinical value, including representa-tive data collection, robust validation, workflow integration, regulation, liability, pri-vacy, and equitable access. Rather than replacing surgical judgment, AI for quality assurance should be understood as a set of tools for augmenting the surgical team, scaling expert review, and helping surgery evolve toward a learning system in which intraoperative care is continuously observed, assessed, and improved.
Sleeve gastrectomy (SG) induces weight loss through tubulization of the stomach. Up to 35
Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their design. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals for multi-modal representation learning without relying on manual annotations. We address the surgery-specific linguistic challenges present in surgical video lectures by employing multiple complementary automatic speech recognition systems to generate text transcriptions. We then present a novel method, SurgVLP — Surgical Vision Language Pre-training, for multi-modal representation learning. SurgVLP constructs a new contrastive learning objective to align video clip embeddings with the corresponding multiple text embeddings by bringing them together within a joint latent space. To effectively demonstrate the representational capability of the learned joint latent space, we introduce several vision-and-language surgical tasks and evaluate various vision-only tasks specific to surgery, e.g., surgical tool, phase, and triplet recognition. Extensive experiments across diverse surgical procedures and tasks demonstrate that the multi-modal representations learned by SurgVLP exhibit strong transferability and adaptability in surgical video analysis. Furthermore, our zero-shot evaluations highlight SurgVLP’s potential as a general-purpose foundation model for surgical workflow analysis, reducing the reliance on extensive manual annotations for downstream tasks, and facilitating adaptation methods such as few-shot learning to build a scalable and data-efficient solution for various downstream surgical applications. The code is available at https://github.com/CAMMA-public/SurgVLP.
