Artificial intelligence driven 3D reconstruction for enhanced lung surgery planning

Implantation of the Bonebridge (MED-EL, Innsbruck, Austria), an active semi-implantable transcutaneous bone conduction hearing system, involves the risk of impression or alesion in intracranial structures, such as the dura or sigmoid sinus. Therefore, determining the optimal implant position requires careful preoperative radiological planning. The aim of this study was to provide an overview of the possibilities for preoperative radiological planning for the Bonebridge implantation and to evaluate their indications and feasibility. Asystematic literature search was conducted in the PubMed/MEDLINE database for all studies with preoperative planning or implant placement as the primary endpoint or that secondarily mention preoperative planning. Of 558studies, 49fulfilled the inclusion criteria. In 18studies, preoperative planning and floating mass transducer (FMT) placement were the primary endpoints, whereas in 31studies, preoperative planning was described secondarily. There are both freely available and commercial tools involving different time commitments for preoperative three-dimensional (3D) planning and intraoperative transfer. Preoperative 3D planning can increase the safety of Bonebridge implantation.

Introduction: CT scanning generate tridimensional reconstructions to permit the observation of paranasal sinuses and nasal cavity, and other anatomic structures of our body. The use and application of the 3D reconstructions generated from files of CT examination. The evaluation before sinus surgery through 3D reconstructions from the CT files may help the surgeon for diagnosis, preoperative planning and to acquire more information than with the traditional two-dimensional images obtained with the three different plans: axial, coronal and sagittal. Objective: To investigate and demonstrate the reliability and the feasibility of the evaluation before sinus surgery through 3D reconstructions from CT examinations of patients with a free software. Method: The reconstructions were carried out before the surgeries in order to assess the paranasal sinuses and nasal cavity for 45 patients. After this study, the surgery was digitally stored. Conclusion: With simple tools and personal computer, we evaluated the possibility to generate 3D reconstructions, the preoperative knowledge of the paranasal sinuses and nasal cavity may generate benefits during the performance of surgeries.

Ventral hernias are a surgical challenge, often requiring detailed imaging for surgical planning. Computed tomography (CT) is widely used in preoperative assessment, with three-dimensional (3D) reconstructions increasingly applied in surgical fields. This study aims to assess whether 3D CT reconstructions improve surgical planning compared to conventional two-dimensional (2D) CT. A cross-sectional survey was conducted from October 2024 to January 2025, enrolling 66 surgeons with diverse experience. Participants were randomized into two groups: one assessing a complex ventral hernia using conventional CT and the other using both 2D and 3D reconstructions. Data were collected through questionnaires based on the DECOMP criteria, surgeons' perception of hernia characteristics, surgical planning, and treatment strategies. Statistical analyses, including Fisher's exact test, Chi-square test, and ROC curve analysis, were performed to compare outcomes. No significant differences were found between the groups in the evaluation of the hernia, preoperative planning, or surgical approach. Surgeons predominantly relied on personal interpretation of CT scans rather than radiology reports. Notably, 3D reconstructions decreased the perception of hernia sac omental content (74.2% vs. 97.1%, p = 0.01). Furthermore, 3D visualization did not alter surgical decisions, including mesh selection, component separation, or preoperative techniques for loss of domain. 3D CT reconstructions do not impact the evaluation or surgical planning of complex ventral hernias compared to 2D CT. Although 3D imaging may enhance anatomical visualization, its clinical utility is unclear. Conventional 2D CT, when carefully analyzed, remains sufficient for surgical decision-making. Further research is needed to assess 3D imaging's benefits.

Objective To explore the application value of three-dimensional (3D) visualization technology in preoperative planning of precise hepatectomy. Methods Clinical data of 19 patients (15 males, 4 females; mean age: 45±4) with hepatocelular carcinoma (HCC) undergoing precise hepatectomy in First Department of Hepatobilliary Surgery, Zhujiang Hospital of Southern Medical University from January 2013 to December 2013 were analyzed retrospectively. The informed consents of all patients were obtained and the ethical committee approval was received. The patients received 64-slice CT scan before operation to get the sub-millimeter CT scan data, then the data were imported into the 3D visualization software MI-3DVS. The image segmentation, 3D reconstruction, individual liver segmentation, volume calculation, virtual resection plane design, surgical planning were conducted respectively. Results All the patients underwent 3D reconstruction of liver, liver segmentation and volume calculation. The reconstruction results showed that the interhepatic vasculatures can be indentified to over level 3. The 3D anatomical morphology of interhepatic vascular system, individual liver segmentation, tumor location, size and quantity could be clearly displayed. The compliance rate of the actual intraoperative findings and preoperative 3D reconstruction results was 100% (19/19). The preoperative plan was defined according to the individual 3D reconstruction results. And the compliance rate of the actual operative process and preoperative plan was 100% (19/19). All the operations were performed successfully and no death case occurred during the perioperative period. Six patients suffered hydrothorax after operation and were cured by drainage. Conclusion Three-dimensional visualization technology is helpful for the accurate preoperative diagnosis of liver tumors, and the surgical planning benefits the precise operation. Key words: Hepatectomy; Carcinoma, hepatocellular; Imaging, three-dimensional; Preoperative planning

IntroductionPulmonary segmentectomy, when combined with hilar and mediastinal lymphadenectomy, is currently considered the gold standard treatment for early-stage lung tumors (NSCLC) smaller than 2 cm in diameter. The preoperative planning for segmentectomies usually includes a contrast-enhanced CT with 2D reconstructions (axial, coronary, and sagittal). Recent technological advances allow 3D (volume rendering) reconstructions of preoperative CT scans, intended to improve the surgeon’s understanding of the segmental anatomy.The study aims to investigate the added value of 3D reconstruction in enhancing the surgeon’s understanding of anatomical structures, thus facilitating surgical planning and improving oncological outcomes.Methods and analysisThis is a prospective, randomized, controlled study.Patients will be randomized into two groups:1. Group 2D: the preoperative workup for these patients will consist of a contrast-enhanced chest CT with two-dimensional (2D) reconstructions (axial, coronary, and sagittal);2. Group 3D: the preoperative workup for these patients will consist of a contrast-enhanced chest CT with two-dimensional (2D) reconstructions (axial, coronary, and sagittal) and a 3D reconstruction (volume rendering) of the same chest CT employing dedicated software.The primary endpoints will be negative margin (R0) resection rate, resection margin (staple line-to-tumor distance), and thoracotomy conversions.We will use Fisher’s exact test for binary outcomes and Mann–Whitney U test for continuous outcomes. For subgroup analyses, we will use regression. Multivariable analyses will be based on logistic regression for binary outcomes and linear regression for continuous outcomes.Ethics and disseminationThe protocol and the model informed consent forms have been reviewed and approved by the ethics committee (N.: 1–2023) concerning scientific content and compliance with applicable research and human subject regulations.A Subcommittee on Publications was established to review all publications and report its recommendations to the steering committee. The anonymized participant-level dataset and statistical code for generating the results will not be publicly available.Trial registrationThe protocol was registered at ClinicalTrials.gov (ID: NCT05716815; Prospective rAndomized sTudy efficaCy tHree-dimensional rEconstructions Segmentectomy - Full-Text View - ClinicalTrials.gov). Jan 19, 2023.

The management of complex fractures at the time of revision surgery remains one of the most challenging tasks for orthopaedic trauma surgeons. As the major principle of treatment remains to achieve an anatomic reduction and a stable fixation, precise preoperative diagnostics and treatment planning are of utmost importance. Thus, knowledge of the 3-dimensional anatomy of the fracture site and its surrounding tissue is indispensable. However, radiographic tools have thus far mostly been unable to recapitulate the complexity of the fracture site in toto. In recent years, the development of 3-dimensional (3D) printers has led to novel opportunities in preoperative planning of complex operative procedures. Although the application of 3D printers has become increasingly popular in orthopaedic surgery, its implementation in trauma surgery is so far mostly limited to the preoperative planning of surgery in patients with pelvic and acetabular fractures/defects. Moreover, reports describing the advantages using this sophisticated methodology in revision trauma surgery are sparse. In this article, we report our experience using novel 3D printing technologies for the management of revision surgery in orthopaedic trauma. In particular, we describe the benefit of using 3D printing technologies in the preoperative planning of complex revision surgery of the proximal tibia, the elbow joint, the distal femur, the ankle joint, and several others. With the advantage to preoperatively plan the optimal surgical approach, implant placement, and contouring as well as the possibility to anticipate intraoperative difficulties, we believe that this emerging technology is of significant value for revision surgery in orthopaedic trauma.

Patient safety is crucial in donor nephrectomy. Individualized 3D reconstructions from CT imaging are gaining popularity for improving preoperative planning. This study evaluates whether such models enhance anatomical assessment and surgical preparation in robotic live donor nephrectomy. This retrospective pilot study included 24 patients who underwent robotic live donor nephrectomy between 2022 and 2025. 3D models were reconstructed by the surgeon using MED EINS software and compared to conventional CT reports regarding vascular anatomy. Of the 24 nephrectomies, 75% were left-sided. No intraoperative complications occurred; minor postoperative complications (Clavien-Dindo I/II) were observed in 16.7% of cases. Donors had a mean age of 52.9 years and a mean BMI of 28.0. Most had a single renal artery (83.3%) and vein (91.7%). The mean operative time was 205 min, and hospital stay averaged 6.4 days. Donors were often parents or partners (each 41.7%). 3D reconstructions showed high concordance with CT reports. In one case, a second artery was missed on the CT report but visible on the 3D model, demonstrating its utility for detecting anatomical variants. 3D reconstructions have the potential to support and refine preoperative planning in robotic donor nephrectomy by enhancing anatomical visualization. However, their clinical benefit should be further validated in prospective studies.

Surgical procedures for spinal lipoma or tethered spinal cord after myelomeningocele (MMC) repair are often difficult and complicated, because the anatomical structures can be deformed in complex and unpredictable ways. Imaging helps the surgeon understand the patient's spinal anatomy. Whereas two-dimensional images provide only limited information for surgical planning, three-dimensional (3D) reconstructed computed tomography (CT)-magnetic resonance (MR) fusion images produce clearer representations of the spinal regions. Here we describe simple and quick methods for obtaining 3D reconstructed CT-MR fusion images for preoperative planning of surgical procedures using the iPlan(®) cranial (BrainLAB AG, Feldkirchen, Germany) neuronavigation software. 3D CT images of the vertebral bone were combined with heavily T(2)-weighted MR images of the spinal cord, lipoma, cerebrospinal fluid (CSF) space, and nerve root through a process of fusion, segmentation, and reconstruction of the 3D images. We also used our procedure called "Image Overlay" to directly project the 3D reconstructed image onto the body surface using an LED projector. The final reconstructed 3D images took 10-30 minutes to obtain, and provided the surgeon with a representation of the individual pathological structures, so enabled the design of effective surgical plans, even in patients with bony deformity such as scoliosis. None of the 19 patients treated based on our 3D reconstruction method has had neurological complications, except for CSF leakage. This 3D reconstructed imaging method, combined with Image Overlay, improves the visual understanding of complicated surgical situations, and should improve surgical efficiency and outcome.

Three dimensional (3D) reconstruction can realize the accurate preoperative diagnosis of liver and intrahepatic tumors, and can also help to complete the preoperative operation planning. 3D visual surgical navigation technology has been applied in liver surgery. Virtual reality (VR) technology is still in the primary stage of research and development. It can only simulate the operation of 3D reconstruction model of liver, but cannot fully show the actual operation scene. With the development of computer technology and the further maturity of 3D reconstruction and VR technology, their application in liver surgery is showing a bright future.

BackgroundDouble outlet right ventricle (DORV) is a challenging congenital cardiac lesion to surgically master. We utilize computed tomography-guided-three-dimensional (3D) modeling/printing and novel in-house software to delineate anatomical relationships providing operative insight into the surgical approach. Our intent is to highlight this and showcase our technology.MethodsWe have created a repository of 3D heart reconstructions allowing for review of DORV patients. 3D intraoperative software anatomical manipulation and physical 3D prints were used to gain insight into DORV anatomy with the assistance of an on-site 3D Lab. The software used (Arc 3D Model Viewer) was designed in-house by our 3D Lab, tested and refined through ongoing use by our cardiothoracic surgery team. It allows for the subtraction and addition of anatomical structures and rotation in all axes. Clinicians can pan into the heart and determine specific anatomical boundaries and relationships.ResultsFrom 2010 to 2023, our program operated on 71 patients with DORV and our 3D lab has reconstructed 29 3D-hearts. Reconstructions were analyzed using Arc 3D Model Viewer. 3D reconstructions were viewed in our care conferences and intraoperatively allowing for discussion and determination of the optimal operative approach. Overall survival for DORV patients was 96% (68/71) with two mortalities in patients who did not receive 3D reconstructions.Conclusion3D reconstruction has allowed decision-making to be moved out of the operating room into the preoperative planning phase. 3D reconstruction is now standard for all DORV patients in our surgical service. We hope to demonstrate this technology with our newly developed Arc 3D Model Viewer and summarize our clinical results.

Disparity between reported and measured patient weight: can it affect planning in breast reduction surgery?

Current surgical planning relies on conventional two-dimensional (2D) imaging, but this is limited by its inability to fully represent three-dimensional (3D) anatomical relationships. This limitation is particularly evident in thoracic surgery, where accurate visualization of the pulmonary bronchovascular anatomy is essential for planning lung resections in a surgical field that has high anatomical variations and dynamic deformation during surgery. Although 3D reconstruction techniques have been explored to address these limitations, their adoption into routine clinical practice has been constrained by reliance on expensive proprietary software and a lack of detailed, efficient, reproducible workflows. Here, we describe a novel, practical imaging-based approach for generating patient-specific 3D reconstructions of pulmonary anatomy from computed tomography (CT) data using 3D Slicer, an open-source platform for imaging segmentation and 3D modelling. A reproducible step-by-step workflow is presented, detailing segmentation of pulmonary arteries, veins, bronchi, tumour localization, and resection margin assessment, together with common pitfalls, troubleshooting strategies, and factors influencing accuracy and efficiency. The workflow is designed to be intuitive and time-feasible, with model generation achievable within routine pre-operative planning timeframes. The process is demonstrated through two representative cases in which 3D reconstruction altered surgical planning by clarifying ambiguous anatomy, enabling precise pulmonary tumour localization and accurate resection. With the use of 3D reconstruction technology, anatomical understanding and operative precision can be enhanced, supporting more informed surgical decision-making and potentially improving patient outcomes.

Patient-reported outcomes (PROs) are increasingly recognized as a clinical tool for measuring and improving patient-centric care. This review provides a summary on recent advances in the use of PROs in the field of thoracic surgery. PROs have been used as primary endpoints in clinical trials and observational studies evaluating clinical care pathways and quantifying the benefits of minimally invasive surgical techniques for patients undergoing lung surgery. Qualitative and quantitative research has yielded fundamental insights into which PRO domains are meaningful and valued by patients after lung surgery. Patient experience and recovery after esophagectomy have been further characterized by using PROs. New disease-specific survey tools for patients have been developed to track long-term symptoms after esophageal reconstruction. Patient satisfaction has emerged as the key metric used to gauge the patient centeredness of hospital systems. Advances have been made in the application of PROs in multiple areas of thoracic surgery, which include lung and esophageal surgery. The growing focus on the use of PROs in clinical pathways has led to a better understanding on how to optimize patient experience.

Postoperative Pulmonary Complications after Surgery in Patients with Interstitial Lung Disease

Substrate characterization of the right ventricle in repaired tetralogy of Fallot using late enhancement cardiac magnetic resonance.