Augmented Reality Guidance for the Resection of Missing Colorectal Liver Metastases: An Initial Experience

Ntourakis, Dimitrios; Memeo, R.; Soler, Luc; Marescaux, Jacques; Mutter, Didier; Pessaux, Patrick

doi:10.1007/s00268-015-3229-8

Cited by 77 publications

(49 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Implementing safety warnings, such as no-go zones, requires the detection of the critical anatomy. When another imaging modality is used, its registration to the endoscopic video may require the localization of anatomical landmarks [113]. Similarly, implementing degrees of autonomy during robotic surgery requires the localisation and recognition of the neighboring tools and anatomy.…”

Section: B Understanding Image Semanticsmentioning

confidence: 99%

CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer-Assisted Interventions

et al. 2020

View full text Add to dashboard Cite

Data-driven computational approaches have evolved to enable extraction of information from medical images with a reliability, accuracy and speed which is already transforming their interpretation and exploitation in clinical practice. While similar benefits are longed for in the field of interventional imaging, this ambition is challenged by a much higher heterogeneity. Clinical workflows within interventional suites and operating theatres are extremely complex and typically rely on poorly integrated intra-operative devices, sensors, and support infrastructures. Taking stock of some of the most exciting developments in machine learning and artificial intelligence for computer assisted interventions, we highlight the crucial need to take context and human factors into account in order to address these challenges. Contextual artificial intelligence for computer assisted intervention, or CAI4CAI, arises as an emerging opportunity feeding into the broader field of surgical data science. Central challenges being addressed in CAI4CAI include how to integrate the ensemble of prior knowledge and instantaneous sensory information from experts, sensors and actuators; how to create and communicate a faithful and actionable shared representation of the surgery among a mixed human-AI actor team; how to design interventional systems and associated cognitive shared control schemes for online uncertainty-aware collaborative decision making ultimately producing more precise and reliable interventions.Index Terms-Artificial intelligence, computer assisted interventions, interventional workflow, intra-operative imaging, surgical planning, data fusion, surgical scene understanding, contextaware user interface, machine and deep learning, surgical data science

show abstract

Section: B Understanding Image Semanticsmentioning

confidence: 99%

CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer-Assisted Interventions

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This has already been done, but mostly in hepatic surgery (13). The main difficulty in thoracic surgery is that the lung does not have the same anatomical configuration during surgery and on CT, due to deflation and pneumothorax.…”

Section: Video 2 Pre and Intraoperative Use Of 3d Reconstructionmentioning

confidence: 99%

Three-dimensional computed tomography reconstruction for operative planning in robotic segmentectomy: a pilot study

et al. 2018

View full text Add to dashboard Cite

Background: The objective of our pilot study was to assess if three-dimensional (3D) reconstruction performed by Visible Patient™ could be helpful for the operative planning, efficiency and safety of robotassisted segmentectomy. Methods: Between 2014 and 2015, 3D reconstructions were provided by the Visible Patient™ online service and used for the operative planning of robotic segmentectomy. To obtain 3D reconstruction, the surgeon uploaded the anonymized computed tomography (CT) image of the patient to the secured Visible Patient™ server and then downloaded the model after completion. Results: Nine segmentectomies were performed between 2014 and 2015 using a pre-operative 3D model. All 3D reconstructions met our expectations: anatomical accuracy (bronchi, arteries, veins, tumor, and the thoracic wall with intercostal spaces), accurate delimitation of each segment in the lobe of interest, margin resection, free space rotation, portability (smartphone, tablet) and time saving technique. Conclusions: We have shown that operative planning by 3D CT using Visible Patient™ reconstruction is useful in our practice of robot-assisted segmentectomy. The main disadvantage is the high cost. Its impact on reducing complications and improving surgical efficiency is the object of an ongoing study. (5), from port placement (6) to anatomical resection (7,8). KeywordsAlthough 3D reconstruction can be achieved with software such as Advantage Workstation Volume Share (GE Healthcare™, Milwaukee, WI, USA) (9) or Synapse Vincent (Fujifilm™ Co., Tokyo, Japan) (5,8), this is time consuming and relies heavily on medical resources. Thus, we chose to outsource to Visible Patient™ (Strasbourg, France), a company specialized in this area.To be usable in daily practice, we considered that several requirements should be respected, as shown in Table 1.The objective of our pilot study was to assess if 3D reconstruction performed by Visible Patient™ could meet all these criteria and could be helpful for the operative planning, efficiency, and safety of mini-invasive thoracic surgery. MethodsThe present study was approved by the Review Board of our institution (No. E2017-31) and written consent was obtained from each patient to send the anonymized data from their CT to Visible Patient. Inclusion and exclusion criteriaInclusion criteria: patients with a progressing ground glass nodule ≤2 cm, compromised patients with stage I or II solid tumors, patients with small sized solid tumors with no histological documentation (negative CT-guided and fibroscopic biopsy), defined as not resectable by wedge resection by the treating surgeon.Exclusion criteria: patients with lesions extending beyond a single lung segment, rapidly progressive or profuse metastatic diseases, and patients unfit for general anaesthesia. Pre-operative assessmentEach patient was assessed by CT (thorax, abdomen, and brain), PET-CT, respiratory function evaluation, cardiologic assessment (ECG and sometimes echocardiography), and bronchoscopy. Image acquisition and 3D reconstructionAll...

show abstract

“…However, in most implementations, the acquired data are processed after the acquisition and cannot be directly correlated with the sample, delaying the diagnostic and analytical result. Recently, various imaging modalities, such as computed tomography, magnetic resonance imaging, ultrasound image and fluorescence lifetime have been combining their respective imaging information with images of the sample in an augmented way to improve or supplement real‐time surgery . These approaches offer the surgeons a direct interpretation of physical information from the tissues by superimposing the imaging modalities information into the visual field of view, allowing the surgeon to detect and determine locations of disease in a real‐time.…”

Section: Introductionmentioning

confidence: 99%

Raman ChemLighter: Fiber optic Raman probe imaging in combination with augmented chemical reality

Yang

Mondol

Stiebing

et al. 2019

Journal of Biophotonics

View full text Add to dashboard Cite

Raman spectroscopy using fiber optic probe combines non‐contacted and label‐free molecular fingerprinting with high mechanical flexibility for biomedical, clinical and industrial applications. Inherently, fiber optic Raman probes provide information from a single point only, and the acquisition of images is not straightforward. For many applications, it is highly crucial to determine the molecular distribution and provide imaging information of the sample. Here, we propose an approach for Raman imaging using a handheld fiber optic probe, which is built around computer vision–based assessment of positional information and simultaneous acquisition of spectroscopic information. By combining this implementation with real‐time data processing and analysis, it is possible to create not only fiber‐based Raman imaging but also an augmented chemical reality image of the molecular distribution of the sample surface in real‐time. We experimentally demonstrated that using our approach, it is possible to determine and to distinguish borders of different bimolecular compounds in a short time. Because the method can be transferred to other optical probes and other spectroscopic techniques, it is expected that the implementation will have a large impact for clinical, biomedical and industrial applications.

show abstract

Augmented Reality Guidance for the Resection of Missing Colorectal Liver Metastases: An Initial Experience

Abstract: This initial experience suggests that AR may be a helpful navigation tool for the resection of missing CRLM.

Cited by 77 publications

References 67 publications

CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer-Assisted Interventions

CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer-Assisted Interventions

Three-dimensional computed tomography reconstruction for operative planning in robotic segmentectomy: a pilot study

Raman ChemLighter: Fiber optic Raman probe imaging in combination with augmented chemical reality

Contact Info

Product

Resources

About