bronchial tree
Airway Label Prediction in Video Bronchoscopy: Capturing Temporal Dependencies Utilizing Anatomical Knowledge
Keuth, Ron, Heinrich, Mattias, Eichenlaub, Martin, Himstedt, Marian
Purpose: Navigation guidance is a key requirement for a multitude of lung interventions using video bronchoscopy. State-of-the-art solutions focus on lung biopsies using electromagnetic tracking and intraoperative image registration w.r.t. preoperative CT scans for guidance. The requirement of patient-specific CT scans hampers the utilisation of navigation guidance for other applications such as intensive care units. Methods: This paper addresses navigation guidance solely incorporating bronchosopy video data. In contrast to state-of-the-art approaches we entirely omit the use of electromagnetic tracking and patient-specific CT scans. Guidance is enabled by means of topological bronchoscope localization w.r.t. an interpatient airway model. Particularly, we take maximally advantage of anatomical constraints of airway trees being sequentially traversed. This is realized by incorporating sequences of CNN-based airway likelihoods into a Hidden Markov Model. Results: Our approach is evaluated based on multiple experiments inside a lung phantom model. With the consideration of temporal context and use of anatomical knowledge for regularization, we are able to improve the accuracy up to to 0.98 compared to 0.81 (weighted F1: 0.98 compared to 0.81) for a classification based on individual frames. Conclusion: We combine CNN-based single image classification of airway segments with anatomical constraints and temporal HMM-based inference for the first time. Our approach renders vision-only guidance for bronchoscopy interventions in the absence of electromagnetic tracking and patient-specific CT scans possible.
- Europe > Germany > Baden-Württemberg > Freiburg (0.04)
- North America > United States > Missouri > St. Louis County > St. Louis (0.04)
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.04)
- (5 more...)
- Health & Medicine > Therapeutic Area (1.00)
- Health & Medicine > Diagnostic Medicine > Imaging (1.00)
- Information Technology > Sensing and Signal Processing > Image Processing (1.00)
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.90)
Engineers develop a 'magnetic tentacle robot' for lung operations
A bizarre'magnetic tentacle robot' that can pass into the narrow tubes of the lungs to take tissue samples could help save lives, a new study shows. Experts at the University of Leeds have created the device, which consists of external magnets and a'tentacle' – a thin polymer tube containing metallic particles. The so-called'tentacle' is highly flexible and measures just 0.07 of an inch (2 mm) in diameter, about twice the size of the tip of a ballpoint pen. Like something from a horror film, the tentacle would slowly enter the mouth or nose of a patient while they are under general anaesthetic. Guided by the external magnets, it could reach some of the smallest bronchial tubes in the lungs – and could be used to take tissue samples or deliver cancer therapy.