Real-time 6 DOF localization of bronchoscopes is crucial for enhancing intervention quality. However, current vision-based technologies struggle to balance between generalization unseen data and computational speed. In this study, we propose a Depth-based Dual-Loop framework real-time Visually Navigated Bronchoscopy (DD-VNB) that can generalize across patient cases without the need re-training. The DD-VNB integrates two key modules: depth estimation dual-loop localization. To address domain...

Localizing the bronchoscope in real time is essential for ensuring intervention quality. However, most existing vision-based methods struggle to balance between speed and generalization. To address these challenges, we present BronchoTrack, an innovative real-time framework accurate branch-level localization, encompassing lumen detection, tracking, airway association. achieve performance, employ benchmark light weight detector efficient detection. We firstly introduce multi-object tracking...

Localizing the bronchoscope in real time is essential for ensuring intervention quality. However, most existing methods struggle to balance between speed and generalization. To address these challenges, we present BronchoTrack, an innovative real-time framework accurate branch-level localization, encompassing lumen detection, tracking, airway association.To achieve performance, employ a benchmark lightweight detector efficient detection. We are first introduce multi-object tracking...

Bronchoscopy plays a significant role in the early diagnosis and treatment of lung diseases. This process demands physicians to maneuver flexible endoscope for reaching distal lesions, particularly requiring substantial expertise when examining airways upper lobe. With development artificial intelligence robotics, reinforcement learning (RL) method has been applied manipulation interventional surgical robots. However, unlike human who utilize multimodal information, most current RL methods...

Accurate bronchoscope localization is essential for pulmonary interventions, by providing six degrees of freedom (DOF) in airway navigation. However, the robustness current vision-based methods often compromised clinical practice, and they struggle to perform real-time generalize across cases unseen during training. To overcome these challenges, we propose a novel Probabilistic Airway Navigation System (PANS), leveraging Monte-Carlo method with pose hypotheses likelihoods achieve robust...

Single-image depth estimation is essential for endoscopy tasks such as localization, reconstruction, and augmented reality. Most existing methods in surgical scenes focus on in-domain estimation, limiting their real-world applicability. This constraint stems from the scarcity inferior labeling quality of medical data training. In this work, we present EndoOmni, first foundation model zero-shot cross-domain endoscopy. To harness potential diverse training data, refine advanced self-learning...

Monocular depth estimation has shown promise in general imaging tasks, aiding localization and 3D reconstruction. While effective various domains, its application to bronchoscopic images is hindered by the lack of labeled data, challenging use supervised learning methods. In this work, we propose a transfer framework that leverages synthetic data with labels for training adapts domain knowledge accurate real bronchoscope data. Our network demonstrates improved prediction on footage using...

Accurate and complete segmentation of airways in chest CT images is essential for the quantitative assessment lung diseases facilitation pulmonary interventional procedures. Although deep learning has led to significant advancements medical image segmentation, maintaining airway continuity remains particularly challenging. This difficulty arises primarily from small dispersed nature structures, as well class imbalance scans. To address these challenges, we designed a Multi-scale Nested...

In this letter, we propose a novel multicarrier transmission scheme named as coordinate interleaved high-dimensional orthogonal frequency division multiplexing with index modulation (CI-HD-OFDM-IM). each subblock of the proposed scheme, two HD symbols optimal rotation angles are combined by interleaving technique to obtain an additional diversity gain and improve bit error performance. The single symbol maximum likelihood (ML) detection is exploited in receiver. average probability (ABEP)...

In order to universally reflect the impact of environmental changes on survival different predators, this paper will illustrate adaptability predator-prey model above mentioned problem by taking climate change a hypothetical species as an example. Therefore, instead considering capacity constant, we calculate number predators giving under discrete temperature value.

Abstract As the carrier of visual information, image is an important source information for human beings, and camera has always been one most sensors smart car line patrol. By using to patrol line, can obtain optimal path furthest prospect, so as achieve high speed which difficult be achieved by other sensors. However, camera’s acquisition very affected light. In case solar interference, traditional processing methods not good results. this paper, we will discuss method dealing with...