A5074984614- Optical Coherence Tomography Applications
- Soft Robotics and Applications
- Coronary Interventions and Diagnostics
- Retinal and Macular Surgery
- Adaptive Control of Nonlinear Systems
- Photoacoustic and Ultrasonic Imaging
- Digital Media Forensic Detection
- Inertial Sensor and Navigation
- AI in cancer detection
- Target Tracking and Data Fusion in Sensor Networks
- Optical measurement and interference techniques
- Generative Adversarial Networks and Image Synthesis
- Advanced Image Processing Techniques
- Advanced Measurement and Detection Methods
- Image Processing Techniques and Applications
- Gastrointestinal Bleeding Diagnosis and Treatment
- Control Systems and Identification
- Cerebrovascular and Carotid Artery Diseases
- Retinal Imaging and Analysis
- Image and Video Stabilization
- Acute Ischemic Stroke Management
- Medical Image Segmentation Techniques
- Optical Imaging and Spectroscopy Techniques
- Colorectal Cancer Screening and Detection
- Advanced Control Systems Design
University of Verona
2022-2025
Université de Strasbourg
2021-2025
Inserm
2025
Centre National de la Recherche Scientifique
2023-2025
University of Pennsylvania
2025
Laboratoire des Sciences de l'Ingénieur, de l'Informatique et de l'Imagerie
2020-2022
China Aerospace Science and Technology Corporation
2019
Shanghai Jiao Tong University
2019
Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects actions, including in surgical videos. While conventional object-centric methods videos leverage recurrent processing to achieve efficiency, they often struggle with maintaining long-range temporal coherence required long applications. On the other hand, fully parallel entire enhances consistency but introduces significant...
Ultrasound (US) imaging enables the evaluation of vascular structures in real time, and it can provide morphological pathological information during US-guided procedures. Automatic prediction structure boundaries help clinicians locating measuring target more accurately efficiently. Most existing US segmentation methods use per-pixel classification or regression, which require post-processing to obtain contour coordinates. In this work, we present ACE-Net, a novel approach that directly...
Optical Coherence Tomography (OCT) is increasingly used in endoluminal procedures since it provides high-speed and high resolution imaging. Distortion instability of images obtained with a proximal scanning endoscopic OCT system are significant due to the motor rotation irregularity, friction between rotating probe outer sheath synchronization issues. On-line compensation artefacts essential ensure image quality suitable for real-time assistance during diagnosis or minimally invasive...
Optical coherence tomography (OCT) is a growing imaging technique for real-time early diagnosis of digestive system diseases. As with other well-established medical modalities, OCT requires validated performance and standardized test methods assessment. A major limitation in the development testing new technologies lack models simultaneous clinical procedure emulation characterization healthy diseased tissues. Currently, former can be tested large animal latter small disease or excised human...
SignificanceEndoscopic optical coherence tomography (OCT) enables real-time biopsy of human organs. Endoscopic probes require miniaturization optics, which in turn limits field view. When larger imaging areas are needed such as the gastrointestinal tract, operator must manually scan probe over tissue to extend view, often resulting an imperfect scanning pattern and increased risk missing lesions. Automatic has potential view OCT, allowing user focus on image interpretation during...
Optical Coherence Tomography (OCT) is an emerging medical imaging modality for luminal organ diagnosis. The non-constant rotation speed of optical components in the OCT catheter tip causes rotational distortion volumetric scanning. By improving scanning process, this instability can be partially reduced. To further correct image, a data stabilization algorithm proposed. first estimates Non-Uniform Rotational Distortion (NURD) each B-scan by using Convolutional Neural Network (CNN). A...
Weakly supervised video object segmentation (WSVOS) enables the identification of maps without requiring an extensive training dataset masks, relying instead on coarse labels indicating presence. Current state-of-the-art methods either require multiple independent stages processing that employ motion cues or, in case end-to-end trainable networks, lack accuracy, part due to difficulty learning from videos with transient This limits application WSVOS for semantic annotation surgical where...
In this article, we present a method for tuning controller parameters cascade PID based on the step response performance characteristics of closed loop system with application to an unmanned aerial vehicle(UAV). With specifically designed identification procedures, neural network mapping is obtained automatically when UAV flying around target height. model, gradual regression and optimization algorithm proposed tune controller. The model primly illustrated relation between performance,...
This paper proposes a low-cost six Degree-of-Freedom (6-DOF) navigation system for small aerial robots based on the integration of Global Position System (GPS) receiver with sensors inertional Microelectromechanical Systems (MEMS). In problem fusing Inertial Measurement Unit (IMU) GPS, effect time synchronization error attitude estimation is concerned. A fusion algorithm which can estimate motion states and simultaneously proposed. adds loop to improve accuracy. Compared another augmented...
Optical Coherence Tomography (OCT) shows the ability of real-time diagnosis for external environment or internal small lumen. OCT has not been applied to larger lumen like colon stomach due difficulty scanning. In this work, we use a robotized helical scanning probe explore large Based on segmentation stabilized image, high accurate distance and quantitative contact feedback are obtained robotic The proposed method distance/contact robustness both phantom real deformable tissue. is conducted...
Side-viewing catheter-based medical imaging modalities are used to produce cross-sectional images underneath tissue surfaces. Mainstream side-viewing catheters based on Optical Coherence Tomography (OCT) or Ultrasound, and they often applied the luminal environment. Automatic lumen segmentation provides geometry information for tasks like robotic control assessment real-time diagnosis task with catheters. In this work, we propose a novel deep neural networks explicit coordinates encoding,...
Optical Coherence Tomography (OCT) has the ability to acquire cross-sectional images under tissue surfaces in real-time, which can provide real-time characterization. One of possible applications is improving accuracy white-light based diagnosis digestive system. In this work, we integrate OCT with a robotic surgical endoscope, using local scanning form complementary information white light endoscopic camera. Meanwhile, camera help roughly guide probe potential pathological area. To...
The rotational distortion of endoscopic Optical Coherence Tomography (OCT) is caused by friction optical fiber and motor instabilities. On-line compensation essential to provide real-time feedback. We proposed a new method that integrates Convolutional Neural Network based warping parameters prediction algorithm correct the azimuthal position each image line. This solves problem drift in iterative processing an overall shifting parameter predicting nets with time 145ms/frame variation...
Endoscopic submucosal dissection (ESD) is a minimally invasive treatment for early stage colorectal cancer that can be performed in teleoperation with robotized flexible interventional endoscope. However, the tissue elevation step which requires needle insertion still manual operation. In this work we present robotic placement using image-guidance combines white-light camera images to control alignment of and OCT catheter. are used determine position tip during its insertion. This procedure...