Guiqiu Liao

Analyse et correction d'images OCT pour le contrôle d'endoscopes flexibles robotisés: L'objectif de cette thèse est d'automatiser l'imagerie robotique en permettant une opération en boucle fermée pour une numérisation automatique précise en présence de mouvement tissulaire. Tout d'abord, un problème spécifique des cathéters OCT de numérisation rotative, appelé distorsion de rotation non uniforme(NURD), qui entrave les tâches de diagnostic et de navigation, est examiné. Une nouvelle solution pour la correction en ligne est proposée. Ensuite, un algorithme de segmentation multi-surfaces d'images OCT à vision latérale est développé, qui est également adapté à l'échographie intravasculaire (IVUS). Un pipeline d'apprentissage fédéré décentralisé est démontré pour former le réseau d'encodage de lignes A avec des images OCT et IVUS, améliorant les performances du réseau. Enfin, une rétroaction en temps réel est fournie pour la numérisation volumétrique robotique, en maintenant les tissus mous dans le champ de vision et en limitant la force de contact.

Optical Coherence Tomography (OCT) offers real-time, high-resolution imaging of tissue internal structures, presenting a potential enhancement over conventional endoscopic examination of the digestive system surface. However, miniaturized OCT probes typically present challenges with a limited field of view and require precise positioning to optimize tissue visualization. This research addresses the challenge by leveraging robotizing a surgical endoscope and a steerable OCT probe to provide closed-loop scanning of larger areas in the presence of tissue motion. We propose a robotic multi-pullback technique, supported by real-time, tactile feedback from OCT images. Deep learning algorithms are employed for OCT image stabilization and segmentation, enabling autonomous robotic volumetric OCT scanning. Compared to previous works, our closed-loop control approach considers, in addition to the probe flexibility, also the movements and deformations of the tissue during the robotic scanning. For experimental validation, we designed a moving soft tissue phantom with force sensing and compared the proposed method with fixed-angle approaches. Our method consistently maintained minimal contact forces (around 50 mN) and clear tissue visibility for tissues with different stiffness and motion patterns. Resulting imaging quality was further validated using a multi-layer optical phantom under dynamic conditions.

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 in OCT volumetric scanning. By improving the scanning process, this instability can be partially reduced. To further correct the rotational distortion in the OCT image, a volumetric data stabilization algorithm is proposed. The algorithm first estimates the Non-Uniform Rotational Distortion (NURD) for each B-scan by using a Convolutional Neural Network (CNN). A correlation map between two successive B-scans is computed and provided as input to the CNN. To solve the problem of accumulative error in iterative frame stream processing, we deploy an overall rotation estimation between reference orientation and actual OCT image orientation. We train the network with synthetic OCT videos by intentionally adding rotational distortion into real OCT images. As part of this article we discuss the proposed method in two different scanning modes: the first is a conventional pullback mode where the optical components move along the protection sheath, and the second is a self-designed scanning mode where the catheter is globally translated by using an external actuator. The efficiency and robustness of the proposed method are evaluated with synthetic scans as well as real scans under two scanning modes.

Optical coherence tomography (OCT) is a growing imaging technique for real-time early diagnosis of digestive system diseases. As with other well-established medical imaging modalities, OCT requires validated imaging performance and standardized test methods for performance assessment. A major limitation in the development and testing of new imaging technologies is the lack of models for simultaneous clinical procedure emulation and characterization of healthy and diseased tissues. Currently, the former can be tested in large animal models and the latter can be tested in small animal disease models or excised human biopsy samples. In this study, a 23 cm by 23 cm optical phantom was developed to mimic the thickness and near-infrared optical properties of each anatomical layer of a human colon, as well as the surface topography of colorectal polyps and visual appearance compatible with white light endoscopy.

In this article, we present a method for tuning controller parameters for cascade PID based on the step response performance characteristics of a closed loop system with application to an unmanned aerial vehicle(UAV). With specifically designed system identification procedures, a neural network mapping is obtained automatically when the UAV is flying around the target height. With this network system model, a gradual regression and optimization algorithm is proposed to tune the controller. The regression model primly illustrated the relation between PID parameters with controller performance, and the construction for optimization cost function takes the physical significance of step response performance of flying machine into account. Experimental data collected from fight experiment when auto-tuner is implemented on a quadrotorcraft demonstrate the efficiency of the proposed method.