No description available.

<div>In this thesis, the design of the robotic cannula for minimally invasive robotic lumbar discectomy is presented. Lumbar discectomy is the surgery to remove the herniated disc material that is pressing on a nerve root or spinal cord. </div><div><br></div><div>Recently, a robotic approach to performing this procedure has been proposed that utilizes multiple teleoperated articulated instruments inserted into the surgical workspace using a single cannula. In this paper, a new robotic cannula system to work in conjunction with this new procedure is presented. It allows for the independent teleoperated control of the axial position and rotation of up to three surgical instruments at the same time. The mechanical design, modeling, controller design, and the performance of the prototype of the new system are presented in this paper demonstrating a fully functioning device for this application. A novel worm gear and rack system allow for the instrument translation while and embedded gear trains produce the rotational movement. Steady-state errors of less than 10 microns for translation and less than 0.5 degree for rotation motion are achieved in position tracking; steady-state errors of less than 100 micron per second of translation and less than 0.5 degree per second for rotation motion are obtained in speed tracking. </div>

Deep learning approaches have been explored for surgical tool classification in laparoscopic videos. Convolutional neural networks (CNN) are prominent among the proposed approaches. However, concerns about the robustness and generalisability of CNN approaches have been raised. This paper evaluates CNN generalisability across different procedures and in data from different surgical settings. Moreover, generalisation performance to new types of procedures is assessed and insights are provided into the effect of increasing the size and representativeness of training data on the generalisation capabilities of CNN. Five experiments were conducted using three datasets. The DenseNet-121 model showed high generalisation capability within the dataset, with a mean average precision of 93%. However, the model performance diminished on data from different surgical sites and across procedure types (27% and 38%, respectively). The generalisation performance of the CNN model was improved by increasing the quantity of training videos on data of the same procedure type (the best improvement was 27%). These results highlight the importance of evaluating the performance of CNN models on data from unseen sources in order to determine their real classification capabilities. While the analysed CNN model yielded reasonably robust performance on data from different subjects, it showed a moderate reduction in performance for different surgical settings.

É estudada, conceitualmente a técnica de recapeamento de quadril de cães como modelo cirúrgico. A artroplastia do quadril foi desenvolvida com a finalidade de estabelecer a mobilidade articular e também no alívio da dor de pacientes humanos. Em animais, principalmente os cães, a artroplastia total, é um procedimento cirúrgico muito utilizado na articulação coxofemoral para a correção de patologias de quadril, sejam elas degenerativas traumáticas ou inflamatórias além de aliviar a dor. A artroplastia de recapeamento de quadril em humanos tem se mostrado uma técnica muito eficiente por estar próxima da anatomia natural do quadril e tem sido aplicada em pacientes jovens e ativos. A vantagem de se realizar a técnica de recapeamento é que nesta, há uma ressecção mínima da cabeça femoral e que promove uma melhora em relação à estabilidade da articulação, entretanto essa técnica ainda não é aplicada em animais. O presente trabalho tem por objetivo estudar a técnica de recapeamento de quadril de cães de forma análoga as técnicas aplicadas em humanos e também, propor um projeto de ferramental cirúrgico específico em conjunto com o protocolo cirúrgico. A técnica conceitual de artroplastia de recapeamento de quadril de cães foi desenvolvida a partir de um fêmur canino onde foram desenvolvidos os conceitos da técnica cirúrgica e o protótipo do ferramental cirúrgico necessário para o desenvolvimento desta técnica. Inicialmente foram feitas aquisições das imagens dos objetos do trabalho (fêmur canino, ferramental cirúrgico e prótese cirúrgica) que foram convertidas em arquivos CAD; a partir destes foram gerados cópias em gesso através do processo de impressão 3D do ferramental cirúrgico desde o guia de furação até a fresa de chanframento e também da prótese cirúrgica de recapeamento. A fabricação do ferramental cirúrgico obtido pelo processo de impressão 3D possibilitou uma análise visual dos protótipos que serviram de modelos para a fabricação do ferramental cirúrgico definitivo, sendo este, confeccionado em aço. Isso permitiu sua validação em bancada de laboratório através de testes realizados em modelos de ossos de cães em resina. Conclui-se que a técnica de recapeamento de quadril de cães validada em bancada de laboratório poderá ser realizada em conjunto com o ferramental cirúrgico proposto para em um futuro muito próximo ser usado em articulações de cães portadores de displasia coxofemoral devido a sua funcionalidade e à demanda de casos clínicos para este procedimento. A técnica cirúrgica de recapeamento estudada poderá ser oferecida a população a um custo acessível por ser inovadora e promissora no contexto da ortopedia veterinária. / The study conceptually describes a surgical model for dog hip resurfacing technique. Hip arthroplasty was developed to restore joint mobility and relieve of human patients pain. In animals, especially dogs, total arthroplasty is a surgical procedure commonly used to correct traumatic, degenerative and inflammatory hip diseases and alleviate pain. The resurfacing hip arthroplasty in humans, applied in young and active patients, has shown to be an efficient technique. The advantage of using this technique is that there will be a minimal resection of the femoral head, improving the stability of the joint; however it has not been applied to animals yet. The present dissertation reports on the study of hip resurfacing technique for dogs in a similar way it is applied in humans. It also proposes a specific surgical tooling design in conjunction with the surgical protocol. The technical concept of hip resurfacing arthroplasty for dogs was developed from a canine femur from which the concepts of the surgical technique and the prototypes of the necessary surgical tools were developed. Initially, images of the objects used in the work (canine femur, surgical tools and surgical prosthesis) were acquired. They were then converted into CAD files, which generated plaster copies of surgical tools, from the hole guide to the to cutter and chamfer, and also surgical resurfacing prosthesis through the 3D printing process. The manufacture of the surgical tools models obtained by 3D printing process allowed a visual analysis of the prototypes that served as references for the definitive surgical tool made in steel. Such tools were validated by means of laboratory bench tests using resin models of dogs\' bones. It was possible to conclude that the technique of hip resurfacing in dogs can be employed in conjunction with the proposed surgical tools in the joints of dogs with hip dysplasia in a very near future. Due to its full functionality and large demand of clinical cases for this procedure, the technique may be offered to the population at an affordable cost. It is also an innovative and promising technique in the context of veterinary orthopedics.

É estudada, conceitualmente a técnica de recapeamento de quadril de cães como modelo cirúrgico. A artroplastia do quadril foi desenvolvida com a finalidade de estabelecer a mobilidade articular e também no alívio da dor de pacientes humanos. Em animais, principalmente os cães, a artroplastia total, é um procedimento cirúrgico muito utilizado na articulação coxofemoral para a correção de patologias de quadril, sejam elas degenerativas traumáticas ou inflamatórias além de aliviar a dor. A artroplastia de recapeamento de quadril em humanos tem se mostrado uma técnica muito eficiente por estar próxima da anatomia natural do quadril e tem sido aplicada em pacientes jovens e ativos. A vantagem de se realizar a técnica de recapeamento é que nesta, há uma ressecção mínima da cabeça femoral e que promove uma melhora em relação à estabilidade da articulação, entretanto essa técnica ainda não é aplicada em animais. O presente trabalho tem por objetivo estudar a técnica de recapeamento de quadril de cães de forma análoga as técnicas aplicadas em humanos e também, propor um projeto de ferramental cirúrgico específico em conjunto com o protocolo cirúrgico. A técnica conceitual de artroplastia de recapeamento de quadril de cães foi desenvolvida a partir de um fêmur canino onde foram desenvolvidos os conceitos da técnica cirúrgica e o protótipo do ferramental cirúrgico necessário para o desenvolvimento desta técnica. Inicialmente foram feitas aquisições das imagens dos objetos do trabalho (fêmur canino, ferramental cirúrgico e prótese cirúrgica) que foram convertidas em arquivos CAD; a partir destes foram gerados cópias em gesso através do processo de impressão 3D do ferramental cirúrgico desde o guia de furação até a fresa de chanframento e também da prótese cirúrgica de recapeamento. A fabricação do ferramental cirúrgico obtido pelo processo de impressão 3D possibilitou uma análise visual dos protótipos que serviram de modelos para a fabricação do ferramental cirúrgico definitivo, sendo este, confeccionado em aço. Isso permitiu sua validação em bancada de laboratório através de testes realizados em modelos de ossos de cães em resina. Conclui-se que a técnica de recapeamento de quadril de cães validada em bancada de laboratório poderá ser realizada em conjunto com o ferramental cirúrgico proposto para em um futuro muito próximo ser usado em articulações de cães portadores de displasia coxofemoral devido a sua funcionalidade e à demanda de casos clínicos para este procedimento. A técnica cirúrgica de recapeamento estudada poderá ser oferecida a população a um custo acessível por ser inovadora e promissora no contexto da ortopedia veterinária. / The study conceptually describes a surgical model for dog hip resurfacing technique. Hip arthroplasty was developed to restore joint mobility and relieve of human patients pain. In animals, especially dogs, total arthroplasty is a surgical procedure commonly used to correct traumatic, degenerative and inflammatory hip diseases and alleviate pain. The resurfacing hip arthroplasty in humans, applied in young and active patients, has shown to be an efficient technique. The advantage of using this technique is that there will be a minimal resection of the femoral head, improving the stability of the joint; however it has not been applied to animals yet. The present dissertation reports on the study of hip resurfacing technique for dogs in a similar way it is applied in humans. It also proposes a specific surgical tooling design in conjunction with the surgical protocol. The technical concept of hip resurfacing arthroplasty for dogs was developed from a canine femur from which the concepts of the surgical technique and the prototypes of the necessary surgical tools were developed. Initially, images of the objects used in the work (canine femur, surgical tools and surgical prosthesis) were acquired. They were then converted into CAD files, which generated plaster copies of surgical tools, from the hole guide to the to cutter and chamfer, and also surgical resurfacing prosthesis through the 3D printing process. The manufacture of the surgical tools models obtained by 3D printing process allowed a visual analysis of the prototypes that served as references for the definitive surgical tool made in steel. Such tools were validated by means of laboratory bench tests using resin models of dogs\' bones. It was possible to conclude that the technique of hip resurfacing in dogs can be employed in conjunction with the proposed surgical tools in the joints of dogs with hip dysplasia in a very near future. Due to its full functionality and large demand of clinical cases for this procedure, the technique may be offered to the population at an affordable cost. It is also an innovative and promising technique in the context of veterinary orthopedics.

Radiofrequency ablation (RFA) is a minimally invasive treatment for either hepatocellular carcinoma or metastasis liver carcinoma. In order to resect large lesions, the surgeon has to perform multiple time-consuming destruction cycles and reposition the RFA needle for each of them. The critical step in handling a successful ablation and preventing local recurrence is the correct positioning of the needle. For small tumors, the surgeon places the middle of the active needle tip in the center of the tumor under intra-operative ultrasound guidance. When one application is not enough to cover the entire tumor, the surgeon needs to repeat the treatment after repositioning of the needle, but US guidance is obstructed by the opacity stemming from the first RFA application. In this case the surgeon can only rely on anatomical knowledge and the repositioning of the RFA needle becomes a subjective task limiting the treatment accuracy. We have developed a computer assisted surgery guidance application for this repositioning procedure. Our software application handles the complete process from preoperative image analysis to tool tracking in the operating room. Our framework is mostly used for this RFA procedure, but is also suitable for any other medical or surgery application.

L’ère numérique change de plus en plus le monde en raison de la quantité de données récoltées chaque jour. Le domaine médical est fortement affecté par cette explosion, car l’exploitation de ces données est un véritable atout pour l’aide à la pratique médicale. Dans cette thèse, nous proposons d’utiliser les vidéos chirurgicales dans le but de créer un système de chirurgie assistée par ordinateur. Nous nous intéressons principalement à reconnaître les gestes chirurgicaux à chaque instant afin de fournir aux chirurgiens des recommandations et des informations pertinentes. Pour ce faire, l’objectif principal de cette thèse est de reconnaître les outils chirurgicaux dans les vidéos de chirurgie de la cataracte. Dans le flux vidéo du microscope, ces outils sont partiellement visibles et certains se ressemblent beaucoup. Pour relever ces défis, nous proposons d'ajouter une caméra supplémentaire filmant la table opératoire. Notre objectif est donc de détecter la présence des outils dans les deux types de flux vidéo : les vidéos du microscope et les vidéos de la table opératoire. Le premier enregistre l'oeil du patient et le second enregistre les activités de la table opératoire. Deux tâches sont proposées pour détecter les outils dans les vidéos de la table : la détection des changements et la détection de présence d'outil. Dans un premier temps, nous proposons un système similaire pour ces deux tâches. Il est basé sur l’extraction des caractéristiques visuelles avec des méthodes de classification classique. Il fournit des résultats satisfaisants pour la détection de changement, cependant, il fonctionne insuffisamment bien pour la tâche de détection de présence des outils sur la table. Dans un second temps, afin de résoudre le problème du choix des caractéristiques, nous utilisons des architectures d’apprentissage profond pour la détection d'outils chirurgicaux sur les deux types de vidéo. Pour surmonter les défis rencontrés dans les vidéos de la table, nous proposons de générer des vidéos artificielles imitant la scène de la table opératoire et d’utiliser un réseau de neurones à convolutions (CNN) à base de patch. Enfin, nous exploitons l'information temporelle en utilisant un réseau de neurones récurrent analysant les résultats de CNNs. Contrairement à notre hypothèse, les expérimentations montrent des résultats insuffisants pour la détection de présence des outils sur la table, mais de très bons résultats dans les vidéos du microscope. Nous obtenons des résultats encore meilleurs dans les vidéos du microscope après avoir fusionné l’information issue de la détection des changements sur la table et la présence des outils dans l’oeil. / The digital era is increasingly changing the world due to the sheer volume of data produced every day. The medical domain is highly affected by this revolution, because analysing this data can be a source of education/support for the clinicians. In this thesis, we propose to reuse the surgery videos recorded in the operating rooms for computer-assisted surgery system. We are chiefly interested in recognizing the surgical gesture being performed at each instant in order to provide relevant information. To achieve this goal, this thesis addresses the surgical tool recognition problem, with applications in cataract surgery. The main objective of this thesis is to address the surgical tool recognition problem in cataract surgery videos.In the surgical field, those tools are partially visible in videos and highly similar to one another. To address the visual challenges in the cataract surgical field, we propose to add an additional camera filming the surgical tray. Our goal is to detect the tool presence in the two complementary types of videos: tool-tissue interaction and surgical tray videos. The former records the patient's eye and the latter records the surgical tray activities.Two tasks are proposed to perform the task on the surgical tray videos: tools change detection and tool presence detection.First, we establish a similar pipeline for both tasks. It is based on standard classification methods on top of visual learning features. It yields satisfactory results for the tools change task, howev-lateer, it badly performs the surgical tool presence task on the tray. Second, we design deep learning architectures for the surgical tool detection on both video types in order to address the difficulties in manually designing the visual features.To alleviate the inherent challenges on the surgical tray videos, we propose to generate simulated surgical tray scenes along with a patch-based convolutional neural network (CNN).Ultimately, we study the temporal information using RNN processing the CNN results. Contrary to our primary hypothesis, the experimental results show deficient results for surgical tool presence on the tray but very good results on the tool-tissue interaction videos. We achieve even better results in the surgical field after fusing the tool change information coming from the tray and tool presence signals on the tool-tissue interaction videos.

Radiofrequency ablation (RFA) is a minimally invasive treatment for either hepatocellular carcinoma or metastasis liver carcinoma. In order to resect large lesions, the surgeon has to perform multiple time-consuming destruction cycles and reposition the RFA needle for each of them. The critical step in handling a successful ablation and preventing local recurrence is the correct positioning of the needle. For small tumors, the surgeon places the middle of the active needle tip in the center of the tumor under intra-operative ultrasound guidance. When one application is not enough to cover the entire tumor, the surgeon needs to repeat the treatment after repositioning of the needle, but US guidance is obstructed by the opacity stemming from the first RFA application. In this case the surgeon can only rely on anatomical knowledge and the repositioning of the RFA needle becomes a subjective task limiting the treatment accuracy. We have developed a computer assisted surgery guidance application for this repositioning procedure. Our software application handles the complete process from preoperative image analysis to tool tracking in the operating room. Our framework is mostly used for this RFA procedure, but is also suitable for any other medical or surgery application. / Doctorat en Sciences de l'ingénieur / info:eu-repo/semantics/nonPublished