Abstract: The invention relates to a device for carrying out a method for selecting an optimal treatment for the percutaneous ablation of a lesion within an anatomical structure of interest of a patient. The method uses a machine learning algorithm trained to calculate, from a medical image on which the lesion can be seen, and for each of a plurality of available treatments, a confidence score, the value of which represents a likelihood of success of said treatment for the ablation of the lesion. The machine learning algorithm is trained beforehand using a set of training elements each comprising a medical image on which a lesion can be seen within the anatomical structure of interest of another patient, a treatment selected from the various available treatments for treating said other patient, and a confidence score for the selected treatment on said other patient. The optimal treatment is then selected on the basis of the confidence scores calculated for the different available treatments.

Abstract: The invention relates to an optical navigation system for determining the position of a patient's anatomy of interest. The system comprises a locating device having at least two optical sensors and a patient reference having at least three optical markers. The system also comprises a reflecting device. When the line of sight between the patient reference and an optical sensor is intersected by an obstacle, the optical sensors are configured to measure, for each optical marker of the patient reference, a quantity representing the position of said optical marker in the frame of reference of the locating device from optical radiation originating from said optical marker and having a path reflected by the reflecting device to each optical sensor.

Abstract: The invention relates to a method and device for planning a surgical procedure aiming to ablate a tissue in an anatomical area of interest of a patient. On the basis of a preoperative image of the anatomical area of interest and of a set of planning parameters (P), a simulated image is generated by a neural network that has been previously trained using learning elements corresponding, respectively, to a similar surgical procedure for ablating a tissue in an anatomical area of interest for another patient. Each learning element comprises a preoperative image of the anatomical area of interest of a patient, planning parameters (P) used for the surgical procedure on this patient, and a postoperative image of the anatomical area of interest of this patient after the surgical procedure. An estimated ablation region may be segmented in the simulated image in order to be compared with a segmented region to be treated in the preoperative image.

Abstract: A medical robot (10) comprises a robotic arm (13) equipped with a tool guide (14) for guiding a medical instrument (15) along a trajectory defined by an entry point at the patient's skin and a target point at a lesion to be treated in an anatomy of interest of the patient. The medical robot cooperates with an ultrasound probe (40) and with a navigation system (30) for determining the position of the robot, the position of the ultrasound probe, and the position of a patient marker (22). The robot is configured to generate a model of the position of the target point and the position of the entry point according to the position of the patient marker on the basis of ultrasound images acquired by the ultrasound probe during at least one respiratory cycle of the patient. The model thus generated then allows the robotic arm to be controlled in real time according to the position of the patient marker in order to guide the medical instrument with precision.

Abstract: The invention relates to a medical robot comprising a robotic arm equipped with a tool guide for guiding a medical instrument along a trajectory defined by an entry point at the patient's skin and a target point at a lesion to be treated in an anatomical region of interest of the patient. The robotic arm is also provided with an ultrasound probe. The medical robot cooperates with a navigation system allowing determination of the position of a robot marker and the position of a patient marker. During a prepararatory phase, the robot is configured to place the ultrasound probe in contact with the patient and in a plane containing the lesion and the trajectory to be followed. During a guiding phase, the medical robot is configured to control the robotic arm in real time based on the ultrasound images acquired by the ultrasound probe, in order to guide the medical instrument along the trajectory to be followed.

Abstract: The invention relates to a method for generating synthetic medical images representing an anatomy of interest and an anomaly within said anatomy of interest. The method comprises generating majority segmentation masks associated with real medical images without anomaly, generating minority segmentation masks associated with real medical images with an anomaly, training a neural network to generate a synthetic medical image on the basis of a segmentation mask, generating artificial segmentation masks on the basis of the majority and minority segmentation masks by combining a segmentation of the anatomy of interest by a majority segmentation mask with a segmentation of the anomaly by a minority segmentation mask, and generating synthetic medical images on the basis of the artificial segmentation masks and using the previously trained neural network.

Abstract: The invention relates to a medical robot (10) comprising a motorized mobile base (13), spatial-location sensors (17) secured to the mobile base, and a control unit (16) that stores in memory an intervention plan comprising at least one action to be performed on the anatomy of interest of a patient (30). The control unit is configured to: —detect, from information coming from the spatial-location sensors (17), a position of the anatomy of interest of the patient with respect to the medical robot, —identify, from the position of the anatomy of interest of the patient and from the intervention plan, at least one favourable position of the mobile base of the medical robot for which position the medical robot is capable of performing the action or actions from the intervention plan, —move the mobile base of the medical robot into an optimal position selected from among the favourable position or positions identified.

Abstract: This invention concerns an automated registration method and device for a surgical robot enabling registration between a first three-dimensional location system comprising an optical distance sensor and a second three-dimensional location system comprising optical acquisition means. The method comprises: a first step of intraoperative registration between the first location system and data recorded on an anatomical surface of a patient and; a second step of intraoperative registration of two three-dimensional location systems. The second registration step is performed at the same time as the first registration step by detection, by the optical acquisition means, of at least one point of a point cloud acquired by the optical sensor during the first intraoperative registration.

Abstract: The invention relates to a medical robot for assisting a practitioner during a medical intervention on a relevant anatomical part of a patient. The medical robot comprises a robotic arm equipped, at one end, with a tool guide intended to guide a medical instrument. The medical robot also comprises a control unit configured to control the movement of the robotic arm. The tool guide is coupled to a force sensor. When the medical robot is used in a “cooperative manual control” mode, the control unit is configured to determine, using the force sensor, a force applied by the practitioner to the tool guide and to calculate a speed of movement of the tool guide on the basis of a gain factor applied to the determined force. Advantageously, the value of the gain factor is variable and is calculated on the basis of the determined force.

Abstract: The disclosure is directed to a synchronization device and method for identifying a specific moment in a patient's respiratory cycle to aid medical interventions. The device includes a locating apparatus, a patient reference with radio-opaque markers, a detectable locating element, an X-ray detector, and a control unit for data recording and processing. The invention aims to improve the accuracy and efficiency of medical procedures by synchronizing them with the patient's respiratory cycle.

Abstract: A robotic device for a minimally invasive medical intervention on soft tissues is provided. The robotic device uses a medical instrument having a robot arm having several degrees of freedom and having an end suitable for receiving the medical instrument, an image capture system suitable for capturing position information concerning the anatomy of the patient, a storage medium having a biomechanical model of the human body, a processing circuit configured to determine a position setpoint and an orientation setpoint for said medical instrument on the basis of the biomechanical model, on the basis of the position information and on the basis of a trajectory to be followed by the medical instrument in order to perform the medical intervention, and a control circuit configured to control the robot arm in order to place the medical instrument in the position setpoint and the orientation setpoint.

Abstract: An augmented-reality navigation system is used to assist a practitioner during a surgical operation on an anatomical structure of interest of a patient. The operation is planned on a pre-operational medical image. The navigation system comprises a camera that is intended to be worn by the practitioner on his head, a display device for displaying, in real-time, the real images acquired by the camera and an augmented-reality content superposed on the real images, and a control unit connected to the camera and to the display device. The control unit is configured to generate a predictive model of the movement of a marker placed in proximity to the anatomical structure of interest on the basis of the movement followed by the marker during one or more respiratory cycles of the patient.

Abstract: The invention relates to a recalibration device (1) used during the acquisition of images of an anatomical area of a patient during robot-assisted surgery, including a body (3) made of radxoliacent material, which comprises fiducial markers (9) made of radiopaque material, said body (3) having a bearing surface (7) intended to be manually placed on a surface of said anatomical area of the patient. According to the invention, said fiducial markers (9) are arranged in a specific geometrical pattern enabling a certain detection of the positioning and orientation of the recalibration device (1) in a three-dimensional digital model built from the images derived from the acquisition of the anatomical area.

Abstract: The invention relates to a method for positioning an articulated arm of a medical robot assisted by a navigation system comprising an electromagnetic field generator and two sensors. The generated field forms a measurement zone in which the position of a sensor can be determined by the navigation system and communicated to the robot. A first sensor is positioned at an anatomical location of interest of a patient. A second sensor is positioned on the articulated arm. When the two sensors are located in the measurement zone, a so-called “region of reduced influence” of the measurement zone is determined, in which the introduction of a metal object has virtually no influence on the determination of the position of the sensors by the navigation system. The articulated arm is then configured so that any metal part of the articulated arm located in the measurement zone is situated within the region of reduced influence.

Abstract: The invention relates to a method for evaluating in post-treatment an ablation of a portion of an anatomy of interest of an individual, the anatomy of interest comprising at least one lesion. The evaluation method comprises in particular a step of automatically determining a contour of the ablation region by means of an automatic learning method, such as a neural network, analyzing the post-treatment image of the anatomy of interest of the individual, said automatic learning method being preloaded during a so-called training phase using a database comprising a plurality of post-operative medical images of an anatomy of identical interest of a set of patients, each medical image of the database being associated with an ablation region of the anatomy of interest of said patient. The invention also relates to an electronic device comprising a processor and a computer memory storing instructions of such an evaluation method.

Abstract: The invention relates to a method for evaluating in post-treatment an ablation of a portion of an anatomy of interest of an individual, the anatomy of interest comprising at least one lesion. The post-treatment evaluation method comprises in particular a step of automatically evaluating a risk of recurrence of the lesion of the anatomy of interest of the individual based on the analysis of a pair of pre-operative and post-operative medical images of the anatomy of interest of the individual by means of automatic learning method of the neural network type, said method being preloaded during a so-called training phase on a database comprising a plurality of pairs of medical images of an anatomy of interest identical to a plurality of individuals, each medical image pair of the database being associated with a recurrence status of a lesion of the anatomy of interest of said patient.

Abstract: The invention relates to a method for automatically planning a trajectory to be followed during a medical intervention by a medical instrument targeting an anatomy of interest of a patient, said automatic planning method comprising the steps of: acquiring at least one medical image of the anatomy of interest; determining a target point on the previously acquired image; generating a set of trajectory planning parameters from the medical image of the anatomy of interest and the previously determined target point, the set of planning parameters comprising coordinates of an entry point on the medical image. The set of parameters is generated using a machine learning method of neural network type. The invention also relates to a guiding device implementing the set of planning parameters obtained.

Abstract: The invention relates to an optical navigation system for determining the position of a patient's anatomy of interest. The system comprises a locating device having at least two optical sensors and a patient reference having at least three optical markers. The system also comprises a reflecting device. When the line of sight between the patient reference and an optical sensor is intersected by an obstacle, the optical sensors are configured to measure, for each optical marker of the patient reference, a quantity representing the position of said optical marker in the frame of reference of the locating device from optical radiation originating from said optical marker and having a path reflected by the reflecting device to each optical sensor.

Abstract: The invention relates to a method and device for planning a surgical procedure aiming to ablate a tissue in an anatomical area of interest of a patient. On the basis of a preoperative image of the anatomical area of interest and of a set of planning parameters (P), a simulated image is generated by a neural network that has been previously trained using learning elements corresponding, respectively, to a similar surgical procedure for ablating a tissue in an anatomical area of interest for another patient. Each learning element comprises a preoperative image of the anatomical area of interest of a patient, planning parameters (P) used for the surgical procedure on this patient, and a postoperative image of the anatomical area of interest of this patient after the surgical procedure. An estimated ablation region may be segmented in the simulated image in order to be compared with a segmented region to be treated in the preoperative image.

Abstract: A device for guiding a needle includes a tool holder intended to be fixed to the end of a medical assistance robotic arm, said tool-holder supporting a needle guide; the needle guide includes two jaws including a respective groove, said two grooves extending along parallel longitudinal axes, said jaws being supported by the tool-holder so as to allow mobility in rotation of the jaws relative to one another between a position termed the “guiding position” in which the grooves are adjacent and define a duct for guiding a needle and a position termed the “disengaged position” in which the grooves are moved away from one another and define a needle lateral disengagement zone.