MRI suffers from an inherent trade-off between signal-to-noise ratio, acquisition time, and spatial resolution [1]–[3]. K-space undersampling allows for a reduction in acquisition time at the cost of decreased signal-to-noise ratio and/or spatial resolution [7]. Initially developed to aid in tissue segmentation [18], [19], U-Nets have also been utilized effectively to improve the image quality of a diverse array of MRI contrasts [20]–[22]. The performance of U-Nets can be enhanced by providing the network with a fully sampled complementary contrast as a prior to allow for cross-contrast feature transfer [29]. We implement aim to verify that cross-contrast feature transfer improves the quality of images output by a dense U-Net (DU-Net). We assess whether the choice of complementary T1 or T2 weighted MRI contrasts for undersampling affects the quality of output images. We also aim to improve the sensitivity of image quality metrics used to compare networks by restricting their calculation to areas bounded around regions of clinical diagnostic interest. The quality of DU-Net outputs does not change significantly when the contrast used as a prior is exchanged; image quality metrics are all within one standard deviation of each other. There is also no quantifiable difference between models trained with a cross-contrast prior and those that are not. There are, however, qualitative improvements, particularly in the regions around tumors. Bounding error calculation regions leads to an increase in the significance of the measured difference between DU-Net outputs in most cases.

In the field of MRI super-resolution, training an image upscaling network under a pixel-oriented cost function (e.g., Mean-Intensity-Error) has proven to boost the signal-to-noise ratio. However, these types of cost functions tend to miss high-frequency details and fail to achieve an ideal sharpness, which is a pivotal image property for clinical applications to make diagnoses. To address this issue, the cost function of these upscaling networks typically includes a perceptual loss function, which is well recognized for the reconstruction of textures and enhancing sharpness, in addition to a pixel-oriented one. In this paper, we investigate the effect of perceptual loss on several MRI super-resolution metrics. We train UNet architecture under two loss function scenarios: One only including a pixel-oriented loss function, and the other a fusion of pixel-oriented and perceptual losses. We then employ an ablation study using a mixed effect model on a comprehensive set of evaluation criteria to measure the significance of change upon the inclusion of perceptual loss. Our results show that even though perceptual loss substantially shifts the networks towards outputting sharper images, it only causes negligible performance degradation in the accuracy of the reconstructed regions of interest, which can be alleviated using proper hyperparameter tuning.

Augmented reality (AR) enables immersion into imaging data, especially for visualization of 3-dimensional imaging data. High-quality and dynamic sceneries in AR platforms can positively impact many biomedical and bioinformatics fields, including education, training, research, and clinical practice. To create such sceneries, collaboration between multiple software platforms is crucial. While many file formats are capable of storing 3D models, 3D data sharing and collaboration between different applications to harness the power of each one in order to create high-quality multidimensional AR sceneries have always been challenging. It requires a common file format to enable real-time and efficient processing along the pipeline. Universal Scene Description (USD) is an open-source file format for robust and scalable interchange and augmentation of 3D scenes from various sources. It was also recently adopted by NVIDIA into its Omniverse platform and standardized by the Alliance for OpenUSD (AOUSD). The use of high-fidelity USD can be transformative in bioinformation for synergetic and interactive immersion of researchers and clinicians into 3D/4D data. AR immersion into USD data requires communication of servers or cloud facilities with the users' head-mounted display (HMD) or hand-held display (HHD) devices. We present a software application to bridge this gap between multi-modality AR immersion and USD data, which offers real-time multi-user AR immersion into USD data to enhance the potential of USD and take the AR immersion experience to the next level.

The advent of intraoperative real-time image guidance has led to the emergence of new surgical interventional paradigms including image-guided robot assistance. Most often the use of an intraoperative imaging modality is limited to visual perception of the area of procedure. In this work, we propose a system for performing interventions with real-time Magnetic Resonance Imaging (rtMRI). The described computational core, processes on-the-fly rtMRI and generates dynamic guidance virtual fixture that in turn is used to update visualization and a force-feedback interface. The system was experimentally tested by applying it to a simulated Transapical Aortic Valve Implantation with a virtual robotic manipulator. The study results demonstrate significant improvement in the surgical task by decreasing the duration of the procedure and increasing safety in the presence of cardiac and breathing motion.

This work presents an interventional planning software to be used in conjunction with a robotic manipulator to perform transrectal MR guided prostate biopsies. The interventional software was designed taking in consideration a generic manipulator used under the two modes of operation: side-firing and end-firing of the biopsy needle. Studies were conducted with urologists using the software to plan virtual biopsies. The results show features of software relevant for operating efficiently under the two modes of operation.

Finding the appropriate set of features in cardiac MRI images to localize different areas and anomalies of heart is an essential problem. Convolutional neural networks are known to be well suited for the task to extract features from gray scale images where the intensity is enhanced. This paper proposes a convolutional neural network architecture which can be used to localize the myocardial infarction on the heart using low resolution late gadolinium enhanced (LGE) images. LGE images are T1 weighted MRI images that use contrast agents to increase the intensity of regions where blood accumulates, as a result, areas of heart like ventricle and infarction are brighter as compared to other regions of the heart. We create a U-Net inspired model and train it with the LGE cardiac images to locate and segment the infarction. Our data set has small number of training images with low contrast, which makes it difficult to generalize the features of infarction. To tackle this issue, we propose geometric transformations and pixel intensity manipulations, that should be used for augmenting LGE images to create a diverse training data set. We also propose a chained U-Net approach to reduce the search space for segmenting infarction in LGE cardiac images. Our analysis show a reduction of error from 82% to 68% in segmentation by using the proposed augmentation and the chaining technique. However, it falls short of human level accuracy. Later part of this paper describes the limitation of our current work and lists the future work to overcome those limitations.

This work presents a novel deep learning architecture called BNU-Net for the purpose of cardiac segmentation based on short-axis MRI images. Its name is derived from the Batch Normalized (BN) U-Net architecture for medical image segmentation. New generations of deep neural networks (NN) are called convolutional NN (CNN). CNNs like U-Net have been widely used for image classification tasks. CNNs are supervised training models which are trained to learn hierarchies of features automatically and robustly perform classification. Our architecture consists of an encoding path for feature extraction and a decoding path that enables precise localization. We compare this approach with a parallel approach named U-Net. Both BNU-Net and U-Net are cardiac segmentation approaches: while BNU-Net employs batch normalization to the results of each convolutional layer and applies an exponential linear unit (ELU) approach that operates as activation function, U-Net does not apply batch normalization and is based on Rectified Linear Units (ReLU). The presented work (i) facilitates various image preprocessing techniques, which includes affine transformations and elastic deformations, and (ii) segments the preprocessed images using the new deep learning architecture. We evaluate our approach on a dataset containing 805 MRI images from 45 patients. The experimental results reveal that our approach accomplishes comparable or better performance than other state-of-the-art approaches in terms of the Dice coefficient and the average perpendicular distance.

Prostate biopsy is considered as a definitive way for diagnosing prostate malignancies. Urologists are currently moving towards MR-guided prostate biopsies over conventional transrectal ultrasound-guided biopsies for prostate cancer detection. Recently, robotic systems have started to emerge as an assistance tool for urologists to perform MR-guided prostate biopsies. However, these robotic assistance systems are designed for a specific clinical environment and cannot be adapted to modifications or changes applied to the clinical setting and/or workflow. This work presents the preliminary design of a cable-driven manipulator developed to be used in both MR scanners and MR-ultrasound fusion systems. The proposed manipulator design and functionality are evaluated on a simulated virtual environment. The simulation is created on an in-house developed interventional planning software to evaluate the ergonomics and usability. The results show that urologists can benefit from the proposed design of the manipulator and planning software to accurately perform biopsies of targeted areas in the prostate.

This paper investigates the effectiveness of Common Spatial Patterns (CSP) analysis of EEG signals on the automatic detection of focal epileptic seizures. Focal seizures are characterized by unilaterally triggered abnormal brain activity. CSP analysis has been frequently used in literature for multichannel EEG signal separation between two states. In the present study, EEG recordings from 10 subjects aged 7.7±4.4 years, including 63 seizures, were analyzed with respect to seizure detection and discrimination between interictal and ictal periods. Machine learning techniques of feature selection and classification were used in the analysis, resulting in a best achieved classification accuracy of 91.1%.

The emerging potential of augmented reality (AR) to improve 3D medical image visualization for diagnosis, by immersing the user into 3D morphology is further enhanced with the advent of wireless head-mounted displays (HMD). Such information-immersive capabilities may also enhance planning and visualization of interventional procedures. To this end, we introduce a computational platform to generate an augmented reality holographic scene that fuses pre-operative magnetic resonance imaging (MRI) sets, segmented anatomical structures, and an actuated model of an interventional robot for performing MRI-guided and robot-assisted interventions. The interface enables the operator to manipulate the presented images and rendered structures using voice and gestures, as well as to robot control. The software uses forbidden-region virtual fixtures that alerts the operator of collisions with vital structures. The platform was tested with a HoloLens HMD in silico. To address the limited computational power of the HMD, we deployed the platform on a desktop PC with two-way communication to the HMD. Operation studies demonstrated the functionality and underscored the importance of interface customization to fit a particular operator and/or procedure, as well as the need for on-site studies to assess its merit in the clinical realm.

Heart disease is highly prevalent in developed countries, causing 1 in 4 deaths. In this work we propose a method for a fully automated 4D reconstruction of the left ventricle of the heart. This can provide accurate information regarding the heart wall motion and in particular the hemodynamics of the ventricles. Such metrics are crucial for detecting heart function anomalies that can be an indication of heart disease. Our approach is fast, modular and extensible. In our testing, we found that generating the 4D reconstruction from a set of 250 MRI images takes less than a minute. The amount of time saved as a result of our work could greatly benefit physicians and cardiologist as they diagnose and treat patients.

Fluidic transmission mechanisms use fluids to transmit force through conduits. We previously presented a transmission mechanism called solid-media transmission (SMT), which uses conduits filled with spheres and spacers for push-only bidirectional transmission. In this paper, we present new designs of SMT-actuated one-degree-of-freedom (DoF) and two-degree-of-freedom positioning manipulators, and report experiment studies to assess their performance. In these studies, closed-loop position control was performed with a PI controller and/or master-slave control. With braided PTFE tubing, SMT exhibited sub-millimeter accuracy, with a tolerance of ±0.05 mm for the tested transmission lines with lengths up to 4m.

This work presents a prototype holographic interface (HI) for the 3D visualization of MRI data for the purpose of planning neurosurgical procedures. The presented HI (i) immerses the operator to a mixed reality (MiR) scene, which includes MRI data and virtual renderings, (ii) facilitates interactive manipulation of the objects of the MiR scene for planning and (iii) is the front-end of a pipeline that links the operator to the MRI scanner for on-the-fly control of the scanner. Preliminary qualitative evaluation revealed that holographic visualization of high-resolution 3D MRI data offers an intuitive and interactive perspective of the complex brain vasculature and anatomical structures. These early work further suggests that immersive experience may be an unparalleled tool in better planning neurosurgical procedures. Further development is required to speed up the pipeline from the MRI scanner to the HI and incorporating means of manipulations other than gestures.

Needle-based image-guided interventions (NB-IGI) are well established practices that are rapidly expanding to a wider range of therapeutic and diagnostic interventions due to their impact on clinical outcomes. In parallel, a number of robotic manipulators are emerging to increase accuracy, decrease inter-operator variabilities, and reduce the duration of the procedure. Most current systems are application-specific, thereby are appropriate for a limited number of procedures and further exacerbating the already rising costs of healthcare. In order to expand clinical usage of robotic NB-IGI, and eventually reduce the burden on healthcare costs, this paper proposes a modular, customizable robotic systems concept. The concept includes simplified hardware and control techniques, and initial results demonstrate that accuracy is within clinically acceptable limits. Preliminary designs, implementations, and assessments of the proposed system demonstrate its potential and clinical value.

Magnetic resonance imaging (MRI)-guided, manipulator-assisted interventions have the potential to improve patient outcomes. This work presents a force transmission mechanism, called solid-media transmission (SMT), for actuating manipulators inside MRI scanners. The SMT mechanism is based on conduits filled with spheres and spacers made of a nonmagnetic, nonconductive material that forms a backbone for bidirectional transmission. Early modeling and experimental studies assessed SMT and identified limitations and improvements. Simulations demonstrated the detrimental role of friction, which can be alleviated with a choice of low friction material and long spacers. However, the length of the spacer is limited by the desired bending of the conduit. A closed-loop control law was implemented to drive the SMT. The 3rd order system fit ratio is 92.3%. A 1-m long SMT was experimentally tested under this closed-loop controller with heuristically set parameters using a customized benchtop setup. For commanded displacements of 1 to 50 mm, the SMT-actuated 1 degree of freedom stage exhibited sub-millimeter accuracy, which ranged from 0.109 ± 0:057 mm to 0.045 ± 0.029 mm depending on the commanded displacement. However, such accuracy required long control times inversely proportional to displacement ranging from 7.56 ± 1.85s to 2.53 ± 0.11s. This was attributed to friction as well as backlash which is due to suboptimal packing of the media. In MR studies, a 4-m long SMT-actuated 1 DoF manipulator was powered by a servo motor located inside the scanner room but outside the 5 Gauss line of the magnet. With shielding and filtering, the SNR of MR images during the operation of the servo motor and SMT- actuation was found to be 89 ± 9% of the control case.

Image-guided and robot-assisted surgical procedures are rapidly evolving due to their potential to improve patient management and cost effectiveness. Magnetic Resonance Imaging (MRI) is used for pre-operative planning and is also investigated for real-time intra-operative guidance. A new type of technology is emerging that uses the magnetic field gradients of the MR scanner to maneuver ferromagnetic agents for local delivery of therapeutics. With this approach, MRI is both a sensor and forms a closed-loop controlled entity that behaves as a robot (we refer to them as MRbots). The objective of this paper is to introduce a computational framework for preoperative planning using MRI and modeling of MRbot maneuvering inside tortuous blood vessels. This platform generates a virtual corridor that represents a safety zone inside the vessel that is then used to access the safety of the MRbot maneuvering. In addition, to improve safety we introduce a control that sets speed based on the local curvature of the vessel. The functionality of the framework was then tested on a realistic operational scenario of accessing a neurological lesion, a meningioma. This virtual case study demonstrated the functionality and potential of MRbots as well as revealed two primary challenges: real-time MRI (during propulsion) and the need of very strong gradients for maneuvering small MRbots inside narrow cerebral vessels. Our ongoing research focuses on further developing the computational core, MR tracking methods, and on-line interfacing to the MR scanner.

Cardiac gating or breath-hold MRI acquisition is challenging. In particular, data collected in a short amount of time might be insufficient for the diagnosis of patients with impaired breath-holding capabilities and/or arrhythmia. A major challenge in cardiac MRI is the motion of the heart itself, the pulsate blood flow, and the respiratory motion. Furthermore, the motion of the diaphragm in the chest moving up and down gets translated to the heart when a patient breathes. Therefore, artifacts arise due to the changes in signal intensity or phase as a function of time, resulting in blurry images. This paper describes a novel reconstruction strategy for real time cardiac MRI without requiring the use of an electro-cardiogram or of breath holding. In this research we focused on automation and evaluation of the performance of our proposed method in real time MRI data to ensure a good basis for the signal extraction. Hence, it assists in the reconstruction. The proposed method enables one to extract cardiac beating waveforms directly from real-time cardiac MRI series collected from freely breathing patients and without cardiac gating. Our method only requires minimal user involvement as initialization step. Thereafter, the method follows the registered area in every frame and updates itself.

Efficient and intuitive interfacing of the interventionalist to the information and tools available from image-guided robotic assisted surgeries is required to achieve the full benefit of these technologies. Ongoing research has been performed into the use of forbidden region guided fixtures (FRVF) for human-in-the-loop control of image-guided procedures via haptic force-feedback devices (FFD). Although commercially available FFD provide sufficient degrees-of-freedom (DoF), collaborating clinicians, as well as the results of our previous work indicate that these systems are not completely intuitive for controlling fixed-point access interventional tool which have a remote center of motion. Within this context, we introduce a new FFD which is designed with the same DoF constraints as a fixed-point access interventional tool. The device is tested in a clinical simulation of a robot assisted trans-apical valve implantation under guidance from real-time magnetic resonance imaging. Pre-acquired real-time images are used in the clinical simulation to dynamically update the FRVF and therefore provide guiding forces to allow the operator to see the safe boundaries of operation via a visualization interface and physically feel them through the FFD. Inertial and gravity compensation and per DoF dynamic response of the physical prototype are validated and the frequency response of the system demonstrates it is adequate for tactile sensing. During clinical simulation the operator was successfully able to maneuver the tool within the safe path to the region of interest with the guidance of visual and force-feedback.

Co-registering pre- and intra- operative MR data is an important yet challenging problem due to different acquisition parameters, resolutions, and plane orientations. Despite its importance, previous approaches are often computationally intensive and thus cannot be employed in real-time. In this paper, a novel three-step approach is proposed to dynamically register pre-operative 4D MR data with intra-operative 2D RT-MRI to guide intracardiac procedures. Specifically, a novel preparatory step, executed in the pre-operative phase, is introduced to generate bridging information that can be used to significantly speed up the on-the-fly registration in the intraoperative procedure. Our experimental results demonstrate an accuracy of 0.42 mm and a processing speed of 26 FPS of the proposed approach on an off-the-shelf PC. This approach, is in particularly developed for performing intra-cardiac procedures with real-time MR guidance.

Interrogation of tissue with combined molecular methods, such as light-induced fluorescence (LIF) and MR spectroscopy (MRS), may lead to new paradigms in assessing tissue malignancy in situ. The limited tissue penetration (LIF) or low sensitivity (MRS) of those modalities is usually addressed by local placement of the sensor via trans-needle or trans-catheter access. This work introduces a system and methodological approaches for mechanically scanning an area of interest with an MR-compatible manipulator that carries two sensors: an optical fiber for LIF and a miniature RF coil for MRS. Experimental studies on multi-compartment phantoms demonstrated dual-modality scanning and the generation of one-dimensional MRS/LIF scans inherently registered to MRI that was used to guide the scanning.

The development and initial testing of a prototype concentric tube robot suitable for surgical applications is presented. The system is endowed with 3 degrees-of-freedom and consists of a three concentric tubes assembly and an actuation module. Design issues are discussed in a general context of concentric tube robots in view of their potential applications in surgery. Among the distinct features of the system is that the actuation module provides a mechanical decoupling between the available motions that effectively facilitates control of the device. Such robotic systems are considered particularly suitable for MR- guided interventions and compatibility issues with the specific imaging modality are discussed. Initial experimental testing of the device is presented which involved tip targeting and steering trials using direct visual feedback for guidance.

Robot-assisted surgical procedures are perpetually evolving due to potential improvement in patient treatment and healthcare cost reduction. Integration of an imaging modality intraoperatively further strengthens these procedures by incorporating the information pertaining to the area of intervention. Such information needs to be effectively rendered to the operator as a human-in-the-loop requirement. In this work, we propose a guidance approach that uses real-time MRI to assist the operator in performing robot-assisted procedure in a beating heart. Specifically, this approach provides both real-time visualization and force-feedback based guidance for maneuvering an interventional tool safely inside the dynamic environment of a heart's left ventricle. Experimental evaluation of the functionality of this approach was tested on a simulated scenario of transapical aortic valve replacement and it demonstrated improvement in control and manipulation by providing effective and accurate assistance to the operator in real-time.

Robotic manipulators have emerged and are continuously evolving as a valuable tool in medical applications. This work introduces a new biomedical application for robotics: multimodality imaging by facilitating scanning of spatially localized bio-sensing and co-registration. Established or currently emerging molecular and near cellular modalities, such as optical and magnetic resonance spectroscopy, offer new opportunities for assessing tissue pathophysiology in situ. The limited tissue penetration of those modalities can be addressed by locally placing the sensor, i.e. with a minimally invasive trans-needle or trans-catheter approach. Herein, we describe the use of a robotic manipulator to scan the area of interest by carrying such a sensor for generating 1-D scans while registering them to a guiding modality. The approach is demonstrated by using a miniature RF coil for collecting proton MR spectra (MRS) and scanning an area of interest on phantoms with the manipulator. MRI is used to guide this procedure as well as co-register MR imaging and spectroscopy. LineScans on two compartment phantoms demonstrated a clear spatial distribution of the resonances originating from those compartments in agreement with the scout guiding MR images. The system described herein, is a generalized platform for performing MR-guided multimodality and multilevel sensing.

As a part of an ongoing project, in this paper we introduce the first version of a system which has a novel methodology for Cine (as in cinema) MRI based control of a cardiac robot for beating heart surgeries. The system uses the preoperative planning approach that we developed earlier, and integrates it to the intraoperative algorithms for controlling a robot and tracking some specific landmarks of a highly dynamical surgical field. In particular, our late studies presented herein aim to demonstrate the feasibility of integrating appropriate computational tools to achieve the volumetric image guidance for minimally invasive surgeries in the beating heart. We conceive of the system as practicable for in vitro experiments upon the completion of the first physical prototype, which may pave the way for expansion of the approach for other complex surgeries as well.

In this paper we present a new approach for curve clustering designed for analysis of spatiotemporal data. Such kind of data contains both spatial and temporal patterns that we desire to capture. The proposed methodology is based on regression and Gaussian mixture modeling and the novelty of the herein work is the incorporation of spatial smoothness constraints in the form of a prior for the data labels. This enables the proposed model to take into account the underlying property of spatiotemporal data that spatially adjacent data points most likely should belong to the same cluster. A maximum a posteriori Expectation Maximization (MAP-EM) algorithm is used for learning this model. We present numerical experiments with simulated data where the ground truth is known in order to assess the value of the introduced smoothness constraint, and also with real cardiac perfusion MRI data. The results are very promising and demonstrate the value of the proposed constraint for analysis of such data .

The aim of this work is to develop a seven degree of freedom (DOF) remotely controlled manipulator to perform minimally invasive interventions with real-time magnetic resonance imaging (MRI) guidance inside clinical cylindrical scanners. Control of the device is based on MR images collected pre-operatively and in real-time during the procedure. A user interface fuses all sensor information for man-in-the-loop control. Stereotactic guidance uses multislice and/or three-dimensional MR images to set a trajectory of insertion. Free-handed (or manual) guidance uses a master/slave control device, which replicates the kinematics structure of the arm, to control its movement. The control software checks any motion of the manipulator whether it is within an allowable volume extracted from MR images. The device control is performed with a host/target computer configuration. The system is connected to the MR scanner to receive the MR images and send the coordinates of the end-effector for dynamic control of the imaged plane. The manipulator compatibility with the MR environment and image-guided maneuvering was tested on a 1.5 Tesla MR scanner

A popular configuration for the actuation of robotic manipulators with articulated joints is to have motors directly attached to the joints. This approach does not involve any transmission elements between the actuators and the joints and it is advantageous in many respects. However, in certain cases this configuration may not be appropriate and manipulators with remotely-actuated joints may be desirable. In this article different alternatives for the implementation of remote actuation would be discussed and a case study would be presented relevant to a robotic arm, which was designed to operate inside a closed cylindrical magnetic resonance imaging (MRI) scanner for the performance of image-guided interventions. The transfer of motion to the articulated joints of the arm was implemented using drive shafts and universal joints (u-joints). Experimental testing of the arm highlights issues relevant to remote actuation

A method is proposed for fast magnetic resonance imaging (MRI) acquisition of targeted specific structures. The method is based on the correlation between the inverse space (k-space) and the real space geometry of the imaged structure. Theoretical and simulation studies were performed with segments of straight and curved vessels. In cases when we are interested for only a segment of a vessel, as example for interventions, these studies show that as small as 1/8 of the whole k-space data is sufficient to reconstruct the interested vessel without compromise in the image quality.

We have developed a device to perform minimally invasive interventions in the breast with realtime MRI guidance for the early detection and treatment of breast cancer. The device uses five computer-controlled degrees of freedom to perform minimally invasive interventions inside a closed MRI scanner. Typically the intervention would consist of a biopsy of the suspicious lesion for diagnosis, but may involve therapies to destroy or remove malignant tissue in the breast. The procedure proceeds with: (a) conditioning of the breast along a prescribed orientation, (b) definition of an insertion vector by its height and pitch angle, and (c) insertion into the breast. The entire device is made of materials compatible with MRI, avoiding artifacts and distortion of the local magnetic field. The device is remotely controlled via a graphical user interface. This is the first surgical robotic device to perform real-time MRI-guided breast interventions in the United States.

The objective of this work was to develop a robotic apparatus for MR-guided biopsy and therapeutic interventions in the breast. This device facilitates (i) conditioning of the breast, by setting the orientation and degree of compression, (ii) definition of the interventional probe trajectory, by setting the height and angulation of a probe guide and (iii) positioning of an interventional probe, by setting the depth of insertion. The apparatus is fitted with appropriate computer-controlled degrees of freedom for optimal approach for delivering and monitoring interventions with MR-guidance, such as diagnostic or therapeutic trans-cannula or subcutaneous minimally invasive procedures. The entire device is constructed of MR compatible material, i.e. non-magnetic and non-conductive, to eliminate artifacts and distortion of the local magnetic field. The apparatus is remotely controlled by means of ultrasonic actuators and a graphics user interface, providing real-time MR-guided planning and monitoring of the operation.