Electrical impedance tomography image reconstruction for lung monitoring based on ensemble learning algorithms

Electrical impedance tomography (EIT) is a promising non-invasive imaging technique that visualizes the electrical conductivity of an anatomic structure to form based on measured boundary voltages. However, the EIT inverse problem for the image reconstruction is nonlinear and highly ill-posed. Therefore, in this work, a simulated dataset that mimics the human thorax was generated with boundary voltages based on given conductivity distributions. To overcome the challenges of image reconstruction, an ensemble learning method was proposed. The ensemble method combines several convolutional neural network models, which are the simple Convolutional Neural Network (CNN) model, AlexNet, AlexNet with residual block, and the modified AlexNet model. The ensemble models' weights selection was based on average technique giving the best coefficient of determination (R2 score). The reconstruction quality is quantitatively evaluated by calculating the root mean square error (RMSE), the coefficient of determination (R2 score), and the image correlation coefficient (ICC). The proposed method's best performance is an RMSE of 0.09404, an R2 score of 0.926186, and an ICC of 0.95783 using an ensemble model. The proposed method is promising as it can construct valuable images for clinical EIT applications and measurements compared to previous studies.

Untethered Microgrippers for Precision Medicine

Microgrippers, a branch of micro/nanorobots, refer to motile miniaturized machines that are of a size in the range of several to hundreds of micrometers. Compared with tethered grippers or other microscopic diagnostic and surgical equipment, untethered microgrippers play an indispensable role in biomedical applications because of their characteristics such as miniaturized size, dexterous shape tranformation, and  controllable motion, which enables the microgrippers to enter hard-to-reach regions to execute specific medical tasks for disease diagnosis and treatment. To date, numerous medical microgrippers are developed, and their potential in cell manipulation, targeted drug delivery, biopsy, and minimally invasive surgery  are explored. To achieve controlled locomotion and efficient target-oriented actions, the materials, size, microarchitecture, and morphology of microgrippers shall be deliberately designed. In this review, the authors summarizes the latest progress in untethered micrometer-scale grippers. The working mechanisms of shape-morphing and actuation methods for effective movement are first introduced. Then, the design principle and state-of-the-art fabrication techniques of microgrippers are discussed. Finally, their applications in the precise medicine are highlighted, followed by offering future perspectives for the development of untethered medical microgrippers.

3-D real-time ultrasound tracking of acoustically actuated swimming microdrone

Maneuverable microswimmers/microdrones that navigate in hard-to-reach spaces inside human bodies hold a great potential for various biomedical applications. Acoustically actuated microswimmers have already demonstrated feasibility. However, for eventual translation of this technology, a robust 3-D tracking strategy for the microswimmer is particularly required. This paper presents our lab-designed 3-D ultrasound tracking system for real-time tracking of an acoustically actuated 3-D swimming microdrone. The ultrasound tracking system utilizing two ultrasound probes, a step motor and a host controller, was built to track the 3-D arbitrary motion of the microdrone in real-time. The performance of tracking was evaluated in the benchtop experiments by comparing the reconstructed trajectories with synchronized camera recordings. The ultrasound tracking system showed high reliability, with an average error of less than 0.3 mm across six different trials when compared to camera tracking. The results demonstrated the capability of our lab-designed 3-D ultrasound tracking system in accurately tracking the undetermined motion of the acoustic actuated 3-D swimming microdrone in real-time. The developed tracking system holds promise as a potential approach for biomedical applications and could pave the way for future clinical translation of the microswimmer technology.

Capsule robot pose and mechanism state detection in ultrasound using attention-based hierarchical deep learning

Ingestible robotic capsules with locomotion capabilities and on-board sampling mechanism have great potential for non-invasive diagnostic and interventional use in the gastrointestinal tract. Real-time tracking of capsule location and operational state is necessary for clinical application, yet remains a significant challenge. To this end, we propose an approach that can simultaneously determine the mechanism state and in-plane 2D pose of millimeter capsule robots in an anatomically representative environment using ultrasound imaging. Our work proposes an attention-based hierarchical deep learning approach and adapts the success of transfer learning towards solving the multi-task tracking problem with limited dataset. To train the neural networks, we generate a representative dataset of a robotic capsule within ex-vivo porcine stomachs. Experimental results show that the accuracy of capsule state classification is 97%, and the mean estimation errors for orientation and centroid position are 2.0 degrees and 0.24 mm (1.7% of the capsule's body length) on the hold-out test set. Accurate detection of the capsule while manipulated by an external magnet in a porcine stomach and colon is also demonstrated. The results suggest our proposed method has the potential for advancing the wireless capsule-based technologies by providing accurate detection of capsule robots in clinical scenarios.

Review of Bubble Applications in Microrobotics: Propulsion, Manipulation, and Assembly

In recent years, microbubbles have been widely used in the field of microrobots due to their unique properties. Microbubbles can be easily produced and used as power sources or tools of microrobots, and the bubbles can even serve as microrobots themselves. As a power source, bubbles can propel microrobots to swim in liquid under low-Reynolds-number conditions. As a manipulation tool, microbubbles can act as the micromanipulators of microrobots, allowing them to operate upon particles, cells, and organisms. As a microrobot, microbubbles can operate and assemble complex microparts in two- or three-dimensional spaces. This review provides a comprehensive overview of bubble applications in microrobotics including propulsion, micromanipulation, and microassembly. First, we introduce the diverse bubble generation and control methods. Then, we review and discuss how bubbles can play a role in microrobotics via three functions: propulsion, manipulation, and assembly. Finally, by highlighting the advantages and current challenges of this progress, we discuss the prospects of microbubbles in microrobotics.

CeFlowBot: A Biomimetic Flow-Driven Microrobot that Navigates under Magneto-Acoustic Fields

Aquatic organisms within the Cephalopoda family (e.g., octopuses, squids, cuttlefish) exist that draw the surrounding fluid inside their bodies and expel it in a single jet thrust to swim forward. Like cephalopods, several acoustically powered microsystems share a similar process of fluid expulsion which makes them useful as microfluidic pumps in lab-on-a-chip devices. Herein, an array of acoustically resonant bubbles are employed to mimic this pumping phenomenon inside an untethered microrobot called CeFlowBot. CeFlowBot contains an array of vibrating bubbles that pump fluid through its inner body thereby boosting its propulsion. CeFlowBots are later functionalized with magnetic layers and steered under combined influence of magnetic and acoustic fields. Moreover, acoustic power modulation of CeFlowBots is used to grasp nearby objects and release it in the surrounding workspace. The ability of CeFlowBots to navigate remote environments under magneto-acoustic fields and perform targeted manipulation makes such microrobots useful for clinical applications such as targeted drug delivery. Lastly, an ultrasound imaging system is employed to visualize the motion of CeFlowBots which provides means to deploy such microrobots in hard-to-reach environments inaccessible to optical cameras.

Real-Time Ultrasound Doppler Tracking and Autonomous Navigation of a Miniature Helical Robot for Accelerating Thrombolysis in Dynamic Blood Flow

Untethered small-scale robots offer great promise for medical applications in complex biological environments. However, challenges remain in the control and medical imaging of a robot for targeted delivery inside a living body, especially in flowing conditions (e.g., blood vessels). In this work, we report a strategy to autonomously navigate a miniature helical robot in dynamic blood flow under ultrasound Doppler imaging guidance. A magnetic torque and force-hybrid control approach is implemented, enabling the actuation of a millimeter-scale helical robot against blood flow under a rotating magnetic field with a controllable field gradient. Experimental results demonstrate that the robot (length 7.30 mm; diameter 2.15 mm) exhibits controlled navigation in vascular environments, including upstream and downstream navigation in flowing and pulsatile flowing blood with flow rates up to 24 mL/min (mean flow velocity: 14.15 mm/s). During navigation, the rotating robot-induced Doppler signals enable real-time localization and tracking in flowing and pulsatile flowing blood environments. Moreover, the robot can be selectively navigated along different paths by actively controlling the robot's orientation. We apply this autonomous strategy for localizing thrombus and accelerating thrombolysis rate. Compared with conventional tissue plasminogen activator (tPA) thrombolysis, the robot-enhanced shear stress and tPA convection near the clot-blood interface increase the unblocking and thrombolysis efficiency up to 4.8- and 3.5-fold, respectively. Such a medical imaging-guided navigation strategy provides simultaneous robot navigation and localization in complex dynamic biological environments, providing an intelligent approach toward real-time targeted delivery and diagnostic applications in vivo.

Biologically inspired micro-robotic swimmers remotely controlled by ultrasound waves

We 3D print micro-robotic swimmers with the size of animal cells using a Nanoscribe. The micro-swimmers are powered by the microstreaming flows induced by the oscillating air bubbles entrapped within the micro-robotic swimmers. Previously, micro-swimmers propelled by acoustic streaming require the use of a magnetic field or an additional ultrasound transducer to steer their direction. Here, we show a two-bubble based micro-swimmer that can be propelled and steered entirely using one ultrasound transducer. The swimmer displays boundary following traits similar to those biological swimmers that are known to be important for performing robust biological functions. The micro-robotic swimmer has the potential to advance the current technology in targeted drug delivery and remote microsurgery.

Bubbles in microfluidics: an all-purpose tool for micromanipulation

In recent decades, the integration of microfluidic devices and multiple actuation technologies at the microscale has greatly contributed to the progress of related fields. In particular, microbubbles are playing an increasingly important role in microfluidics because of their unique characteristics that lead to specific responses to different energy sources and gas-liquid interactions. Many effective and functional bubble-based micromanipulation strategies have been developed and improved, enabling various non-invasive, selective, and precise operations at the microscale. This review begins with a brief introduction of the morphological characteristics and formation of microbubbles. The theoretical foundations and working mechanisms of typical micromanipulations based on acoustic, thermodynamic, and chemical microbubbles in fluids are described. We critically review the extensive applications and the frontline advances of bubbles in microfluidics, including microflow patterns, position and orientation control, biomedical applications, and development of bubble-based microrobots. We lastly present an outlook to provide directions for the design and application of microbubble-based micromanipulation tools and attract the attention of relevant researchers to the enormous potential of microbubbles in microfluidics.

3D printing of functional microrobots

3D printing (also called "additive manufacturing" or "rapid prototyping") is able to translate computer-aided and designed virtual 3D models into 3D tangible constructs/objects through a layer-by-layer deposition approach. Since its introduction, 3D printing has aroused enormous interest among researchers and engineers to understand the fabrication process and composition-structure-property correlation of printed 3D objects and unleash its great potential for application in a variety of industrial sectors. Because of its unique technological advantages, 3D printing can definitely benefit the field of microrobotics and advance the design and development of functional microrobots in a customized manner. This review aims to present a generic overview of 3D printing for functional microrobots. The most applicable 3D printing techniques, with a focus on laser-based printing, are introduced for the 3D microfabrication of microrobots. 3D-printable materials for fabricating microrobots are reviewed in detail, including photopolymers, photo-crosslinkable hydrogels, and cell-laden hydrogels. The representative applications of 3D-printed microrobots with rational designs heretofore give evidence of how these printed microrobots are being exploited in the medical, environmental, and other relevant fields. A future outlook on the 3D printing of microrobots is also provided.

Real-Time Magnetic Navigation of a Rotating Colloidal Microswarm Under Ultrasound Guidance

OBJECTIVE

Untethered microrobots hold great promise for applications in biomedical field including targeted delivery, biosensing, and microsurgery. A major challenge of using microrobots to perform in vivo tasks is the real-time localization and motion control using medical imaging technologies. Here we report real-time magnetic navigation of a paramagnetic nanoparticle-based microswarm under ultrasound guidance.

METHODS

A three-axis Helmholtz electromagnetic coil system integrated with an ultrasound imaging system is developed for generation, actuation, and closed-loop control of the microswarm. The magnetite nanoparticle-based microswarm is generated and navigated using rotating magnetic fields. In order to localize the microswarm in real time, the dynamic imaging contrast has been analyzed and exploited in image process to increase the signal-to-noise ratio. Moreover, imaging of the microswarm at different depths are experimentally studied and analyzed, and the minimal dose of nanoparticles for localizing a microswarm at different depths is ex vivo investigated. For real-time navigating the microswarm in a confined environment, a PI control scheme is designed.

RESULTS

Image differencing-based processing increases the signal-to-noise ratio, and the microswarm can be ex vivo localized at depth of 2.2-7.8 cm. Experimental results show that the microswarm is able to be real-time navigated along a planned path in a channel, and the average steady-state error is 0.27 mm (  ∼ 33.7% of the body length).

SIGNIFICANCE

The colloidal microswarm is real-time localized and navigated using ultrasound feedback, which shows great potential for biomedical applications that require real-time noninvasive tracking.

Contactless acoustic micro/nano manipulation: a paradigm for next generation applications in life sciences

Acoustic actuation techniques offer a promising tool for contactless manipulation of both synthetic and biological micro/nano agents that encompass different length scales. The traditional usage of sound waves has steadily progressed from mid-air manipulation of salt grains to sophisticated techniques that employ nanoparticle flow in microfluidic networks. State-of-the-art in microfabrication and instrumentation have further expanded the outreach of these actuation techniques to autonomous propulsion of micro-agents. In this review article, we provide a universal perspective of the known acoustic micromanipulation technologies in terms of their applications and governing physics. Hereby, we survey these technologies and classify them with regards to passive and active manipulation of agents. These manipulation methods account for both intelligent devices adept at dexterous non-contact handling of micro-agents, and acoustically induced mechanisms for self-propulsion of micro-robots. Moreover, owing to the clinical compliance of ultrasound, we provide future considerations of acoustic manipulation techniques to be fruitfully employed in biological applications that range from label-free drug testing to minimally invasive clinical interventions.