Varying ultrasound power level to distinguish surgical instruments and tissue

Precise angle estimation of capsule robot in ultrasound using heatmap guided two-stage network

PURPOSE

A capsule robot can be controlled inside gastrointestinal (GI) tract by an external permanent magnet outside of human body for finishing non-invasive diagnosis and treatment. Locomotion control of capsule robot relies on the precise angle feedback that can be achieved by ultrasound imaging. However, ultrasound-based angle estimation of capsule robot is interfered by gastric wall tissue and the mixture of air, water, and digestive matter existing in the stomach.

METHODS

To tackle these issues, we introduce a heatmap guided two-stage network to detect the position and estimate the angle of the capsule robot in ultrasound images. Specifically, this network proposes the probability distribution module and skeleton extraction-based angle calculation to obtain accurate capsule robot position and angle estimation.

RESULTS

Extensive experiments were finished on the ultrasound image dataset of capsule robot within porcine stomach. Empirical results showed that our method obtained small position center error of 0.48 mm and high angle estimation accuracy of 96.32%.

CONCLUSION

Our method can provide precise angle feedback for locomotion control of capsule robot.

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.

Optically-guided instrument for transapical beating-heart delivery of artificial mitral chordae tendineae

OBJECTIVE

We sought to develop an instrument that would enable the delivery of artificial chordae tendineae (ACT) using optical visualization of the leaflet inside the beating heart.

METHODS

A delivery instrument was developed together with an ACT anchor system. The instrument incorporates an optically clear silicone grasping surface in which are embedded a camera and LED for direct leaflet visualization during localization, grasping, and chordal delivery. ACTs, comprised of T-shaped anchors and an expanded polytetrafluoroethylene chordae, were fabricated to enable testing in a porcine model. Ex vivo experiments were used to measure the anchor tear-out force from the mitral leaflets. In vivo experiments were performed in which the mitral leaflets were accessed transapically using only optical guidance and ACTs were deployed in the posterior and anterior leaflets (P2 and A2 segments).

RESULTS

In 5 porcine ex vivo experiments, the mean force required to tear the anchors from the leaflets was 3.8 ± 1.2 N. In 5 porcine in vivo nonsurvival procedures, 14 ACTs were successfully placed in the leaflets (9 in P2 and 5 in A2). ACT implantation took an average of 3.22 ± 0.83 minutes from entry to exit through the apex.

CONCLUSIONS

Optical visualization of the mitral leaflet during chordal placement is feasible and provides direct feedback to the operator throughout the deployment sequence. This enables visual confirmation of the targeted leaflet location, distance from the free edge, and successful deployment of the chordal anchor. Further studies are needed to refine and assess the device for clinical use.

Dispersion characterization of magnetic actuated needleless injections with particle image velocimetry

Conventional needle-based approaches in intravitreal drug delivery carry needle-stick-injury risk and could scare patients (belonephobia). Alternatively, our group has explored the application of an electromagnetic needleless injector in this paper. This work aims to improve intravitreal drug delivery, which in the future could assist physicians with automation and benefit patients by providing a needleless approach. Electromagnetic needleless intravitreal injections lack quantification studies. We investigate the delivery properties of the needleless injector where the characterization can be used to refine the design parameters of the prototype in subsequent iterations. Experiments were performed to characterize the injectant delivered from the electromagnetic needleless injector. Penetration tests were conducted to observe the influences of various injection barriers and tissues. Ultrasonic imaging modality was explored for future applications of the prototype. The dispersion of the injectant was controllable where injection depth and distribution is dependent on the input voltage. The synthetic barriers highlighted significant energy losses for penetration (maximum velocity falls from 4.46 to 1.57 mm/s with a 0.1-mm barrier). The biological barriers were difficult to penetrate with the current prototype. Our results indicate that the current electromagnetic injector offers controllable dispersion (depth and distribution) correlated with input voltages, which should have increased injection power for use with biological tissue. Ultrasonic imaging modality produced velocity profiles comparable to the optical approach which is promising for future in vivo studies. The influences of injection barriers should be further investigated in in vivo experiments with ultrasonic imaging modalities. Graphical abstract .

High dynamic range ultrasound imaging

PURPOSE

High dynamic range (HDR) imaging is a popular computational photography technique that has found its way into every modern smartphone and camera. In HDR imaging, images acquired at different exposures are combined to increase the luminance range of the final image, thereby extending the limited dynamic range of the camera. Ultrasound imaging suffers from limited dynamic range as well; at higher power levels, the hyperechogenic tissue is overexposed, whereas at lower power levels, hypoechogenic tissue details are not visible. In this work, we apply HDR techniques to ultrasound imaging, where we combine ultrasound images acquired at different power levels to improve the level of detail visible in the final image.

METHODS

Ultrasound images of ex vivo and in vivo tissue are acquired at different acoustic power levels and then combined to generate HDR ultrasound (HDR-US) images. The performance of five tone mapping operators is quantitatively evaluated using a similarity metric to determine the most suitable mapping for HDR-US imaging.

RESULTS

The ex vivo and in vivo results demonstrated that HDR-US imaging enables visualizing both hyper- and hypoechogenic tissue at once in a single image. The Durand tone mapping operator preserved the most amount of detail across the dynamic range.

CONCLUSIONS

Our results strongly suggest that HDR-US imaging can improve the utility of ultrasound in image-based diagnosis and procedure guidance.