On-the-fly point annotation for fast medical video labeling.

PURPOSE: In medical research, deep learning models rely on high-quality annotated data, a process often laborious and time-consuming. This is particularly true for detection tasks where bounding box annotations are required. The need to adjust two corners makes the process inherently frame-by-frame. Given the scarcity of experts' time, efficient annotation methods suitable for clinicians are needed. METHODS: We propose an on-the-fly method for live video annotation to enhance the annotation efficiency. In this approach, a continuous single-point annotation is maintained by keeping the cursor on the object in a live video, mitigating the need for tedious pausing and repetitive navigation inherent in traditional annotation methods. This novel annotation paradigm inherits the point annotation's ability to generate pseudo-labels using a point-to-box teacher model. We empirically evaluate this approach by developing a dataset and comparing on-the-fly annotation time against traditional annotation method. RESULTS: Using our method, annotation speed was 3.2 × faster than the traditional annotation technique. We achieved a mean improvement of 6.51 ± 0.98 AP@50 over conventional method at equivalent annotation budgets on the developed dataset. CONCLUSION: Without bells and whistles, our approach offers a significant speed-up in annotation tasks. It can be easily implemented on any annotation platform to accelerate the integration of deep learning in video-based medical research.

Early-stage clinical evaluation of real-time artificial intelligence assistance for laparoscopic cholecystectomy.

The growing availability of surgical digital data and developments in analytics such as artificial intelligence (AI) are being harnessed to improve surgical care. However, technical and cultural barriers to real-time intraoperative AI assistance exist. This early-stage clinical evaluation shows the technical feasibility of concurrently deploying several AIs in operating rooms for real-time assistance during procedures. In addition, potentially relevant clinical applications of these AI models are explored with a multidisciplinary cohort of key stakeholders.

Organ-based estimation and minimization of clinician's X-ray dose.

PURPOSE: Hybrid surgeries, allowing real-time visualization of patient inner anatomy, are possible through the use of intraoperative X-ray imaging. However, the intensive use of X-rays can have undesired consequences for the clinicians or the patient in the operating room (OR). METHODS: In this paper, we provide a tool to visualize the X-rays and to optimally place protective shields in the hybrid operating room to reduce the clinician's dose according to their most sensitive body parts. We first acquire measurements in a hybrid operating room with dosimeters placed at different locations on a mannequin simulating a clinician. We demonstrate that a small displacement of a protective shield has significant consequences on the dose received by a clinician. Then, we reproduce the scene virtually and use Monte Carlo simulations to estimate the dose received by the clinician. Finally, we optimally place protective shields with a Nelder-Mead-based numerical optimization algorithm. RESULTS: The results show a high sensitivity of the clinician's dose to protective shield placement. Numerical optimization of the shields' placement can help to reduce the dose and show a decrease between 79 and 89% of the exposition when comparing no external shield protection and our optimal external shield position. CONCLUSION: Our work can help to raise awareness of the risks induced by X-rays during intraoperative surgery and reduce the dose received by the clinicians. In future work, our approach can be linked with human pose estimation algorithms to trace surgeons' moves, estimate dynamically the dose and summarize it in a surgical report, giving the dose for important organs.

Free space optical communication receiver based on a spatial demultiplexer and a photonic integrated coherent combining circuit.

Atmospheric turbulence can generate scintillation or beam wandering phenomena that impairs free space optical (FSO) communication. In this paper, we propose and demonstrate a proof-of-concept FSO communication receiver based on a spatial demultiplexer and a photonic integrated circuit coherent combiner. The receiver collects the light from several Hermite Gauss spatial modes and coherently combine on chip the energy from the different modes into a single output. The FSO receiver is characterized with a wavefront emulator bench that generates arbitrary phase and intensity patterns. The multimode receiver presents a strong resilience to wavefront distortions, compared to a monomode FSO receiver. The system is then used to detect an analog modulation of an optical beam through a random wavefront profile to mimic the transmission of a signal on a degraded optical link.

Evaluation of chronically implanted subdural boron doped diamond/CNT recording electrodes in miniature swine brain.

When implantable recording devices for brain or neural electrical activity are designed, the number of available materials for electrodes is quite limited. The material must be biocompatible with respect to ISO10993, its electrochemical properties must remain stable and the response of cells or tissues can be mitigated, especially on the glial scar. This involves electrode characterization pre- implantation and impedance spectroscopy during chronic implantation, in order to evaluate both electrode properties and performance. This study was aimed at a comparison of the long-term behavior of a nanostructured boron-doped diamond (BDD) with a nanostructured Platinum Iridium (PtIr) electrode. Firstly, a batch of cortical grids with bare and modified contacts (2 mm in diameter) was engineered for implantation. Secondly a miniature swine model was developed. This study highlighted the predominant role of electrode surface roughness on the quality of recordings. Rough PtIr contacts and BDD coated ones showed comparable behavior after three-month implantation with a slight increase of the modulus of the impedance and a tissue capsule. Nevertheless, immunohistochemistry analysis did not exhibit either a toxic or irritation reaction. With regard to biocompatibility, promising long term results are shown for both materials.

Thirty Gigahertz Optoelectronic Mixing in Chemical Vapor Deposited Graphene.

The remarkable properties of graphene, such as broadband optical absorption, high carrier mobility, and short photogenerated carrier lifetime, are particularly attractive for high-frequency optoelectronic devices operating at 1.55 µm telecom wavelength. Moreover, the possibility to transfer graphene on a silicon substrate using a complementary metal-oxide-semiconductor-compatible process opens the ability to integrate electronics and optics on a single cost-effective chip. Here, we report an optoelectronic mixer based on chemical vapor-deposited graphene transferred on an oxidized silicon substrate. Our device consists in a coplanar waveguide that integrates a graphene channel, passivated with an atomic layer-deposited Al2O3 film. With this new structure, 30 GHz optoelectronic mixing in commercially available graphene is demonstrated for the first time. In particular, using a 30 GHz intensity-modulated optical signal and a 29.9 GHz electrical signal, we show frequency downconversion to 100 MHz. These results open promising perspectives in the domain of optoelectronics for radar and radio-communication systems.

3D-nanostructured boron-doped diamond for microelectrode array neural interfacing.

The electrode material is a key element in the design of long-term neural implants and neuroprostheses. To date, the ideal electrode material offering high longevity, biocompatibility, low-noise recording and high stimulation capabilities remains to be found. We show that 3D-nanostructured boron doped diamond (BDD), an innovative material consisting in a chemically stable material with a high aspect ratio structure obtained by encapsulation of a carbon nanotube template within two BDD nanolayers, allows neural cell attachment, survival and neurite extension. Further, we developed arrays of 20-µm-diameter 3D-nanostructured BDD microelectrodes for neural interfacing. These microelectrodes exhibited low impedances and low intrinsic recording noise levels. In particular, they allowed the detection of low amplitude (10-20 µV) local-field potentials, single units and multiunit bursts neural activity in both acute whole embryonic hindbrain-spinal cord preparations and long-term hippocampal cell cultures. Also, cyclic voltammetry measurements showed a wide potential window of about 3 V and a charge storage capacity of 10 mC.cm(-2), showing high potentiality of this material for neural stimulation. These results demonstrate the attractiveness of 3D-nanostructured BDD as a novel material for neural interfacing, with potential applications for the design of biocompatible neural implants for the exploration and rehabilitation of the nervous system.