Dzhoshkun Ismail Shakir

Ultrasound is an essential tool for guidance of many minimally-invasive surgical and interventional procedures, where accurate placement of the interventional device is critical to avoid adverse events. Needle insertion procedures for anaesthesia, fetal medicine and tumour biopsy are commonly ultrasound-guided, and misplacement of the needle may lead to complications such as nerve damage, organ injury or pregnancy loss. Clear visibility of the needle tip is therefore critical, but visibility is often precluded by tissue heterogeneities or specular reflections from the needle shaft. This paper presents the in vitro and ex vivo accuracy of a new, real-time, ultrasound needle tip tracking system for guidance of fetal interventions. A fibre-optic, Fabry-Pérot interferometer hydrophone is integrated into an intraoperative needle and used to localise the needle tip within a handheld ultrasound field. While previous, related work has been based on research ultrasound systems with bespoke transmission sequences, the new system—developed under the ISO 13485 Medical Devices quality standard—operates as an adjunct to a commercial ultrasound imaging system and therefore provides the image quality expected in the clinic, superimposing a cross-hair onto the ultrasound image at the needle tip position. Tracking accuracy was determined by translating the needle tip to 356 known positions in the ultrasound field of view in a tank of water, and by comparison to manual labelling of the the position of the needle in B-mode US images during an insertion into an ex vivo phantom. In water, the mean distance between tracked and true positions was 0.7 ± 0.4 mm with a mean repeatability of 0.3 ± 0.2 mm. In the tissue phantom, the mean distance between tracked and labelled positions was 1.1 ± 0.7 mm. Tracking performance was found to be independent of needle angle. The study demonstrates the performance and clinical compatibility of ultrasound needle tracking, an essential step towards a first-in-human study.

Super-resolution (SR) methods have seen significant advances thanks to the development of convolutional neural networks (CNNs). CNNs have been successfully employed to improve the quality of endomicroscopy imaging. Yet, the inherent limitation of research on SR in endomicroscopy remains the lack of ground truth high-resolution (HR) images, commonly used for both supervised training and reference-based image quality assessment (IQA). Therefore, alternative methods, such as unsupervised SR are being explored. To address the need for non-reference image quality improvement, we designed a novel zero-shot super-resolution (ZSSR) approach that relies only on the endomicroscopy data to be processed in a self-supervised manner without the need for ground-truth HR images. We tailored the proposed pipeline to the idiosyncrasies of endomicroscopy by introducing both: a physically-motivated Voronoi downscaling kernel accounting for the endomicroscope's irregular fibre-based sampling pattern, and realistic noise patterns. We also took advantage of video sequences to exploit a sequence of images for self-supervised zero-shot image quality improvement. We run ablation studies to assess our contribution in regards to the downscaling kernel and noise simulation. We validate our methodology on both synthetic and original data. Synthetic experiments were assessed with reference-based IQA, while our results for original images were evaluated in a user study conducted with both expert and non-expert observers. The results demonstrated superior performance in image quality of ZSSR reconstructions in comparison to the baseline method. The ZSSR is also competitive when compared to supervised single-image SR, especially being the preferred reconstruction technique by experts.

Twin-to-twin transfusion syndrome (TTTS) is a fetal condition that affects monochronic diamniotic pregnancies in which the presence of a certain pattern of intertwin vascular connections, known as anastomoses, results in an imbalance of the blood flow between twins. If this condition remains untreated, the outcome is generally fatal for both twins.¹ Minimally invasive surgery is today the standard of care. The surgeon explores the placenta using a fetoscope with a small field of view to find and photocoagulate all anastomoses. Despite the wide literature in endoscopic scenarios,^2,3 the challenges found in fetoscopic imagery complicate the application of available techniques. To illustrate the complexity of the fetoscopic site, Fig. 1 shows three examples of TTTS procedure where the reduced field of view can be observed. The surgeon must remember the explored areas to navigate through the placental surface building a mental map of the placenta. This is an extremely challenging task even for the best-trained surgeons due to this limited field of view, lack of texture, and turbidity, which hinders the visualization and also precludes any assistance from others. As a solution, mosaicking has been suggested to increase the field of view by stitching the images together in a common space, forming a map of the area.

Purpose Probe-based confocal laser endomicroscopy (pCLE) is a recent imaging modality that allows performing in vivo optical biopsies. The design of pCLE hardware, and its reliance on an optical fibre bundle, fundamentally limits the image quality with a few tens of thousands fibres, each acting as the equivalent of a single-pixel detector, assembled into a single fibre bundle. Video registration techniques can be used to estimate high-resolution (HR) images by exploiting the temporal information contained in a sequence of low-resolution (LR) images. However, the alignment of LR frames, required for the fusion, is computationally demanding and prone to artefacts. Methods In this work, we propose a novel synthetic data generation approach to train exemplar-based Deep Neural Networks (DNNs). HR pCLE images with enhanced quality are recovered by the models trained on pairs of estimated HR images (generated by the video registration algorithm) and realistic synthetic LR images. Performance of three different state-of-the-art DNNs techniques were analysed on a Smart Atlas database of 8806 images from 238 pCLE video sequences. The results were validated through an extensive image quality assessment that takes into account different quality scores, including a Mean Opinion Score (MOS). Results Results indicate that the proposed solution produces an effective improvement in the quality of the obtained reconstructed image. Conclusion The proposed training strategy and associated DNNs allows us to perform convincing super-resolution of pCLE images.

In clinical and pre-clinical research involving medical images, the first step following a Magnetic Resonance Imaging dataset acquisition, usually entails the conversion of image data from the native scanner format to a format suitable for the intended analysis. The proprietary Bruker ParaVision software currently does not provide the tools for conversion of the data to suitable and open formats for research, such as nifti (Cox, Robert W and

GIFT-Grab is an open-source API for acquiring, processing and encoding video streams in real time. GIFT-Grab supports video acquisition using various frame-grabber hardware as well as from standard-compliant network streams and video files. The current GIFT-Grab release allows for multi-channel video acquisition and encoding at the maximum frame rate of supported hardware – 60 frames per second (fps). GIFT-Grab builds on well-established highly configurable multimedia libraries including FFmpeg and OpenCV. GIFT-Grab exposes a simplified high-level API, aimed at facilitating integration into client applications with minimal coding effort. The core implementation of GIFT-Grab is in C++11. GIFT-Grab also features a Python API compatible with the widely used scientific computing packages NumPy and SciPy.GIFT-Grab was developed for capturing multiple simultaneous intra-operative video streams from medical imaging devices. Yet due to the ubiquity of video processing in research, GIFT-Grab can be used in many other areas. GIFT-Grab is hosted and managed on the software repository of the Centre for Medical Image Computing (CMIC) at University College London, and is also mirrored on GitHub. In addition it is available for installation from the Python Package Index (PyPI) via the pip installation tool. Funding statement: This work was supported through an Innovative Engineering for Health award by the Wellcome Trust [WT101957], the Engineering and Physical Sciences Research Council (EPSRC) [NS/A000027/1] and a National Institute for Health Research Biomedical Research Centre UCLH/UCL High Impact Initiative. Sébastien Ourselin receives funding from the EPSRC (EP/H046410/1, EP/J020990/1, EP/K005278) and the MRC (MR/J01107X/1). Luis C. García-Peraza-Herrera is supported by the EPSRC-funded UCL Centre for Doctoral Training in Medical Imaging (EP/L016478/1).