To address the lack of access to ultrasound in remote communities, previous work introduced human teleoperation, a mixed reality and haptics-based tele-ultrasound system. In this approach, a novice takes the role of a cognitive robot controlled remotely by an expert through mixed reality. In this manuscript we summarize new developments to this system and describe a feasibility study assessing its use for long-distance remote abdominal ultrasound examinations. To provide simple but effective haptic feedback, we used an ellipsoid model of the patient with its parameters calibrated using our system's position and force sensors. We tested the system in Skidegate, Haida Gwaii, Canada, with the experts positioned 754 km away in Vancouver, Canada. We performed 11 total scans with 10 novices and 2 sonographers. The sonographers were tasked with acquiring 5 target images in the epigastric region. The image acquisition quality was assessed by 2 radiologists. We collected alignment data and the novices completed task load and usability questionnaires. Both the novices and sonographers provided written and verbal feedback to inform future design iterations. 92

Objective: Modelling ultrasound speckle to characterise tissue properties has generated considerable interest. As speckle is dependent on the underlying tissue architecture, modelling it may aid in tasks such as segmentation or disease detection. For the transplanted kidney, where ultrasound is used to investigate dysfunction, it is unknown which statistical distribution best characterises such speckle. This applies to the regions of the transplanted kid-ney: the cortex, the medulla and the central echogenic complex. Furthermore, it is unclear how these distributions vary by patient variables such as age, sex, body mass index, primary disease or donor type. These traits may influ-ence speckle modelling given their influence on kidney anatomy. We investigate these two aims.Methods: B-mode images from n = 821 kidney transplant recipients (one image per recipient) were automatically segmented into the cortex, medulla and central echogenic complex using a neural network. Seven distinct proba-bility distributions were fitted to each region's histogram, and statistical analysis was performed. Discussion: The Rayleigh and Nakagami distributions had model parameters that differed significantly between the three regions (p <= 0.05). Although both had excellent goodness of fit, the Nakagami had higher Kullbeck-Lei-bler divergence. Recipient age correlated weakly with scale in the cortex (omega: rho = 0.11, p = 0.004), while body mass index correlated weakly with shape in the medulla (m: rho = 0.08, p = 0.04). Neither sex, primary disease nor donor type exhibited any correlation.Conclusion: We propose the Nakagami distribution be used to characterize transplanted kidneys regionally inde-pendent of disease etiology and most patient characteristics.

Purpose: Length and width measurements of the kidneys aid in the detection and monitoring of structural abnormalities and organ disease. Manual measurement results in intra- and inter-rater variability, is complex and time-consuming, and is fraught with error. We propose an automated approach based on machine learning for quantifying kidney dimensions from two-dimensional (2D) ultrasound images in both native and transplanted kidneys. Approach: An nnU-net machine learning model was trained on 514 images to segment the kidney capsule in standard longitudinal and transverse views. Two expert sonographers and three medical students manually measured the maximal kidney length and width in 132 ultrasound cines. The segmentation algorithm was then applied to the same cines, region fitting was performed, and the maximum kidney length and width were measured. Additionally, single kidney volume for 16 patients was estimated using either manual or automatic measurements. Results: The experts resulted in length of 84.8 +/- 26.4 mm [95% CI: 80.0, 89.6] and a width of 51.8 +/- 10.5 mm [49.9, 53.7]. The algorithm resulted a length of 86.3 +/- 24.4 [81.5, 91.1] and a width of 47.1 +/- 12.8 [43.6, 50.6]. Experts, novices, and the algorithm did not statistically significant differ from one another (p > 0.05). Bland-Altman analysis showed the algorithm produced a mean difference of 2.6 mm (SD = 1.2) from experts, compared to novices who had a mean difference of 3.7 mm (SD = 2.9 mm). For volumes, mean absolute difference was 47 mL (31%) consistent with similar to 1 mm error in all three dimensions. Conclusions: This pilot study demonstrates the feasibility of an automatic tool to measure in vivo kidney biometrics of length, width, and volume from standard 2D ultrasound views with comparable accuracy and reproducibility to expert sonographers. Such a tool may enhance workplace efficiency, assist novices, and aid in tracking disease progression. (c) 2023 Society of Photo-Optical Instrumentation Engineers (SPIE)

Ultrasound, because of its low cost, non-ionizing, and non-invasive characteristics, has established itself as a cornerstone radiological examination. Research on ultrasound applications has also expanded, especially with image analysis with machine learning. However, ultrasound data are frequently restricted to closed data sets, with only a few openly available. Despite being a frequently examined organ, the kidney lacks a publicly available ultrasonography data set. The proposed Open Kidney Ultrasound Data Set is the first publicly available set of kidney brightness mode (B-mode) ultrasound data that includes annotations for multi-class semantic segmentation. It is based on data retrospectively collected in a 5-year period from over 500 patients with a mean age of 53.2 +/- 14.7 years, body mass index of 27.0 +/- 5.4 kg/m2, and most common primary diseases being diabetes mellitus, immunoglobulin A (IgA) nephropathy, and hypertension. There are labels for the view and fine-grained manual annotations from two expert sonographers. Notably, this data includes native and transplanted kidneys. Initial bench-marking measurements are performed, demonstrating a state-of-the-art algorithm achieving a Dice Sorenson Coefficient of 0.85 for the kidney capsule. This data set is a high-quality data set, including two sets of expert annotations, with a larger breadth of images than previously available. In increasing access to kidney ultrasound data, future researchers may be able to create novel image analysis techniques for tissue characterization, disease detection, and prognostication.

Prognosis of kidney function in post-transplant patients is important when considering invasive investigations, intervention, or re-transplantation. Ultrasound imaging is a non-invasive tool that may contain subtle textures associated with kidney function. To address this, we developed a prediction model utilizing machine learning and computational image features to predict decline in estimated glomerular filtration rate (eGFR), a key measure of kidney function. Post-transplant ultrasound scans and eGFR values from N = 819 transplant patients were obtained. A multi-stage pipeline was built to first automatically segment the cortex, medulla, and central echo complex from ultrasound. Imaging features (104 total) related to shape, intensity statistics, texture and ultrasound speckle were computed. A random forest (RF) classifier was trained topredict 5-year eGFR decline from the feature set. For comparison, validation was repeated with using only clinical variables and with the Kidney Failure Risk Equation (KFRE). Predictive features were identified by feature-wise decrease in impurity and a mean validation AUC ( ± standard deviation) of 0.81 ± 0.03 was achieved. Comparison AUCs were 0.62 ± 0.04 for the clinical variable model and 0.67 ± 0.03 for the KFRE model. 2-dimensional elongation, cluster shade, and Nakagami speckle shape were the most predictive features. This study provides support that computational image features combined with machine learning may potentially serve as a non-invasive eGFR decline prediction tool to aid post-transplant care.

Techniques for data augmentation are widely employed to avoid overfitting, improve generalizability and overcome data scarcity. This data-oriented approach frequently uses domain-agnostic approaches such as geometric transformations, colour space transformations, and generative adversarial networks. However, utilsing domain-specific characteristics in augmentations may result in additional invariances or improved robustness. We present several augmentation techniques for ultrasound: zoom, time-gain compensation, artificial shadowing, and speckle parameter maps. Zoom and time-gain compensation mimic traditional image quality parameters. For shadowing, we characterize acoustic shadows within abdominal ultrasound images and provide a method for incorporating artificial shadows into existing images. Finally, we transform B-mode ultrasound images into Nakagami-based speckle parameter maps to describe spatial structures that are not visible in conventional B-mode. The augmentations are evaluated by training a fully supervised network and a contrastive learning network for multi-class intra-organ semantic segmentation. Our preliminary results reflect the difficulties of creating augmentations as well as the limitations posed by acoustic shadowing.

Creating ground truth segmentations for medical imaging is labour and time-intensive. Contrastive learning techniques have shown promise in previous work on magnetic resonance, computed tomography and X-ray imaging. We investigate the potential benefits of using ultrasound-inspired adaptations to the contrastive learning paradigm. Specifically, we investigate the novel concepts of temporal coherency and a speckle loss. We first perform a head-to-head label efficiency comparison between two state of the art algorithms, one that is fully supervised and the other that is contrastive. Next, we leverage temporal coherency, the notion that frames within an ultrasound video clip that are close together share structural similarities. Finally, we explore a loss function based on the Nakagami probability distribution in order to provide a speckle noise constraint on the learned embeddings. Using diverse kidney ultrasound data, our preliminary results indicate that temporal partitioning has potential improvements to segmentation accuracy, whereas speckle-based loss does not. Future work will investigate changes to intra-class compactness and inter-class separability.

Data augmentation techniques are frequently used to prevent overfitting, enhance generalizability, and overcome limited amounts of data. This data-oriented approach commonly includes domain-agnostic techniques of geometric transformations, colour space changes, and generative adversarial networks. However, leveraging domain-specific traits in aug- mentations may yield further improvements. We propose three new contributions to ultrasound augmentation: zoom, artificial shadowing, and speckle parameter maps. We first present zoom, a modification on scale which maintains the ultrasound beam shape. We then characterize acoustic shadows within abdominal ultrasound images, and formulate a method to introduce artificial shadows in a realistic manner into existing images. Finally, we transform B-mode ultrasound images into speckle parameter maps based on the Nakagami distribution to represent spatial structures not obvious in conventional B-mode. The three augmentations are evaluated in training a fully supervised network and a contrastive learning network for multi-class intra-organ semantic segmentation. Our preliminary results demonstrate the benefit of using zoom and speckle maps as augmentation, and the challenges presented by acoustic shadowing, in segmentation.

Modelling ultrasound speckle has generated considerable interest for its ability to characterize tissue properties. As speckle is dependent on the underlying tissue architecture, modelling it may aid in tasks like segmentation or disease detection. However, for the transplanted kidney where ultrasound is commonly used to investigate dysfunction, it is currently unknown which statistical distribution best characterises such speckle. This is especially true for the regions of the transplanted kidney: the cortex, the medulla and the central echogenic complex. Furthermore, it is unclear how these distributions vary by patient variables such as age, sex, body mass index, primary disease, or donor type. These traits may influence speckle modelling given their influence on kidney anatomy. We are the first to investigate these two aims. N=821 kidney transplant recipient B-mode images were automatically segmented into the cortex, medulla, and central echogenic complex using a neural network. Seven distinct probability distributions were fitted to each region. The Rayleigh and Nakagami distributions had model parameters that differed significantly between the three regions (p <= 0.05). While both had excellent goodness of fit, the Nakagami had higher Kullbeck-Leibler divergence. Recipient age correlated weakly with scale in the cortex (Omega: rho = 0.11, p = 0.004), while body mass index correlated weakly with shape in the medulla (m: rho = 0.08, p = 0.04). Neither sex, primary disease, nor donor type demonstrated any correlation. We propose the Nakagami distribution be used to characterize transplanted kidneys regionally independent of disease etiology and most patient characteristics based on our findings.