Julia Alison Noble

University of Oxford | OX · Department of Engineering Science

Effective training of large Vision-Language Models (VLMs) on resource-constrained client devices in Federated Learning (FL) requires the usage of parameter-efficient fine-tuning (PEFT) strategies. To this end, we demonstrate the impact of two factors \textit{viz.}, client-specific layer importance score that selects the most important VLM layers fo...

Background The WHO’s recommendations on antenatal care underscore the need for ultrasound assessment during pregnancy. Given that maternal and perinatal mortality remains unacceptably high in underserved regions, these guidelines are imperative for achieving better outcomes. In recent years, portable ultrasound devices have become increasingly popu...

Federated learning is an emerging technology that enables the decentralised training of machine learning-based methods for medical image analysis across multiple sites while ensuring privacy. This review paper thoroughly examines federated learning research applied to medical image analysis, outlining technical contributions. We followed the guidel...

Artificial intelligence (AI) has significant potential to transform healthcare and improve patient care. However, successful development and integration of AI models requires careful consideration of study designs and sample size calculations for development and validation of models, publishing standards, prototype development for translation and c...

3D pose estimation from a 2D cross-sectional view enables healthcare professionals to navigate through the 3D space, and such techniques initiate automatic guidance in many image-guided radiology applications. In this work, we investigate how estimating 3D fetal pose from freehand 2D ultrasound scanning can guide a sonographer to locate a head stan...

We present the first automated multimodal summary generation system, MMSummary, for medical imaging video, particularly with a focus on fetal ultrasound analysis. Imitating the examination process performed by a human sonographer, MMSummary is designed as a three-stage pipeline, progressing from keyframe detection to keyframe captioning and finally...

Auditory and visual signals are two primary perception modalities that are usually present together and correlate with each other, not only in natural environments but also in clinical settings. However, audio-visual modelling in the latter case can be more challenging, due to the different sources of audio/video signals and the noise (both signal-...

Segmentation models for brain lesions in MRI are commonly developed for a specific disease and trained on data with a predefined set of MRI modalities. Each such model cannot segment the disease using data with a different set of MRI modalities, nor can it segment any other type of disease. Moreover, this training paradigm does not allow a model to...

We present a statistical characterisation of fetal anatomies in obstetric ultrasound video sweeps where the transducer follows a fixed trajectory on the maternal abdomen. Large-scale, frame-level manual annotations of fetal anatomies (head, spine, abdomen, pelvis, femur) were used to compute common frame-level anatomy detection patterns expected fo...

Tissue culture is commonly used generic term for the in vitro cultivation of cells (plant, animal cells etc.) transferred in an artificial environment where they can continue to survive and function (Jordan et al., 2009). Tissue culture is a valuable technique to develop stress tolerance, screen stress tolerance, and elucidate physiological and bio...

Background Seroprevalence studies are an alternative approach to estimating the extent of transmission of SARS-CoV-2 and the evolution of the pandemic in different geographical settings. We aimed to determine the SARS-CoV-2 seroprevalence from March 2020 to March 2022 in a rural and urban setting in Kilifi County, Kenya. Methods We obtained repres...

Background The WHO’s recommendations on antenatal care underscore the need for ultrasound assessment during pregnancy. Given that maternal and perinatal mortality remains unacceptably high in low- and middle-income countries (LMICs), these guidelines are imperative for achieving better outcomes. In recent years, portable ultrasound devices have bec...

Maturation of the human fetal brain should follow precisely scheduled structural growth and folding of the cerebral cortex for optimal postnatal function ¹ . We present a normative digital atlas of fetal brain maturation based on a prospective international cohort of healthy pregnant women ² , selected using World Health Organization recommendation...

Automated segmentation of anatomical structures in fetal ultrasound video is challenging due to the highly diverse appearance of anatomies and image quality. In this paper, we propose an ultrasound video anatomy segmentation approach to iteratively memorise and segment incoming video frames, which is suitable for online segmentation. This is achiev...

The most challenging, yet practical, setting of semi-supervised federated learning (SSFL) is where a few clients have fully labeled data whereas the other clients have fully unlabeled data. This is particularly common in healthcare settings where collaborating partners (typically hospitals) may have images but not annotations. The bottleneck in thi...

Out-of-distribution (OOD) detection is essential to improve the reliability of machine learning models by detecting samples that do not belong to the training distribution. Detecting OOD samples effectively in certain tasks can pose a challenge because of the substantial heterogeneity within the in-distribution (ID), and the high structural similar...

Monitoring the healthy development of a fetus requires accurate and timely identification of different maternal-fetal structures as they grow. To facilitate this objective in an automated fashion, we propose a deep-learning-based image classification architecture called the COMFormer to classify maternal-fetal and brain anatomical structures pres...

In this work, we exploit multi-task learning to jointly predict the two decision-making processes of gaze movement and probe manipulation that an experienced sonographer would perform in routine obstetric scanning. A multimodal guidance framework, Multimodal-GuideNet, is proposed to detect the causal relationship between a real-world ultrasound vid...

We propose a novel way of creating graphs from multiple ultrasound (US) video sweeps. A three-node graph models three video sweeps which are obtained from a fetal US sweep protocol. The nodes are assigned binary sequences which represent the frame-level detection of the fetal head across all video frames in a sweep. We build 382 subject-level graph...

Accurate estimation of gestational age is an essential component of good obstetric care and informs clinical decision-making throughout pregnancy. As the date of the last menstrual period is often unknown or uncertain, ultrasound measurement of fetal size is currently the best method for estimating gestational age. The calculation assumes an averag...

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations...

We present a method for classifying human skill at fetal ultrasound scanning from eye-tracking and pupillary data of sonographers. Human skill characterization for this clinical task typically creates groupings of clinician skills such as expert and beginner based on the number of years of professional experience; experts typically have more than 1...

Obstetric ultrasound assessment of fetal anatomy in the first trimester of pregnancy is one of the less explored fields in obstetric sonography because of the paucity of guidelines on anatomical screening and availability of data. This paper, for the first time, examines imaging proficiency and practices of first trimester ultrasound scanning throu...

Ultrasound (US)-probe motion estimation is a fundamental problem in automated standard plane locating during obstetric US diagnosis. Most recent existing recent works employ deep neural network (DNN) to regress the probe motion. However, these deep regression-based methods leverage the DNN to overfit on the specific training data, which is naturall...

Video quality assurance is an important topic in obstetric ultrasound imaging to ensure that captured videos are suitable for biometry and fetal health assessment. Previously, one successful objective approach to automated ultrasound image quality assurance has considered it as a supervised learning task of detecting anatomical structures defined b...

Self-knowledge distillation (SKD) is a recent and promising machine learning approach where a shallow student network is trained to distill its own knowledge. By contrast, in traditional knowledge distillation a student model distills its knowledge from a large teacher network model, which involves vast computational complexity and a large storage...

The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training images and expert annotations. This work describes a fully 3D prototypical few-shot segmentation algorithm, suc...

Background: Pre-eclampsia is a leading cause of maternal mortality and morbidity that involves pregnancy-related stressors on the maternal cardiovascular and metabolic systems. As nutrition is important to support optimal development of the placenta and for the developing fetus, maternal diets may play a role in preventing pre-eclampsia. The purpo...

Background The World Health Organization recommends a package of pregnancy care that includes obstetric ultrasound scans. There are significant barriers to universal access to antenatal ultrasound, particularly because of the cost and need for maintenance of ultrasound equipment and a lack of trained personnel. As low-cost, handheld ultrasound devi...

Eye trackers can provide visual guidance to sonographers during ultrasound (US) scanning. Such guidance is potentially valuable for less experienced operators to improve their scanning skills on how to manipulate the probe to achieve the desired plane. In this paper, a multimodal guidance approach (Multimodal-GuideNet) is proposed to capture the st...

In this work, we present a novel gaze-assisted natural language processing (NLP)-based video captioning model to describe routine second-trimester fetal ultrasound scan videos in a vocabulary of spoken sonography. The primary novelty of our multi-modal approach is that the learned video captioning model is built using a combination of ultrasound vi...

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations...

Eye trackers can provide visual guidance to sonographers during ultrasound (US) scanning. Such guidance is potentially valuable for less experienced operators to improve their scanning skills on how to manipulate the probe to achieve the desired plane. In this paper, a multimodal guidance approach (Multimodal-GuideNet) is proposed to capture the st...

Medical image captioning models generate text to describe the semantic contents of an image, aiding the non-experts in understanding and interpretation. We propose a weakly-supervised approach to improve the performance of image captioning models on small image-text datasets by leveraging a large anatomically-labelled image classification dataset....

We present a method for skill characterisation of sonographer gaze patterns while performing routine second trimester fetal anatomy ultrasound scans. The position and scale of fetal anatomical planes during each scan differ because of fetal position, movements and sonographer skill. A standardised reference is required to compare recorded eye-track...

Visualising patterns in clinicians' eye movements while interpreting fetal ultrasound imaging videos is challenging. Across and within videos, there are differences in size an d position of Areas-of-Interest (AOIs) due to fetal position, movement and sonographer skill. Currently, AOIs are manually labelled or identified using eye-tracker manufactur...

Ultrasound(US)-probe motion estimation is a fundamental problem in automated standard plane locating during obstetric US diagnosis. Most recent existing recent works employ deep neural network(DNN) to regress the probe motion. However, these deep regression-based methods leverage the DNN to overfit on the specific training data, which is naturally...

Purpose For highly operator-dependent ultrasound scanning, skill assessment approaches evaluate operator competence given available data, such as acquired images and tracked probe movement. Operator skill level can be quantified by the completeness, speed, and precision of performing a clinical task, such as biometry. Such clinical tasks are increa...

This study presents a novel approach to automatic detection and segmentation of the Crown Rump Length (CRL) and Nuchal Translucency (NT), two essential measurements in the first trimester US scan. The proposed method automatically localises a standard plane within a video clip as defined by the UK Fetal Abnormality Screening Programme. A Nested Hou...

In this paper we develop a multi-modal video analysis algorithm to predict where a sonographer should look next. Our approach uses video and expert knowledge, defined by gaze tracking data, which is acquired during routine first-trimester fetal ultrasound scanning. Specifically, we propose a spatio-temporal convolutional LSTMU-Net neural network (c...

In this paper, we consider image quality assessment (IQA) as a measure of how images are amenable with respect to a given downstream task, or task amenability. When the task is performed using machine learning algorithms, such as a neural-network-based task predictor for image classification or segmentation, the performance of the task predictor pr...

SlowflowHD is a new ultrasound Doppler imaging technology that allows visualization of flow within small blood vessels. In this mode, a proprietary algorithm differentiates between low-speed flow and signals attributed to tissue motion so that microvessel vasculature can be examined. Our objectives were to describe the low-velocity Doppler mode pri...

In this paper, we consider image quality assessment (IQA) as a measure of how images are amenable with respect to a given downstream task, or task amenability. When the task is performed using machine learning algorithms, such as a neural-network-based task predictor for image classification or segmentation, the performance of the task predictor pr...

BACKGROUND Ultrasound for gestational age (GA) assessment is not routinely available in resource-constrained settings, particularly in rural and remote locations. The TraCer device combines a handheld wireless ultrasound probe and a tablet with Artificial Intelligence (AI)-enabled software that obtains GA from videos of the fetal head by automated...

Background Ultrasound for gestational age (GA) assessment is not routinely available in resource-constrained settings, particularly in rural and remote locations. The TraCer device combines a handheld wireless ultrasound probe and a tablet with artificial intelligence (AI)-enabled software that obtains GA from videos of the fetal head by automated...

We present a method for classifying tasks in fetal ultrasound scans using the eye-tracking data of sonographers. The visual attention of a sonographer captured by eye-tracking data over time is defined by a scanpath. In routine fetal ultrasound, the captured standard imaging planes are visually inconsistent due to fetal position, movements, and son...

Deep networks have been shown to achieve impressive accuracy for some medical image analysis tasks where large datasets and annotations are available. However, tasks involving learning over new sets of classes arriving over extended time is a different and difficult challenge due to the tendency of reduction in performance over old classes while ad...

The performance of many medical image analysis tasks are strongly associated with image data quality. When developing modern deep learning algorithms, rather than relying on subjective (human-based) image quality assessment (IQA), task amenability potentially provides an objective measure of task-specific image quality. To predict task amenability,...

Automated ultrasound (US)-probe movement guidance is desirable to assist inexperienced human operators during obstetric US scanning. In this paper, we present a new visual-assisted probe movement technique using automated landmark retrieval for assistive obstetric US scanning. In a first step, a set of landmarks is constructed uniformly around a vi...

The performance of many medical image analysis tasks are strongly associated with image data quality. When developing modern deep learning algorithms, rather than relying on subjective (human-based) image quality assessment (IQA), task amenability potentially provides an objective measure of task-specific image quality. To predict task amenability,...

Fetal alcohol syndrome (FAS) caused by prenatal alcohol exposure can result in a series of cranio-facial anomalies, and behavioral and neurocognitive problems. Current diagnosis of FAS is typically done by identifying a set of facial characteristics, which are often obtained by manual examination. Anatomical landmark detection, which provides rich...

This paper presents a novel approach to automatic fetal brain biometry motivated by needs in low- and medium- income countries. Specifically, we leverage high-end (HE) ultrasound images to build a biometry solution for low-cost (LC) point-of-care ultrasound images. We propose a novel unsupervised domain adaptation approach to train deep models to b...

The performance of many medical image analysis tasks are strongly associated with image data quality. When developing modern deep learning algorithms, rather than relying on subjective (human-based) image quality assessment (IQA), task amenability potentially provides an objective measure of task-specific image quality. To predict task amenability,...

Ultrasound is the primary modality for obstetric imaging and is highly sonographer dependent. Long training period, insufficient recruitment and poor retention of sonographers are among the global challenges in the expansion of ultrasound use. For the past several decades, technical advancements in clinical obstetric ultrasound scanning have largel...

While performing an ultrasound (US) scan, sonographers direct their gaze at regions of interest to verify that the correct plane is acquired and to interpret the acquisition frame. Predicting sonographer gaze on US videos is useful for identification of spatio-temporal patterns that are important for US scanning. This paper investigates utilizing s...