Andrew Peter King

• PhD
• Professor at King's College London

Background Mandibular osteoradionecrosis (ORN) is a severe late complication affecting patients with head and neck cancer (HNC) treated with radiotherapy that significantly impacts patients’ quality of life and can require costly interventions. While radiation dose is a key factor, other clinical and demographic risk factors influence ORN developme...

Background and purpose While the inclusion of spatial dose information in deep learning (DL)-based normal-tissue complication probability (NTCP) models has been the focus of recent research studies, external validation is still lacking. This study aimed to externally validate a DL-based NTCP model for mandibular osteoradionecrosis (ORN) trained on...

Deep learning (DL) has been proposed for magnetic resonance imaging (MRI) prostate auto-contouring for radiotherapy treatment planning. Recently, there has been growing interest in addressing potential demographic bias in DL models when trained with data that are not representative of the diversity of patient populations, for example by race or sex...

Deep learning (DL) models have been proposed to automate this process, but their use is hindered by the problem of domain shift. For example, DL models trained using data from a single scanner vendor/field strength may not generalise well to data from other scanners.The main aim of this work was to validate the performance of a DL auto-contouring m...

Background/Introduction Cine cardiovascular magnetic resonance (CMR) is the gold-standard technique for the assessment of cardiac function and structure. Manual analysis of cine CMR to estimate structural and functional biomarkers is costly and time-consuming, motivating the use of artificial intelligence (AI) for automation. However, the scan-resc...

Background Atrial Fibrillation (AF) is a prevalent cardiac arrhythmia globally, associated with heightened risks of stroke, dementia, and heart failure. Catheter ablation, the sole curative therapy for AF, yields suboptimal success rates for persistent AF cases. Understanding the mechanisms and dynamics of AF remains challenging, hindering treatmen...

Background: Deep learning (DL) has been proposed for magnetic resonance imaging (MRI) prostate segmentation for radiotherapy treatment planning. In other applications, DL models have exhibited bias in performance based on protected attributes such as race. We aimed to investigate possible race bias in DL prostate MRI segmentation. Methods: DL model...

Objective. Normal tissue complication probability (NTCP) modelling is rapidly embracing deep learning (DL) methods, acknowledging the importance of spatial dose information. Finding effective ways to combine information from radiation dose distribution maps (dosiomics) and clinical data involves technical challenges and requires domain knowledge. W...

Artificial intelligence (AI) methods are being used increasingly for the automated segmentation of cine cardiac magnetic resonance (CMR) imaging. However, these methods have been shown to be subject to race bias, i.e. they exhibit different levels of performance for different races depending on the (im)balance of the data used to train the AI model...

Objective: Cardiovascular ageing is a progressive loss of physiological reserve, modified by environmental and genetic risk factors, that contributes to multi-morbidity due to accumulated damage across diverse cell types, tissues and organs. Obesity is implicated in premature ageing but the effect of body fat distribution in humans is unknown. Here...

Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires significant expe...

Objectives Toxicity-driven adaptive radiotherapy (RT) is enhanced by the superior soft tissue contrast of magnetic resonance (MR) imaging compared with conventional computed tomography (CT). However, in an MR-only RT pathway synthetic CTs (sCT) are required for dose calculation. This study evaluates 3 sCT approaches for accurate rectal toxicity pre...

Atrial fibrillation (AF) is a prevalent cardiac arrhythmia that also carries a high risk of stroke. Catheter ablation has emerged as an effective treatment option for paroxysmal AF, but it results in high recurrence rates in persistent AF cases. Recent studies have highlighted the potential of low voltage- and fibrosis-substrate ablation as effecti...

Background and purpose: Mandibular osteoradionecrosis (ORN) is a severe side effect affecting patients undergoing radiation therapy for head and neck cancer. Variations in the bone's vascularization and composition across the mandible may influence the susceptibility to ORN. Recently, deep learning-based models have been introduced for predicting m...

the use of real-time magnetic resonance imaging (rt-MRI) of speech is increasing in clinical practice and speech science research. Analysis of such images often requires segmentation of articulators and the vocal tract, and the community is turning to deep-learning-based methods to perform this segmentation. While there are publicly available rt-MR...

This paper presents advancements in automated early-stage prediction of the success of reprogramming human induced pluripotent stem cells (iPSCs) as a potential source for regenerative cell therapies. The minuscule success rate of iPSC-reprogramming of around 0.01% to 0.1% makes it labor-intensive, time-consuming, and exorbitantly expensive to gene...

Background Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the Rectus Femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires signi...

This paper proposes a fully-automated technique for estimation of an antenatal risk score for Coarctation of the Aorta (CoA) from fetal T2-weighted 3D cardiac magnetic resonance imaging (CMR). Our framework combines automated multi-class fetal cardiac vessel segmentation based on two fully-labelled atlases (control and CoA) with statistical shape a...

Purpose. Normal tissue complication probability (NTCP) modelling is rapidly embracing deep learning (DL) methods as the need to include spatial dose information is acknowledged. Finding the most appropriate way of combining radiation dose distribution images and clinical data involves technical challenges and requires domain knowledge. We propose d...

In medical imaging, artificial intelligence (AI) is increasingly being used to automate routine tasks. However, these algorithms can exhibit and exacerbate biases which lead to disparate performances between protected groups. We investigate the impact of model choice on how imbalances in subject sex and race in training datasets affect AI-based cin...

Unsupervised anomaly detection methods offer a promising and flexible alternative to supervised approaches, holding the potential to revolutionize medical scan analysis and enhance diagnostic performance. In the current landscape, it is commonly assumed that differences between a test case and the training distribution are attributed solely to path...

Recent research has shown that artificial intelligence (AI) models can exhibit bias in performance when trained using data that are imbalanced by protected attribute(s). Most work to date has focused on deep learning models, but classical AI techniques that make use of hand-crafted features may also be susceptible to such bias. In this paper we inv...

Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this paper, we present a fully-a...

Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed. Muscle mass must be recovered through physiotherapy before patient discharge and ultrasound imaging is frequently used to assess the recovery process by measuring the muscle size over time. However, these manual...

Background: Increased systemic vascular resistance and, in older people, reduced aortic distensibility, are thought to be the hemodynamic determinants of primary hypertension but cardiac output could also be important. We examined the hemodynamics of elevated blood pressure and hypertension in the middle to older-aged UK population participating i...

Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy artificial intelligence (AI) models beyond conventional reporting of performance metrics. When considering their role in a clinical decision support setting, AI classification models should ideally avoid confident wrong predictions and maximise the con...

Unsupervised anomaly detection methods offer a promising and flexible alternative to supervised approaches, holding the potential to revolutionize medical scan analysis and enhance diagnostic performance. In the current landscape, it is commonly assumed that differences between a test case and the training distribution are attributed solely to path...

In medical imaging, artificial intelligence (AI) is increasingly being used to automate routine tasks. However, these algorithms can exhibit and exacerbate biases which lead to disparate performances between protected groups. We investigate the impact of model choice on how imbalances in subject sex and race in training datasets affect AI-based cin...

Cardiovascular ageing is a process that begins early in life and leads to a progressive change in structure and decline in function due to accumulated damage across diverse cell types, tissues and organs contributing to multi-morbidity. Damaging biophysical, metabolic and immunological factors exceed endogenous repair mechanisms resulting in a pro-...

Abnormal spleen enlargement (splenomegaly) is regarded as a clinical indicator for a range of conditions, including liver disease, cancer and blood diseases. While spleen length measured from ultrasound images is a commonly used surrogate for spleen size, spleen volume remains the gold standard metric for assessing splenomegaly and the severity of...

Aims Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function...

Background: Interpreting point-of-care lung ultrasound (LUS) images from intensive care unit (ICU) patients can be challenging, especially in low- and middle- income countries (LMICs) where there is limited training available. Despite recent advances in the use of Artificial Intelligence (AI) to automate many ultrasound imaging analysis tasks, no...

Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Wellcome/EPSRC Centre for Medical Engineering at King’s College London (WT 203148/Z/16/Z), the National Institute for Health Research (NIHR) Cardiovascular MedTech Co-operative award to the Guy’s and St Thomas’ NHS Foundation Trust, and...

Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed. Muscle mass must be recovered through physiotherapy before patient discharge and ultrasound imaging is frequently used to assess the recovery process by measuring the muscle size over time. However, these manual...

Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy artificial intelligence (AI) models beyond conventional reporting of performance metrics. When considering their role in a clinical decision support setting, AI classification models should ideally avoid confident wrong predictions and maximise the con...

Objective: Automated detection of foreshortening, a common challenge in routine 2-D echocardiography, has the potential to improve quality of acquisitions and reduce the variability of left ventricular measurements. Acquiring and labelling the required training data is challenging due to the time-intensive and highly subjective nature of foreshort...

Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): British Heart Foundation (RG/19/6/34387, RE/18/4/34215). Background Population ageing is a global trend and places an increased burden on healthcare resources, predominantly through cardiovascular morbidity and mortality. Ageing can be...

Whilst most of this book has focused on imaging data because of the key role it plays in cardiology, non-imaging data also has an important role to play. This chapter reviews some of the most relevant non-imaging data sources and how they can be used by AI to positively impact patient management. Electrophysiology data, electrocardiograms and elect...

Atrial fibrillation (AF) is the most common cardiac arrhythmia worldwide; however, the current success rates for catheter ablation (CA) therapy, the first-line treatment for AF, are suboptimal. Therefore, extensive research has focused on the relationship between scar tissue in the left atrium (LA) and AF, and its application for patient stratifica...

In this chapter the key concepts of artificial intelligence and machine learning are introduced. The importance of first identifying and defining the right problem is emphasised. A review is provided of different types of machine learning model, and pointers are provided about how to design and train a model to meet the requirements of the chosen p...

In terms of accuracy, deep learning (DL) models have had considerable success in classification problems for medical imaging applications. However, it is well-known that the outputs of such models, which typically utilise the SoftMax function in the final classification layer can be over-confident, i.e. they are poorly calibrated. Two competing sol...

Background: Radiofrequency catheter ablation (RFCA) therapy is the first-line treatment for atrial fibrillation (AF), the most common type of cardiac arrhythmia globally. However, the procedure currently has low success rates in dealing with persistent AF, with a reoccurrence rate of ∼50% post-ablation. Therefore, deep learning (DL) has increasingl...

Supplementary material for “Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation” study

Objective Dynamic magnetic resonance (MR) imaging enables visualisation of articulators during speech. There is growing interest in quantifying articulator motion in two-dimensional MR images of the vocal tract, to better understand speech production and potentially inform patient management decisions. Image registration is an established way to ac...

In terms of accuracy, deep learning (DL) models have had considerable success in classification problems for medical imaging applications. However, it is well-known that the outputs of such models, which typically utilise the SoftMax function in the final classification layer can be over-confident, i.e. they are poorly calibrated. Two competing sol...

In computer vision there has been significant research interest in assessing potential demographic bias in deep learning models. One of the main causes of such bias is imbalance in the training data. In medical imaging, where the potential impact of bias is arguably much greater, there has been less interest. In medical imaging pipelines, segmentat...

Flow analysis carried out using phase contrast cardiac magnetic resonance imaging (PC-CMR) enables the quantification of important parameters that are used in the assessment of cardiovascular function. An essential part of this analysis is the identification of the correct CMR views and quality control (QC) to detect artefacts that could affect the...

This chapter gives an overview of some of the basic mathematical operations in MATLAB that can be useful in engineering applications. This is a very broad topic and only a handful of areas are covered with examples: Scalars and vectors, complex numbers, matrices, including systems of equations, numerical differentiation, and integration. A list of...

This chapter introduces the concept of functions in MATLAB. Functions can be used to divide a solution to a complex problem into a number of solutions to simpler sub-problems, which communicate with each other by passing and receiving arguments. Function naming rules and the syntax for function definitions in MATLAB are introduced, and the importan...

This chapter covers the fundamental concepts of machine learning and how they can be applied in MATLAB. First, important terms such as Artificial Intelligence, Machine Learning, and Deep Learning are introduced and defined. Different types of machine learning model (supervised, unsupervised) are introduced, as well as ways in which they can be eval...

This chapter introduces the concept of control structures, which can be seen as the basic building blocks of computer programs. The concept of conditional control structures is described and illustrations are given for how MATLAB implements this idea using “if-else” and “switch” statements. Different types of logical expression for use with “if” st...

This chapter revisits the subject of code efficiency that was first touched on in Chapter 2. More detail is provided on the considerations for program efficiency, i.e. time and memory efficiency. Ways of assessing time and memory efficiency are introduced. Simple tips for improving program efficiency are covered, such as pre-allocation of arrays an...

This chapter covers the basics of statistics and shows how many common statistical operations can be carried out using MATLAB. Descriptive statistics are covered, including ways of numerically summarizing and visualizing univariate and bivariate datasets. The discussion of inferential statistics includes ways of testing the distribution of a sample...

This chapter extends the topic of data visualization that was first introduced in Chapter 1. Pie chart visualizations are first introduced. Next, different ways of visualizing multiple datasets in MATLAB are introduced and compared, including the ‘yyaxis’ command for producing plots with two different y-axes. Also, visualizations of multivariate da...

This chapter introduces the reader to the fundamental concepts of computer programming and provides a hands-on introduction to the MATLAB software package. The different components of the MATLAB environment are described. The chapter describes how to access the MATLAB documentation to find out more information about built-in MATLAB functions. Basic...

This chapter covers the subject of signal and image processing. The basics of storing and reading 1-D signals are introduced, and the signal processing technique of convolution is described in detail. The basics of images in MATLAB are reviewed and extended, including the difference between color and gray scale images, getting information about an...

In this chapter, more advanced MATLAB data types are introduced. Cells and cell arrays are described, and their differences to standard MATLAB arrays are explained. The MATLAB structure type is also introduced, which allows data of different types to be grouped together. Categorical arrays, tables, and maps are all described, along with practical e...

This chapter gives some details on data types in MATLAB. First, the meaning of a data type is expanded upon. The precision of floating point data types is explained, as well as different ways of displaying floating point values. The ranges of values that can be represented by different numeric types is also explained, as well as the concepts of inf...

This chapter describes how apps with graphical user interfaces (or GUIs) can be created using MATLAB. A simple case study of displaying and interacting with some biomedical data is used to illustrate the basics of app creation using the MATLAB App Designer tool. Concepts such as adding components to the GUI, controlling their behavior in response t...

Background Radiofrequency catheter ablation (RFCA) therapy is the first-line treatment for atrial fibrillation (AF), the most common type of cardiac arrhythmia globally. However, the procedure currently has low success rates in dealing with persistent AF, with a reoccurrence rate of ∼50% post-ablation. Therefore, artificial intelligence (AI), parti...

Background Automated analysis of cardiovascular magnetic resonance images provides the potential to assess aortic distensibility in large populations. The aim of this study was to compare the prediction of cardiovascular events by automated cardiovascular magnetic resonance with those of other simple measures of aortic stiffness suitable for popula...

PurposeThis study aimed to establish a nomogram for predicting overall survival (OS) in oropharyngeal cancer patients treated with curative (chemo)radiotherapy.Materials and methodsThe dynamic nomogram was constructed on 273 patients with oropharyngeal squamous cell carcinoma treated in a Tertiary Head and Neck Cancer Unit. The clinical features th...

Aims Existing strategies that identify post-infarct ventricular tachycardia (VT) ablation target either employ invasive electrophysiological (EP) mapping or non-invasive modalities utilizing the electrocardiogram (ECG). Their success relies on localizing sites critical to the maintenance of the clinical arrhythmia, not always recorded on the 12-lea...

Ultrasound imaging plays a crucial role in assessing disease and making diagnoses for a range of conditions, especially so in low-to-middle-income (LMIC) countries. One such application is the assessment of pleural effusion, which can be associated with multiple morbidities including tuberculosis (TB). Currently, assessment of pleural effusion is p...

Convolutional neural networks (CNNs) are increasingly being used to automate the segmentation of brain structures in magnetic resonance (MR) images for research studies. In other applications, CNN models have been shown to exhibit bias against certain demographic groups when they are under-represented in the training sets. In this work, we investig...

Cardiovascular ageing is a process that begins early in life and leads to a progressive change in structure and decline in function due to accumulated damage across diverse cell types, tissues and organs contributing to multi-morbidity. Damaging biophysical, metabolic and immunological factors exceed endogenous repair mechanisms resulting in a pro-...

Background Radiofrequency catheter ablation (RFCA) therapy is the first-line treatment for atrial fibrillation (AF), the most common type of cardiac arrhythmia globally. However, the procedure currently has low success rates in dealing with persistent AF, with a reoccurrence rate of ∼50% post-ablation. Therefore, artificial intelligence (AI), parti...

The Atherosclerotic Cardiovascular Disease Risk (ASCVD) score by pooled cohort equation is a reliable predictor for future ASCVD events and is used to guide primary prevention in asymptomatic aging subjects. ASCVD risk is associated with burden of coronary artery disease as measured from computed tomography angiography. Purpose We aim to investiga...

Background. Absorbed radiation dose to the mandible is an important risk factor in the development of mandibular osteoradionecrosis (ORN) in head and neck cancer (HNC) patients treated with radiotherapy (RT). The prediction of mandibular ORN may not only guide the RT treatment planning optimisation process but also identify which patients would ben...

Background. Absorbed radiation dose to the mandible is an important risk factor in the development of mandibular osteoradionecrosis (ORN) in head and neck cancer (HNC) patients treated with radio-therapy (RT). The prediction of mandibular ORN may not only guide the RT treatment planning optimisation process but also identify which patients would be...

Flow analysis carried out using phase contrast cardiac magnetic resonance imaging (PC-CMR) enables the quantification of important parameters that are used in the assessment of cardiovascular function. An essential part of this analysis is the identification of the correct CMR views and quality control (QC) to detect artefacts that could affect the...

Congenital heart disease (CHD) encompasses a range of cardiac malformations present from birth, representing the leading congenital diagnosis. 3D volumetric reconstructions of T2w black blood fetal MRI provide optimal vessel visualisation, supporting prenatal CHD diagnosis, a key step for optimal patient management. We present a framework for autom...

Left ventricular (LV) function is an important factor in terms of patient management, outcome, and long-term survival of patients with heart disease. The most recently published clinical guidelines for heart failure recognise that over reliance on only one measure of cardiac function (LV ejection fraction) as a diagnostic and treatment stratificati...

In computer vision there has been significant research interest in assessing potential demographic bias in deep learning models. One of the main causes of such bias is imbalance in the training data. In medical imaging, where the potential impact of bias is arguably much greater, there has been less interest. In medical imaging pipelines, segmentat...

Simpson's biplane rule (SBR) is considered the gold standard method for left ventricle (LV) volume quantification from echocardiography but relies on a summation-of-disks approach that makes assumptions about LV orientation and cross-sectional shape. We aim to identify key limiting factors in SBR and to develop a new robust standard for volume quan...

Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss functions, ignorant of the spatially extended features that characterise anatomy. Therefore, whilst sharing a high sp...

Atrial fibrillation (AF) is the most common cardiac arrhythmia worldwide; however, the current success rates for catheter ablation (CA) therapy, the first-line treatment for AF, are suboptimal. Therefore, extensive research has focused on the relationship between scar tissue in the left atrium (LA) and AF, and its application for patient stratifica...

Convolutional neural networks (CNNs) are increasingly being used to automate the segmentation of brain structures in magnetic resonance (MR) images for research studies. In other applications, CNN models have been shown to exhibit bias against certain demographic groups when they are under-represented in the training sets. In this work, we investig...

In many low-to-middle income (LMIC) countries, ultrasound is used for assessment of pleural effusion. Typically, the extent of the effusion is manually measured by a sonographer, leading to significant intra-/inter-observer variability. In this work, we investigate the use of deep learning (DL) to automate the process of pleural effusion segmentati...

Atrial fibrillation (AF) is globally the most common type of cardiac arrhythmia and is a precursor for serious conditions such as stroke. The success rate of AF treatments, such as catheter ablation (including the current gold standard, pulmonary vein isolation), is suboptimal, warranting better strategies. Fibrosis-substrate isolation ablation (FI...

Objective: Splenomegaly (abnormal splenic enlargement) is a potentially life-threatening condition that occurs in a range of clinical scenarios, including in patients suffering from Sickle cell disease (SCD). Therefore, spleen size assessments from ultrasound imaging are commonly performed in SCD clinics, and typically involve measuring the length...

Background. Absorbed radiation dose to the mandible is an important risk factor in the development of mandibular osteoradionecrosis (ORN) in head and neck cancer (HNC) patients treated with radiotherapy (RT). The prediction of mandibular ORN may not only guide the RT treatment planning optimisation process but also identify which patients would ben...