Nick Byrne

Nick Byrne

Auto-generated profile, based on publicly available information

Nick Byrne

Medical Physics Guy's and St. Thomas' NHS Foundation Trust London UK

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 September 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
JCJames R. Clough
James R. Clough
NBNicholas Byrne
Nicholas Byrne
IOIlkay Oksuz
Ilkay Oksuz
VZVeronika A. Zimmer
Veronika A. Zimmer
JSJulia A. Schnabel
Julia A. Schnabel
AKAndrew P. King
Andrew P. King
We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By using the differentiable properties of persistent homology, a concept used in topological data analysis, we can specify the desired topology of segmented objects in terms of their Betti numbers and then drive the proposed segmentations to contain the specified topological features. Importantly this process does not require any ground-truth labels, just prior knowledge of the topology of the structure being segmented. We demonstrate our approach in four experiments: one on MNIST image denoising and digit recognition, one on left ventricular myocardium segmentation from magnetic resonance imaging data from the UK Biobank, one on the ACDC public challenge dataset and one on placenta segmentation from 3-D ultrasound. We find that embedding explicit prior knowledge in neural network segmentation tasks is most beneficial when the segmentation task is especially challenging and that it can be used in either a semi-supervised or post-processing context to extract a useful training gradient from images without pixelwise labels.

12 July 2017 in European Journal of Cardio-Thoracic Surgery
Verified
Journal Article
Open access
PDF file
IVIsrael Valverde
Israel Valverde
GGGorka Gomez-Ciriza
Gorka Gomez-Ciriza
THTarique Hussain
Tarique Hussain
CSCristina Suarez-Mejias
Cristina Suarez-Mejias
MVMaria N Velasco-Forte
Maria N Velasco-Forte
AHAmir-Reza Hosseinpour
Amir-Reza Hosseinpour
To evaluate the impact of 3D printed models (3D models) on surgical planning in complex congenital heart disease (CHD). A prospective case-crossover study involving 10 international centres and 40 patients with complex CHD (median age 3 years, range 1 month–34 years) was conducted. Magnetic resonance imaging and computed tomography were used to acquire and segment the 3D cardiovascular anatomy. Models were fabricated by fused deposition modelling of polyurethane filament, and dimensions were compared with medical images. Decisions after the evaluation of routine clinical images were compared with those after inspection of the 3D model and intraoperative findings. Subjective satisfaction questionnaire was provided. 3D models accurately replicate anatomy with a mean bias of −0.27 ± 0.73 mm. Ninety-six percent of the surgeons agree or strongly agree that 3D models provided better understanding of CHD morphology and improved surgical planning. 3D models changed the surgical decision in 19 of the 40 cases. Consideration of a 3D model refined the planned biventricular repair, achieving an improved surgical correction in 8 cases. In 4 cases initially considered for conservative management or univentricular palliation, inspection of the 3D model enabled successful biventricular repair. 3D models are accurate replicas of the cardiovascular anatomy and improve the understanding of complex CHD. 3D models did not change the surgical decision in most of the cases (21 of 40 cases, 52.5% cases). However, in 19 of the 40 selected complex cases, 3D model helped redefining the surgical approach.

1 January 2016 in JRSM Cardiovascular Disease
Verified
Journal Article
Open access
NBN Byrne
N Byrne
MFM Velasco Forte
M Velasco Forte
ATAnimesh Tandon
Animesh Tandon
IVIsrael Valverde
Israel Valverde
THT Hussain
T Hussain
Background: Shortcomings in existing methods of image segmentation preclude the widespread adoption of patient-specific 3D printing as a routine decision-making tool in the care of those with congenital heart disease. We sought to determine the range of cardiovascular segmentation methods and how long each of these methods takes. Methods: A systematic review of literature was undertaken. Medical imaging modality, segmentation methods, segmentation time, segmentation descriptive quality (SDQ) and segmentation software were recorded. Results: Totally 136 studies met the inclusion criteria (1 clinical trial; 80 journal articles; 55 conference, technical and case reports). The most frequently used image segmentation methods were brightness thresholding, region growing and manual editing, as supported by the most popular piece of proprietary software: Mimics (Materialise NV, Leuven, Belgium, 1992–2015). The use of bespoke software developed by individual authors was not uncommon. SDQ indicated that reporting of image segmentation methods was generally poor with only one in three accounts providing sufficient detail for their procedure to be reproduced. Conclusions and implication of key findings: Predominantly anecdotal and case reporting precluded rigorous assessment of risk of bias and strength of evidence. This review finds a reliance on manual and semi-automated segmentation methods which demand a high level of expertise and a significant time commitment on the part of the operator. In light of the findings, we have made recommendations regarding reporting of 3D printing studies. We anticipate that these findings will encourage the development of advanced image segmentation methods.

31 August 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
NBNick Byrne
Nick Byrne
JCJames R. Clough
James R. Clough
IVIsrael Valverde
Israel Valverde
Giovanni MontanaGiovanni Montana
Giovanni Montana
AKAndrew P. King
Andrew P. King
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 spatial overlap with the ground truth, inferred CNN-based segmentations can lack coherence, including spurious connected components, holes and voids. Such results are implausible, violating anticipated anatomical topology. In response, (single-class) persistent homology-based loss functions have been proposed to capture global anatomical features. Our work extends these approaches to the task of multi-class segmentation. Building an enriched topological description of all class labels and class label pairs, our loss functions make predictable and statistically significant improvements in segmentation topology using a CNN-based post-processing framework. We also present (and make available) a highly efficient implementation based on cubical complexes and parallel execution, enabling practical application within high resolution 3D data for the first time. We demonstrate our approach on 2D short axis and 3D whole heart CMR segmentation, advancing a detailed and faithful analysis of performance on two publicly available datasets.

1 February 2018 in JACC: Cardiovascular Imaging
Verified
Journal Article
Closed access
MFMari Nieves Velasco Forte
Mari Nieves Velasco Forte
NBNick Byrne
Nick Byrne
IVIsrael Valverde
Israel Valverde
GCGorka Gomez Ciriza
Gorka Gomez Ciriza
AHAntony Hermuzi
Antony Hermuzi
EREric Rosenthal
Eric Rosenthal

1 March 2017 in Brachytherapy
Verified
Journal Article
Closed access
EJEmma-Louise Jones
Emma-Louise Jones
ABAnna Tonino Baldion
Anna Tonino Baldion
CTChristopher Thomas
Christopher Thomas
TBTom Burrows
Tom Burrows
NBNick Byrne
Nick Byrne
SASarah Aldridge
Sarah Aldridge