Skip to main content
Dr Concetta Piazzese PhD

Dr Concetta Piazzese


Research Associate

School of Engineering

+44 (0)29 2087 0022
Room N/1.51, Queen's Buildings - North Building, 5 The Parade, Newport Road, Cardiff, CF24 3AA
Available for postgraduate supervision


I am a Research Associate at the School of Engineering. I received a MEng degree in Biomedical Engineering from Politecnico di Milano. In 2012, I started a joint Phd between Politecnico di Milano and Università della Svizzera italiana focused on development cardiac models by means of precise and realistic patient-specific geometries extracted from medical images. I also collaborated with the Noninvasive Cardiac Imaging Laboratory (University of Chicago) and with Cardiocentro (Lugano).

I have a strong experience in medical image processing and algorithm development.

I also have a strong experience in supervising undergraduate students.

My current research interests include: X-ray imaging, CT Imaging, MR Imaging, radiomics, machine learning, clinical studies, medical physics, Radiotherapy Trials Quality Assurance (RTTQA).

Member, Medical Engineering group.

Member, Cancer Imaging and Data Analytics research group.

Member, Research Committee.

Member, Cardiff University Research Staff Association (CURSA).

Part Member of the Center for Computational Medicine in Cardiology (CCMC).


Education and Qualification


Phd in Biomedical Engineering (joint PhD), Politecnico di Milano (Italy) and Università della Svizzera Italiana (Switzerland).


Master’s Degree in Biomedical Engineering, Politecnico di Milano (Italy).


Bachelor’s Degree in Biomedical Engineering, Politecnico di Milano (Italy).

Career overview

2017 – Present

Research Associate, School of Engineering, Cardiff University, Cardiff, UK.

2016 – 2017

Research Fellow, Centro Cardiologico Monzino, Milan, Italy.


Visiting Researcher, The University of Chicago, Chicago, Illinois, United States


Biomedical engineer (intern), Laboratorio di Ingegneria Clinica, Fondazione San Raffaele del Monte Tabor, Milan

Honours and awards


Best Poster Award at the 12th IEEE-EMBS International Summer School on Biomedical Imaging, Saint-Jacut de la Mer, France, June 16th - June 24th.


Rosanna Degani Young Investigator's Finalist Award, IEEE Computers in Cardiology.






2020 – Present

Co-leader of the module Engineering Computing (EN1094).

2017 – Present

Lecturer of the module Medical Image Processing (EN4505).


Tutor of the module Biomedical Image Processing Laboratory (073588) in Politecnico di Milano (March - June 2016).

Research theme: medical engineering, radiomics, Radiotherapy Trials Quality Assurance (RTTQA).

2017 – PRESENT

TEXRAD: Establishing image derived prognostic and predictive biomarkers of radiotherapy treatments and assessing treatment response using texture analysis.

Radiotherapy is used as part of the treatment approach in approximately 40% of patients cured of their disease, but unfortunately not all patients are cured. There is a much work being done to improve outcomes by increasing the radiotherapy dose or combining (novel) drugs with the radiotherapy, but these may add side effects. We therefore want to be able to improve our prediction of which patients will be cured with standard therapy and which will recur, as these have the most to benefit from intensifying the treatment. There are several approaches being pursued, based on samples of the cancer, blood samples or imaging. This study aims to derive more information from the imaging that is routinely taken as part of patients’ care, using locally developed, highly sophisticated analysis programs.

ARENA: Extension of RTTQA outlining activity into the educational arena.

Delineation of radiotherapy target volume has an essential role in modern treatment planning. However, it is affected by intra-interobserver variations and it has been identified as a weakness in radiotherapy planning. For this reason, accurate target volume delineation (TVD) is necessary to ensure optimal tumour coverage. ARENA, a collaborative project among Cardiff University, Velindre Cancer Centre and Singleton Hospital, aims at facilitating higher quality and standardised TVD approach through development of tumour site-specific TVD instructional modules and corresponding outlining module.

2012 – 2016

An inter-modality statistical shape modelling approach for the 3D segmentation of cardiac structures from magnetic resonance images.

Cardiac magnetic resonance (CMR) imaging is considered the reference modality for quantification of ventricular volume and function. Important clinical parameters are still derived from manual segmentation of the data. Different automated or semi-automated segmentation techniques have been proposed to improve reproducibility and preserve accuracy. To this respect, model-based methods, such as statistical shape models (SSM), have become a powerful tool to segment medical images by deforming and matching a predefined geometric shape to the locations of extracted features of the desired structure to be detected. The goal of this project was to develop and optimize an inter-modality SSM approach and adapt it to segment different cardiac structures (such as the LV endocardium and epicardium, and the right ventricular (RV) endocardium) with minimal user interaction.