Open to Research Collaborations

Biomedical
Engineer &
Researcher

Bridging medicine and technology through medical imaging, signal processing, and machine learning — building tools that move from bench to bedside.

View Projects Get In Touch
5+
Years Research
12
Projects
3
Publications
98%
Model Accuracy
About Me

Passionate about
healthcare innovation

I am a Biomedical Engineer with a deep focus on applying computational methods to solve real-world clinical challenges. My work sits at the intersection of medical imaging, machine learning, and translational research — developing tools designed to move from the lab bench to the bedside.

Currently pursuing my PhD at the University of Sheffield, I am investigating novel deep learning architectures for automated medical image analysis, with a focus on early disease detection and AI-assisted diagnostic support. My interdisciplinary background spans signal processing, bioinformatics, and clinical data science.

Beyond research, I am committed to open science — contributing to open-source biomedical tooling and collaborating across disciplines to advance computational medicine. I thrive at the boundary between engineering rigour and clinical impact.

3

Peer-Reviewed Publications

12

Open-Source Projects

5+

Years of Research
Expertise

Skills & Experience

A blend of computational skills, research expertise, and clinical knowledge built over years of interdisciplinary work.

Programming & Tools
PythonExpert
MATLABAdvanced
R / StatisticsAdvanced
C++ / EmbeddedIntermediate
ML / AI Frameworks
TensorFlow / KerasExpert
PyTorchAdvanced
scikit-learnExpert
Biomedical Domain
Medical Imaging DICOM / NIfTI Signal Processing ECG / EEG Analysis Bioinformatics scRNA-seq Clinical Trials EHR Analysis MRI / CT / PET Histopathology PACS / HL7 / FHIR Computer Vision
Research & Lab
Statistical Analysis Systematic Review Cell Culture PCR / qPCR Western Blot Microscopy Grant Writing IRB / Ethics
Education
2022 – Present
PhD in Biomedical Engineering
University of Sheffield
Deep learning for automated medical image segmentation and early disease detection. EPSRC-funded. Supervised by [Supervisor Name].
2020 – 2022
MSc Biomedical Engineering
University of Sheffield · Distinction
Dissertation: "CNN-based tumour detection in multi-parametric MRI." Graduated with highest distinction.
2017 – 2020
BSc Biomedical Science
University of [X] · First Class Honours
Specialised in molecular biology and computational methods. Final project: ECG anomaly detection in wearable devices.
Experience
2023 – Present
Graduate Research Assistant
University of Sheffield · POLARIS MRI Research Lab
Developing attention-gated U-Net variants for prostate cancer segmentation. Processing multi-centre DICOM datasets across NHS sites.
Summer 2022
Research Intern
NHS Digital · Data Science Team
Built predictive readmission models using linked EHR data. Deployed as an internal clinical decision-support tool.
2021 – 2022
Teaching Assistant
University of Sheffield
Led Python and MATLAB labs for undergraduate biomedical engineering cohorts. Received outstanding student feedback.
Portfolio

Featured Projects

Selected research and engineering projects spanning medical imaging, signal processing, and AI for healthcare.

Imaging · ML

Prostate Cancer Segmentation via U-Net

Multi-parametric MRI segmentation using attention-gated U-Net. Achieves 0.91 Dice score on ProstateX — validated across 3 NHS sites with multi-centre DICOM data.

PyTorchU-Net DICOMMulti-centre
Code Paper
Signal · ML

ECG Arrhythmia Detection with 1D-CNN

Real-time cardiac arrhythmia classification across 8 classes using 1D-CNNs on 12-lead ECG signals. 98.4% accuracy on PhysioNet CINC 2017 challenge dataset.

TensorFlow1D-CNN PhysioNetReal-time
Code Demo
Bio · ML

Cancer Biomarker Discovery via scRNA-seq

Single-cell RNA sequencing pipeline for identifying novel cancer biomarkers. GNN-based cell-type classification across 50,000+ cells. Manuscript in preparation.

PythonGNN scRNA-seqSeurat
Code Preprint
Imaging

Chest X-Ray Pathology Classifier

Multi-label classification of 14 thoracic pathologies using DenseNet-121 with Grad-CAM explainability. Trained on 112k NIH ChestX-ray14 images. Clinical validation ongoing.

DenseNetGrad-CAM NIH DatasetXAI
Code Demo
Signal

EEG Motor Imagery BCI System

Brain-computer interface for 4-class motor imagery classification using EEGNet and CSP features. 85% accuracy for stroke rehabilitation. Validated on BCI Competition IV Dataset 2a.

EEGNetCSP MNE-PythonBCI
Code Paper
ML · Bio

Drug–Target Interaction Prediction

Graph neural network predicting drug-target binding affinity using molecular fingerprints and protein sequence embeddings. AUROC 0.94 on BindingDB. Supports early-stage drug discovery.

PyGGNN RDKitDrug Discovery
Code Paper
Contact

Let's Connect

Open to research collaborations, PhD opportunities, industry partnerships, and speaking invitations.

Get In Touch

Whether you have a research question, a collaboration idea, or just want to connect — my inbox is always open.

Email sedwards6@sheffield.ac.uk
LinkedIn Connect on LinkedIn
GitHub View repositories
Google Scholar Research publications

Send a Message