Info - Cancer

Info - Cancer

We investigate the use of multi-parametric magnetic resonance imaging and spectroscopy for cancer diagnosis, focused on early-stage cancers, robustness of diagnosis results, and computationally lightweight machine learning approaches. We are particularly interested in explainable artificial intelligence to produce justifications for diagnosis results and incorporate human expert feedback.

People

Publications

  • P Gerbino, FC Langbein, K Sidorov, S Shermer. Capsule Network with Attention-Guided Reconstruction for Prostate Cancer Detection in Multi-Parametric MRI. All-Wales Medical Physics & Clinical Engineering Summer Meeting, Swansea, June 2025.
  • S Shermer, FC Langbein, A Muftah, Unlocking Early-Stage Prostate Cancer: Texture Feature Analysis of mpMRI. All-Wales Medical Physics & Clinical Engineering Summer Meeting, Swansea, June 2025.
  • T Greatrix, FC Langbein, RM Whitaker, GB Colombo, LD Turner. High-Confidence Labelling of Pathology Reports using LLM-Based Unanimous Ensembles with Limited Data. Proc AI in Healthcare (AIiH), Cambridge, UK, September 2025. [PDF]
  • E Alwadee, X Sun, Y Qin, FC Langbein. LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation. Computers in Biology and Medicine, 184:109353, 2025. [DOI:10.1016/j.compbiomed.2024.109353] [arXiv:2404.05911] [PDF]
  • Asmail Muftah, SM Shermer, Frank C Langbein. Texture Feature Analysis for Classification of Early-Stage Prostate Cancer in mpMRI. Proc AI in Healthcare (AIiH), LNCS 14976:118-131, Swansea, UK, September 2024. [DOI:10.1007/978-3-031-67285-9_9] [arXiv:2406.15571] [PDF] [PDF:poster]
  • E Alwadee, X Sun, Y Qin, FC Langbein. Assessing and Enhancing the Robustness of Brain Tumor Segmentation using a Probabilistic Deep Learning Architecture. Proc 2024 ISMRM & ISMRT Annual Meeting & Exhibition, Singapore, May 2024. [PDF] [Slides:PDF] [Video]
  • I Papadopoulos, J Phillips, R Evans, N Fenn, S Shermer. Evaluation of Diffusion Weighted Imaging in the Context of Multi-Parametric MRI of the Prostate in the assessment of suspected low volume prostatic carcinoma. Magnetic Resonance Imaging, 47:131-136, 2018. [DOI:10.1016/j.mri.2017.11.014] [arXiv:1711.09703]
  • ZG Portakal, S Shermer, E Spezi, T Perrett, J Phillips. Effect of Noise Floor Suppression on Diffusion Kurtosis for Prostate Brachytherapy. Radiotherapy and Oncology, 123:S938-S938, 2017. [PDF:poster]
  • S Shermer, I Papadopoulos, G Portakal, J Phillips, R Evans. Multimodal magnetic resonance imaging and spectroscopy for prostate cancer screening and staging. Physica Medica, 32, Suppl. 3, 324, 2016. [DOI:10.1016/j.ejmp.2016.07.217]
  • ZG Portakal, JW Phillips, CE Richards, E Spezi, T Perrett, DG Lewis, Z Yegingil. EP-1878: Feasibility of gel phantoms in MRI for the assessment of kurtosis for prostate brachytherapy. J Radiotherapy and Oncology, 119:S887-S888, 2016. [PDF]

Presentations

  • S Shermer. Quantitative MRI and Spectroscopy: from quantification of chemicals in the brain to diagnostic tools for prostate cancer. Healthcare Technologies Research Group seminar at the School of Computer Science and Informatics, Cardiff University, 16/2/2022. [YouTube:video]

PhDs

  • Piero Gerbino. Human-Centric Explainable AI for Prostate Cancer Diagnosis. School of Computer Science and Informatics, Cardiff University, ongoing.
  • EJ Alwadee. Novel Adaptive Down-sample Neural Network Classification for Detecting Brain Tumour from MRI Brain Images. School of Computer Science and Informatics, Cardiff University, ongoing.
  • O Ukwandu. Developing A Robust Artificial Intelligence System for Precision Diagnosis of Prostate Cancer Using Magnetic Resonance Imaging. School of Computer Science and Informatics, Cardiff University, ongoing.
  • AAS Muftah. Computer-aided diagnosis of prostate cancer via machine learning using multiparametric MRI. PhD thesis, School of Computer Science and Informatics, Cardiff University, 2024. [ORCA]
  • I Papadopoulos. Multi-parametric MRI of Prostate Cancer: Assessmnet of Spectroscopy, Diffusion, Dynamic Contrast and Relaxometry for Active Surveillance and Staging. PhD thesis, Swansea University, 2018. [DOI:10.23889/Suthesis.51146]

Reports

  • J Thavaratnem. Comparative Analysis of 2D and 3D U-Net Convolutional Neural Networks for Brain Tumour Detection in MRI Images. BSc Computer Science dissertation, 2024.
  • Michał Danikiewicz. Data Management App for Oncological Ablation. BSc Computer Science dissertation, Cardiff University, 2024.
  • E Alwadee, FC Langbein, X Sun, Y Qin. An Efficient, Interpretable, and Lightweight Deep Learning Model for Brain Tumour Segmentation. Technical report, Cardiff University, 2024.
  • J Chen. A Deep Learning Approach for Segmentation of Clinically Significant Prostate MRI Images. MSc Computing dissertation, Cardiff University, 2023.
  • M Bors. Anatomical Segmentation of Prostate MR Images, BSc Computer Science dissertation, Cardiff University, 2023. [Archive]
  • O Ukwandu. An Explainable Artificial Intelligence System for Precision Diagnosis of Prostate Cancer Using Magnetic Resonance Imaging. Technical report, Cardiff University, 2023.
  • W Glover. Prostate MR Image Segmentation, MSc Computing dissertation, Cardiff University, 2022. [Archive]
  • E Alwadee. Brain Tumour Segmentation Based on Deep Learning Approach. Technical report, Cardiff University, 2022.
  • A Nightingale. Delineating Regions of Interest in MRI/S Prostate Scans for Cancer Diagnosis. MSc Computing dissertation, Cardiff University. 2020.
  • D Morgan. Delineating regions of interest in MRI prostate scans. BSc Computer Science dissertation, Cardiff University, 2019. [Archive]

Code and Results

Data

We use the following

  • prostate cancer datasets:
    • Swansea University PCa data set: a collection of anonymized multi-parametric MRI data, primarily representing early-stage PCa
    • I2CVB: Initiative for Collaborative Computer Vision Benchmarking
    • MSD Prostate: Medical Segmentation Decathlon
    • PI-CAI images and labels: PI-CAI Grand Challenge
    • PROMISE12: PROMISE12 Grand Challenge
    • ProstateX data and masks: SPIE-AAPM-NCI PROSTATEx Challenge
    • QIN Prostate: QIN PROSTATE
  • and brain cancer datasets:

Workshops

  • Cancer AI Meeting, Swansea University, 31 July 2024.
  • PCa Workshop, Swansea University, 15th November 2018.
  • VLunch Seminar, Cardiff University, August 2018: Rhodri Evans, Prostate Cancer Diagnosis.

Locations

The wiki is written and maintained on Qyber\black at https://qyber.black/ca/info-cancer/.

Contact

For any general enquiries relating to this project group, send an e-mail.

License

CC BY-NC-SA 4.0 This wiki is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

The publications, code, data, etc. may be under a different license. Check the relevant information provided with these products.

If you wish to use any content available under the qyber.black and qyber.dev domains to develop an AI system (or anything else), we expect that any code, models, and other results are made available under a license compatible with the contents' license. We reserve the right to corrupt models, code or anything else that violates this by inserting suitable mechanisms in the content of qyber.black and qyber.dev.