PeopleofSuperintelligence

Researcher

Andrew P. Bradley

Also known as Andrew Bradley

Andrew P. Bradley is a medical image analysis researcher whose 1997 Pattern Recognition paper on the area under the ROC curve has more than 6,000 Scopus citations. With a University of Queensland PhD, he was an ARC Future Fellow and Director of Research for the university's School of Information Technology and Electrical Engineering from 2011 to 2016. His later work applied deep learning to medical images: in 2017 he coauthored papers on mammograms, CT-based longevity prediction and hip-fracture detection, and in 2025 a study of saliency methods for a race-detecting chest x-ray network. By 2022 he was Associate Dean of Research and Innovation for the Science and Engineering Faculty at Queensland University of Technology, and he is now an adjunct professor there and at the University of the Sunshine Coast, and Director of AI and ML at Whipbird Signals.

Now at
Queensland University of Technology, University of the Sunshine Coast and Whipbird Signals Pty Ltd
Badges
Links
Website, X and LinkedIn

Timeline

  1. 1997

    Area under the ROC curve

    In 1997, he publishes a Pattern Recognition paper on the use of the area under the ROC curve in the evaluation of machine learning algorithms. It evaluates six machine learning algorithms on six medical diagnostics data sets and recommends AUC over overall accuracy for single-number evaluation. Scopus lists more than 6,000 citations for the paper.

  2. 2007

    Rules from support vector machines

    In 2007, he and Nahla Barakat publish SQRex-SVM in IEEE Transactions on Knowledge and Data Engineering. The algorithm extracts rules directly from the support vectors of a trained support vector machine, using a modified sequential covering algorithm.

  3. 2011–2016

    ARC Future Fellow at Queensland

    A University of Queensland PhD graduate, he is an ARC Future Fellow and Director of Research for the university's School of Information Technology and Electrical Engineering from 2011 to 2016. His fellowship project (FT110100623) is Multi-modal virtual microscopy for quantitative diagnostic pathology.

  4. 2014–2016

    Segmenting overlapping cervical cells

    From 2014 to 2016, he, Gustavo H. Carneiro and Jacinto C. Nascimento hold an ARC Discovery grant (DP140102794) on the automated analysis of multi-modal medical data using deep belief networks. In 2015, he coauthors with Zhi Lu and Gustavo Carneiro an IEEE Transactions on Image Processing paper that segments overlapping cervical cells with a joint optimization of multiple level set functions.

  5. 2017

    Deep learning for radiology images

    In 2017, he coauthors an IEEE Transactions on Medical Imaging paper with Gustavo Carneiro and Jacinto Nascimento that applies deep learning to jointly classify unregistered mammogram views and breast-lesion segmentation maps. He also coauthors a Scientific Reports paper with Luke Oakden-Rayner and colleagues that predicts patient longevity from routine CT imaging. In November 2017, he is one of five authors of a paper on a deep learning system that detects hip fractures on pelvic x-rays with an area under the ROC curve of 0.994.

  6. By 2022

    Associate Dean at QUT

    By 2022, he is Associate Dean of Research and Innovation for the Science and Engineering Faculty at Queensland University of Technology. His earlier industry roles include Chief Technology Officer of Ausonex, a company that designs and develops hearing test instruments, and Principal Biomedical Engineer at Maxwell MRI, a company developing diagnostic tools powered by artificial intelligence and multi-parametric magnetic resonance imaging.

  7. 2025

    Saliency maps and race detection

    In 2025, he coauthors with Salamata Konate and colleagues a study in Computational and Structural Biotechnology Journal that applies eight saliency methods to a deep neural network that detects a patient's race from chest x-rays. The study finds that saliency maps in medicine should be used with caution.

  8. As of October 2026

    Adjunct professor and AI director

    As of October 2026, he is Director of AI and ML at Whipbird Signals Pty Ltd and holds adjunct professorships at the University of the Sunshine Coast and Queensland University of Technology. His work centers on the application and evaluation of computer-aided diagnosis systems in medical imaging.

Career

  1. NowQueensland University of TechnologyAssociate Dean of Research and Innovation
  2. NowUniversity of the Sunshine CoastAdjunct Professor
  3. NowWhipbird Signals Pty LtdDirector of AI and ML
  4. 2011–2016University of QueenslandARC Future Fellow
  5. AusonexChief Technology Officer
  6. Maxwell MRIPrincipal Biomedical Engineer

Education

  1. University of QueenslandPhD

From the biography.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Queensland University of Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Queensland University of Technology. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Queensland University of Technology. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University of Queensland. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Andrew P. Bradley yet. Send us a free-licensed photo.

  1. The use of the area under the ROC curve in the evaluation of machine learning algorithms | QUT ePrints eprints.qut.edu.au. Checked 21 October 2026.
  2. Rule extraction from support vector machines: A sequential covering approach | QUT ePrints eprints.qut.edu.au. Checked 21 October 2026.
  3. Andrew Bradley - Signal Processing, Artificial Intelligence and Vision Technologies research.qut.edu.au. Checked 21 October 2026.
  4. Grants & Awards staff.itee.uq.edu.au. Checked 21 October 2026.
  5. An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells | QUT ePrints eprints.qut.edu.au. Checked 21 October 2026.
  6. Automated analysis of unregistered multi-view mammograms with deep learning | QUT ePrints eprints.qut.edu.au. Checked 21 October 2026.
  7. Precision Radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework | QUT ePrints eprints.qut.edu.au. Checked 21 October 2026.
  8. Detecting hip fractures with radiologist-level performance using deep neural networks arxiv.org. Checked 21 October 2026.
  9. Andrew Bradley - QUT Centre for Data Science research.qut.edu.au. Checked 21 October 2026.
  10. Interpretability of AI race detection model in medical imaging with saliency methods | QUT ePrints eprints.qut.edu.au. Checked 21 October 2026.
  11. Andrew P. Bradley | alphaXiv alphaxiv.org. Checked 21 October 2026.