PeopleofSuperintelligence

Researcher

Dirk Vandermeulen

Dirk Vandermeulen is a medical-imaging researcher whose computer-vision work spans neurosurgery and forensic imaging. He began applying computer vision to forensic imaging in 2002 and coauthored two COVID-19 CT studies in 2020, on segmentation and explainable classification. In 2023, he coauthored a genome-wide association study that identified 30 loci linked to cranial-vault shape. In 2024, he was a professor of medical and forensic image analysis at KU Leuven; in 2025, he coauthored an interpretable study of molar staging. As of October 2026, he is a professor at University Hospitals Leuven.

Now at
Department of Electrical Engineering, KU Leuven and University Hospitals Leuven
Works
427
Citations
18,760
h-index
55
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. Since 2002

    Computer vision in forensics

    Initially, his research focuses on image processing for computer-assisted stereotactic neurosurgery. Since 2002, he applies computer vision and medical image analysis to forensic imaging, including craniofacial reconstruction, biometric authentication and facial analysis.

  2. 2020

    Deep learning for COVID-19 CT

    In 2020, he coauthors a comparison of 12 deep-learning algorithms for segmenting lungs and lesions in COVID-19 chest CT scans. An ensemble produces mean Dice scores of 0.982 for lung segmentation, 0.724 for binary lesion segmentation and 0.469 for multiclass lesion segmentation.

  3. 2020

    Explainable CT diagnosis

    In 2020, he coauthors an explainable semi-supervised system for classifying COVID-19 from CT images. Variational autoencoders produce feature embeddings, and a convolutional neural network performs classification.

  4. 2023

    Genetics of cranial shape

    In 2023, he coauthors a multi-ancestry genome-wide association study of 3D cranial-vault shape from MRI scans of 6,772 children. The study identifies 30 genome-wide significant loci.

  5. 2024

    Professor at KU Leuven

    In 2024, he is a professor of medical and forensic image analysis at KU Leuven's Division for Image and Speech Processing in the Department of Electrical Engineering. He is also an extraordinary professor at the University of Pretoria, South Africa.

  6. 2025

    Interpreting dental-stage models

    In 2025, he coauthors a forensic dental-age study that combines a convolutional autoencoder and a Vision Transformer to classify second and third molar stages. The framework improves accuracy for both teeth; its latent-space metrics and image reconstructions point to variation within the tooth 38 dataset as a source of the remaining performance gap.

  7. As of October 2026

    Professor at University Hospitals Leuven

    As of October 2026, he is a professor at University Hospitals Leuven in Leuven, Belgium.

Career

  1. NowDepartment of Electrical Engineering, KU LeuvenProfessor of medical and forensic image analysis
  2. NowUniversity Hospitals LeuvenProfessor
  3. 2024University of PretoriaExtraordinary Professor
  4. 2013–2015IMEC
  5. 1988–2026KU Leuven

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes KU Leuven. 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.
  2. Universities keep AI researchers for a median of 6 years, compared with 2 years at frontier labsIncludes KU Leuven. Across 15,811 dated work stays (6,529 people), median role tenure runs from 6 years at universities to 2 years at frontier labs. We compare all five organization types, starting decades from the 1970s to the 2020s, and the organizations that keep people longest.
  3. The United States employs an estimated 48% of people shaping AIIncludes KU Leuven. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes KU Leuven. 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.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Dirk Vandermeulen yet. Send us a free-licensed photo.

  1. Dirk Vandermeulen – IACI 2024 iaci2024.com. Checked 22 October 2026.
  2. Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients arxiv.org. Checked 22 October 2026.
  3. Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging arxiv.org. Checked 22 October 2026.
  4. Joint multi-ancestry and admixed GWAS reveals the complex genetics behind human cranial vault shape nature.com. Checked 22 October 2026.
  5. An Autoencoder and Vision Transformer-based Interpretability Analysis of the Differences in Automated Staging of Second and Third Molars arxiv.org. Checked 22 October 2026.
  6. An autoencoder and vision transformer based interpretability analysis on the performance differences in automated staging of second and third molars nature.com. Checked 22 October 2026.
  7. Loop | Dirk Vandermeulen loop.frontiersin.org. Checked 22 October 2026.