Melba logo

Machine Learning for Biomedical Imaging

Welcome to Melba (Machine Learning for Biomedical Imaging), a web-based journal devoted to the free and unrestricted access of high quality articles in the broad field that bridges machine learning and biomedical imaging.

You can read more about the mission statement of the journal, or jump right away to the journal publications. For authors, instructions are available here.




Latest publications


More publications...


Latest news


2025/03/28 – Special issue on Fairness of AI in Medical Imaging (FAIMI)

MELBA is excited to launch a special issue in collaboration with the FAIMI initiative, spotlighting research at the intersection of machine learning, medical imaging, and ethics.This issue invites contributions on:

  • Bias assessment in ML for medical imaging
  • Definitions and applicability of fairness in clinical contexts
  • Healthcare inequalities and bias mitigation
  • Ethical, legal, and regliatory considerations
  • Causality, dataset bias, and moreWe welcome extended versions of FAIMI workshop papers and new submissions from the community.
Deadline extended: April 21, 2025. More details: https://faimi-workshop.github.io/2024-melba/

Read more...


2025/03/21 – HTML version of articles available

After staying in a beta state for some time, and leveraging the great work of tools such as LaTeXML, we are now including an HTML version of the articles directly into the paper pages. This is intended to facilitate skimming through articles, notably on phone or tablet.

html content within pages

Read more...


2024/05/14 – MELBA Symposium on Generative Models

We are thrilled to announce the MELBA Symposium on Generative Models, which will take place on Tuesday, June 11 at 9-11:30 AM EDT, 3-5:30 PM CEST! Join us for an exciting lineup of talks from spotlight papers at MELBA surrounding generative models, machine learning and biomedical imaging. Afterwards, there will be a panel discussion with all speakers moderated by a member of the MELBA board.

Zoom link: https://cornell.zoom.us/j/97915132810?pwd=b21TNmVDbzJURWcrSUlNcHdrU2Vydz09
Meeting ID: 979 1513 2810
Passcode: 115605

Read more...


More blog posts...