Call for papers

Aim and Scope

We welcome submissions, as full or short papers, for the 3rd edition of Medical Imaging with Deep Learning. The conference is a forum for deep learning researchers, clinicians and health-care companies working at the intersection of medical image analysis and machine learning for healthcare and medicine, including disease detection, diagnosis, staging, prognosis, intervention, treatment selection and monitoring of disease progression.

Imaging is a cornerstone of medicine, and deep learning has shown its potential to leverage the rapidly growing numbers of medical imaging studies. However, most deep learning research in computer vision and machine learning has focused on natural images. Investigating and deepening these techniques to the challenges of medical imaging is an important research challenge.

MIDL has a broad scope, including all areas of medical image analysis and computer-assisted intervention, where deep learning is a key element. Topics of interest include but are not limited to:

  • Semantic segmentation of medical images
  • Learning based image registration
  • Computer-aided detection and diagnosis
  • Image acquisition, reconstruction and synthesis
  • Transfer learning and domain adaptation
  • Learning with noisy labels and limited data
  • Unsupervised deep learning and representation learning
  • Uncertainty estimation for medical diagnosis
  • Interpretability and explainable deep learning
  • Integration of imaging and clinical data
  • Validation studies and deep learning applications in radiology, pathology, endoscopy, dermatology, ophthalmology, and beyond

Inquiries to the program chairs can be addressed directly to [email protected].

OpenReview conference website

Two-Track Submissions

Conference submissions follow two tracks: full conference papers and short papers.

Full papers contain methodological developments or well-validated applications of deep learning algorithms in medical imaging. There is no strict limit on paper length. However, we strongly recommend limiting the paper length to 8 pages with an additional page for the references and as many pages as needed in an appendix section (all in a single pdf). The appropriateness of using additional pages over the recommended length will be judged by reviewers. The papers will go through a full, double-blind reviewing process via OpenReview, with a two-week period for author rebuttal and discussion. A selection of full papers will be invited for oral presentation, whereas the rest will be assigned a poster presentation. All accepted full papers will be published as a volume in the Proceedings of Machine Learning Research.

Short papers are up to 3 pages and can, for example, focus on novel methodological ideas without extensive validation. We also specifically accept short papers discussing recently published or submitted journal contributions to give authors the opportunity to present their work and obtain feedback from conference attendees. Selection of short papers is based on a light double-blind review process via OpenReview, without a discussion period. All accepted short papers will be presented as posters at the conference.

Special issue

A selection of the best full papers will be invited to submit an extension of their work for a special issue in MELBA (Journal of Machine Learning for Biomedical Imaging), a new, web-based open-access journal.

More details to come.

Full author instructions

Full author instructions can be found on the dedicated page.