Call for papers

We welcome submissions, as full or short papers, for the 5th edition of Medical Imaging with Deep Learning (MIDL 2022). MIDL is a forum for deep learning researchers, clinicians and health-care companies working at the intersection of machine learning and medical image analysis. MIDL 2022 will be a hybrid event, if the pandemic conditions permit, allowing both online and onsite participation in Zürich, Switzerland.

MIDL has a large scope including all areas where deep learning is used to analyze biomedical imaging data. Topics of interest include but are not limited to:

• 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
• 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.

Submissions presenting validation studies demonstrating clinical relevance and novel applications are encouraged as much as novel methodological contributions.

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

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. The paper length is strictly limited to 8 pages excluding references and appendix. There are no page limits for the references and appendix section. However, reviewers are not obliged to go over the appendices for evaluating a submission. The papers will go through a full, single-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. 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 single-blind review process via OpenReview, without a discussion period. All accepted short papers will be presented at the conference.

Important Dates

For submission deadlines and the schedule of the review process see Important Dates. For submission details see Author Instructions.