Scaling Datasets, Annotations and Algorithms for Medical Image Segmentation

Dear Colleagues,

Image segmentation serves as a pivotal component across a myriad of clinical applications in healthcare, encompassing disease diagnosis, treatment planning, outcome prediction, and robotic surgery, among other things. Artificial intelligence (AI) can delineate anatomical structures and localize abnormalities in medical images, but this ability requires large-scale datasets, comprehensive annotations, and cutting-edge algorithms. Several disciplines, including natural language processing (e.g., GPTs), representation learning (e.g., MAE), and image segmentation (e.g., SAMs), have witnessed the transformative power of scaling data for AI training. Nevertheless, in the field of medical image analysis, this concept remains relatively underexplored due to the inherent challenges related to data and annotation curation in a medical context. This Special Issue aims to fill this gap, with a primary focus on datasets, annotations, and algorithms for medical image segmentation. We seek the contribution of publicly available medical datasets, tackling the challenges of domain shift, transfer learning, and multi-modal learning. We encourage the creation of new annotations for a variety of organs and tumors, including partial labels, noisy labels, clinical applications, and the promotion of standardized labeling protocols. We also invite contributions that develop novel algorithms to exploit large datasets, such as high-resolution imaging and benchmarking AI models, and ultimately establish foundational models for medicine.

The topics of interest include, but are not limited to, the following:

1. Deep learning architectures for medical image segmentation;
2. Transfer learning and unsupervised learning in medical image segmentation;
3. Multimodal and multiorgan image segmentation;
4. Segmentation of pathological regions in different imaging modalities;
5. Real-time image segmentation and applications in surgery;
6. Interpretability and explainability in machine learning models for segmentation;
7. Evaluation metrics and benchmarks in medical image segmentation;
8. Robustness and reliability of machine learning models in segmentation;
9. Incorporation of clinical information into machine learning models;
10. Machine learning models for large-scale or high-dimensional data segmentation.

Dr. Zongwei Zhou
Dr. Jeya Maria Jose
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.