Innovative AI-Based Approaches to Image Segmentation

Dear Colleagues,

Image segmentation is a crucial component of AI research and applications. It enables the precise delineation of objects and regions across diverse domains, including medical diagnostics, autonomous driving, remote sensing, and industrial inspection. Segmentation is essential for enabling downstream tasks, such as object detection and scene understanding, while also facilitating critical decision-making in safety-critical systems. While traditional algorithms have demonstrated consistent performance in controlled settings, they often encounter challenges when confronted with heterogeneous data, complex scenes, and real-time constraints. Driven by the growth in AI, researchers are currently exploring new frontiers in segmentation accuracy, adaptability, and scalability.

This Special Issue invites cutting-edge contributions that leverage AI’s transformative potential to address longstanding challenges in segmentation. The following topics will be of particular interest: deep convolutional and transformer-based architectures, semi-supervised and self-supervised learning strategies, graph neural networks, domain adaptation, and hybrid solutions that integrate classical techniques with modern data-driven models. We welcome submissions that present novel algorithms, comprehensive benchmarks, interpretable models, real-world application studies, and open-source tools. By uniting theoretical insights with practical implementations, this Special Issue aims to chart new directions for AI-based image segmentation and foster collaborations that accelerate the development of reliable, explainable, and efficient solutions. Interdisciplinary and cross-domain studies that bridge gaps between research fields are especially encouraged.

Dr. Shuyue Guan
Guest Editor

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. Informatics is an international peer-reviewed open access quarterly 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 1800 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.

• deep convolutional neural networks
• transformer-based segmentation models
• semi-supervised learning
• self-supervised learning
• graph neural networks
• domain adaptation
• real-time segmentation
• medical image segmentation
• remote sensing segmentation