Dear Colleagues,

Medical imaging allows the observation of the internal characteristics of a body through images for clinical analysis and medical interventions.

This field is undergoing rapid development, resulting in improvement in the quality of the images as well as in the quantity of the observed features. Moreover, its democratization is leading to a wide availability of medical image data in almost all pathologies. However, it remains crucial to be able to extract useful and robust information for targeted medical analysis and decisions. Faced with this afflux of data, these treatments allowing extraction must be as automatic as possible, robust, and in line with the needs of physicians in order to empower their efficiency on medical analysis.

Nevertheless, if hundreds of articles are published each year describing semi-automatic or automatic quantification methods, they are unfortunately without a reference implementation (i.e., without source code). The authors or vendors are by essence reluctant to share their algorithms, because there is simply no practical way to (1) share the algorithms and (2) evaluate their performance in a fair way on the same database elaborated from realistic data derived from routine examinations. As a consequence, and as pointed out by many researchers, all available methods, from simple to sophisticated algorithms, are “not as objective as one might think”, requiring user inputs or final supervision to distinguish some artifact and/or noise voxels, i.e., useless information.

As a consequence, despite the huge number of papers that describe over-performing isolated solutions and an increasing number of black box services, there is still a large community of physicians or clinical researchers that are missing satisfactory automatic quantification tools to segment the anatomy and extract quantitative indicators with available quality control to determine the advances or limitations. State-of-the-art and a priori solutions are published but unavailable and unsuitable for worldwide deployment in the clinical (or clinical research) environment where they could be tested in broader patient populations, improved, and made rapidly available for the entire physician and developer community. Widely available clinical databases and common numerical datasets are also missing that could enable the community to easily and rapidly test and evaluate new algorithms, especially in a world of limited resources, where an urgent need therefore emerges for more durable and coordinated research.

In this Special Issue, I would like to invite all colleagues and researchers who share these concerns and who develop approaches attempting to address them to submit their important papers describing their solutions to achieve more reproducible, useful research that can be quickly transferred to clinical research.

The objective of this Special Issue is to collect papers of paramount importance for our future that offer solutions to this critical need: (i) methods that can be used on any image data acquired independently of the scanner manufacturer and that address the abovementioned concerns, (ii) intelligent methods that can both allow unified performance tests on numerical datasets and confidentiality, (iii) smart ways to create shared databases with expert referenced knowledge that the community could feed into and use to demonstrate the performance of new algorithms, and (iv) computer processing methods that are able to enrich diagnosis by extracting objective and clinically useful information from medical images.

Prof. Dr. Magalie Viallon
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. 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.

• medical imaging
• quantitative
• intelligent analysis
• diagnosis
• image segmentation
• image registration
• data mining
• reproducible and open research
• AI
• algorithms
• computer processing methods

• Quantitative and Intelligent Analysis of Medical Imaging in Diagnostics (8 articles)