The Rise and Future of Radiology AI with the Advent of Machine Learning and Computer Vision

Dear Colleagues,

With advancements in artificial intelligence (AI) in the form of machine leaning (ML) and computer vision technologies, medical imaging informatics, specifically radiology AI, is becoming increasingly sophisticated, and is already capable of handling complex tasks as diagnostic aids. Worldwide, a few companies are already using AI to improve the accuracy of lung cancer screenings in CT scans, using deep learning (DL) algorithms to analyze mammograms, helping radiologists identify breast cancer cases that may have been missed by human radiologists, automating image analysis and improving the efficiency of diagnostic imaging in emergencies like myocardial infarction, etc. Advanced ML/DL algorithms and computer vision technologies enable efficient processing of large amounts of data, facilitating real-time image analysis, which allows patterns and anomalies to be detected that may be overlooked by the human eye. It is estimated that approximately one-third of radiologists are currently utilizing some form of AI in practice. In addition to diagnostic imaging, the combination of AI and natural language processing (NLP) can help retrieve and analyze key historical points from a patient’s electronic medical record (EMR) and automate the radiology report generation process to reduce the burden of a long wait time for analysis by radiologists. However, the greatest challenge in radiology AI is not whether the technologies will be capable enough to be useful, but rather ensuring their adoption in daily clinical practice by increasing explainabilty, interpretability and trustworthiness. For widespread adoption to take place, AI systems must be approved by regulators and integrated with EHR systems. These challenges will ultimately be overcome, but it will take much longer to do so than it will take for the technologies themselves to mature.

In light of these developments, we are pleased to invite you to submit your recent work to this Special Issue.

This Special Issue invites manuscripts (research, reviews, and case studies) on AI/ ML-based ongoing progress and related development in medical imaging and its influence in healthcare. Research areas may include the four main types of imaging modalities, X-rays (including computed tomography and fluoroscopy), ultrasound, magnetic resonance imaging and nuclear, and may also include (but are not limited to) the following:

• AI/ML/DL-based screening systems in radiology;
• Multi-class and multi-label classification of radiology images;
• Attention (transformers)-based decision support systems (DSS) in radiology;
• Explainable AI (XAI) in radiology;
• Trustworthy AI systems ;
• DL-based automatic medical image interpretation;
• AI-powered radiology report creation;
• Explainable AI in automated report generation;
• Addressing bias in biomedical image data and imaging informatics;
• Integration of EHR and radiology;
• ML- and NLP-based understanding of clinical documentation.

We look forward to receiving your contributions.

Dr. Md Mahmudur Rahmanon
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. Healthcare 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 2700 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
• artificial intelligence
• machine learning
• deep learning
• computer vision
• radiology AI
• decision support system
• explainable system