AI and Medical Imaging in Breast Disease

Dear Colleagues, 

For multiple decades, artificial intelligence (AI) has been of interest to improve the practice of breast imaging tasks, such as detection and diagnosis. Computer-aided detection of breast cancer on mammograms was among the first automated medical image analysis methods approved for clinical use. New techniques such as radiomics and deep learning are poised to transform medical imaging-based healthcare with developments fueled by improvements in, and availability of, multiple imaging modalities, larger datasets, and better computing resources. Deep learning revolutionized analysis methods by enabling imaging feature learning on its own rather than relying on human-engineered radiomics features. There are many ongoing AI research studies on methodology, evaluation, and applications of various breast imaging modalities (including full-field digital mammography, breast tomosynthesis, ultrasound, and MRI). AI algorithms will impact all aspects of imaging-based breast cancer patient care with tasks including detection, diagnosis, prognosis, treatment response assessment, and risk assessment. However, the news is not all good. On the one hand, the current AI revolution resulted in a reduction in technical barriers for researchers to start developing new AI methods, or use existing models in new applications, because many deep learning architectures and pre-trained weights are available as open source. On the other hand, many factors hamper translation to clinical practice, including a lack of explainability and interpretability, lack of standardization, lack of reproducibility and generalizability (due to, e.g., small single-institution datasets, improper training/testing protocols, or incorrect use of statistics), model aging, and bias.

This Special Issue is intended to provide an overview of the development of AI in clinical breast imaging. The primary aim is to provide an overview of exiting new applications of both ‘conventional’ methods—using human-engineered radiomics features—and deep learning AI algorithms involving all aspects of imaging-based patient care for breast disease. The secondary aim is to provide a resource for researchers to help to identify and mitigate potential pitfalls in the translation of their breast imaging AI applications to clinical practice.

Dr. Karen Drukker
Prof. Dr. Lubomir Hadjiiski
Dr. Despina Kontos
Dr. Marco Caballo
Dr. Shandong Wu
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 250 words) can be sent to the Editorial Office for assessment.

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.