Application of Machine Learning Using Ultrasound Images

Dear Colleagues

Ultrasound imaging is an indispensable imaging tool that is found in almost all global hospitals as it provides real-time images, uses ionizing radiation, can be conducted with portable systems, and is inexpensive—with systems ranging in price from about USD 10,000 for phone-based systems to over USD 300,000 for high-end systems providing a wide range of capabilities. However, ultrasound images suffer from low tissue contrast, image speckle, shadowing, and various artifacts, making image interpretation difficult. Furthermore, the use of ultrasound and interpretation of the images also suffer from user variability. Nevertheless, ultrasound imaging is used in disease diagnosis, assessing response to therapy, guiding biopsies, and guiding surgical interventions. Applications of ultrasound imaging are very wide and include obstetrics, gynecology, cancer, cardiac, vascular, urology, musculoskeletal, and many other diseases and conditions.

Although machine learning tools such as deep learning have primarily been used in applications with CT and MR images, due to some of the limitations of ultrasound imaging, applications of machine learning to ultrasound images have lagged. However, over the past few years, applications of deep learning methods have increased exponentially, including applications using ultrasound images. Deep learning tools promise to make ultrasound imaging less variable and user-dependent, make procedure time shorter, and improve guidance of biopsy and therapy applicators in image-guided interventions. Opportunities include pathology detection, classification of pathology as benign or malignant, segmentation of lesion size needed for monitoring response to therapy, quantification of changes in pathology in response to therapy, guidance and tracking of tools in the body, and other applications.

We are seeking contributions presenting machine learning algorithms, techniques, and applications that will contribute to making ultrasound imaging a more robust detection, diagnostic, pathology quantification, and image-guidance method.

Prof. Dr. Aaron Fenster
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. Journal of Imaging is an international peer-reviewed open access monthly 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.

• Application of Machine Learning Using Ultrasound Images, 2nd Edition in Journal of Imaging (5 articles)
• Application of Machine Learning Using Ultrasound Images, 3rd Edition in Journal of Imaging