Machine Learning in Ultrasound Imaging

Dear Colleagues,

Ultrasound imaging has long been a cornerstone of diagnostic medicine owing to its safety, portability, cost-effectiveness, and real-time imaging capabilities. With recent advances in machine learning (ML) and artificial intelligence (AI), ultrasound is undergoing a transformative shift toward more automated, accurate, and intelligent applications. Machine learning enables improvements in image acquisition, reconstruction, segmentation, disease classification, and quantitative analysis, offering the potential to enhance clinical workflows, reduce operator dependency, and improve patient outcomes.

Despite these advances, ultrasound imaging poses unique challenges for ML applications, including high variability in image quality, speckle noise, operator dependence, and limited annotated datasets. Addressing these challenges requires innovation at the intersection of medical imaging, computational methods, and clinical translation. This Special Issue seeks to gather cutting-edge research studies that advance the field of ML in ultrasound imaging, with the goal of fostering cross-disciplinary collaboration between computer scientists, engineers, and clinicians.

We invite high-quality original research articles on all aspects of machine learning applied to ultrasound imaging. We particularly encourage submissions that bridge algorithmic innovation with clinical relevance, as well as collaborative works that demonstrate the potential of machine learning to transform ultrasound practice in real-world healthcare settings. Contributions from both methodological researchers and clinical practitioners are welcome, ensuring a balanced exchange of ideas that can drive the next generation of ultrasound technology. Topics of interest include, but are not limited to, the following:

• Image Processing and Enhancement
• Speckle noise reduction, super-resolution, and artifact correction.
• Reconstruction and beamforming with ML-based methods.
• Segmentation and Detection
• Automated segmentation of organs, tissues, and lesions.
• Object detection for pathology localization and guidance.
• Quantitative Analysis and Biomarkers
• Feature extraction for disease classification and risk stratification.
• ML-based approaches to elastography, Doppler analysis, and quantitative metrics.
• Clinical Applications
• Computer-aided diagnosis for cancer, cardiovascular disease, musculoskeletal disorders, and fetal/maternal health.
• Real-time guidance in interventional and point-of-care ultrasound.
• Ultrasound for surgical robotics.
• Methodological Advances
• Deep learning architectures tailored for ultrasound data.
• Domain adaptation, transfer learning, foundation models, synthetic data generation, and federated learning for limited or imbalanced datasets.
• Explainability, interpretability, and trustworthiness in AI-driven ultrasound.
• Emerging Directions
• Integration of multimodal imaging with ultrasound (e.g., ultrasound and CT/MRI).
• AI-powered portable and wearable ultrasound devices.
• Clinical validation studies and real-world deployment challenges.

We look forward to receiving your contributions.

Dr. Laura Brattain
Dr. Vivek Singh
Dr. Md Mostafa Kamal Sarker
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 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. Bioengineering 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 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.

• computer-aided diagnosis
• medical image analysis
• image segmentation
• procedural guidance
• clinical decision support
• elastography
• contrast-enhanced ultrasound
• point-of-care ultrasound (POCUS)
• multimodal imaging