Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. Despite this, there are still many challenges before each of these steps can be realized to be automated via machine learning.

Machine learning could make medical imaging systems intelligent. Machine learning–based data processing methods have the potential to decrease imaging time. Furthermore, intelligent imaging systems could reduce unnecessary imaging, improve positioning, and help improve the characterization of the findings. For example, an intelligent Magnetic Resonance (MR) imager may recognize a lesion and suggest modifications in the sequence to achieve optimal characterization of the lesion. This is one future challenge on which machine learning can offer a perspective. Automated detection of findings within medical images in radiology is an area where machine learning can have an impact as well. Automated detection itself is a wide area of research challenges before it can be brought down to clinical applications in assisting doctors in their decision-making. Interpretation of the detected findings in medical imaging (either normal or abnormal) requires a high level of expert knowledge, experience, and clinical judgment based on each clinical case scenario. For a machine to function as an independent image interpreter, extensive acquisition of data-derived knowledge is required. Thus, machine learning could improve the interpretation of findings as an aid to the radiologist. In addition, machine learning could be used for organ-specific classification and organ radiation dose estimation from computed tomography (CT) data sets. Machine learning can be used to make specific selections of the various contrasts used and aid in quantifying them for patient-specific based on their specific parameters. Machine learning can also be used to identify the amount of dose of nuclear medicine that can be given specifically to patients for nuclear medicine imaging. These areas bring in a lot of new features for radiological and nuclear medicine imaging.

This Special Issue will focus on listing the current advances and the next immediate challenges that are involved in the application of machine learning towards medical, radiological, and nuclear medicine imaging. In this Special Issue, we look for current applications, challenges, and future perspectives of machine learning and deep learning techniques in medical diagnostic radiology and nuclear medicine imaging, which includes magnetic resonance imaging (MRI), CT, positron emission tomography (PET), single-photon emission computed tomography (SPECT) and ultrasound imaging. The Special Issue welcomes original research that discusses the current challenges faced in MRI contrast imaging like data integration, image fusion of various radiological images for diagnosis of disease, staging of disease from radiological imaging, the necessity of big data, and ground truth annotation. We also welcome review articles.

Potential topics include but are not limited to the following:

• Machine learning advances in MRI contrast agent handling
• Automatic patient-specific radiation dose estimation
• Multimodal radiological imaging-based disease detection
• Data Integration of MRI and PET for staging, characterizing a disease
• Challenges in a combination of various radiological imaging for specific disease detection
• Machine learning for selection of contrast agents for MRI
• Automated detection of the findings of an MRI Scan
• Image fusion – challenges for a combination of SPECT, PET, MRI, and CT imaging for specific disease marking
• Challenges in building an Intelligent Imaging System
• Developing machine learning-based tools to aid a radiologist
• Challenges in the application of deep learning in radiology
• Machine learning for tumor characterization
• Machine learning for automatic 3D tumor size detection
• Artificial Intelligence for localizing tumors