Deep Learning in Medical Imaging and Sensing
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".
Deadline for manuscript submissions: closed (31 March 2024) | Viewed by 7506
Special Issue Editors
Interests: medical imaging; inverse problems; image reconstruction; deep learning
Interests: medical imaging; inverse problems; unrolled neural networks; single-pixel imaging; spectral computed tomography
Interests: inverse problems; tomography; machine learning
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Advancements in medical imaging are essential for accurate diagnosis, monitoring and outcome prediction, as well as for investigating the underlying mechanisms of diseases. The recent success of deep learning (DL) is pushing the limits of what is possible with imaging and has already become the state-of-the-art for several tasks: segmentation, automatic diagnosis, computer-aided detection (CAD), image restoration and image reconstruction, among others. At the same time, DL is being rapidly adopted by many medical imaging providers.
Despite its current success, many challenges still remain. This Special Issue will address some of these challenges, such as explainability and interpretability, the hungry-data nature of DL models, and the need for robust methods in order to be translated to the clinic. One of the main challenges is the lack of annotated data in most medical applications. In this case, domain adaptation, self-supervised learning, and synthetic generation-based approaches play a critical role.
However, more data is not always the only solution. Leveraging a priori information in the form of architecture design (CNNs, ViT), knowledge of the underlying physics, or other a priori information can reduce the problem complexity and the amount of needed data. This is very relevant for inverse problems arising in medical imaging: denoising, deblurring, super-resolution, image reconstruction under limited conditions, and natural ill-posed problems (EIT, ECT, MIT). Actually, the current trend in inverse problems is to move towards the so-called model-based deep learning (MBDL) approaches, which combine model-based methods with DL. MBDL methods (plug-and-play and unrolled algorithms) include a data consistency term that ensures robustness, making them perfectly suited for medical imaging. However, these methods are still under development.
DL can also play an important role in sensor imaging for optimal sensor design and optimization of the transmitting and receiving processes. Optimal design can be beneficial for ultrasound, X-rays imaging, low-resolution imaging systems such as EIT, and others. Digital twin models could further unlock the potential with the low-res imaging systems with the aid of more established imaging information as well as physiological modelling.
The aim of this Special Issue of Sensors is to propose and highlight novel methods, architectures, and applications of deep learning in medical imaging and sensors. We expect submissions of articles related, but not limited to, the following topics:
- Deep learning for medical imaging and imaging sensors (ultrasound, CT, MRI, spectral CT, optical imaging, PET, EIT, etc.);
- Deep learning for image reconstruction and image restoration;
- Deep learning for segmentation;
- Deep learning for computer aided detection and diagnosis;
- Semi/weak/self/unsupervised learning.
Dr. Juan Felipe Pérez-Juste Abascal
Dr. Nicolas Ducros
Prof. Dr. Manuchehr Soleimani
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. Sensors 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.
Keywords
- deep learning
- medical imaging
- imaging sensor
- image reconstruction
- segmentation
- diagnosis
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.
Further information on MDPI's Special Issue polices can be found here.
