Building Generalizable Deep Learning Model for Medical Image Analysis for Multi-Center/Multi-Scanner Data
A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".
Deadline for manuscript submissions: closed (15 May 2023) | Viewed by 383
Special Issue Editors
Interests: medical image analysis; machine learning; imaging biomarker; image & video analysis
Interests: medical images analysis; multimedia compression
Interests: image video analysis; computer vision; watermarking
Special Issue Information
Dear Colleagues,
Several deep-learning methods have been developed for medical image segmentation/classification focusing on model architectures, model parameter optimization, and transfer learning. Although these methods provide very good performance within a dataset, they are not robust enough to apply in general clinical settings where target tissue appearance can vary within the same subject, scanner, or time point. The most common way to build a robust deep-learning method is utilizing a large quantity of manually labeled data, but in the medical domain, this is not possible because of the cost of labelling, the unpredictable shape and location of tissue abnormalities, and data privacy. In this Special Issue, we will explore the following topics:
(1) Recent one-shot/few-shot learning developments for medical image classification/segmentation using a minimal number of labelled images.
(2) Generative adversarial networks (GAN)/auto-encoder-based data augmentation for building generalizable deep learning models.
(3) Federated learning (FL) to collaboratively train deep-learning models using isolated patient data owned by different hospitals for various clinical applications, including medical image segmentation.
(4) Transfer-learning models targeting a small quantity of labelled data and trained model performance in large datasets.
(5) Evaluation of deep-learning/transfer-learning models in multicenter, multiscanner datasets.
(6) Evolution of performance differences/transfer learning in deep-learning models in patients and healthy subjects.
(7) Noise reduction in old MRI/CT scans to improve the performance of deep-learning models using GAN for longitudinal data analysis.
Dr. Sibaji Gaj
Dr. Shuvendu Rana
Dr. Nilkanta Sahu
Dr. Barath Narayanan
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. Electronics 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 2400 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
- generative adversarial networks
- one shot
- few-shot learning
- medical image augmentation
- federated learning (FL)
- MRI noise removal
- MRI
- CT
- X-ray
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.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
