Special Issue "Machine-Learning-Based Process and Analysis of Medical Images"
Deadline for manuscript submissions: 31 December 2023 | Viewed by 265
Interests: medical image analysis; deep learning; computer vision; machine learning; colonoscopy; gastrointestinal endoscopy; wireless capsule endoscopy; surgical data science; radiation oncology; radiation therapy; organs at risk; prostate, liver, and lung cancer; robustness, generalization, and trustworthy AI systems; transparent system; out-of-distribution detection; reproducibility
In recent years, deep learning has achieved impressive success in leading to increased use of deep learning algorithms in the different fields of medical image analysis tasks. However, there are several challenges with the current deep learning models, such as deep learning algorithms being data-hungry and requiring large amounts of labeled data for achieving high performance in supervised learning settings. The collection of a large dataset requires a lot of time, resources including qualified medical experts, infrastructure, interdisciplinary collaboration, and regulatory approvals. In addition to obtaining datasets, a team of experienced doctors and computer scientists are required to provide high-quality annotations, which is extremely labor-intensive and burdensome. Despite data collection and annotations, it is not feasible to deploy large deep learning models to edge devices for various medical applications within a resource-constrained situation. The current deep learning models are not robust, and their performance can drop when there is a change in conditions (such as testing with different cohort populations, and scanners), which leads to challenges in deploying deep learning models into real-world clinical applications. The trustworthiness and societal impact of such models have not been explored much. Despite the minimal amount of research carried out to address the limitations of the availability of limited datasets, label efficiency, and lightweight algorithms, these fields have not been fully explored. Therefore, in this Special Issue, we encourage submissions on potential research problems raised by limited datasets, label efficiency, hardware efficiency, and trustworthy and reproducible (training time and testing) deep learning that can prepare for more biomedical applications in future. This Special Issue will be devoted to unveiling the most recent progress in obtaining analytical and numerical solutions to nonlinear differential equations through various methods and to stimulating collaborative research activities.
Dr. Debesh Jha
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. Mathematics 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 2100 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.
- deep learning (architecture, generative models, real-time algorithms, lightweight network design, etc.)
- medical image segmentation/classification with limited training datasets
- trustworthy machine learning (privacy, fairness, transparency, safety, ethics, AI safety, etc.)
- computer-aided diagnosis
- image segmentation
- weakly/semi/unsupervised/self-supervised learning methods
- resource-efficient learning
- out-of-distribution detection
- early cancer detection and diagnosis
- single-shot/one-shot/few-shot learning methods
- imaging informatics
- domain adaptation
- biomedical applications (endoscopy, colonoscopy, Alzheimer's disease, laparoscopy, head and neck, organs at risk, prostate, lung cancer, liver, breast, etc.)
- rare disease diagnosis with limited training datasets
- surgical data science