Machine-Learning-Based Process and Analysis of Medical Images

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: 31 August 2024 | Viewed by 1793

Special Issue Editor

Department of Radiology, Northwestern University, Chicago, IL, USA
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

Special Issue Information

Dear Colleagues,

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
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at 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 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.


  • 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

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


17 pages, 5158 KiB  
nmPLS-Net: Segmenting Pulmonary Lobes Using nmODE
by Peizhi Dong, Hao Niu, Zhang Yi and Xiuyuan Xu
Mathematics 2023, 11(22), 4675; - 17 Nov 2023
Viewed by 738
Pulmonary lobe segmentation is vital for clinical diagnosis and treatment. Deep neural network-based pulmonary lobe segmentation methods have seen rapid development. However, there are challenges that remain, e.g., pulmonary fissures are always not clear or incomplete, especially in the complex situation of the [...] Read more.
Pulmonary lobe segmentation is vital for clinical diagnosis and treatment. Deep neural network-based pulmonary lobe segmentation methods have seen rapid development. However, there are challenges that remain, e.g., pulmonary fissures are always not clear or incomplete, especially in the complex situation of the trilobed right pulmonary, which leads to relatively poor results. To address this issue, this study proposes a novel method, called nmPLS-Net, to segment pulmonary lobes effectively using nmODE. Benefiting from its nonlinear and memory capacity, we construct an encoding network based on nmODE to extract features of the entire lung and dependencies between features. Then, we build a decoding network based on edge segmentation, which segments pulmonary lobes and focuses on effectively detecting pulmonary fissures. The experimental results on two datasets demonstrate that the proposed method achieves accurate pulmonary lobe segmentation. Full article
(This article belongs to the Special Issue Machine-Learning-Based Process and Analysis of Medical Images)
Show Figures

Figure 1

Back to TopTop