Background: Deep learning-based super-resolution (SR) algorithms aim to reconstruct low-resolution (LR) images into high-fidelity high-resolution (HR) images by learning the low- and high-frequency information. Experts' diagnostic requirements are fulfilled in medical application scenarios through the high-quality reconstruction of LR digital medical images.
Purpose: Medical image SR algorithms should satisfy the requirements of arbitrary resolution and high efficiency in applications. However, there is currently no relevant study available. Several SR research on natural images have accomplished the reconstruction of resolutions without limitations. However, these methodologies provide challenges in meeting medical applications due to the large scale of the model, which significantly limits efficiency. Hence, we suggest a highly effective method for reconstructing medical images at any desired resolution.
Methods: Statistical features of medical images exhibit greater continuity in the region of neighboring pixels than natural images. Hence, the process of reconstructing medical images is comparatively less challenging. Utilizing this property, we develop a neighborhood evaluator to represent the continuity of the neighborhood while controlling the network's depth.
Results: The suggested method has superior performance across seven scales of reconstruction, as evidenced by experiments conducted on panoramic radiographs and two external public datasets. Furthermore, the proposed network significantly decreases the parameter count by over 20× and the computational workload by over 10× compared to prior researches. On large-scale reconstruction, the inference speed can be enhanced by over 5×.
Conclusion: The novel proposed SR strategy for medical images performs efficient reconstruction at arbitrary resolution, marking a significant breakthrough in the field. The given scheme facilitates the implementation of SR in mobile medical platforms.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.compbiomed.2024.108212 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Systematic application of saliency maps to explain the decisions of convolutional neural networks for glaucoma diagnosis based on disc and cup geometry.
Biomed Phys Eng Express
January 2025
Department of Ophthalmology, Hospital Universitario de Canarias, Carretera Ofra S/N, La Laguna, Santa Cruz de Tenerife, 38320, SPAIN.
This paper systematically evaluates saliency methods as explainability tools for convolutional neural networks trained to diagnose glaucoma using simplified eye fundus images that contain only disc and cup outlines. These simplified images, a methodological novelty, were used to relate features highlighted in the saliency maps to the geometrical clues that experts consider in glaucoma diagnosis. Despite their simplicity, these images retained sufficient information for accurate classification, with balanced accuracies ranging from 0.
View Article and Find Full Text PDFMultimodal multiview bilinear graph convolutional network for mild cognitive impairment diagnosis.
Biomed Phys Eng Express
January 2025
Shandong University of Traditional Chinese Medicine, Qingdao Academy of Chinese Medical Sciences, Jinan, Shandong, 250355, CHINA.
Mild cognitive impairment (MCI) is a significant predictor of the early progression of Alzheimer's disease, and it can be used as an important indicator of disease progression. However, many existing methods focus mainly on the image itself when processing brain imaging data, ignoring other non-imaging data (e.g.
View Article and Find Full Text PDFWhat has brain diffusion magnetic resonance imaging taught us about chronic primary pain: a narrative review.
Pain
February 2025
Department of Anesthesiology, Faculty of Medicine and Health Sciences, Université de Sherbrooke, Sherbrooke, QC, Canada.
Chronic pain is a pervasive and debilitating condition with increasing implications for public health, affecting millions of individuals worldwide. Despite its high prevalence, the underlying neural mechanisms and pathophysiology remain only partly understood. Since its introduction 35 years ago, brain diffusion magnetic resonance imaging (MRI) has emerged as a powerful tool to investigate changes in white matter microstructure and connectivity associated with chronic pain.
View Article and Find Full Text PDFConfined cell migration along extracellular matrix space in vivo.
Proc Natl Acad Sci U S A
January 2025
Center for Complexity and Biosystems, Department of Environmental Science and Policy, University of Milan, 20133 Milan, Italy.
Collective migration of cancer cells is often interpreted using concepts derived from the physics of active matter, but the experimental evidence is mostly restricted to observations made in vitro. Here, we study collective invasion of metastatic cancer cells injected into the mouse deep dermis using intravital multiphoton microscopy combined with a skin window technique and three-dimensional quantitative image analysis. We observe a multicellular but low-cohesive migration mode characterized by rotational patterns which self-organize into antiparallel persistent tracks with orientational nematic order.
View Article and Find Full Text PDFOncogenic IDH1 drives robust loss of histone acetylation and increases chromatin heterogeneity.
Proc Natl Acad Sci U S A
January 2025
Department of Immunology and Regenerative Biology, Weizmann Institute of Science, Rehovot 7610001, Israel.
Malignant gliomas are heterogeneous tumors, mostly incurable, arising in the central nervous system (CNS) driven by genetic, epigenetic, and metabolic aberrations. Mutations in isocitrate dehydrogenase (IDH1/2) enzymes are predominantly found in low-grade gliomas and secondary high-grade gliomas, with IDH1 mutations being more prevalent. Mutant-IDH1/2 confers a gain-of-function activity that favors the conversion of a-ketoglutarate (α-KG) to the oncometabolite 2-hydroxyglutarate (2-HG), resulting in an aberrant hypermethylation phenotype.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!