Dataset Information

Systematic Review of Magnetic Resonance Lymphangiography From a Technical Perspective.

ABSTRACT:

Background

Clinical examination and lymphoscintigraphy are the current standard for investigating lymphatic function. Magnetic resonance imaging (MRI) facilitates three-dimensional (3D), nonionizing imaging of the lymphatic vasculature, including functional assessments of lymphatic flow, and may improve diagnosis and treatment planning in disease states such as lymphedema.

Purpose

To summarize the role of MRI as a noninvasive technique to assess lymphatic drainage and highlight areas in need of further study.

Study type

Systematic review.

Population

In October 2019, a systematic literature search (PubMed) was performed to identify articles on magnetic resonance lymphangiography (MRL).

Field strength/sequence

No field strength or sequence restrictions.

Assessment

Article quality assessment was conducted using a bespoke protocol, designed with heavy reliance on the National Institutes of Health quality assessment tool for case series studies and Downs and Blacks quality checklist for health care intervention studies.

Statistical tests

The results of the original research articles are summarized.

Results

From 612 identified articles, 43 articles were included and their protocols and results summarized. Field strength was 1.5 or 3.0 T in all studies, with 25/43 (58%) employing 3.0 T imaging. Most commonly, imaging of the peripheries, upper and lower limbs including the pelvis (32/43, 74%), and the trunk (10/43, 23%) is performed, including two studies covering both regions. Imaging protocols were heterogenous; however, T₂ -weighted and contrast-enhanced T₁ -weighted images are routinely acquired and demonstrate the lymphatic vasculature. Edema, vessel, quantity and morphology, and contrast uptake characteristics are commonly reported indicators of lymphatic dysfunction.

Data conclusion

MRL is uniquely placed to yield large field of view, qualitative and quantitative, 3D imaging of the lymphatic vasculature. Despite study heterogeneity, consensus is emerging regarding MRL protocol design. MRL has the potential to dramatically improve understanding of the lymphatics and detect disease, but further optimization, and research into the influence of study protocol differences, is required before this is fully realized.

Level of evidence

2 TECHNICAL EFFICACY: Stage 2.

SUBMITTER: Mills M

PROVIDER: S-EPMC7611641 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.