Objectives: Despite showing encouraging outcomes, the precision of deep learning (DL) models using different convolutional neural networks (CNNs) for diagnosis remains under investigation. This systematic review aims to summarise the status of DL MRI models developed for assisting the diagnosis of a variety of knee abnormalities.
Materials And Methods: Five databases were systematically searched, employing predefined terms such as 'Knee AND 3D AND MRI AND DL'. Selected inclusion criteria were used to screen publications by title, abstract, and full text. The synthesis of results was performed by two independent reviewers.
Results: Fifty-four articles were included. The studies focused on anterior cruciate ligament injuries (n = 19, 36%), osteoarthritis (n = 9, 17%), meniscal injuries (n = 13, 24%), abnormal knee appearance (n = 11, 20%), and other (n = 2, 4%). The DL models in this review primarily used the following CNNs: ResNet (n = 11, 21%), VGG (n = 6, 11%), DenseNet (n = 4, 8%), and DarkNet (n = 3, 6%). DL models showed high-performance metrics compared to ground truth. DL models for the detection of a specific injury outperformed those by up to 4.5% for general abnormality detection.
Conclusion: Despite the varied study designs used among the reviewed articles, DL models showed promising outcomes in the assisted detection of selected knee pathologies by MRI. This review underscores the importance of validating these models with larger MRI datasets to close the existing gap between current DL model performance and clinical requirements.
Key Points: Question What is the status of DL model availability for knee pathology detection in MRI and their clinical potential? Findings Pathology-specific DL models reported higher accuracy compared to DL models for the detection of general abnormalities of the knee. DL model performance was mainly influenced by the quantity and diversity of data available for model training. Clinical relevance These findings should encourage future developments to improve patient care, support personalised diagnosis and treatment, optimise costs, and advance artificial intelligence-based medical imaging practices.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1007/s00330-024-11105-8 | DOI Listing |
J Environ Manage
December 2024
CE3c - Centre for Ecology, Evolution and Environmental Changes & CHANGE - Global Change and Sustainability Institute, Departamento de Biologia Animal, Faculdade de Ciências, Universidade de Lisboa, 1749-016, Lisboa, Portugal.
Bats provide important ecosystem services, particularly in agriculture, yet integrating bat management into conservation plans remains challenging. Some landscape features considerably influence bat presence, diversity, and ecosystem service provision. Understanding the relationship between landscape structure, composition, pest suppression, and ecosystem services is crucial.
View Article and Find Full Text PDFJ Environ Manage
December 2024
Key Laboratory for Utility of Environment-Friendly Composites and Biomass in Universities of Gansu Province, Lanzhou, 730000, China; Key Laboratory of Environment-Friendly Composites of the State Ethnic Affairs Commission, Lanzhou, 730000, China. Electronic address:
The treatment of biodegradable plastics through composting has garnered increasing attention. This study aimed to investigate the effects of Biochar FN1 bacteria and ferrous sulfate on nitrogen retention, greenhouse gas emissions, and degradable plastics during composting and to elucidate their synergistic mechanisms on microbial communities. Compared with the control, applying biochar-loaded FN1 bacteria composites combined with Ferrous sulfate (SGC) markedly accelerated organic matter degradation and reduced cumulative CO and NH emissions.
View Article and Find Full Text PDFJ Environ Manage
December 2024
Nuclear and Engineering Nonproliferation Division, Los Alamos National Laboratory, Los Alamos, NM, 87545, USA.
Monitoring nuclear reactor operations is vital for nuclear safeguards as it ensures that reactors are in compliance with international legal agreements. Validating nuclear facilities and activities, including potential clandestine activities, is currently accomplished by using remotely sensed data from satellites and aircrafts and on-site sampling. However, these techniques are temporally-limited as sampling and interpretation of environmental releases frequently involve labor-intensive, on-site collections.
View Article and Find Full Text PDFJ Environ Manage
December 2024
School of Geography and Ocean Science, Nanjing University, Xianlin Ave.163, 210023, Nanjing, China.
The complex life cycle traits of amphibians make them especially sensitive to environmental change, and their ongoing conservation requires the maintenance of suitable habitat that accounts for such life cycle characteristics which may impacted by local environmental dynamics arising from climate change and human disturbance. Many existing studies on amphibian habitats disregard this important issue, leading to uncertainty in managing critical habitats. The application of appropriate conservation practices is therefore constrained by the fact that the major factors influencing amphibian habitats, and their spatio-temporal dynamics at different life stages, are poorly understood.
View Article and Find Full Text PDFBiosens Bioelectron
December 2024
2020 X-Lab, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, 200050, China; Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing, 100049, China; State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, 200050, China; School of Graduate Study, University of Chinese Academy of Sciences, Beijing, 100049, China. Electronic address:
Anti-seizure medications and deep brain stimulation are widely used therapies to treat seizures; however, both face limitations such as resistance and the unpredictable nature of seizures. Recent advancements, including responsive neural stimulation and on-demand drug release, have been developed to address these challenges. However, a gap remains, as electrical stimulation provides only transient effects while medication has a delayed onset.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!