Dual-Stream Attention-Based Classification Network for Tibial Plateau Fractures via Diffusion Model Augmentation and Segmentation Map Integration

Current Medical Science, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 25, 2025

Language: Английский

---

The Role of Artificial Intelligence in Diagnostic Neurosurgery: A Systematic Review

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 4, 2025

Background: Artificial intelligence (AI) is increasingly applied in diagnostic neurosurgery, enhancing precision and decision-making neuro-oncology, vascular, functional, spinal subspecialties. Despite its potential, variability outcomes necessitates a systematic review of performance applicability. Methods: A comprehensive search PubMed, Cochrane Library, Embase, CNKI, ClinicalTrials.gov was conducted from January 2020 to 2025. Inclusion criteria comprised studies utilizing AI for reporting quantitative metrics. Studies were excluded if they focused on non-human subjects, lacked clear metrics, or did not directly relate applications neurosurgery. Risk bias assessed using the PROBAST tool. This study registered PROSPERO, number CRD42025631040 26^th, Results: Within 186 studies, neural networks (29%) hybrid models (49%) dominated. categorised into neuro-oncology (52.69%), vascular neurosurgery (19.89%), functional (16.67%), (11.83%). Median accuracies exceeded 85% most categories, with achieving high accuracy tumour detection, grading, segmentation. Vascular excelled stroke intracranial haemorrhage median AUC values 97%. Functional showed promising results, though sensitivity specificity underscores need standardised datasets validation. Discussion: The review’s limitations include lack data weighting, absence meta-analysis, limited collection timeframe, quality, risk some studies. Conclusion: AI shows potential improving across neurosurgical domains. Models used stroke, ICH, aneurysm conditions such as Parkinson’s disease epilepsy demonstrate results. However, sensitivity, specificity, further research model refinement ensure clinical viability effectiveness.

Language: Английский

---

The Application of Artificial Intelligence in Spine Surgery: A Scoping Review

JAAOS Global Research and Reviews, Journal Year: 2025, Volume and Issue: 9(4)

Published: April 1, 2025

Background: A comprehensive review on the application of artificial intelligence (AI) within spine surgery as a specialty remains lacking. Methods: This scoping was conducted upon PubMed and EMBASE databases according to Preferred Reporting Items for Systematic Reviews Meta-Analyses guidelines. Our analysis focused publications from January 1, 2020, March 31, 2024, with specific focus AI in field surgery. Review articles predominantly concerning secondary validation algorithms, medical physics, electronic devices, biomechanics, preclinical, lack clinical emphasis were excluded. Results: One hundred five studies included after our inclusion/exclusion criteria applied. Most (n = 100) through supervised learning prelabeled data sets. Overall, 38 used conventional machine methods predefined features, whereas 67 deep methods, image analyses. Only 25.7% (27/105) collected more than 1,000 patients model development validation. Data originated only single center 72 studies. The most common prognostication (38/105), followed by diagnosis (35/105), processing (29/105), surgical assistance (3/105). Conclusion: domain has significant potential advance patient-specific diagnosis, management, execution.

Language: Английский

---

RadImageNet and ImageNet as Datasets for Transfer Learning in the Assessment of Dental Radiographs: A Comparative Study

Deleted Journal, Journal Year: 2024, Volume and Issue: unknown

Published: July 24, 2024

Abstract Transfer learning (TL) is an alternative approach to the full training of deep (DL) models from scratch and can transfer knowledge gained large-scale data solve different problems. ImageNet, which a publicly available dataset, commonly used dataset for TL-based image analysis; many studies have applied pre-trained ImageNet clinical prediction tasks reported promising results. However, some questioned effectiveness using consists solely natural images, medical analysis. The aim this study was evaluate whether RadImageNet, could achieve superior performance in classification dental imaging modalities compared with models. To RadImageNet TL, two datasets were used. (1) classifying presence or absence supernumerary teeth panoramic radiographs (2) sex lateral cephalometric radiographs. Performance evaluated by comparing area under curve (AUC). On radiograph gave average AUCs 0.68 ± 0.15 ( p < 0.01), had values 0.74 0.19. In contrast, on demonstrated 0.76 0.09, achieved 0.75 0.17. difference between TL depends

Language: Английский

---

In vivo X-ray based imaging methods to assess bone quality

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Language: Английский

---

3H-ObjectDet: A Target Detection Method Based on Haar Wavelet Transform Downsampling and Hybrid Attention Mechanism for Medical Fracture Image

Published: Dec. 27, 2024

Language: Английский

---