Synthetic Data Generation in Healthcare: A Scoping Review of reviews on domains, motivations, and future applications DOI Creative Commons
Miguel Rujas,

Rodrigo Martín Gómez del Moral Herranz,

Giuseppe Fico

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 9, 2024

Abstract The development of Artificial Intelligence (AI) in the healthcare sector is generating a great impact. However, one primary challenges for implementation this technology access to high-quality data due issues collection and regulatory constraints, which synthetic an emerging alternative. This Scoping review analyses reviews from past 10 years three different databases (i.e., PubMed, Scopus, Web Science) identify domains where are currently generated, motivations behind their creation, future uses, limitations, types data. A total 13 main were identified, with Oncology, Neurology, Cardiology being most frequently mentioned. Five principal uses also identified. Furthermore, it was found that predominant type generated unstructured, particularly images. Finally, several work directions suggested, including exploring new less commonly used (e.g., video text), developing evaluation benchmark standard generative models specific domains.

Language: Английский

Uveal Melanoma: Comprehensive Review of Its Pathophysiology, Diagnosis, Treatment, and Future Perspectives DOI Creative Commons
Merve Kulbay, Emily Marcotte,

Raheem Remtulla

et al.

Biomedicines, Journal Year: 2024, Volume and Issue: 12(8), P. 1758 - 1758

Published: Aug. 5, 2024

Uveal melanoma (UM) is the most common intraocular malignancy in adults. Recent advances highlight role of tumor-derived extracellular vesicles (TEV) and circulating hybrid cells (CHC) UM tumorigenesis. Bridged with liquid biopsies, a novel technology that has shown incredible performance detecting cancer or products derived from tumors bodily fluids, it can significantly impact disease management outcome. The aim this comprehensive literature review to provide summary current knowledge ongoing posterior pathophysiology, diagnosis, treatment. first section manuscript discusses complex intricate TEVs CHCs. second part delves into epidemiology, etiology risk factors, clinical presentation, prognosis UM. Third, diagnostic methods, ensued by tools for early detection UM, such as biopsies artificial intelligence-based technologies, are paramount importance review. fundamental principles, limits, challenges associated these tools, well their potential tracker progression, discussed. Finally, treatment modalities provided, followed an overview preclinical research studies further insights on biomolecular pathway alterations therapeutic targets This thus important resource all healthcare professionals, clinicians, researchers working field ocular oncology.

Language: Английский

Citations

7
Colour fusion effect on deep learning classification of uveal melanoma DOI
ALBERT DADZIE, Sabrina P. Iddir, Mansour Abtahi

et al.

Eye, Journal Year: 2024, Volume and Issue: 38(14), P. 2781 - 2787

Published: May 21, 2024

Language: Английский

Citations

4
Personalized Treatment Strategies for Breast Adenoid Cystic Carcinoma: A Machine Learning Approach DOI Open Access
Sakhr Alshwayyat,

M. Bashar Abu Al Hawa,

Mustafa Alshwayyat

et al.

The Breast, Journal Year: 2025, Volume and Issue: 79, P. 103878 - 103878

Published: Jan. 13, 2025

Language: Английский

Citations

0
Machine learning in ocular oncology and oculoplasty: Transforming diagnosis and treatment DOI Open Access

Dipali Mane,

Khuspe Pankaj Ramdas

IP International Journal of Ocular Oncology and Oculoplasty, Journal Year: 2025, Volume and Issue: 10(4), P. 196 - 207

Published: Jan. 14, 2025

In the domains of ocular oncology and oculoplasty, machine learning (ML) has become a game-changing technology, providing previously unheard-of levels precision in diagnosis, treatment planning, outcome prediction. Using imaging modalities, genomic data, clinical characteristics, this chapter investigates integration algorithms detection tumours, including retinoblastoma uveal melanoma. Through predictive modelling real-time decision-making, it also emphasises how ML might improve surgical outcomes orbital reconstruction eyelid correction. Automated examination fundus photographs, histological slides, 3D been made possible by methods like deep natural language processing, which have improved individualised therapeutic approaches decreased diagnostic errors. Additionally, use augmented reality robotics surgery is significant development oculoplasty. Notwithstanding its potential, issues data heterogeneity, algorithm interpretability, ethical considerations are roadblocks that need to be addressed. This explores cutting-edge developments, real-world uses, potential future paths, offering researchers doctors thorough resource. Dipali Vikas Mane, Associate Professor, Shriram Shikshan Sanstha’s College Pharmacy, Paniv-413113

Language: Английский

Citations

0
Machine learning demonstrates clinical utility in distinguishing retinoblastoma from pseudo retinoblastoma with RetCam images DOI Creative Commons

Owen Cruz-Abrams,

Ricardo Dodds Rojas,

David H. Abramson

et al.

Ophthalmic Genetics, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 6

Published: Jan. 20, 2025

Retinoblastoma is diagnosed and treated without biopsy based solely on appearance (with the indirect ophthalmoscope imaging). More than 20 benign ophthalmic disorders resemble retinoblastoma errors in diagnosis continue to be made worldwide. A better noninvasive method for distinguishing from pseudo needed. RetCam imaging of largest center U.S. (Memorial Sloan Kettering Cancer Center, New York, NY) were used this study. We several neural networks (ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152, a Vision Image Transformer, or VIT), using 80% images training, 10% validation, testing. Two thousand eight hundred eighty-two patients with at diagnosis, 1,970 804 normal pediatric fundus included. The highest sensitivity (98.6%) was obtained ResNet-101 model, as accuracy F1 scores 97.3% 97.7%. specificity (97.0%) precision attained ResNet-152 model. Our machine learning algorithm successfully distinguished high if implemented worldwide will prevent hundreds eyes incorrectly being surgically removed yearly.

Language: Английский

Citations

0
Advances in primary eye care and ophthalmic imaging contribute to earlier detection of uveal melanoma DOI Open Access

Vilde Bjertnæs,

Anna Dalseng Hatling,

Olav H. Haugen

et al.

Acta Ophthalmologica, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 31, 2025

To report how the evolving role of optometrists in primary eye care and advances ophthalmic imaging have affected diagnosis management posterior uveal melanoma (UM). Retrospective, single-centre cohort study patients diagnosed with UM from 1993 to 2022 Bergen, Norway. Four hundred nine were included, comparisons made between those 2007 2008 2022. The median tumour diameter decreased 13.3 11.3 mm (p = 0.002), thickness 6.9 4.5 < 0.001). distance border optic disc foveola increased 3.5 0.011), 3.0 4.0 0.001), respectively. Two sixty-two (64%) experienced symptoms associated UM, a duration 152.5 81 days first second half period, respectively best corrected visual acuity at improved 0.5 logMAR (Snellen equivalent, 6/19) 0.2 6/9.5) period proportion asymptomatic was 23.5% 41.9% UMs incidentally detected by 3.0% 18.1% 0.009), fundus photography 1.5% temporal changes patient characteristics suggest that are now being an earlier stage. This may part be attributed introduction widefield cameras opportunistic screening patients.

Language: Английский

Citations

0
Artificial intelligence methods in diagnosis of retinoblastoma based on fundus imaging: a systematic review and meta-analysis DOI
Rian Vilar Lima, Mateus Pimenta Arruda, Maria C. Muñiz

et al.

Graefe s Archive for Clinical and Experimental Ophthalmology, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 18, 2024

Language: Английский

Citations

3
Synthetic data generation in healthcare: A scoping review of reviews on domains, motivations, and future applications DOI Creative Commons
Miguel Rujas,

Rodrigo Martín Gómez del Moral Herranz,

Giuseppe Fico

et al.

International Journal of Medical Informatics, Journal Year: 2024, Volume and Issue: 195, P. 105763 - 105763

Published: Dec. 17, 2024

Language: Английский

Citations

3
Recent Advances in Molecular and Genetic Research on Uveal Melanoma DOI Creative Commons
Aurélie Fuentes-Rodriguez,

Andrew Mitchell,

Sylvain L. Guérin

et al.

Cells, Journal Year: 2024, Volume and Issue: 13(12), P. 1023 - 1023

Published: June 12, 2024

Uveal melanoma (UM), a distinct subtype of melanoma, presents unique challenges in its clinical management due to complex molecular landscape and tendency for liver metastasis. This review highlights recent advancements understanding the pathogenesis, genetic alterations, immune microenvironment UM, with focus on pivotal genes, such as GNAQ/11, BAP1, CYSLTR2, delves into distinctive chromosomal classifications emphasizing role mutations rearrangements disease progression metastatic risk. Novel diagnostic biomarkers, including circulating tumor cells, DNA extracellular vesicles, are discussed, offering potential non-invasive approaches early detection monitoring. It also explores emerging prognostic markers their implications patient stratification personalized treatment strategies. Therapeutic approaches, histone deacetylase inhibitors, MAPK pathway trends concepts like CAR T-cell therapy, evaluated efficacy UM treatment. identifies research, limited options need improved tools, suggests future directions, discovery novel therapeutic targets, immunotherapeutic strategies, advanced drug delivery systems. The concludes by importance continued research innovation addressing improve outcomes develop more effective

Language: Английский

Citations

1
Machine learning and single-cell RNA sequencing reveal relationship between intratumor CD8+ T cells and uveal melanoma metastasis DOI Creative Commons
Shuming Chen,

Zichun Tang,

Qiaoqian Wan

et al.

Cancer Cell International, Journal Year: 2024, Volume and Issue: 24(1)

Published: Oct. 30, 2024

Uveal melanoma (UM) is adults' most common primary intraocular malignant tumor. It has been observed that 40% of patients experience distant metastasis during subsequent treatment. While there exist multigene models developed using machine learning methods to assess and prognosis, the immune microenvironment's specific mechanisms influencing tumor microenvironment have not clarified. Single-cell transcriptome sequencing can accurately identify different types cells in a tissue for precise analysis. This study aims develop model with fewer genes evaluate risk UM provide theoretical basis immunotherapy.

Language: Английский

Citations

1