Validation of the Relationship Between Iris Color and Uveal Melanoma Using Artificial Intelligence With Multiple Paths in a Large Chinese Population.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang H
PROVIDER: S-EPMC8417124 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
Validation of the Relationship Between Iris Color and Uveal Melanoma Using Artificial Intelligence With Multiple Paths in a Large Chinese Population.
Zhang Haihan H Liu Yueming Y Zhang Kai K Hui Shiqi S Feng Yu Y Luo Jingting J Li Yang Y Wei Wenbin W
Frontiers in cell and developmental biology 20210819
Previous studies have shown that light iris color is a predisposing factor for the development of uveal melanoma (UM) in a population of Caucasian ancestry. However, in all these studies, a remarkably low percentage of patients have brown eyes, so we applied deep learning methods to investigate the correlation between iris color and the prevalence of UM in the Chinese population. All anterior segment photos were automatically segmented with U-NET, and only the iris regions were retained. Then th ...[more]
Similar Datasets
Project description:Uveal melanoma (UM) is a global disease which especially occurs in elderly people. Its incidence varies widely between populations, with the highest incidence among Caucasians, and a South-to-North increase in Europe. As northern Europeans often have blond hair and light eyes, we wondered whether iris colour may be a predisposing factor for UM and if so, why. We compared the distribution of iris colour between Dutch UM patients and healthy Dutch controls, using data from the Rotterdam Study (RS), and reviewed the literature regarding iris colour. We describe molecular mechanisms that might explain the observed associations. When comparing a group of Dutch UM patients with controls, we observed that individuals from Caucasian ancestry with a green/hazel iris colour (Odds Ratio (OR) = 3.64, 95% Confidence Interval (CI) 2.57-5.14) and individuals with a blue/grey iris colour (OR = 1.38, 95% CI 1.04-1.82) had a significantly higher crude risk of UM than those with brown eyes. According to the literature, this may be due to a difference in the function of pheomelanin (associated with a light iris colour) and eumelanin (associated with a brown iris colour). The combination of light-induced stress and aging may affect pheomelanin-carrying melanocytes in a different way than eumelanin-carrying melanocytes, increasing the risk of developing a malignancy.
| S-EPMC7583924 | biostudies-literature
Project description:Uveal melanoma (UM) is the most common intraocular tumour in adults and despite surgical or radiation treatment of primary tumours, ~50% of patients progress to metastatic disease. Therapeutic options for metastatic UM are limited, with clinical trials having little impact. Here we perform whole-genome sequencing (WGS) of 103 UM from all sites of the uveal tract (choroid, ciliary body, iris). While most UM have low tumour mutation burden (TMB), two subsets with high TMB are seen; one driven by germline MBD4 mutation, and another by ultraviolet radiation (UVR) exposure, which is restricted to iris UM. All but one tumour have a known UM driver gene mutation (GNAQ, GNA11, BAP1, PLCB4, CYSLTR2, SF3B1, EIF1AX). We identify three other significantly mutated genes (TP53, RPL5 and CENPE).
| S-EPMC7229209 | biostudies-literature
Project description:Background Cardiac MRI measurements have diagnostic and prognostic value in the evaluation of cardiopulmonary disease. Artificial intelligence approaches to automate cardiac MRI segmentation are emerging but require clinical testing. Purpose To develop and evaluate a deep learning tool for quantitative evaluation of cardiac MRI functional studies and assess its use for prognosis in patients suspected of having pulmonary hypertension. Materials and Methods A retrospective multicenter and multivendor data set was used to develop a deep learning-based cardiac MRI contouring model using a cohort of patients suspected of having cardiopulmonary disease from multiple pathologic causes. Correlation with same-day right heart catheterization (RHC) and scan-rescan repeatability was assessed in prospectively recruited participants. Prognostic impact was assessed using Cox proportional hazard regression analysis of 3487 patients from the ASPIRE (Assessing the Severity of Pulmonary Hypertension In a Pulmonary Hypertension Referral Centre) registry, including a subset of 920 patients with pulmonary arterial hypertension. The generalizability of the automatic assessment was evaluated in 40 multivendor studies from 32 centers. Results The training data set included 539 patients (mean age, 54 years ± 20 [SD]; 315 women). Automatic cardiac MRI measurements were better correlated with RHC parameters than were manual measurements, including left ventricular stroke volume (r = 0.72 vs 0.68; P = .03). Interstudy repeatability of cardiac MRI measurements was high for all automatic measurements (intraclass correlation coefficient range, 0.79-0.99) and similarly repeatable to manual measurements (all paired t test P > .05). Automated right ventricle and left ventricle cardiac MRI measurements were associated with mortality in patients suspected of having pulmonary hypertension. Conclusion An automatic cardiac MRI measurement approach was developed and tested in a large cohort of patients, including a broad spectrum of right ventricular and left ventricular conditions, with internal and external testing. Fully automatic cardiac MRI assessment correlated strongly with invasive hemodynamics, had prognostic value, were highly repeatable, and showed excellent generalizability. Clinical trial registration no. NCT03841344 Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Ambale-Venkatesh and Lima in this issue. An earlier incorrect version appeared online. This article was corrected on June 27, 2022.
| S-EPMC9527336 | biostudies-literature
Project description:PurposeTo evaluate the magnetic resonance imaging (MRI) characteristics of uveal melanoma (UM), to compare them with fundoscopy and ultrasound (US), and to validate them with histopathology.MethodsMR images from 42 UM were compared with US and fundoscopy, and on 14 enucleated cases with histopathology.ResultsA significant relationship between the signal intensity on T1 and pigmentation on histopathology was found (p=0.024). T1 hyperintense UM were always moderately or strongly pigmented on histopathology, while T1-hypointense UM were either pigmented or non-pigmented. Mean apparent diffusion coefficient (ADC) of the UM was 1.16 ± 0.26 × 10-3 mm2/s. Two-thirds of the UM had a wash-out and the remaining a plateau perfusion time-intensity curve (TIC). MRI was limited in evaluating the basal diameter of flat tumors. US tends to show larger tumor prominence (0.5mm larger, p=0.008) and largest basal diameter (1.4mm larger, p<0.001). MRI was good in diagnosing ciliary body involvement, extrascleral extension, and optic nerve invasion, but limited on identifying scleral invasion. An increase of tumor prominence was associated with lower ADC values (p=0.030) and favored a wash-out TIC (p=0.028). An increase of tumor ADC correlated with a plateau TIC (p=0.011).ConclusionsThe anatomical and functional MRI characteristics of UM were comprehensively assessed. Knowing the MRI characteristics of UM is important in order to confirm the diagnosis and to differentiate UM from other intra-ocular lesions and because it has implications for treatment planning. MRI is a good technique to evaluate UM, being only limited in case of flat tumors or on identifying scleral invasion.
| S-EPMC8724164 | biostudies-literature
Project description:BackgroundMarital status influences the presentation and outcome of various cancers. We explored the relationship between marital status and survival of uveal melanoma (UM) and factors influencing this relationship.MethodsWe conducted a retrospective cohort study on patients diagnosed with UM and registered in the Surveillance Epidemiology and End Results program between 1973 and 2017. Cox regression model was conducted to calculate the hazard ratio of overall and cancer-specific survival rate and delineate the effect of each confounder.ResultsThe study involved 10,557 patients with a male-to-female ratio of 1:1.1. Most of the diagnosed patients were aged between 40 and 79 years (81%). Married patients (62%) represented the majority, followed by singles (12%), widowed (11%), and then divorced patients (7%). Single patients were the youngest group (mean age of 59.3 years) while widowed patients were the oldest (mean age of 75.8 years). In the Cox regression model for overall survival, married and single patients exhibited the best overall survival (no significant difference in between them), both surpassing divorced and widowed patients. Married patients were at a significantly lower risk to die from UM than divorced patients. Female patients and younger age groups showed the best overall and cancer-specific survival.ConclusionMaintained marriages improved the survival of UM patients. Widowed and divorced patients should be included in specially designed support programs during their cancer management.
| S-EPMC9617958 | biostudies-literature
Project description:Epiretinal membrane (ERM) is a common ophthalmological disorder of high prevalence. Its symptoms include metamorphopsia, blurred vision, and decreased visual acuity. Early diagnosis and timely treatment of ERM is crucial to preventing vision loss. Although optical coherence tomography (OCT) is regarded as a de facto standard for ERM diagnosis due to its intuitiveness and high sensitivity, ophthalmoscopic examination or fundus photographs still have the advantages of price and accessibility. Artificial intelligence (AI) has been widely applied in the health care industry for its robust and significant performance in detecting various diseases. In this study, we validated the use of a previously trained deep neural network based-AI model in ERM detection based on color fundus photographs. An independent test set of fundus photographs was labeled by a group of ophthalmologists according to their corresponding OCT images as the gold standard. Then the test set was interpreted by other ophthalmologists and AI model without knowing their OCT results. Compared with manual diagnosis based on fundus photographs alone, the AI model had comparable accuracy (AI model 77.08% vs. integrated manual diagnosis 75.69%, χ2 = 0.038, P = 0.845, McNemar's test), higher sensitivity (75.90% vs. 63.86%, χ2 = 4.500, P = 0.034, McNemar's test), under the cost of lower but reasonable specificity (78.69% vs. 91.80%, χ2 = 6.125, P = 0.013, McNemar's test). Thus our AI model can serve as a possible alternative for manual diagnosis in ERM screening.
| S-EPMC8481557 | biostudies-literature
Project description:ImportanceThe development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals.ObjectiveTo investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics.Design, setting, and participantsThis multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023.ExposuresAll whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care.Main outcomes and measuresThe area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity.ResultsThe study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479).Conclusions and relevanceThe findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.
| S-EPMC10851139 | biostudies-literature
Project description:BackgroundCoronary angiography is fundamental for the diagnosis and treatment of coronary artery disease. Manual quantitative coronary angiography (QCA) is accurate and reproducible; however, it is time-consuming and labor-intensive. However, recent advancements in artificial intelligence (AI) have enabled automated and rapid analysis of medical images, addressing the need for real-time quantitative coronary analysis.AimsThis study aimed to evaluate the accuracy of AI-based QCA (AI-QCA) compared with that via manual QCA and clinician acceptance.MethodsThis retrospective, single-center study was conducted in two phases. Phase 1 was a pilot study comparing AI-QCA with manual QCA and visual estimation. It involved 15 patients who underwent coronary angiography at Seoul National University Bundang Hospital between September 2011 and July 2021. Phase 2 included a larger cohort of 762 patients, with 1002 coronary angiograms analyzed between May 2020 and April 2021.ResultsIn phase 1, AI-QCA and manual QCA consistency varied among the observers, with AI-QCA showing superior consistency compared with visual estimation. However, a strong correlation between AI-QCA and manual-QCA was found in phase 2. AI-QCA accurately identified and quantitatively analyzed multiple lesions in the major vessels, providing results comparable with those of manual QCA.ConclusionsAI-QCA demonstrated high concordance with manual QCA, offering real-time analysis and reduced workload. Therefore, AI-QCA has the potential to be a valuable tool for diagnosing and treating coronary artery disease, necessitating further studies for clinical validation.
| S-EPMC11653446 | biostudies-literature
Project description:AimThe objective was to evaluate the relationship between the regression rate of ciliary body melanoma and choroidal melanoma after brachytherapy and chromosome 3 monosomy status.MethodsWe conducted a prospective and consecutive case series of patients who underwent biopsy and brachytherapy for ciliary/choroidal melanoma. Tumor biopsy performed at the time of radiation plaque placement was analyzed with fluorescence in situ hybridization to determine the percentage of tumor cells with chromosome 3 monosomy. The regression rate was calculated as the percent change in tumor height at months 3, 6, and 12. The relationship between regression rate and tumor location, initial tumor height, and chromosome 3 monosomy (percentage) was assessed by univariate linear regression (R version 3.1.0).ResultsOf the 75 patients included in the study, 8 had ciliary body melanoma, and 67 were choroidal melanomas. The mean tumor height at the time of diagnosis was 5.2 mm (range: 1.90-13.00). The percentage composition of chromosome 3 monosomy ranged from 0-20% (n = 35) to 81-100% (n = 40). The regression of tumor height at months 3, 6, and 12 did not statistically correlate with tumor location (ciliary or choroidal), initial tumor height, or chromosome 3 monosomy (percentage).ConclusionThe regression rate of choroidal melanoma following brachytherapy did not correlate with chromosome 3 monosomy status.
| S-EPMC5567042 | biostudies-literature
Project description:PurposeThe purpose of this study was to profile protein expression liquid vitreous biopsies from patients with uveal melanoma (UM) using mass spectrometry to identify prognostic biomarkers, signaling pathways, and therapeutic targets.MethodsVitreous biopsies were collected from two cohorts in a pilot study: comparative control eyes with epiretinal membranes (ERM; n = 3) and test eyes with UM (n = 8). Samples were analyzed using liquid chromatography-tandem mass spectrometry (LC-MS/MS). Identified proteins were compared to data from a targeted multiplex ELISA proteomics platform.ResultsA total of 69 significantly elevated proteins were detected in the UM vitreous, including LYVE-1. LC-MS/MS identified 62 significantly upregulated proteins in UM vitreous that were not previously identified by ELISA. Analysis of differential protein expression by tumor molecular classification (gene expression profiling [GEP] and preferentially expressed antigen in melanoma [PRAME]) further identified proteins that correlated with these classifications. Patients with high-risk GEP tumors displayed elevated vitreous expression of HGFR (fold-change [FC] = 2.66E + 03, P value = 0.003) and PYGL (FC = 1.02E + 04, P = 1.72E-08). Patients with PRAME positive tumors displayed elevated vitreous expression of ENPP-2 (FC = 3.21, P = 0.04), NEO1 (FC = 2.65E + 03, P = 0.002), and LRP1 (FC = 5.59E + 02, P value = 0.01). IGF regulatory effectors were highly represented (P value = 1.74E-16). Cross-platform analysis validated seven proteins identified by ELISA and LC-MS/MS.ConclusionsProteomic analysis of liquid biopsies may provide prognostic information supporting gene expression of tumor biopsies. The use of multiple protein detection platforms in the same patient samples increases the sensitivity of candidate biomarker detection and allows for precise characterization of the vitreous proteome.
| S-EPMC10653261 | biostudies-literature