Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range.
Ontology highlight
ABSTRACT:
SUBMITTER: Pouyet E
PROVIDER: S-EPMC8471921 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may particularly benefit from this technology. Quantitative optical coherence tomography angiography (OCTA) imaging provides excellent capability to identify subtle vascular distortions, which are useful for classifying retinovascular diseases. However, application of AI for differentiation and classification of multiple eye diseases is not yet established. In this study, we demonstrate supervised machine learning based multi-task OCTA classification. We sought 1) to differentiate normal from diseased ocular conditions, 2) to differentiate different ocular disease conditions from each other, and 3) to stage the severity of each ocular condition. Quantitative OCTA features, including blood vessel tortuosity (BVT), blood vascular caliber (BVC), vessel perimeter index (VPI), blood vessel density (BVD), foveal avascular zone (FAZ) area (FAZ-A), and FAZ contour irregularity (FAZ-CI) were fully automatically extracted from the OCTA images. A stepwise backward elimination approach was employed to identify sensitive OCTA features and optimal-feature-combinations for the multi-task classification. For proof-of-concept demonstration, diabetic retinopathy (DR) and sickle cell retinopathy (SCR) were used to validate the supervised machine leaning classifier. The presented AI classification methodology is applicable and can be readily extended to other ocular diseases, holding promise to enable a mass-screening platform for clinical deployment and telemedicine.
| S-EPMC6617139 | biostudies-literature
Project description:Determination of malignancy in thyroid nodules remains a major diagnostic challenge. Here we report the feasibility and clinical utility of developing an AI-defined protein-based biomarker panel for diagnostic classification of thyroid nodules: based initially on formalin-fixed paraffin-embedded (FFPE), and further refined for fine-needle aspiration (FNA) tissue specimens of minute amounts which pose technical challenges for other methods. We first developed a neural network model of 19 protein biomarkers based on the proteomes of 1724 FFPE thyroid tissue samples from a retrospective cohort. This classifier achieved over 91% accuracy in the discovery set for classifying malignant thyroid nodules. The classifier was externally validated by blinded analyses in a retrospective cohort of 288 nodules (89% accuracy; FFPE) and a prospective cohort of 294 FNA biopsies (85% accuracy) from twelve independent clinical centers. This study shows that integrating high-throughput proteomics and AI technology in multi-center retrospective and prospective clinical cohorts facilitates precise disease diagnosis which is otherwise difficult to achieve by other methods.
| S-EPMC9448820 | biostudies-literature
Project description:We present the design, fabrication, and characterization of an infrared (IR) polarization sensing detector with a wide dynamic range and sub-wavelength dimensions. The detector consists of two orthogonal slot antennas, each loaded with two microbolometers at its edges. The polarization of the incoming IR radiation is detected by comparing the received power levels in the bolometer pairs corresponding to each slot antenna. The IR radiation is sensed by applying a dc bias voltage to each antenna and measuring the changes in the dc current caused by the change of the bolometer resistance as they absorb the incoming IR radiation. In this design, the ratio of the absorbed power in the bolometers is a one to one function of the polarization of the incident wave. A prototype of this detector, designed to have maximum sensitivity at λ = 10.6 μm, was designed, fabricated, and characterized. The fabricated detector has an area of 0.7λ × 0.7λ, where λ is the free-space wavelength. The polarization sensing response is characterized under different angles of incidence. The measurement results show that the device has a dynamic range of 24 dB between two orthogonal orientations of EM wave polarization for incidence angles in the range of ±20° from boresight.
| S-EPMC5727214 | biostudies-literature
Project description:We applied PCT-DIA on a total of 1161 nodules from 1133 patients using either tissue cores (1 mm diameter; 0.5–1 mm depth) punched from regions of interest marked on retrospective FFPE tissue blocks or prospective cytology specimens from FNA aspirates. The samples comprise (i) a discovery set of FFPE samples from Singapore General Hospital (n = 579 nodules) where histopathological diagnoses were confirmed on central review by a board-certified pathologist; and independent test sets from twelve hospitals in China and Singapore consisting of (ii) retrospective test sets of FFPE samples (n = 288 nodules) with the same histopathological assessment and classification as the discovery sample set, and (iii) a prospective test set of FNA biopsies (n = 294 nodules) which were additionally scored by the Bethesda System for reporting thyroid cytopathology.
2022-09-07 | PXD036554 |
Project description: Not available
| S-EPMC11226427 | biostudies-literature
Project description:PurposeTo quantify the central visual field (VF) loss patterns in glaucoma using artificial intelligence.DesignRetrospective study.ParticipantsVFs of 8712 patients with 13 951 Humphrey 10-2 test results from 13 951 eyes for cross-sectional analyses, and 824 patients with at least 5 reliable 10-2 test results at 6-month intervals or more from 1191 eyes for longitudinal analyses.MethodsTotal deviation values were used to determine the central VF patterns using the most recent 10-2 test results. A 24-2 VF within a 3-month window of the 10-2 tests was used to stage eyes into mild, moderate, or severe functional loss using the Hodapp-Anderson-Parrish scale at baseline. Archetypal analysis was applied to determine the central VF patterns. Cross-validation was performed to determine the optimal number of patterns. Stepwise regression was applied to select the optimal feature combination of global indices, average baseline decomposition coefficients from central VFs archetypes, and other factors to predict central VF mean deviation (MD) slope based on the Bayesian information criterion (BIC).Main outcome measuresThe central VF patterns stratified by severity stage based on 24-2 test results and a model to predict the central VF MD change over time using baseline test results.ResultsFrom cross-sectional analysis, 17 distinct central VF patterns were determined for the 13 951 eyes across the spectrum of disease severity. These central VF patterns could be divided into isolated superior loss, isolated inferior loss, diffuse loss, and other loss patterns. Notably, 4 of the 5 patterns of diffuse VF loss preserved the less vulnerable inferotemporal zone, whereas they lost most of the remaining more vulnerable zone described by the Hood model. Inclusion of coefficients from central VF archetypical patterns strongly improved the prediction of central VF MD slope (BIC decrease, 35; BIC decrease of >6 indicating strong prediction improvement) than using only the global indices of 2 baseline VF results. Eyes with baseline VF results with more superonasal and inferonasal loss were more likely to show worsening MD over time.ConclusionsWe quantified central VF patterns in glaucoma, which were used to improve the prediction of central VF worsening compared with using only global indices.
| S-EPMC7246163 | biostudies-literature
Project description:BackgroundThe COVID-19 pandemic unexpectedly broke out at the end of 2019. Due to the highly contagious, widespread, and risky nature of this disease, the pandemic prevention and control has been a tremendous challenge worldwide. One potentially powerful tool against the COVID-19 pandemic is artificial intelligence (AI). This study systematically assessed the effectiveness of AI in infection prevention and control during the first wave of COVID-19 in China. METHODS: To better evaluate the role of AI in a pandemic emergency, we focused on the first-wave COVID-19 in the period from the early December 2019 to the end of April 2020 across 304 cities in China. We employed three sets of dependent variables to capture various dimensions of the effect of AI: (1) the time to the peak of cumulative confirmed cases, (2) the case fatality rate and whether there were severe cases, and (3) the number of local policies for work and production resumption and the time span to having the first such policy. The main explanatory variable was the local AI development measured by the number of AI patents. To fit the features of different dependent variables, we employed a variety of estimation methods, including the OLS, Tobit, Probit, and Poisson estimations. We included a large set of control variables and added interaction terms to test the mechanisms through which AI took an effect.ResultsOur results showed that AI had highly significant effects on (1) screening and detecting the disease, and (2) monitoring and evaluating the epidemic evolution. Specifically, AI was useful to screen and detect the COVID-19 in cities with high cross-city mobility. Also, AI played an important role for production resumption in cities with high risk to reopen. However, there was limited evidence supporting the effectiveness of AI in the diagnosis and treatment of the disease.ConclusionsThese results suggested that AI can play an important role against the pandemic.
| S-EPMC9186483 | biostudies-literature
Project description:Creativity has traditionally been considered an ability exclusive to human beings. However, the rapid development of artificial intelligence (AI) has resulted in generative AI chatbots that can produce high-quality artworks, raising questions about the differences between human and machine creativity. In this study, we compared the creativity of humans (n = 256) with that of three current AI chatbots using the alternate uses task (AUT), which is the most used divergent thinking task. Participants were asked to generate uncommon and creative uses for everyday objects. On average, the AI chatbots outperformed human participants. While human responses included poor-quality ideas, the chatbots generally produced more creative responses. However, the best human ideas still matched or exceed those of the chatbots. While this study highlights the potential of AI as a tool to enhance creativity, it also underscores the unique and complex nature of human creativity that may be difficult to fully replicate or surpass with AI technology. The study provides insights into the relationship between human and machine creativity, which is related to important questions about the future of creative work in the age of AI.
| S-EPMC10502005 | biostudies-literature
Project description:Objective: The primary objective of this study was to predict subgroups of autism spectrum disorder (ASD) based on the Diagnostic Statistical Manual for Mental Disorders-IV Text Revision (DSM-IV-TR) by machine learning (ML). The secondary objective was to set up a ranking of Autism Diagnostic Interview-Revised (ADI-R) diagnostic algorithm items based on ML, and to confirm whether ML can sufficiently predict the diagnosis with these minimum items.Methods: In the first experiment, a multiclass decision forest algorithm was applied, and the diagnostic algorithm score value of 1,269 Korean ADI-R test data was used for prediction. In the second experiment, we used 539 Korean ADI-R case data (over 48 months with verbal language) to apply mutual information to rank items used in the ADI diagnostic algorithm.Results: In the first experiment, the results of predicting in the case of pervasive developmental disorder not otherwise specified as "ASD" were almost three times higher than predicting it as "No diagnosis." In the second experiment, the top 10 ranking items of ADI-R were mainly related to the quality abnormality of communication.Conclusion: In conclusion, we verified the applicability of ML in diagnosis and found that the application of artificial intelligence for rapid diagnosis or screening of ASD patients may be useful.
| S-EPMC7711119 | biostudies-literature
Project description:ObjectivesThis study aimed to explore and develop artificial intelligence approaches for efficient classification of pulmonary nodules based on CT scans.Materials and methodsA number of 1007 nodules were obtained from 551 patients of LIDC-IDRI dataset. All nodules were cropped into 64 × 64 PNG images , and preprocessing was carried out to clean the image from surrounding non-nodular structure. In machine learning method, texture Haralick and local binary pattern features were extracted. Four features were selected using principal component analysis (PCA) algorithm before running classifiers. In deep learning, a simple CNN model was constructed and transfer learning was applied using VGG-16 and VGG-19, DenseNet-121 and DenseNet-169 and ResNet as pre-trained models with fine tuning.ResultsIn statistical machine learning method, the optimal AUROC was 0.885 ± 0.024 with random forest classifier and the best accuracy was 0.819 ± 0.016 with support vector machine. In deep learning, the best accuracy reached 90.39% with DenseNet-121 model and the best AUROC was 96.0%, 95.39% and 95.69% with simple CNN, VGG-16 and VGG-19, respectively. The best sensitivity reached 90.32% using DenseNet-169 and the best specificity attained was 93.65% when applying the DenseNet-121 and ResNet-152V2.ConclusionDeep learning methods with transfer learning showed several benefits over statistical learning in terms of nodule prediction performance and saving efforts and time in training large datasets. SVM and DenseNet-121 showed the best performance when compared with their counterparts. There is still more room for improvement, especially when more data can be trained and lesion volume is represented in 3D.Clinical relevance statementMachine learning methods offer unique opportunities and open new venues in clinical diagnosis of lung cancer. The deep learning approach has been more accurate than statistical learning methods. SVM and DenseNet-121 showed superior performance in pulmonary nodule classification.
| S-EPMC10195968 | biostudies-literature