Deep learning for gradability classification of handheld, non-mydriatic retinal images.
Ontology highlight
ABSTRACT:
SUBMITTER: Nderitu P
PROVIDER: S-EPMC8096843 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PURPOSE:Nowadays, complex digital imaging systems allow detailed retinal imaging without dilating patients' pupils. These so-called non-mydriatic cameras have advantages in common circumstances (eg, for screening or emergency purposes) but present limitations in terms of image quality and field of view. We compare the usefulness of two non-mydriatic camera systems (ie, a handheld versus a stand-alone device) for fundus imaging. The primary outcome was image quality. The secondary outcomes were learning effects and quality grade-influencing factors. METHODS:The imaging procedures followed standard protocol and were all performed by the same investigator. Camera 1 (DRS®) was a stand-alone system, while Camera 2 (Smartscope® PRO) was a mobile system. In order to evaluate possible learning effects, we selected an examiner with no prior training in the use of these systems. The images were graded separately by two experienced and "blinded" ophthalmologists following a defined protocol. RESULTS:In total, 211 people were enrolled. Quality grade comparisons showed significantly better grades for Camera 1. Both systems achieved better quality grades for macular images than for disc-centered images. No remarkable learning effects could be demonstrated. CONCLUSIONS:Both camera systems are useful for fundus imaging. The greater mobility of Camera 2 was associated with lower image quality. For screening scenarios or telemedicine, it must be determined whether image quality or mobility is more important.
| S-EPMC5587188 | biostudies-literature
Project description:The diagnosis and the subtyping of non-Hodgkin lymphoma (NHL) are challenging and require expert knowledge, great experience, thorough morphological analysis, and often additional expensive immunohistological and molecular methods. As these requirements are not always available, supplemental methods supporting morphological-based decision making and potentially entity subtyping are required. Deep learning methods have been shown to classify histopathological images with high accuracy, but data on NHL subtyping are limited. After annotation of histopathological whole-slide images and image patch extraction, we trained and optimized an EfficientNet convolutional neuronal network algorithm on 84,139 image patches from 629 patients and evaluated its potential to classify tumor-free reference lymph nodes, nodal small lymphocytic lymphoma/chronic lymphocytic leukemia, and nodal diffuse large B-cell lymphoma. The optimized algorithm achieved an accuracy of 95.56% on an independent test set including 16,960 image patches from 125 patients after the application of quality controls. Automatic classification of NHL is possible with high accuracy using deep learning on histopathological images and routine diagnostic applications should be pursued.
| S-EPMC8156071 | biostudies-literature
Project description:This study proposes a simple convolutional neural network (CNN)-based model for vehicle classification in low resolution surveillance images collected by a standard security camera installed distant from a traffic scene. In order to evaluate its effectiveness, the proposed model is tested on a new dataset containing tiny (100 × 100 pixels) and low resolution (96 dpi) vehicle images. The proposed model is then compared with well-known VGG16-based CNN models in terms of accuracy and complexity. Results indicate that although the well-known models provide higher accuracy, the proposed method offers an acceptable accuracy (92.9%) as well as a simple and lightweight solution for vehicle classification in low quality images. Thus, it is believed that this study might provide useful perception and understanding for further research on the use of standard low-cost cameras to enhance the ability of the intelligent systems such as intelligent transportation system applications.
| S-EPMC9268885 | biostudies-literature
Project description:Drill core lithology is an important indicator reflecting the geological conditions of the drilling area. Traditional lithology identification usually relies on manual visual inspection, which is time-consuming and professionally demanding. In recent years, the rapid development of convolutional neural networks has provided an innovative way for the automatic prediction of drill core images. In this work, a core dataset containing a total of 10 common lithology categories in underground engineering was constructed. ResNeSt-50 we adopted uses a strategy of combining channel-wise attention and multi-path network to achieve cross-channel feature correlations, which significantly improves the model accuracy without high model complexity. Transfer learning was used to initialize the model parameters, to extract the feature of core images more efficiently. The model achieved superior performance on testing images compared with other discussed CNN models, the average value of its Precision, Recall, F1-score for each category of lithology is 99.62%, 99.62%, and 99.59%, respectively, and the prediction accuracy is 99.60%. The test results show that the proposed method is optimal and effective for automatic lithology classification of borehole cores.
| S-EPMC9249224 | biostudies-literature
Project description:Topological characterization of the Retinal microvascular nEtwork visualized by portable fuNDus camera (TREND) is a database comprising of 72 color digital retinal images collected from the students of the Faculty of Medicine at the University of Montenegro, in the period from February 18th to March 11th 2020. The database also includes binarized images of manually segmented microvascular networks associated with each raw image. The participant demographic characteristics, health status, and social habits information such as age, sex, body mass index, smoking history, alcohol use, as well as previous medical history was collected. As proof of the concept, a smaller set of 10 color digital fundus images from healthy older participants is also included. Comparison of the microvascular parameters of these two sets of images demonstrate that digital fundus images recorded with a hand-held portable camera are able to capture the changes in patterns of microvascular network associated with aging. The raw images from the TREND database provide a standard that defines normal retinal anatomy and microvascular network geometry in young healthy people in Montenegro as it is seen with the digital hand-held portable non-mydriatic MiiS HORUS Scope DEC 200.This knowledge could facilitate the application of this technology at the primary level of health care for large scale telematic screening for complications of chronic diseases, such as hypertensive and diabetic retinopathy. In addition, it could aid in the development of new methods for early detection of age-related changes in the retina, systemic chronic diseases, as well as eye-specific diseases. The associated manually segmented images of the microvascular networks provide the standard that can be used for development of automatic software for image quality assessment, segmentation of microvascular network, and for computer-aided detection of pathological changes in retina. The TREND database is freely available at https://doi.org/10.5281/zenodo.4521043.
| S-EPMC8301647 | biostudies-literature
Project description:Full-field electroretinograms (ERGs) are used to evaluate retinal function in patients with various types of hereditary and acquired retinal diseases. However, ERG recordings require relatively invasive procedures, including pupillary dilation and the use of contact lens electrodes. Thus, it would be helpful to have a simpler and noninvasive screening method. The purpose of this study was to determine whether a new, handheld, portable ERG device, RETeval™, can be used to screen patients for cone dysfunction.Thirty-five eyes of 35 patients who had reduced cone responses ascertained by a conventional ERG system using contact lens electrodes were studied. The causative diseases included achromatopsia, cone dystrophy, cone-rod dystrophy, retinitis pigmentosa, choroidal dystrophy, autoimmune retinopathy, and Stargardt disease. The flicker ERGs were recorded with the RETeval™ under undilated conditions with skin electrodes (stimulus strength, 3.0 cd·s/m(2); frequency, 28.3 Hz), and the responses were compared to that of 50 healthy eyes. The amplitudes and implicit times of the fundamental component of the flicker ERGs were analyzed in three age groups: Group A, ?20 years; Group B, 21-40 years; and Group C, ?41 years.In all of the age groups, the amplitudes of the ERGs were significantly smaller and the implicit times significantly longer in patients with cone dysfunction than in the control eyes. All but one of the patients had flicker amplitudes lower than the mean -2.0 standard deviation of control eyes.The RETeval™ has a potential of being used to screen for cone dysfunction. The entire examination takes <5 minutes and does not require pupil dilatation or a contact lens electrode. Although the flicker responses do not provide information on the scotopic functions, the RETeval™ device can be used to determine which patients require additional full-field ERG testing with dilated pupils under both scotopic and photopic conditions.
| S-EPMC4936817 | biostudies-other
Project description:Histopathological characterization of colorectal polyps is critical for determining the risk of colorectal cancer and future rates of surveillance for patients. However, this characterization is a challenging task and suffers from significant inter- and intra-observer variability.We built an automatic image analysis method that can accurately classify different types of colorectal polyps on whole-slide images to help pathologists with this characterization and diagnosis.Our method is based on deep-learning techniques, which rely on numerous levels of abstraction for data representation and have shown state-of-the-art results for various image analysis tasks.Our method covers five common types of polyps (i.e., hyperplastic, sessile serrated, traditional serrated, tubular, and tubulovillous/villous) that are included in the US Multisociety Task Force guidelines for colorectal cancer risk assessment and surveillance. We developed multiple deep-learning approaches by leveraging a dataset of 2074 crop images, which were annotated by multiple domain expert pathologists as reference standards.We evaluated our method on an independent test set of 239 whole-slide images and measured standard machine-learning evaluation metrics of accuracy, precision, recall, and F1 score and their 95% confidence intervals.Our evaluation shows that our method with residual network architecture achieves the best performance for classification of colorectal polyps on whole-slide images (overall accuracy: 93.0%, 95% confidence interval: 89.0%-95.9%).Our method can reduce the cognitive burden on pathologists and improve their efficacy in histopathological characterization of colorectal polyps and in subsequent risk assessment and follow-up recommendations.
| S-EPMC5545773 | biostudies-other
Project description:We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells.
| S-EPMC8021159 | biostudies-literature
Project description:Tumor histology is an important predictor of therapeutic response and outcomes in lung cancer. Tissue sampling for pathologist review is the most reliable method for histology classification, however, recent advances in deep learning for medical image analysis allude to the utility of radiologic data in further describing disease characteristics and for risk stratification. In this study, we propose a radiomics approach to predicting non-small cell lung cancer (NSCLC) tumor histology from non-invasive standard-of-care computed tomography (CT) data. We trained and validated convolutional neural networks (CNNs) on a dataset comprising 311 early-stage NSCLC patients receiving surgical treatment at Massachusetts General Hospital (MGH), with a focus on the two most common histological types: adenocarcinoma (ADC) and Squamous Cell Carcinoma (SCC). The CNNs were able to predict tumor histology with an AUC of 0.71(p = 0.018). We also found that using machine learning classifiers such as k-nearest neighbors (kNN) and support vector machine (SVM) on CNN-derived quantitative radiomics features yielded comparable discriminative performance, with AUC of up to 0.71 (p = 0.017). Our best performing CNN functioned as a robust probabilistic classifier in heterogeneous test sets, with qualitatively interpretable visual explanations to its predictions. Deep learning based radiomics can identify histological phenotypes in lung cancer. It has the potential to augment existing approaches and serve as a corrective aid for diagnosticians.
| S-EPMC7943565 | biostudies-literature
Project description:ObjectivesThis study aimed to investigate the accuracy of deep learning algorithms to diagnose tooth caries and classify the extension and location of dental caries in cone beam computed tomography (CBCT) images. To the best of our knowledge, this is the first study to evaluate the application of deep learning for dental caries in CBCT images.MethodsThe CBCT image dataset comprised 382 molar teeth with caries and 403 noncarious molar cases. The dataset was divided into a development set for training and validation and test set. Three images were obtained for each case, including axial, sagittal, and coronal. The test dataset was provided to a multiple-input convolutional neural network (CNN). The network made predictions regarding the presence or absence of dental decay and classified the lesions according to their depths and types for the provided samples. Accuracy, sensitivity, specificity, and F1 score values were measured for dental caries detection and classification.ResultsThe diagnostic accuracy, sensitivity, specificity, and F1 score for caries detection in carious molar teeth were 95.3%, 92.1%, 96.3%, and 93.2%, respectively, and for noncarious molar teeth were 94.8%, 94.3%, 95.8%, and 94.6%. The CNN network showed high sensitivity, specificity, and accuracy in classifying caries extensions and locations.ConclusionsThis research demonstrates that deep learning models can accurately identify dental caries and classify their depths and types with high accuracy, sensitivity, and specificity. The successful application of deep learning in this field will undoubtedly assist dental practitioners and patients in improving diagnostic and treatment planning in dentistry.Clinical significanceThis study showed that deep learning can accurately detect and classify dental caries. Deep learning can provide dental caries detection accurately. Considering the shortage of dentists in certain areas, using CNNs can lead to broader geographic coverage in detecting dental caries.
| S-EPMC10988262 | biostudies-literature