Deep Learning for Glaucoma Detection and Identification of Novel Diagnostic Areas in Diverse Real-World Datasets.
Ontology highlight
ABSTRACT:
SUBMITTER: Noury E
PROVIDER: S-EPMC9145034 | biostudies-literature | 2022 May
REPOSITORIES: biostudies-literature
Publications
Deep Learning for Glaucoma Detection and Identification of Novel Diagnostic Areas in Diverse Real-World Datasets.
Noury Erfan E Mannil Suria S SS Chang Robert T RT Ran An Ran AR Cheung Carol Y CY Thapa Suman S SS Rao Harsha L HL Dasari Srilakshmi S Riyazuddin Mohammed M Chang Dolly D Nagaraj Sriharsha S Tham Clement C CC Zadeh Reza R
Translational vision science & technology 20220501 5
<h4>Purpose</h4>To develop a three-dimensional (3D) deep learning algorithm to detect glaucoma using spectral-domain optical coherence tomography (SD-OCT) optic nerve head (ONH) cube scans and validate its performance on ethnically diverse real-world datasets and on cropped ONH scans.<h4>Methods</h4>In total, 2461 Cirrus SD-OCT ONH scans of 1012 eyes were obtained from the Glaucoma Clinic Imaging Database at the Byers Eye Institute, Stanford University, from March 2010 to December 2017. A 3D dee ...[more]
Similar Datasets
Project description:Real-world retinal optical coherence tomography (OCT) scans are available in abundance in primary and secondary eye care centres. They contain a wealth of information to be analyzed in retrospective studies. The associated electronic health records alone are often not enough to generate a high-quality dataset for clinical, statistical, and machine learning analysis. We have developed a deep learning-based age-related macular degeneration (AMD) stage classifier, to efficiently identify the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage of AMD in retrospective data. We trained a two-stage convolutional neural network to classify macula-centered 3D volumes from Topcon OCT images into 4 classes: Normal, iAMD, GA and nAMD. In the first stage, a 2D ResNet50 is trained to identify the disease categories on the individual OCT B-scans while in the second stage, four smaller models (ResNets) use the concatenated B-scan-wise output from the first stage to classify the entire OCT volume. Classification uncertainty estimates are generated with Monte-Carlo dropout at inference time. The model was trained on a real-world OCT dataset, 3765 scans of 1849 eyes, and extensively evaluated, where it reached an average ROC-AUC of 0.94 in a real-world test set.
| S-EPMC10636170 | biostudies-literature
Project description:We developed and validated a deep-learning algorithm for polyp detection. We used a YOLOv2 to develop the algorithm for automatic polyp detection on 8,075 images (503 polyps). We validated the algorithm using three datasets: A: 1,338 images with 1,349 polyps; B: an open, public CVC-clinic database with 612 polyp images; and C: 7 colonoscopy videos with 26 polyps. To reduce the number of false positives in the video analysis, median filtering was applied. We tested the algorithm performance using 15 unaltered colonoscopy videos (dataset D). For datasets A and B, the per-image polyp detection sensitivity was 96.7% and 90.2%, respectively. For video study (dataset C), the per-image polyp detection sensitivity was 87.7%. False positive rates were 12.5% without a median filter and 6.3% with a median filter with a window size of 13. For dataset D, the sensitivity and false positive rate were 89.3% and 8.3%, respectively. The algorithm detected all 38 polyps that the endoscopists detected and 7 additional polyps. The operation speed was 67.16 frames per second. The automatic polyp detection algorithm exhibited good performance, as evidenced by the high detection sensitivity and rapid processing. Our algorithm may help endoscopists improve polyp detection.
| S-EPMC7239848 | biostudies-literature
Project description:We present comprehensive datasets of Brazilian disasters from January 2003 to February 2021 as well as real-world optimization instances built up from these data. The data were gathered through a series of open available reports obtained from different government and institutional sources. Afterwards, data consolidation and summarization were carried out using Excel and Python. The datasets include 9 types of disaster, such as flash floods, landslides and droughts, and the corresponding number of affected people during an 18-year or a 218-month observation period for 5,402 Brazilian municipalities, totaling more than 65,000 observations. Data on relevant geographical, demographic and socioeconomic aspects of the affected municipalities are also provided. These encompass geographic coordinates, regions, population, income, development indicators, amongst other information. From a statistical point of view, the data on disasters can address a number of applications using both supervised and unsupervised machine learning techniques such as, for time series analysis or other dynamic models using socioeconomic data as explanatory variables, i.e. data on the size of the poor population, income, education and general development. The geographic dataset can be useful for aggregating analyses concerning the various forms of territorial organization and allows for the visualization of data in maps. All the aforementioned data can be also used to devise realistic optimization instances related to diverse humanitarian logistics and/or disaster management problems, such as facility location, location-allocation, vehicle routing, and so forth. In particular, we describe two real-world instances for the location-allocation problem studied in [1]. For that purpose, we partially use the given datasets and included other information such as costs and distances relevant to the optimization model. Although using real-world cases to test optimization approaches is a common and encouraged practice in Operations Research, comprehensive datasets and practical optimization instances, as presented in this article, are rarely described and/or available in the academic literature.
| S-EPMC8931360 | biostudies-literature
Project description:In recent years, there is increasing enthusiasm in the healthcare research community for artificial intelligence to provide big data analytics and augment decision making. One of the prime reasons for this is the enormous impact of deep learning for utilization of complex healthcare big data. Although deep learning is a powerful analytic tool for the complex data contained in electronic health records (EHRs), there are also limitations which can make the choice of deep learning inferior in some healthcare applications. In this paper, we give a brief overview of the limitations of deep learning illustrated through case studies done over the years aiming to promote the consideration of alternative analytic strategies for healthcare.
| S-EPMC6550223 | biostudies-literature
Project description: Not available
| S-EPMC11543466 | biostudies-literature
Project description:ObjectivesTo conduct an external validation of an automated artificial intelligence (AI) diagnostic system using fundus photographs from a real-life multicentre cohort.MethodsWe designed external validation in multiple scenarios, consisting of 3049 images from Qilu Hospital of Shandong University in China (QHSDU, validation dataset 1), 7495 images from three other hospitals in China (validation dataset 2), and 516 images from high myopia (HM) population of QHSDU (validation dataset 3). The corresponding sensitivity, specificity and accuracy of this AI diagnostic system to identify glaucomatous optic neuropathy (GON) were calculated.ResultsIn validation datasets 1 and 2, the algorithm yielded accuracy of 93.18% and 91.40%, area under the receiver operating curves (AUC) of 95.17% and 96.64%, and significantly higher sensitivity of 91.75% and 91.41%, respectively, compared to manual graders. On the subsets complicated with retinal comorbidities, such as diabetic retinopathy or age-related macular degeneration, in validation datasets 1 and 2, the algorithm achieved accuracy of 87.54% and 93.81%, and AUC of 97.02% and 97.46%, respectively. In validation dataset 3, the algorithm achieved comparable accuracy of 81.98% and AUC of 87.49%, with a sensitivity of 83.61% and specificity of 81.76% on GON recognition specifically in the HM population.ConclusionsWith acceptable generalization capability across varying levels of image quality, different clinical centres, or certain retinal comorbidities, such as HM, the automatic AI diagnostic system had the potential to provide expert-level glaucoma detection.
| S-EPMC10698045 | biostudies-literature
Project description:The intuition behind this data acquisition is to encourage research for addressing the problem of weeds in agriculture through computer vision applications. Data is acquired in the form of images from uniform and random crop-spacing fields. In other words, we have taken a step forward to identify weeds from fields that follow any method of sowing, which ultimately leads to the transformation of traditional agriculture into precision agriculture. Sorghum crop and its associated weeds are chosen as the research objects during this process. These acquired data are used in framing two datasets. The first dataset termed 'SorghumWeedDataset_Classification' is a crop-weed classification dataset created with 4312 data samples for addressing crop-weed classification problems. The second dataset termed 'SorghumWeedDataset_Segmentation' is a crop-weed segmentation dataset that contains 5555 manually pixel-wise annotated data segments from 252 data samples for addressing crop-weed localization, detection, and segmentation problems. All data samples are acquired in April and May 2023 from Sri Ramaswamy Memorial (SRM) Care Farm, Chengalpattu district, Tamil Nadu, India. Manually annotated data samples and data segments are verified by agronomists. The datasets are made publicly available to the research community to solve the crop-weed problems using state-of-the-art image processing, machine learning, and deep learning algorithms. To the best of our knowledge, these are the first open-access crop-weed research datasets from Indian fields for classification and segmentation to deal with weed issues in uniform and random crop-spacing fields. However, other available datasets (from Indian fields) are either non-research datasets or available on subscription/request.
| S-EPMC10789999 | biostudies-literature
Project description:BackgroundHigh-throughput and selective detection of organelles in immunofluorescence images is an important but demanding task in cell biology. The centriole organelle is critical for fundamental cellular processes, and its accurate detection is key for analysing centriole function in health and disease. Centriole detection in human tissue culture cells has been achieved typically by manual determination of organelle number per cell. However, manual cell scoring of centrioles has a low throughput and is not reproducible. Published semi-automated methods tally the centrosome surrounding centrioles and not centrioles themselves. Furthermore, such methods rely on hard-coded parameters or require a multichannel input for cross-correlation. Therefore, there is a need for developing an efficient and versatile pipeline for the automatic detection of centrioles in single channel immunofluorescence datasets.ResultsWe developed a deep-learning pipeline termed CenFind that automatically scores cells for centriole numbers in immunofluorescence images of human cells. CenFind relies on the multi-scale convolution neural network SpotNet, which allows the accurate detection of sparse and minute foci in high resolution images. We built a dataset using different experimental settings and used it to train the model and evaluate existing detection methods. The resulting average F1-score achieved by CenFind is > 90% across the test set, demonstrating the robustness of the pipeline. Moreover, using the StarDist-based nucleus detector, we link the centrioles and procentrioles detected with CenFind to the cell containing them, overall enabling automatic scoring of centriole numbers per cell.ConclusionsEfficient, accurate, channel-intrinsic and reproducible detection of centrioles is an important unmet need in the field. Existing methods are either not discriminative enough or focus on a fixed multi-channel input. To fill this methodological gap, we developed CenFind, a command line interface pipeline that automates cell scoring of centrioles, thereby enabling channel-intrinsic, accurate and reproducible detection across experimental modalities. Moreover, the modular nature of CenFind enables its integration in other pipelines. Overall, we anticipate CenFind to prove critical for accelerating discoveries in the field.
| S-EPMC10045196 | biostudies-literature
Project description:Artificial intelligence (AI) based on deep learning has shown excellent diagnostic performance in detecting various diseases with good-quality clinical images. Recently, AI diagnostic systems developed from ultra-widefield fundus (UWF) images have become popular standard-of-care tools in screening for ocular fundus diseases. However, in real-world settings, these systems must base their diagnoses on images with uncontrolled quality ("passive feeding"), leading to uncertainty about their performance. Here, using 40,562 UWF images, we develop a deep learning-based image filtering system (DLIFS) for detecting and filtering out poor-quality images in an automated fashion such that only good-quality images are transferred to the subsequent AI diagnostic system ("selective eating"). In three independent datasets from different clinical institutions, the DLIFS performed well with sensitivities of 96.9%, 95.6% and 96.6%, and specificities of 96.6%, 97.9% and 98.8%, respectively. Furthermore, we show that the application of our DLIFS significantly improves the performance of established AI diagnostic systems in real-world settings. Our work demonstrates that "selective eating" of real-world data is necessary and needs to be considered in the development of image-based AI systems.
| S-EPMC7603327 | biostudies-literature
Project description:Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope light curves. The approach is based on related work from the literature and enhanced to validation with real light curves. A CNN classification model is trained from a mixture of real and synthetic data. The model is then validated only with unknown real data. The best ratio of synthetic data is determined by the performance of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.
| S-EPMC9132280 | biostudies-literature