Open-source, machine and deep learning-based automated algorithm for gestational age estimation through smartphone lens imaging.
Ontology highlight
ABSTRACT:
SUBMITTER: Desai AD
PROVIDER: S-EPMC6491013 | biostudies-literature | 2018 Dec
REPOSITORIES: biostudies-literature
Publications
Open-source, machine and deep learning-based automated algorithm for gestational age estimation through smartphone lens imaging.
Desai Arjun D AD Peng Chunlei C Fang Leyuan L Mukherjee Dibyendu D Yeung Andrew A Jaffe Stephanie J SJ Griffin Jennifer B JB Farsiu Sina S
Biomedical optics express 20181107 12
Gestational age estimation at time of birth is critical for determining the degree of prematurity of the infant and for administering appropriate postnatal treatment. We present a fully automated algorithm for estimating gestational age of premature infants through smartphone lens imaging of the anterior lens capsule vasculature (ALCV). Our algorithm uses a fully convolutional network and blind image quality analyzers to segment usable anterior capsule regions. Then, it extracts ALCV features us ...[more]
Similar Datasets
Project description:Assessment of tumor infiltrating lymphocytes (TILs) as a prognostic variable in melanoma has not seen broad adoption due to lack of standardization. Automation could represent a solution. Here, using open source software, we build an algorithm for image-based automated assessment of TILs on hematoxylin-eosin stained sections in melanoma. Using a retrospective collection of 641 melanoma patients comprising four independent cohorts; one training set (N?=?227) and three validation cohorts (N?=?137, N?=?201, N?=?76) from 2 institutions, we show that the automated TIL scoring algorithm separates patients into favorable and poor prognosis cohorts, where higher TILs scores were associated with favorable prognosis. In multivariable analyses, automated TIL scores show an independent association with disease-specific overall survival. Therefore, the open source, automated TIL scoring is an independent prognostic marker in melanoma. With further study, we believe that this algorithm could be useful to define a subset of patients that could potentially be spared immunotherapy.
| S-EPMC6884485 | biostudies-literature
Project description:BackgroundStep counts are increasingly used in public health and clinical research to assess wellbeing, lifestyle, and health status. However, estimating step counts using commercial activity trackers has several limitations, including a lack of reproducibility, generalizability, and scalability. Smartphones are a potentially promising alternative, but their step-counting algorithms require robust validation that accounts for temporal sensor body location, individual gait characteristics, and heterogeneous health states.ObjectiveOur goal was to evaluate an open-source step-counting method for smartphones under various measurement conditions against step counts estimated from data collected simultaneously from different body locations ("internal" validation), manually ascertained ground truth ("manual" validation), and step counts from a commercial activity tracker (Fitbit Charge 2) in patients with advanced cancer ("wearable" validation).MethodsWe used eight independent datasets collected in controlled, semi-controlled, and free-living environments with different devices (primarily Android smartphones and wearable accelerometers) carried at typical body locations. Five datasets (N=103) were used for internal validation, two datasets (N=107) for manual validation, and one dataset (N=45) used for wearable validation. In each scenario, step counts were estimated using a previously published step-counting method for smartphones that uses raw sub-second level accelerometer data. We calculated mean bias and limits of agreement (LoA) between step count estimates and validation criteria using Bland-Altman analysis.ResultsIn the internal validation datasets, participants performed 751.7±581.2 (mean±SD) steps, and the mean bias was -7.2 steps (LoA -47.6, 33.3) or -0.5%. In the manual validation datasets, the ground truth step count was 367.4±359.4 steps while the mean bias was -0.4 steps (LoA -75.2, 74.3) or 0.1 %. In the wearable validation dataset, Fitbit devices indicated mean step counts of 1931.2±2338.4, while the calculated bias was equal to -67.1 steps (LoA -603.8, 469.7) or a difference of 0.3 %.ConclusionsThis study demonstrates that our open-source step counting method for smartphone data provides reliable step counts across sensor locations, measurement scenarios, and populations, including healthy adults and patients with cancer.
| S-EPMC10081434 | biostudies-literature
Project description:BackgroundConvolutional neural networks (CNNs) have been shown to be powerful tools to assist with object detection and-like a human observer-may be trained based on a relatively small cohort of reference subjects. Rapid, accurate organ recognition in medical imaging permits a variety of new quantitative diagnostic techniques. In the case of therapy with targeted radionuclides, it may permit comprehensive radiation dose analysis in a manner that would often be prohibitively time-consuming using conventional methods.MethodsAn automated image segmentation tool was developed based on three-dimensional CNNs to detect right and left kidney contours on non-contrast CT images. Model was trained based on 89 manually contoured cases and tested on a cohort of patients receiving therapy with 177Lu-prostate-specific membrane antigen-617 for metastatic prostate cancer. Automatically generated contours were compared with those drawn by an expert and assessed for similarity based on dice score, mean distance-to-agreement, and total segmented volume. Further, the contours were applied to voxel dose maps computed from post-treatment quantitative SPECT imaging to estimate renal radiation dose from therapy.ResultsNeural network segmentation was able to identify right and left kidneys in all patients with a high degree of accuracy. The system was integrated into the hospital image database, returning contours for a selected study in approximately 90?s. Mean dice score was 0.91 and 0.86 for right and left kidneys, respectively. Poor performance was observed in three patients with cystic kidneys of which only few were included in the training data. No significant difference in mean radiation absorbed dose was observed between the manual and automated algorithms.ConclusionAutomated contouring using CNNs shows promise in providing quantitative assessment of functional SPECT and possibly PET images; in this case demonstrating comparable accuracy for radiation dose interpretation in unsealed source therapy relative to a human observer.
| S-EPMC6010550 | biostudies-literature
Project description:In this study, we propose a new open-source simulation platform that comprises computer-aided design and computer-aided engineering tools for highly automated evaluation of electric field distribution and neural activation during Deep Brain Stimulation (DBS). It will be shown how a Volume Conductor Model (VCM) is constructed and examined using Python-controlled algorithms for generation, discretization and adaptive mesh refinement of the computational domain, as well as for incorporation of heterogeneous and anisotropic properties of the tissue and allocation of neuron models. The utilization of the platform is facilitated by a collection of predefined input setups and quick visualization routines. The accuracy of a VCM, created and optimized by the platform, was estimated by comparison with a commercial software. The results demonstrate no significant deviation between the models in the electric potential distribution. A qualitative estimation of different physics for the VCM shows an agreement with previous computational studies. The proposed computational platform is suitable for an accurate estimation of electric fields during DBS in scientific modeling studies. In future, we intend to acquire SDA and EMA approval. Successful incorporation of open-source software, controlled by in-house developed algorithms, provides a highly automated solution. The platform allows for optimization and uncertainty quantification (UQ) studies, while employment of the open-source software facilitates accessibility and reproducibility of simulations.
| S-EPMC7384674 | biostudies-literature
Project description:Scientists have begun using self-replicating rapid prototyper (RepRap) 3-D printers to manufacture open source digital designs of scientific equipment. This approach is refined here to develop a novel instrument capable of performing automated large-area four-point probe measurements. The designs for conversion of a RepRap 3-D printer to a 2-D open source four-point probe (OS4PP) measurement device are detailed for the mechanical and electrical systems. Free and open source software and firmware are developed to operate the tool. The OS4PP was validated against a wide range of discrete resistors and indium tin oxide (ITO) samples of different thicknesses both pre- and post-annealing. The OS4PP was then compared to two commercial proprietary systems. Results of resistors from 10 to 1 MΩ show errors of less than 1% for the OS4PP. The 3-D mapping of sheet resistance of ITO samples successfully demonstrated the automated capability to measure non-uniformities in large-area samples. The results indicate that all measured values are within the same order of magnitude when compared to two proprietary measurement systems. In conclusion, the OS4PP system, which costs less than 70% of manual proprietary systems, is comparable electrically while offering automated 100 micron positional accuracy for measuring sheet resistance over larger areas.
| S-EPMC5459207 | biostudies-other
Project description:Although there is increased interest in utilizing machine learning (ML) to support drug development, technical hurdles associated with complex algorithms have limited widespread adoption. In response, we have developed Pharm-AutoML, an open-source Python package that enables users to automate the construction of ML models and predict clinical outcomes, especially in the context of pharmacological interventions. In particular, our approach streamlines tedious steps within the ML workflow, including data preprocessing, model tuning, model selection, results analysis, and model interpretation. Moreover, our open-source package helps to identify the most predictive ML pipeline among defined search spaces by selecting the best data preprocessing strategy and tuning the ML model hyperparameters. The package currently supports multiclass classification tasks, and additional functions are being developed. Using a set of five publicly available biomedical datasets, we show that our Pharm-AutoML outperforms other ML frameworks, including H2O with default settings, by demonstrating improved predictive accuracy of classification. We further illustrate how model interpretation methods can be utilized to help explain the fine-tuned ML pipeline to end users. Pharm-AutoML provides both novice and expert users improved clinical predictions and scientific insights.
| S-EPMC8129712 | biostudies-literature
Project description:Smartphone-based sensing is becoming a convenient way to collect data in science, especially in environmental research. Recent studies that use smartphone sensing methods focus predominantly on single sensors that provide quantitative measurements. However, interdisciplinary projects call for study designs that connect both, quantitative and qualitative data gathered by smartphone sensors. Therefore, we present a novel open-source task automation solution and its evaluation in a personal exposure study with cyclists. We designed an automation script that advances the sensing process with regard to data collection, management and storage of acoustic noise, geolocation, light level, timestamp, and qualitative user perception. The benefits of this approach are highlighted based on data visualization and user handling evaluation. Even though the automation script is limited by the technical features of the smartphone and the quality of the sensor data, we conclude that task automation is a reliable and smart solution to integrate passive and active smartphone sensing methods that involve data processing and transfer. Such an application is a smart tool gathering data in population studies.
| S-EPMC6111588 | biostudies-literature
Project description:High-density Electroencephalography (HD-EEG) has proven to be the EEG montage that estimates the neural activity inside the brain with highest accuracy. Multiple studies have reported the effect of electrode number on source localization for specific sources and specific electrode configurations. The electrodes for these configurations are often manually selected to uniformly cover the entire head, going from 32 to 128 electrodes, but electrode configurations are not often selected according to their contribution to estimation accuracy. In this work, an optimization-based study is proposed to determine the minimum number of electrodes that can be used and to identify the optimal combinations of electrodes that can retain the localization accuracy of HD-EEG reconstructions. This optimization approach incorporates scalp landmark positions of widely used EEG montages. In this way, a systematic search for the minimum electrode subset is performed for single- and multiple-source localization problems. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) combined with source reconstruction methods is used to formulate a multi-objective optimization problem that concurrently minimizes (1) the localization error for each source and (2) the number of required EEG electrodes. The method can be used for evaluating the source localization quality of low-density EEG systems (e.g. consumer-grade wearable EEG). We performed an evaluation over synthetic and real EEG datasets with known ground-truth. The experimental results show that optimal subsets with 6 electrodes can attain an equal or better accuracy than HD-EEG (with more than 200 channels) for a single source case. This happened when reconstructing a particular brain activity in more than 88% of the cases in synthetic signals and 63% in real signals, and in more than 88% and 73% of cases when considering optimal combinations with 8 channels. For a multiple-source case of three sources (only with synthetic signals), it was found that optimized combinations of 8, 12 and 16 electrodes attained an equal or better accuracy than HD-EEG with 231 electrodes in at least 58%, 76%, and 82% of cases respectively. Additionally, for such electrode numbers, lower mean errors and standard deviations than with 231 electrodes were obtained.
| S-EPMC9250504 | biostudies-literature
Project description:Fluorescence microscopy is an important technique for cellular and microbiological investigations. Translating this technique onto a smartphone can enable particularly powerful applications such as on-site analysis, on-demand monitoring, and point-of-care diagnostics. Current fluorescence smartphone microscope setups require precise illumination and imaging alignment which altogether limit its broad adoption. We report a multi-color fluorescence smartphone microscope with a single contact lens-like add-on lens and slide-launched total-internal-reflection guided illumination for three common tasks in investigative fluorescence microscopy: autofluorescence, fluorescent stains, and immunofluorescence. The open-source, simple and cost-effective design has the potential for do-it-yourself fluorescence smartphone microscopy.
| S-EPMC5695954 | biostudies-literature
Project description:Background and objectiveEver since its discovery, calcium imaging has proven its worth in discovering new insights into the mechanisms of cellular communication. Yet, the analysis of the data generated by calcium imaging experiments demands a large amount of time from researchers. Tools enabling automated and semi-automated analysis are available, but often they allow automating only a part of the data analysis process. Therefore, we developed CALIMA (https://aethelraed.nl/calima), a free and open-source standalone software tool that provides an opportunity to quickly detect cells, to obtain the calcium spikes, and to determine the underlying network structure of neuronal cell cultures.MethodsOwing to the difference of Gaussians algorithm applied for the cell detection, CALIMA is able to detect regions of interest (ROIs) quickly. The z-scoring algorithm provides a means to set the requirements for spike detection, and the neuronal connections can be reconstructed by analyzing the cross-correlation between the cellular activity. We evaluated CALIMA's reliability, speed, and functionality with a special focus on neuronal cell detection and network reconstruction. The evaluation was performed by using real-life data such as a known example dataset (cultured primary rat cortical neurons, University of Pennsylvania) and by analyzing video graphic footage of in vitro brain cell samples (SH-SY5Y neuroblastoma cultures, one sample with synchronous neuron firing). The obtained results were compared to the corresponding outcomes observed on same datasets for other similar software solutions. Moreover, we compared the results of segmentation and peak detection analysis, the ones obtained using CALIMA and those acquired manually.ResultsCALIMA was able to detect the cells in the cultures within seconds. The average sensitivity was 82% across the datasets checked, comparing favorably with the alternative software solutions. Using the correct parameters, CALIMA's Ca-spikes detection sensitivity reached 96%. Lastly, neuronal networks were reconstructed by combining the data on the ROI's activity and the cell's positions, finding the most likely inter-cell connections.ConclusionsWe found that CALIMA proved to be a robust and fast tool to analyze the data of experiments for the digital reconstruction of the neuronal cellular network while being able to process the analysis steps with minimal user input required and in a time efficient manner.
| S-EPMC6718774 | biostudies-literature