A5087127737- Digital Imaging for Blood Diseases
- Neurobiology and Insect Physiology Research
- Mosquito-borne diseases and control
- Malaria Research and Control
- Insect Pheromone Research and Control
- Insect and Arachnid Ecology and Behavior
- Cell Image Analysis Techniques
- Plant and animal studies
- Fiscal Policies and Political Economy
- Probabilistic and Robust Engineering Design
- Neural Networks and Applications
- Species Distribution and Climate Change
- Model Reduction and Neural Networks
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- COVID-19 diagnosis using AI
- Electoral Systems and Political Participation
- Machine Learning and Data Classification
- Microfluidic and Bio-sensing Technologies
- Gaussian Processes and Bayesian Inference
- Machine Learning in Healthcare
- Animal and Plant Science Education
- Parasites and Host Interactions
- Phonocardiography and Auscultation Techniques
- Global Health and Surgery
Bellevue Hospital Center
2014-2023
Intellectual Ventures (United States)
2014-2023
University of Washington
2012-2022
University of Washington Applied Physics Laboratory
2020-2022
Applied Mathematics (United States)
2020
Seattle University
2014-2019
Automated data-driven modeling, the process of directly discovering governing equations a system from data, is increasingly being used across scientific community. PySINDy Python package that provides tools for applying sparse identification nonlinear dynamics (SINDy) approach to model discovery. In this major update PySINDy, we implement several advanced features enable discovery more general differential noisy and limited data. The library candidate terms extended actuated systems, partial...
The optical microscope remains a widely-used tool for diagnosis and quantitation of malaria. An automated system that can match the performance well-trained technicians is motivated by shortage trained microscopists. We have developed computer vision leverages deep learning to identify malaria parasites in micrographs standard, field-prepared thick blood films. prototype application diagnoses P. falciparum with sufficient accuracy achieve competency level 1 World Health Organization external...
Microscopic examination of Giemsa-stained blood films remains a major form diagnosis in malaria case management, and is reference standard for research. However, as with other visualization-based diagnoses, accuracy depends on individual technician performance, making standardization difficult reliability poor. Automated image recognition based machine-learning, utilizing convolutional neural networks, offers potential to overcome these drawbacks. A prototype digital microscope device...
Abstract Background Microscopic examination of Giemsa-stained blood films remains the reference standard for malaria parasite detection and quantification, but is undermined by difficulties in ensuring high-quality manual reading inter-reader reliability. Automated quantification may address this issue. Methods A multi-centre, observational study was conducted during 2018 2019 at 11 sites to assess performance EasyScan Go, a microscopy device employing machine-learning-based image analysis....
Abstract Background Manual microscopy remains a widely-used tool for malaria diagnosis and clinical studies, but it has inconsistent quality in the field due to variability training practices. Automated diagnostic systems based on machine learning hold promise improve reproducibility of microscopy. The World Health Organization (WHO) designed 55-slide set (WHO 55) their External Competence Assessment Malaria Microscopists (ECAMM) programme, which can also serve as valuable benchmark...
We consider the data-driven discovery of governing equations from time-series data in limit high noise. The algorithms developed describe an extensive toolkit methods for circumventing deleterious effects noise context <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sparse identification nonlinear dynamics</i> (SINDy) framework. offer two primary contributions, both focused on noisy acquired a system <inline-formula...
Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children’s lives. However, current ML efforts largely neglect crucial use case constraints are thus not clinically useful. Two factors in particular to developing translatable clinical field settings: (i) clear understanding the needs that solutions must accommodate; (ii) task-relevant metrics guiding evaluating models. Neglect these has seriously...
The optical microscope is one of the most widely used tools for diagnosing infectious diseases in developing world. Due to its reliance on trained microscopists, field microscopy often suffers from poor sensitivity, specificity, and reproducibility. goal this work, called Autoscope, a low-cost automated digital coupled with set computer vision classification algorithms, which can accurately diagnose variety diseases, targeting use-cases Our initial target malaria, because high difficulty...
The haemozoin crystal continues to be investigated extensively for its potential as a biomarker malaria diagnostics. In order valuable biomarker, it must present in detectable quantities the peripheral blood and distinguishable from false positives. Here, dark-field microscopy coupled with sophisticated image processing algorithms is used characterize abundance of within infected erythrocytes field samples determine window detection blood. Thin smears Plasmodium falciparum-infected...
Ultrasound (US) imaging holds promise as a low-cost versatile, non-invasive point-of-care diagnostic modality in low-and middle-income countries (LMICs). Still, lung US can be challenging to interpret because air bronchograms are anechoic and the images mostly contain artifacts rather than anatomy. To help overcome these barriers, advances computer vision machine learning (ML) provide tools automatically recognize abnormal features, offering valuable information healthcare workers for...
Abstract Schistosomiasis currently affects over 250 million people and remains a public health burden despite ongoing global control efforts. Conventional microscopy is practical tool for diagnosis screening of Schistosoma haematobium , but identification eggs requires skilled microscopist. Here we present machine learning (ML)-based strategy automated detection S. that combines two imaging contrasts, brightfield (BF) darkfield (DF), to improve diagnostic performance. We collected BF DF...
Accurate diagnostics are essential for disease control and elimination efforts. However, access to neglected tropical diseases (NTDs) is hindered by limited healthcare infrastructure in many NTD-endemic regions, as well reliance on time- labor-intensive diagnostic methods, such smear microscopy. New tools that portable, rapid, low-cost, meet World Health Organization (WHO) sensitivity specificity targets urgently needed accelerate NTD programs. Here, we introduce the NTDscope, a portable...
The insect olfactory system, which includes the antennal lobe (AL), mushroom body (MB), and ancillary structures, is a relatively simple neural system capable of learning. Its structural features, are widespread in biological systems, process stimuli through cascade networks where large dimension shifts occur from stage to sparsity randomness play critical role coding. Learning partly enabled by neuromodulatory reward mechanism octopamine stimulation AL, whose increased activity induces...
A capillary flow driven microfluidic system for the generation and staining of thin thick blood smears prior to microscopy is presented.
Introduction Light microscopy remains a standard method for detection of malaria parasites in clinical cases but training to expert level requires considerable time. Moreover, excessive workflow causes fatigue and can impact performance. An automated tool could aid clinics with limited access highly skilled microscopists, where case numbers are excessive, or multi-site studies consistency is essential. The EasyScan GO an scanning microscope combined machine learning software designed detect...
Malaria is a life-threatening disease affecting millions. Microscopy-based assessment of thin blood films standard method to (i) determine malaria species and (ii) quantitate high-parasitemia infections. Full automation microscopy by machine learning (ML) challenging task because field-prepared slides vary widely in quality presentation, artifacts often heavily outnumber relatively rare parasites. In this work, we describe complete, fully-automated framework for film analysis that applies ML...
Malaria is a life-threatening disease affecting millions. Microscopy-based assessment of thin blood films standard method to (i) determine malaria species and (ii) quantitate high-parasitemia infections. Full automation microscopy by machine learning (ML) challenging task because field-prepared slides vary widely in quality presentation, artifacts often heavily outnumber relatively rare parasites. In this work, we describe complete, fully-automated framework for film analysis that applies ML...
Enabling end-users of Augmentative and Alternative Communication (AAC) systems to add personalized video content at runtime holds promise for improving communication, but the requirements such are as yet unclear. To explore this issue, we present Vid2Speech, a prototype AAC system children with complex communication needs (CCN) that uses enhance representations action words. We describe three design goals guided integration in our early-stage prototype: 1) Providing social-temporal...