Katy Blumer

Katy Blumer

Auto-generated profile, based on publicly available information

Katy Blumer

Google Research, Google, LLC, Mountain View, California

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 February 2018 in Nature Biomedical Engineering
Verified
Journal Article
Closed access
PDF file
RPRyan Poplin
Ryan Poplin
AVAvinash V. Varadarajan
Avinash V. Varadarajan
KBKaty Blumer
Katy Blumer
YLYun Liu
Yun Liu
MMMichael V. McConnell
Michael V. McConnell
DWDale R. Webster
Dale R. Webster

1 April 2019 in Ophthalmology
Verified
Journal Article
Open access
RSRory Sayres
Rory Sayres
ATAnkur Taly
Ankur Taly
EREhsan Rahimy
Ehsan Rahimy
KBKaty Blumer
Katy Blumer
DCDavid Coz
David Coz
DWDale R. Webster
Dale R. Webster
To understand the impact of deep learning diabetic retinopathy (DR) algorithms on physician readers in computer-assisted settings. Evaluation of diagnostic technology. One thousand seven hundred ninety-six retinal fundus images from 1612 diabetic patients. Ten ophthalmologists (5 general ophthalmologists, 4 retina specialists, 1 retina fellow) read images for DR severity based on the International Clinical Diabetic Retinopathy disease severity scale in each of 3 conditions: unassisted, grades only, or grades plus heatmap. Grades-only assistance comprised a histogram of DR predictions (grades) from a trained deep-learning model. For grades plus heatmap, we additionally showed explanatory heatmaps. For each experiment arm, we computed sensitivity and specificity of each reader and the algorithm for different levels of DR severity against an adjudicated reference standard. We also measured accuracy (exact 5-class level agreement and Cohen's quadratically weighted κ), reader-reported confidence (5-point Likert scale), and grading time. Readers graded more accurately with model assistance than without for the grades-only condition (P < 0.001). Grades plus heatmaps improved accuracy for patients with DR (P < 0.001), but reduced accuracy for patients without DR (P = 0.006). Both forms of assistance increased readers' sensitivity moderate-or-worse DR: unassisted: mean, 79.4% [95% confidence interval (CI), 72.3%-86.5%]; grades only: mean, 87.5% [95% CI, 85.1%-89.9%]; grades plus heatmap: mean, 88.7% [95% CI, 84.9%-92.5%] without a corresponding drop in specificity (unassisted: mean, 96.6% [95% CI, 95.9%-97.4%]; grades only: mean, 96.1% [95% CI, 95.5%-96.7%]; grades plus heatmap: mean, 95.5% [95% CI, 94.8%-96.1%]). Algorithmic assistance increased the accuracy of retina specialists above that of the unassisted reader or model alone; and increased grading confidence and grading time across all readers. For most cases, grades plus heatmap was only as effective as grades only. Over the course of the experiment, grading time decreased across all conditions, although most sharply for grades plus heatmap. Deep learning algorithms can improve the accuracy of, and confidence in, DR diagnosis in an assisted read setting. They also may increase grading time, although these effects may be ameliorated with experience.

1 June 2018 in Investigative Ophthalmology & Visual Science
Verified
Journal Article
Open access
PDF file
AVAvinash V. Varadarajan
Avinash V. Varadarajan
RPRyan Poplin
Ryan Poplin
KBKaty Blumer
Katy Blumer
CAChristof Angermueller
Christof Angermueller
JLJoe Ledsam
Joe Ledsam
DWDale R. Webster
Dale R. Webster
Purpose: We evaluate how deep learning can be applied to extract novel information such as refractive error from retinal fundus imaging. Methods: Retinal fundus images used in this study were 45- and 30-degree field of view images from the UK Biobank and Age-Related Eye Disease Study (AREDS) clinical trials, respectively. Refractive error was measured by autorefraction in UK Biobank and subjective refraction in AREDS. We trained a deep learning algorithm to predict refractive error from a total of 226,870 images and validated it on 24,007 UK Biobank and 15,750 AREDS images. Our model used the “attention” method to identify features that are correlated with refractive error. Results: The resulting algorithm had a mean absolute error (MAE) of 0.56 diopters (95% confidence interval [CI]: 0.55–0.56) for estimating spherical equivalent on the UK Biobank data set and 0.91 diopters (95% CI: 0.89–0.93) for the AREDS data set. The baseline expected MAE (obtained by simply predicting the mean of this population) was 1.81 diopters (95% CI: 1.79–1.84) for UK Biobank and 1.63 (95% CI: 1.60–1.67) for AREDS. Attention maps suggested that the foveal region was one of the most important areas used by the algorithm to make this prediction, though other regions also contribute to the prediction. Conclusions: To our knowledge, the ability to estimate refractive error with high accuracy from retinal fundus photos has not been previously known and demonstrates that deep learning can be applied to make novel predictions from medical images.

7 August 2015 in Journal of Materials Chemistry B
Verified
Journal Article
Closed access
PDF file
FBF. Benyettou
F. Benyettou
RRR. Rezgui
R. Rezgui
FRF. Ravaux
F. Ravaux
TJT. Jaber
T. Jaber
KBK. Blumer
K. Blumer
ATA. Trabolsi
A. Trabolsi
We present the synthesis of a silver nanoparticle (AgNP) based drug-delivery system that achieves the simultaneous intracellular delivery of doxorubicin (Dox) and alendronate (Ald) and improves the anticancer therapeutic indices of both drugs. Water, under microwave irradiation, was used as the sole reducing agent in the size-controlled, bisphosphonate-mediated synthesis of stabilized AgNPs. AgNPs were coated with the bisphosphonate Ald, which templated nanoparticle formation and served as a site for drug attachment. The unreacted primary ammonium group of Ald remained free and was subsequently functionalized with either Rhodamine B (RhB), through amide formation, or Dox, through imine formation. The RhB-conjugated NPs (RhB–Ald@AgNPs) were studied in HeLa cell culture. Experiments involving the selective inhibition of cell membrane receptors were monitored by confocal fluorescence microscopy and established that macropinocytosis and clathrin-mediated endocytosis were the main mechanisms of cellular uptake. The imine linker of the Dox-modified nanoparticles (Dox–Ald@AgNPs) was exploited for acid-mediated intracellular release of Dox. We found that Dox–Ald@AgNPs had significantly greater anti-cancer activity in vitro than either Ald or Dox alone. Ald@AgNPs can accommodate the attachment of other drugs as well as targeting agents and therefore constitute a general platform for drug delivery.

1 July 2016 in Biochimica et Biophysica Acta (BBA) - Biomembranes
Verified
Journal Article
Open access
RRRachid Rezgui
Rachid Rezgui
KBKaty Blumer
Katy Blumer
GYGilbert Yeoh-Tan
Gilbert Yeoh-Tan
ATAdam J. Trexler
Adam J. Trexler
MMMazin Magzoub
Mazin Magzoub
Cell-penetrating peptides (CPPs) have emerged as a potentially powerful tool for drug delivery due to their ability to efficiently transport a whole host of biologically active cargoes into cells. Although concerted efforts have shed some light on the cellular internalization pathways of CPPs, quantification of CPP uptake has proved problematic. Here we describe an experimental approach that combines two powerful biophysical techniques, fluorescence-activated cell sorting (FACS) and fluorescence correlation spectroscopy (FCS), to directly, accurately and precisely measure the cellular uptake of fluorescently-labeled molecules. This rapid and technically simple approach is highly versatile and can readily be applied to characterize all major CPP properties that normally require multiple assays, including amount taken up by cells (in moles/cell), uptake efficiency, internalization pathways, intracellular distribution, intracellular degradation and toxicity threshold. The FACS-FCS approach provides a means for quantifying any intracellular biochemical entity, whether expressed in the cell or introduced exogenously and transported across the plasma membrane.

1 April 2016 in Nucleic Acids Research
Verified
Journal Article
Open access
PDF file
SNStefan Niekamp
Stefan Niekamp
KBKaty Blumer
Katy Blumer
PNParsa M. Nafisi
Parsa M. Nafisi
KTKathy Tsui
Kathy Tsui
JGJohn Garbutt
John Garbutt
SDShawn Douglas
Shawn Douglas
Scalable production of DNA nanostructures remains a substantial obstacle to realizing new applications of DNA nanotechnology. Typical DNA nanostructures comprise hundreds of DNA oligonucleotide strands, where each unique strand requires a separate synthesis step. New design methods that reduce the strand count for a given shape while maintaining overall size and complexity would be highly beneficial for efficiently producing DNA nanostructures. Here, we report a method for folding a custom template strand by binding individual staple sequences to multiple locations on the template. We built several nanostructures for well-controlled testing of various design rules, and demonstrate folding of a 6-kb template by as few as 10 unique strand sequences binding to 10 ± 2 locations on the template strand.