Lior Drukker

Lior Drukker

Auto-generated profile, based on publicly available information

Lior Drukker

Nuffield Department of Women's & Reproductive Health, University of Oxford, Oxford, OX3 9DU, United Kingdom; Department of Obstetrics and Gynecology, Tel-Aviv University, Tel Aviv, Ramat Aviv, 69978, Israel

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
12 June 2020 in Ultrasound in Obstetrics & Gynecology
Verified
Journal Article
Open access
PDF file
LDL. Drukker
L. Drukker
JNJ. A. Noble
J. A. Noble
APA. T. Papageorghiou
A. T. Papageorghiou
Artificial intelligence (AI) uses data and algorithms to aim to draw conclusions that are as good as, or even better than, those drawn by humans. AI is already part of our daily life; it is behind face recognition technology, speech recognition in virtual assistants (such as Amazon Alexa, Apple's Siri, Google Assistant and Microsoft Cortana) and self‐driving cars. AI software has been able to beat world champions in chess, Go and recently even Poker. Relevant to our community, it is a prominent source of innovation in healthcare, already helping to develop new drugs, support clinical decisions and provide quality assurance in radiology. The list of medical image‐analysis AI applications with USA Food and Drug Administration or European Union (soon to fall under European Union Medical Device Regulation) approval is growing rapidly and covers diverse clinical needs, such as detection of arrhythmia using a smartwatch or automatic triage of critical imaging studies to the top of the radiologist's worklist. Deep learning, a leading tool of AI, performs particularly well in image pattern recognition and, therefore, can be of great benefit to doctors who rely heavily on images, such as sonologists, radiographers and pathologists. Although obstetric and gynecological ultrasound are two of the most commonly performed imaging studies, AI has had little impact on this field so far. Nevertheless, there is huge potential for AI to assist in repetitive ultrasound tasks, such as automatically identifying good‐quality acquisitions and providing instant quality assurance. For this potential to thrive, interdisciplinary communication between AI developers and ultrasound professionals is necessary. In this article, we explore the fundamentals of medical imaging AI, from theory to applicability, and introduce some key terms to medical professionals in the field of ultrasound. We believe that wider knowledge of AI will help accelerate its integration into healthcare. © 2020 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.

4 August 2015 in Transfusion
Verified
Journal Article
Closed access
PDF file
LDLior Drukker
Lior Drukker
YHYael Hants
Yael Hants
RFRivka Farkash
Rivka Farkash
RRRosa Ruchlemer
Rosa Ruchlemer
ASArnon Samueloff
Arnon Samueloff
SGSorina Grisaru‐Granovsky
Sorina Grisaru‐Granovsky

1 June 2020 in American Journal of Obstetrics and Gynecology
Verified
Journal Article
Open access
LDLior Drukker
Lior Drukker
ESEleonora Staines-Urias
Eleonora Staines-Urias
JVJosé Villar
José Villar
FBFernando C. Barros
Fernando C. Barros
MCMaria Carvalho
Maria Carvalho
APAris T. Papageorghiou
Aris T. Papageorghiou
Reference values for umbilical artery Doppler indices are used clinically to assess fetal well-being. However, many studies that have produced reference charts have important methodologic limitations, and these result in significant heterogeneity of reported reference ranges. To produce international gestational age-specific centiles for umbilical artery Doppler indices based on longitudinal data and the same rigorous methodology used in the original Fetal Growth Longitudinal Study of the INTERGROWTH-21st Project. In Phase II of the INTERGROWTH-21st Project (the INTERBIO-21st Study), we prospectively continued enrolling pregnant women according to the same protocol from 3 of the original populations in Pelotas (Brazil), Nairobi (Kenya), and Oxford (United Kingdom) that had participated in the Fetal Growth Longitudinal Study. Women with a singleton pregnancy were recruited at <14 weeks' gestation, confirmed by ultrasound measurement of crown-rump length, and then underwent standardized ultrasound every 5±1 weeks until delivery. From 22 weeks of gestation umbilical artery indices (pulsatility index, resistance index, and systolic/diastolic ratio) were measured in a blinded fashion, using identical equipment and a rigorously standardized protocol. Newborn size at birth was assessed using the international INTERGROWTH-21st Standards, and infants had detailed assessment of growth, nutrition, morbidity, and motor development at 1 and 2 years of age. The appropriateness of pooling data from the 3 study sites was assessed using variance component analysis and standardized site differences. Umbilical artery indices were modeled as functions of the gestational age using an exponential, normal distribution with second-degree fractional polynomial smoothing; goodness of fit for the overall models was assessed. Of the women enrolled at the 3 sites, 1629 were eligible for this study; 431 (27%) met the entry criteria for the construction of normative centiles, similar to the proportion seen in the original fetal growth longitudinal study. They contributed a total of 1243 Doppler measures to the analysis; 74% had 3 measures or more. The healthy low-risk status of the population was confirmed by the low rates of preterm birth (4.9%) and preeclampsia (0.7%). There were no neonatal deaths and satisfactory growth, health, and motor development of the infants at 1 and 2 years of age were documented. Only a very small proportion (2.8%-6.5%) of the variance of Doppler indices was due to between-site differences; in addition, standardized site difference estimates were marginally outside this threshold in only 1 of 27 comparisons, and this supported the decision to pool data from the 3 study sites. All 3 Doppler indices decreased with advancing gestational age. The 3rd, 5th 10th, 50th, 90th, 95th, and 97th centiles according to gestational age for each of the 3 indices are provided, as well as equations to allow calculation of any value as a centile and z scores. The mean pulsatility index according to gestational age = 1.02944 + 77.7456*(gestational age)-2 - 0.000004455*gestational age3. We present here international gestational age-specific normative centiles for umbilical artery Doppler indices produced by studying healthy, low-risk pregnant women living in environments with minimal constraints on fetal growth. The centiles complement the existing INTERGROWTH-21st Standards for assessment of fetal well-being.

13 August 2020 in BJOG: An International Journal of Obstetrics & Gynaecology
Verified
Journal Article
Closed access
PDF file
LDLior Drukker
Lior Drukker
EBE Bradburn
E Bradburn
GRGabriel B. Rodriguez
Gabriel B. Rodriguez
NRNia Wyn Roberts
Nia Wyn Roberts
LILawrence Impey
Lawrence Impey
APAris T. Papageorghiou
Aris T. Papageorghiou

1 October 2020 in Medical Image Analysis
Verified
Journal Article
Open access
YCYifan Cai
Yifan Cai
RDRichard Droste
Richard Droste
HSHarshita Sharma
Harshita Sharma
PCPierre Chatelain
Pierre Chatelain
LDLior Drukker
Lior Drukker
JNJ. Alison Noble
J. Alison Noble
We present a novel multi-task neural network called Temporal SonoEyeNet (TSEN) with a primary task to describe the visual navigation process of sonographers by learning to generate visual attention maps of ultrasound images around standard biometry planes of the fetal abdomen, head (trans-ventricular plane) and femur. TSEN has three components: a feature extractor, a temporal attention module (TAM), and an auxiliary video classification module (VCM). A soft dynamic time warping (sDTW) loss function is used to improve visual attention modelling. Variants of the model are trained on a dataset of 280 video clips, each containing one of the three biometry planes and lasting 3-7 seconds, with corresponding real-time recorded gaze tracking data of an experienced sonographer. We report the performances of the different variants of TSEN for visual attention prediction at standard biometry plane detection. The best model performance is achieved using bi-directional convolutional long-short term memory (biCLSTM) in both TAM and VCM, and it outperforms a previous spatial model on all static and dynamic saliency metrics. As an auxiliary task to validate the clinical relevance of the visual attention modelling, the predicted visual attention maps were used to guide standard biometry plane detection in consecutive US video frames. All spatio-temporal TSEN models achieve higher scores compared to a spatial-only baseline; the best performing TSEN model achieves F1 scores on these standard biometry planes of 83.7%, 89.9% and 81.1%, respectively.

27 August 2014 in Acta Obstetricia et Gynecologica Scandinavica
Verified
Journal Article
Closed access
PDF file
LDLior Drukker
Lior Drukker
YHYael Hants
Yael Hants
ESEinav Sharon
Einav Sharon
Hen Y SelaHen Y Sela
Hen Y Sela
SGSorina Grisaru‐Granovsky
Sorina Grisaru‐Granovsky