LDLior Drukker

Lior Drukker

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lior Drukker has a total of 166 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ScanAhead: Simplifying standard plane acquisition of fetal head ultrasound

    by Qianhui Men, He Zhao, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble


  • Intrahepatic portosystemic shunt: salvage mechanism for oligohydramnios complicating fetal growth restriction

    by Y. Gilboa, L. Drukker, J. Bar, D. Berbing‐Goldstein, Y. Geron, Y. Mozer Glassberg, E. Hadar, R. Charach, R. Bardin

    Objective: Portosystemic shunts in growth‐restricted fetuses are more common than previously thought. We aimed to describe fetuses with growth restriction and transient oligohydramnios in which a congenital intrahepatic portosystemic shunt (CIPSS) was noted during follow‐up. Methods: This was a retrospective study of all fetuses diagnosed with growth restriction and transient oligohydramnios during a 5‐year period in a large tertiary referral center. Our routine evaluation of growth‐restricted fetuses includes monitoring of estimated fetal weight, assessment of biophysical profile, Doppler imaging, thorough examination of the umbilical–portal system and evaluation of cardiac function using fetal tricuspid annular plane systolic excursion (f‐TAPSE). We compared these parameters before and after the resolution of the oligohydramnios using descriptive statistics and the Wilcoxon signed‐rank test for paired non‐parametric variables. During the surveillance of fetuses with transient oligohydramnios, we noted the appearance of a CIPSS and followed up such cases after birth. Results: A total of 2144 women with a singleton pregnancy with suspected fetal growth restriction were referred to our center between January 2018 and December 2022. In 12 fetuses, oligohydramnios was evident upon initial assessment, and a CIPSS was diagnosed with normalization of amniotic fluid level. The median gestational age at diagnosis of growth restriction and oligohydramnios was 25 (range, 21–30) weeks. The estimated fetal weight was at the 1 st percentile in 10/12 fetuses. The median amniotic fluid index was 5 (range, 2–5) cm at the initial appointment and improved significantly to 13 (range, 11–20) cm following the shunt diagnosis ( P = 0.002). Among fetuses with f‐TAPSE data available, the f‐TAPSE increased significantly from 4.0 (range, 3.0–5.0) mm before the diagnosis of CIPSS to 8.0 (range, 5.0–9.4) mm following the diagnosis ( P = 0.043). The median gestational age at delivery was 36.3 (range, 30.8–38.4) weeks. In nine (75%) fetuses, the diagnosed shunt was left portal to left hepatic vein. Neonatal follow‐up revealed spontaneous shunt resolution within 30 months in all newborns. One newborn required embolization owing to suspected shunt, however, no shunt was detected during the procedure. Conclusions: The development of CIPSS in growth‐restricted fetuses with oligohydramnios appears to improve hemodynamic status as evidenced by normalization of amniotic fluid index and increase in f‐TAPSE. Evaluation of the liver portal system in fetuses with growth restriction offers an understanding of the shunt salvage phenomenon. © 2025 International Society of Ultrasound in Obstetrics and Gynecology.


  • Open Access

    Predictive capacity of fetal pancreatic circumference for gestational diabetes mellitus

    by Y. Gilboa, Y. Geron, S. Perlman, L. Drukker, K. Ofir, A. Ellert, R. Bardin, R. Achiron, Z. Kivilevitch

    Objective: To assess the capacity of fetal pancreatic size, before standard blood glucose testing for screening and diagnosis, to predict maternal gestational diabetes mellitus (GDM).Methods: This was a retrospective cohort study of low‐risk pregnant women recruited during routine second‐trimester fetal anatomical screening at 20–25 weeks' gestation at two ultrasound units in Israel between 2017 and 2020. The predictive performance of fetal pancreatic circumference ≥ 80th and ≥ 90th centiles and glucose challenge test (GCT) was examined for the outcome of GDM. The independent‐samples t‐test was used to compare mean pancreatic circumference centile between pregnancies with GDM and those without GDM. Diagnostic performance was evaluated with 2 × 2 contingency tables and receiver‐operating‐characteristics (ROC) curves.Results: Overall, 195 women were selected for statistical analysis. Twenty‐four (12.3%) women were diagnosed subsequently with GDM. The mean ± SD fetal pancreatic circumference centile was significantly higher in the GDM group compared with the non‐GDM group (82.4 ± 14.6 vs 62.8 ± 27.6; P < 0.001). The pancreatic circumference centile was correlated positively with the estimated fetal weight centile (Pearson's coefficient, 0.243; P = 0.001). The 80th centile cut‐off for pancreatic circumference had the highest sensitivity (70.8%) and positive predictive value (23.3%) for future maternal GDM, with the best trade‐off between sensitivity and specificity achieved at the 75th centile cut‐off (sensitivity, 79%; specificity, 60%). The GCT had better specificity (90.2%) and negative predictive value (97.9%) compared with both cut‐offs in pancreatic circumference. The area under the ROC curve was higher for pancreatic circumference compared with GCT (0.71 vs 0.64) and only the former was statistically significant (P = 0.001).Conclusions: Fetal pancreatic circumference has a higher positive predictive capacity compared with GCT. Measuring pancreatic circumference can identify pregnancies at high risk for maternal GDM, thereby promoting earlier diagnosis and treatment, decreasing the time period during which the fetus is exposed to high maternal glucose levels and improving infant outcome. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.


  • The Holy Grail of obstetric ultrasound: can artificial intelligence detect hard‐to‐identify fetal cardiac anomalies?

    by L. Drukker

    Linked article: This Editorial comments on articles by Day et al. and Taksøe‐Vester et al.


  • Open Access

    Automating the Human Action of First-Trimester Biometry Measurement from Real-World Freehand Ultrasound

    by Robail Yasrab, He Zhao, Zeyu Fu, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble


  • Open Access

    EP02.22: ISUOG 2022 international trainee survey: evaluation by N‐GEN committee of current and future ultrasound training opportunities

    by S. Murugesu, H. Meehan, J. Miranda, A. Dall'Asta, D. L. Rolnik, L. Drukker, M. M. Acda, M. Al‐Memar, T. Amin, M. Leonardi, et al.

  • Open Access

    Gaze-probe joint guidance with multi-task learning in obstetric ultrasound scanning

    by Qianhui Men, Clare Teng, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble


  • Open Access

    Memory-based unsupervised video clinical quality assessment with multi-modality data in fetal ultrasound

    by He Zhao, Qingqing Zheng, Clare Teng, Robail Yasrab, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble


  • Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound

    by Zeyu Fu, Jianbo Jiao, Robail Yasrab, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble

    Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pair sampling in a contrastive learning manner. The proposed approach is demonstrated for automated fetal ultrasound imaging tasks, enabling the positive pairs from the same or different ultrasound scans that are anatomically similar to be pulled together and thus improving the representation learning. We empirically investigate the effect of inclusion of anatomy information with coarse- and fine-grained granularity, for contrastive learning and find that learning with fine-grained anatomy information which preserves intra-class difference is more effective than its counterpart. We also analyze the impact of anatomy ratio on our AWCL framework and find that using more distinct but anatomically similar samples to compose positive pairs results in better quality representations. Experiments on a large-scale fetal ultrasound dataset demonstrate that our approach is effective for learning representations that transfer well to three clinical downstream tasks, and achieves superior performance compared to ImageNet supervised and the current state-of-the-art contrastive learning methods. In particular, AWCL outperforms ImageNet supervised method by 13.8% and state-of-the-art contrastive-based method by 7.1% on a cross-domain segmentation task. Keywords Representation learning Contrastive learning Ultrasound


  • A Machine Learning Method for Automated Description and Workflow Analysis of First Trimester Ultrasound Scans

    by Robail Yasrab, Zeyu Fu, He Zhao, Lok Hin Lee, Harshita Sharma, Lior Drukker, Aris T Papageorgiou, J. Alison Noble

    Obstetric ultrasound assessment of fetal anatomy in the first trimester of pregnancy is one of the less explored fields in obstetric sonography because of the paucity of guidelines on anatomical screening and availability of data. This paper, for the first time, examines imaging proficiency and practices of first trimester ultrasound scanning through analysis of full-length ultrasound video scans. Findings from this study provide insights to inform the development of more effective user-machine interfaces, of targeted assistive technologies, as well as improvements in workflow protocols for first trimester scanning. Specifically, this paper presents an automated framework to model operator clinical workflow from full-length routine first-trimester fetal ultrasound scan videos. The 2D+t convolutional neural network-based architecture proposed for video annotation incorporates transfer learning and spatio-temporal (2D+t) modelling to automatically partition an ultrasound video into semantically meaningful temporal segments based on the fetal anatomy detected in the video. The model results in a cross-validation A1 accuracy of 96.10%, F1 = 0.95, precision = 0.94 and recall = 0.95. Automated semantic partitioning of unlabelled video scans (n=250) achieves a high correlation with expert annotations (ρ = 0.95, p = 0.06). Clinical workflow patterns, operator skill and its variability can be derived from the resulting representation using the detected anatomy labels, order, and distribution. It is shown that nuchal translucency (NT) is the toughest standard plane to acquire and most operators struggle to localize high-quality frames. Furthermore, it is found that newly qualified operators spend 25.56% more time on key biometry tasks than experienced operators.