Yoav Binenbaum

Yoav Binenbaum

Auto-generated profile, based on publicly available information

Yoav Binenbaum

The Wyss Institute for Biologically Inspired Engineering, Harvard University, Cambridge, Massachusetts, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
3 June 2024 in Nature Biomedical Engineering
Verified
Journal Article
Closed access
PDF file
DZDavid K. Y. Zhang
David K. Y. Zhang
JBJoshua M. Brockman
Joshua M. Brockman
KAKwasi Adu-Berchie
Kwasi Adu-Berchie
YLYutong Liu
Yutong Liu
YBYoav Binenbaum
Yoav Binenbaum
DMDavid J. Mooney
David J. Mooney

20 December 2024 in Communications Medicine
Verified
Journal Article
Open access
PDF file
GSGil Shamai
Gil Shamai
RSRan Schley
Ran Schley
ACAlexandra Cretu
Alexandra Cretu
TNTal Neoran
Tal Neoran
ESEdmond Sabo
Edmond Sabo
RKRon Kimmel
Ron Kimmel
Background Molecular profiling of estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (also known as Her2) is essential for breast cancer diagnosis and treatment planning. Nevertheless, current methods rely on the qualitative interpretation of immunohistochemistry and fluorescence in situ hybridization (FISH), which can be costly, time-consuming, and inconsistent. Here we explore the clinical utility of predicting receptor status from digitized hematoxylin and eosin-stained (H&E) slides using machine learning trained and evaluated on a multi-institutional dataset. Methods We developed a deep learning system to predict ER, PR, and ERBB2 statuses from digitized H&E slides and evaluated its utility in three clinical applications: identifying hormone receptor-positive patients, serving as a second-read tool for quality assurance, and addressing intratumor heterogeneity. For development and validation, we collected 19,845 slides from 7,950 patients across six independent cohorts representative of diverse clinical settings. Results Here we show that the system identifies 30.5% of patients as hormone receptor-positive, achieving a specificity of 0.9982 and a positive predictive value of 0.9992, demonstrating its ability to determine eligibility for hormone therapy without immunohistochemistry. By restaining and reassessing samples flagged as potential false negatives, we discover 31 cases of misdiagnosed ER, PR, and ERBB2 statuses. Conclusions These findings demonstrate the utility of the system in diverse clinical settings and its potential to improve breast cancer diagnosis. Given the substantial focus of current guidelines on reducing false negative diagnoses, this study supports the integration of H&E-based machine learning tools into workflows for quality assurance.

1 December 2019 in Transplantation and Cellular Therapy
Verified
Journal Article
Open access
SBSzilvia Baron
Szilvia Baron
YBYoav Binenbaum
Yoav Binenbaum
SASivan Berger Achituv
Sivan Berger Achituv
YTYael Tene
Yael Tene
RERonit Elhasid
Ronit Elhasid
Impaired neutrophil extracellular trap (NET) formation compromises the host defense after engraftment following hematopoietic stem cell transplantation (HSCT) despite adequate neutrophil counts. The aims of the present study were to determine reference ranges for the activity of key enzymes of NET formation-neutrophil elastase (NE) and myeloperoxidase (MPO)-in a healthy population and to unravel the recovery dynamics of NET formation over time following HSCT, along with NE and MPO enzymatic activities. Reference ranges of NE and MPO activity were derived from 50 healthy volunteers. During 2017 to 2018, 11 consecutive pediatric patients undergoing allogeneic or autologous HSCT were recruited at a single referral center for pediatric hemato-oncology. Patients were followed for up to 1 year following engraftment. The mean reference value was 7.5 ± .4 mU for NE activity and 2.17 ± .4 U for MPO activity in the healthy population, and enzymatic activity of MPO was significantly higher in males. At 3 weeks following neutrophil engraftment, all study participants demonstrated extremely low enzymatic NE activity, whereas MPO activity was above the lower normal reference range at all time points. Reduced NE activity corresponded to the inability to form NETs. Neutrophil function improved over time, but partial impairment persisted for 7 months following transplantation. The ability of neutrophils to form NETs was significantly impaired for 3 weeks after engraftment in the setting of HSCT, exposing patients to bacterial infections. NE activity might serve as a surrogate marker for the capacity of neutrophils to form NETs.

26 September 2017 in Physics of Plasmas
Verified
Journal Article
Closed access
YSYa. Z. Slutsker
Ya. Z. Slutsker
VSV. E. Semenov
V. E. Semenov
Yakov KrasikYakov Krasik
Yakov Krasik
MRM. A. Ryzhkov
M. A. Ryzhkov
JFJ. Felsteiner
J. Felsteiner
JCJ. T. Cohen
J. T. Cohen
We present an analytical model of cold atmospheric plasma formed by a dielectric barrier discharge (DBD), which is based on the lumped and distributed elements of an equivalent electric circuit of this plasma. This model is applicable for a wide range of frequencies and amplitudes of the applied voltage pulses, no matter whether or not the generated plasma plume interacts with a target. The model allows quantitative estimation of the plasma plume length and the energy delivered to the plasma. Also, the results of this model can be used for the design of DBD guns which efficiently generate cold atmospheric plasma. A comparison of the results of the model with those obtained in experiments shows a fairly good agreement.

5 May 2026 in Advanced Materials
Verified
Journal Article
Open access
PDF file
WJWei‐Hung Jung
Wei‐Hung Jung
EHEmie Humann
Emie Humann
JPJoshua M. Price
Joshua M. Price
YBYoav Binenbaum
Yoav Binenbaum
AHAzra Haseki
Azra Haseki
DMDavid J. Mooney
David J. Mooney
The tumor microenvironment shapes immune surveillance through its mechanical properties, yet the role of matrix viscoelasticity remains unclear. Here, we used a tunable collagen system that models human tissue viscoelasticity to define how matrix relaxation directs dendritic cell (DC) behavior. Slow‐relaxing, elastic networks restrict actomyosin‐driven remodeling, limiting DC motility and reducing DC‐T cell encounters and activation. Blocking DC migration in fast‐relaxing matrices recapitulated key aspects of the impaired T cell priming seen in elastic networks, identifying migration as a mechanical checkpoint for immune activation. Prolonged confinement in elastic matrices induced a mechanomemory state, locking DCs into a state of reduced motility and altered chromatin accessibility. Studies using patient‐derived ependymoma samples confirmed these findings, establishing viscoelastic relaxation as a key physical regulator of immune priming. Together, this tunable viscoelastic platform provides a defined, human‐relevant model to dissect and model mechanical control of immunity for therapeutic design.

21 May 2025 in Pediatric Blood & Cancer
Verified
Journal Article
Open access
APArkadi Piven
Arkadi Piven
GSGil Shamai
Gil Shamai
SESarah Elitzur
Sarah Elitzur
GBGalit Pinto Berger
Galit Pinto Berger
YBYoav Binenbaum
Yoav Binenbaum
RERonit Elhasid
Ronit Elhasid
Background: Accurate determination of B/T‐cell lineage and the presence of the ETV6–RUNX1 translocation is critical for diagnosing acute lymphoblastic leukemia (ALL), as these factors influence treatment decisions and outcomes. However, these diagnostic processes often rely on advanced tools unavailable in low‐resource settings, creating a need for alternative solutions.Procedure: We developed a deep learning pipeline to analyze Giemsa‐stained bone marrow (BM) aspirate smears. The models were trained to distinguish between ALL, acute myeloid leukemia (AML), and non‐leukemic BM samples, predict B‐ and T‐cell lineage in ALL, and detect the presence of the ETV6–RUNX1 translocation. The performance was evaluated using cross‐validation (CV) and an external validation cohort.Results: The models achieved a statistically significant area under the curve (AUC) of 0.99 in distinguishing ALL from AML and control samples. In cross‐validation (CV), the models achieved a cross‐validation AUC of 0.74 for predicting B/T subtypes. For predicting ETV6–RUNX1 translocation, the models achieved an AUC of 0.80. External cohort validation confirmed significant AUCs of 0.72 for B/T subtype classification and 0.69 for ETV6–RUNX1 translocation prediction.Conclusions: Convolutional neural networks (CNNs) demonstrate potential as a diagnostic tool for pediatric ALL, enabling the identification of B/T lineage and ETV6–RUNX1 translocation from Giemsa‐stained smears. These results pave the way for future utilization of CNNs as a diagnostic modality for pediatric leukemia in low‐resource settings, where access to advanced diagnostic techniques is limited.