1
|
Lang O, Yaya-Stupp D, Traynis I, Cole-Lewis H, Bennett CR, Lyles CR, Lau C, Irani M, Semturs C, Webster DR, Corrado GS, Hassidim A, Matias Y, Liu Y, Hammel N, Babenko B. Using generative AI to investigate medical imagery models and datasets. EBioMedicine 2024; 102:105075. [PMID: 38565004 PMCID: PMC10993140 DOI: 10.1016/j.ebiom.2024.105075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 03/05/2024] [Accepted: 03/06/2024] [Indexed: 04/04/2024] Open
Abstract
BACKGROUND AI models have shown promise in performing many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust of doctors in AI-based models, especially in domains where AI prediction capabilities surpass those of humans. Moreover, such explanations could enable novel scientific discovery by uncovering signals in the data that aren't yet known to experts. METHODS In this paper, we present a workflow for generating hypotheses to understand which visual signals in images are correlated with a classification model's predictions for a given task. This approach leverages an automatic visual explanation algorithm followed by interdisciplinary expert review. We propose the following 4 steps: (i) Train a classifier to perform a given task to assess whether the imagery indeed contains signals relevant to the task; (ii) Train a StyleGAN-based image generator with an architecture that enables guidance by the classifier ("StylEx"); (iii) Automatically detect, extract, and visualize the top visual attributes that the classifier is sensitive towards. For visualization, we independently modify each of these attributes to generate counterfactual visualizations for a set of images (i.e., what the image would look like with the attribute increased or decreased); (iv) Formulate hypotheses for the underlying mechanisms, to stimulate future research. Specifically, present the discovered attributes and corresponding counterfactual visualizations to an interdisciplinary panel of experts so that hypotheses can account for social and structural determinants of health (e.g., whether the attributes correspond to known patho-physiological or socio-cultural phenomena, or could be novel discoveries). FINDINGS To demonstrate the broad applicability of our approach, we present results on eight prediction tasks across three medical imaging modalities-retinal fundus photographs, external eye photographs, and chest radiographs. We showcase examples where many of the automatically-learned attributes clearly capture clinically known features (e.g., types of cataract, enlarged heart), and demonstrate automatically-learned confounders that arise from factors beyond physiological mechanisms (e.g., chest X-ray underexposure is correlated with the classifier predicting abnormality, and eye makeup is correlated with the classifier predicting low hemoglobin levels). We further show that our method reveals a number of physiologically plausible, previously-unknown attributes based on the literature (e.g., differences in the fundus associated with self-reported sex, which were previously unknown). INTERPRETATION Our approach enables hypotheses generation via attribute visualizations and has the potential to enable researchers to better understand, improve their assessment, and extract new knowledge from AI-based models, as well as debug and design better datasets. Though not designed to infer causality, importantly, we highlight that attributes generated by our framework can capture phenomena beyond physiology or pathophysiology, reflecting the real world nature of healthcare delivery and socio-cultural factors, and hence interdisciplinary perspectives are critical in these investigations. Finally, we will release code to help researchers train their own StylEx models and analyze their predictive tasks of interest, and use the methodology presented in this paper for responsible interpretation of the revealed attributes. FUNDING Google.
Collapse
Affiliation(s)
| | | | - Ilana Traynis
- Work Done at Google Via Advanced Clinical, Deerfield, IL, USA
| | | | | | - Courtney R Lyles
- Google, Mountain View, CA, USA; University of California San Francisco, Department of Medicine, San Francisco, CA, USA
| | | | | | | | | | | | | | | | - Yun Liu
- Google, Mountain View, CA, USA
| | | | | |
Collapse
|
2
|
Gaziv G, Beliy R, Granot N, Hoogi A, Strappini F, Golan T, Irani M. Self-supervised Natural Image Reconstruction and Large-scale Semantic Classification from Brain Activity. Neuroimage 2022; 254:119121. [PMID: 35342004 PMCID: PMC9133799 DOI: 10.1016/j.neuroimage.2022.119121] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Revised: 01/19/2022] [Accepted: 03/19/2022] [Indexed: 11/24/2022] Open
Abstract
Reconstructing natural images and decoding their semantic category from fMRI brain recordings is challenging. Acquiring sufficient pairs of images and their corresponding fMRI responses, which span the huge space of natural images, is prohibitive. We present a novel self-supervised approach that goes well beyond the scarce paired data, for achieving both: (i) state-of-the art fMRI-to-image reconstruction, and (ii) first-ever large-scale semantic classification from fMRI responses. By imposing cycle consistency between a pair of deep neural networks (from image-to-fMRI & from fMRI-to-image), we train our image reconstruction network on a large number of "unpaired" natural images (images without fMRI recordings) from many novel semantic categories. This enables to adapt our reconstruction network to a very rich semantic coverage without requiring any explicit semantic supervision. Specifically, we find that combining our self-supervised training with high-level perceptual losses, gives rise to new reconstruction & classification capabilities. In particular, this perceptual training enables to classify well fMRIs of never-before-seen semantic classes, without requiring any class labels during training. This gives rise to: (i) Unprecedented image-reconstruction from fMRI of never-before-seen images (evaluated by image metrics and human testing), and (ii) Large-scale semantic classification of categories that were never-before-seen during network training. Such large-scale (1000-way) semantic classification from fMRI recordings has never been demonstrated before. Finally, we provide evidence for the biological consistency of our learned model.
Collapse
Affiliation(s)
- Guy Gaziv
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel.
| | - Roman Beliy
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel
| | - Niv Granot
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel
| | - Assaf Hoogi
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel
| | | | - Tal Golan
- Zuckerman Institute, Columbia University, New York, NY USA
| | - Michal Irani
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel.
| |
Collapse
|
3
|
Sepehri B, Ghavami R, Mahmoudi F, Irani M, Ahmadi R, Moradi D. Identifying SARS-CoV-2 main protease inhibitors by applying the computer screening of a large database of molecules. SAR QSAR Environ Res 2022; 33:341-356. [PMID: 35502579 DOI: 10.1080/1062936x.2022.2050424] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/03/2022] [Accepted: 03/02/2022] [Indexed: 06/14/2023]
Abstract
The outbreak of coronavirus disease 2019 (COVID-19) at the end of 2019 affected global health. Its infection agent was called severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Wearing a mask, maintaining social distance, and vaccination are effective ways to prevent infection of SARS-CoV-2, but none of them help infected people. Targeting the enzymes of SARS-CoV-2 is an effective way to stop the replication of the virus in infected people and treat COVID-19 patients. SARS-CoV-2 main protease is a therapeutic target which the inhibition of its enzymatic activity prevents from the replication of SARS-CoV-2. A large database of molecules has been searched to identify new inhibitors for SARS-CoV-2 main protease enzyme. At the first step, ligand screening based on similarity search was used to select similar compounds to known SARS-CoV-2 main protease inhibitors. Then molecules with better predicted pharmacokinetic properties were selected. Structure-based virtual screening based on the application of molecular docking and molecular dynamics simulation methods was used to select more effective inhibitors among selected molecules in previous step. Finally two compounds were considered as SARS-CoV-2 main protease inhibitors.
Collapse
Affiliation(s)
- B Sepehri
- Chemometrics Laboratory, Department of Chemistry, Faculty of Science, University of Kurdistan, Sanandaj, Iran
| | - R Ghavami
- Chemometrics Laboratory, Department of Chemistry, Faculty of Science, University of Kurdistan, Sanandaj, Iran
| | - F Mahmoudi
- Chemometrics Laboratory, Department of Chemistry, Faculty of Science, University of Kurdistan, Sanandaj, Iran
| | - M Irani
- Department of Chemistry, Faculty of Science, University of Kurdistan, Sanandaj, Iran
| | - R Ahmadi
- Chemometrics Laboratory, Department of Chemistry, Faculty of Science, University of Kurdistan, Sanandaj, Iran
| | - D Moradi
- Chemometrics Laboratory, Department of Chemistry, Faculty of Science, University of Kurdistan, Sanandaj, Iran
| |
Collapse
|
4
|
Hoock S, Brüggmann D, Irani M, Fischer K, Steglich Souto A, Wilhelm L, Neuhoff A, Hentrich A, Eichbaum C, Louwen F. 273 Overview of the clinical management and outcome of sars-cov-2 pregnant women and their infants in the university clinic frankfurt, Germany. Eur J Obstet Gynecol Reprod Biol 2022. [PMCID: PMC8941255 DOI: 10.1016/j.ejogrb.2021.11.273] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
|
5
|
Irani M, Canon C, Robles A, Maddy B, Gunnala V, Qin X, Zhang C, Xu K, Rosenwaks Z. Reply: Individualization of ovarian stimulation to safely optimize cycle outcomes. Hum Reprod 2021; 36:262-263. [PMID: 33170251 DOI: 10.1093/humrep/deaa277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- M Irani
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - C Canon
- Obstetrics and Gynecology, New York Presbyterian/Weill Cornell Medicine, New York, NY 10021, USA
| | - A Robles
- Obstetrics and Gynecology, New York Presbyterian/Weill Cornell Medicine, New York, NY 10021, USA
| | - B Maddy
- Weill Cornell Medicine, New York, NY 10021, USA
| | - V Gunnala
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - X Qin
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - C Zhang
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - K Xu
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - Z Rosenwaks
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| |
Collapse
|
6
|
Irani M, Choopani R, Esmaeili S, Dargahi T, Athari S, Athari S. Effect of nettle seed on immune response in a murine model of allergic asthma. Revue Française d'Allergologie 2020. [DOI: 10.1016/j.reval.2020.03.007] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
|
7
|
Irani M, Canon C, Robles A, Maddy B, Gunnala V, Qin X, Zhang C, Xu K, Rosenwaks Z. No effect of ovarian stimulation and oocyte yield on euploidy and live birth rates: an analysis of 12 298 trophectoderm biopsies. Hum Reprod 2020; 35:1082-1089. [DOI: 10.1093/humrep/deaa028] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2019] [Revised: 01/22/2020] [Indexed: 11/14/2022] Open
Abstract
STUDY QUESTION
Does ovarian stimulation affect embryo euploidy rates or live birth rates (LBRs) after transfer of euploid embryos?
SUMMARY ANSWER
Euploidy rates and LBRs after transfer of euploid embryos are not significantly influenced by gonadotropin dosage, duration of ovarian stimulation, estradiol level, follicle size at ovulation trigger or number of oocytes retrieved, regardless of a woman’s age.
WHAT IS KNOWN ALREADY
Aneuploidy rates increase steadily with age, reaching >80% in women >42 years old. The goal of ovarian stimulation is to overcome this high aneuploidy rate through the recruitment of several follicles, which increases the likelihood of obtaining a euploid embryo that results in a healthy conceptus. However, several studies have suggested that a high response to stimulation might be embryotoxic and/or increase aneuploidy rates by enhancing abnormal segregation of chromosomes during meiosis. Furthermore, a recent study demonstrated a remarkable difference in euploidy rates, ranging from 39.5 to 82.5%, among young oocyte donors in 42 fertility centres, potentially suggesting an iatrogenic etiology resulting from different stimulation methods.
STUDY DESIGN, SIZE, DURATION
This is a retrospective cohort study that included 2230 in vitro fertilisation (IVF) with preimplantation genetic testing for aneuploidy (PGT-A) cycles and 930 frozen-thawed single euploid embryo transfer (FET) cycles, performed in our centre between 2013 and 2017.
PARTICIPANTS/MATERIALS, SETTING, METHODS
A total of 12 298 embryos were analysed for ploidy status. Women were divided into five age groups (<35, 35–37, 38–40, 41–42 and >42 years old). Outcomes were compared between different durations of stimulation (<10, 10–12 and ≥13 days), total gonadotropin dosages (<4000, 4000–6000 and >6000 IU), numbers of oocytes retrieved (<10, 10–19 and ≥20 oocytes), peak estradiol levels (<2000, 2000–3000 and >3000 pg/mL), and sizes of the largest follicle on the day of trigger (<20 and ≥20 mm).
MAIN RESULTS AND THE ROLE OF CHANCE
Within the same age group, both euploidy rates and LBRs were comparable between cycles regardless of their differences in total gonadotropin dosage, duration of stimulation, number of oocytes harvested, size of the largest follicles or peak estradiol levels. In the youngest group, (<35 years, n = 3469 embryos), euploidy rates were comparable between cycles with various total gonadotropin dosages (55.6% for <4000 IU, 52.9% for 4000–6000 IU and 62.3% for >6000 IU; P = 0.3), durations of stimulation (54.4% for <10 days, 55.2% for 10–12 days and 60.9% for >12 days; P = 0.2), number of oocytes harvested (59.4% for <10 oocytes, 55.2% for 10–19 oocytes and 53.4% for ≥20 oocytes; P = 0.2), peak estradiol levels (55.7% for E2 < 2000 pg/mL, 55.4% for E2 2000–3000 pg/mL and 54.8% for E2 > 3000 pg/mL; P = 0.9) and sizes of the largest follicle (55.6% for follicles <20 mm and 55.1% for follicles ≥20 mm; P = 0.8). Similarly, in the oldest group (>42 years, n = 1157 embryos), euploidy rates ranged from 8.7% for gonadotropins <4000 IU to 5.1% for gonadotropins >6000 IU (P = 0.3), from 10.8% for <10 days of stimulation to 8.5% for >12 days of stimulation (P = 0.3), from 7.3% for <10 oocytes to 7.4% for ≥20 oocytes (P = 0.4), from 8.8% for E2 < 2000 pg/mL to 7.5% for E2 > 3000 pg/mL (P = 0.8) and from 8.2% for the largest follicle <20 mm to 8.9% for ≥20 mm (P = 0.7). LBRs after single FET were also comparable between these groups.
LIMITATIONS, REASONS FOR CAUTION
Although this large study (2230 IVF/PGT-A cycles, 12 298 embryos and 930 single FET cycles) demonstrates the safety of ovarian stimulation in terms of aneuploidy and implantation potential of euploid embryos, a multi-centre study may help to prove the generalisability of our single-centre data.
WIDER IMPLICATIONS OF THE FINDINGS
These findings reassure providers and patients that gonadotropin dosage, duration of ovarian stimulation, estradiol level, follicle size at ovulation trigger and number of oocytes retrieved, within certain ranges, do not appear to significantly influence euploidy rates or LBRs, regardless of the woman’s age.
STUDY FUNDING/COMPETING INTEREST(S)
No external funding was received and there are no competing interests to declare.
TRIAL REGISTRATION NUMBER
N/A
Collapse
Affiliation(s)
- M Irani
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - C Canon
- Obstetrics and Gynecology, New York Presbyterian/Weill Cornell Medicine, New York, NY 10021, USA
| | - A Robles
- Obstetrics and Gynecology, New York Presbyterian/Weill Cornell Medicine, New York, NY 10021, USA
| | - B Maddy
- Weill Cornell Medicine, New York, NY 10021, USA
| | - V Gunnala
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - X Qin
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - C Zhang
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - K Xu
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| | - Z Rosenwaks
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, New York, NY 10021, USA
| |
Collapse
|
8
|
Sepúlveda P, Cortinez LI, Irani M, Egaña JI, Contreras V, Sánchez Corzo A, Acosta I, Sitaram R. Differential frontal alpha oscillations and mechanisms underlying loss of consciousness: a comparison between slow and fast propofol infusion rates. Anaesthesia 2019; 75:196-201. [PMID: 31788791 DOI: 10.1111/anae.14885] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/16/2019] [Indexed: 12/19/2022]
Abstract
Mechanisms underlying loss of consciousness following propofol administration remain incompletely understood. The objective of this study was to compare frontal lobe electroencephalography activity and brainstem reflexes during intravenous induction of general anaesthesia, in patients receiving a typical bolus dose (fast infusion) of propofol compared with a slower infusion rate. We sought to determine whether brainstem suppression ('bottom-up') predominates over loss of cortical function ('top-down'). Sixteen ASA physical status-1 patients were randomly assigned to either a fast or slow propofol infusion group. Loss of consciousness and brainstem reflexes were assessed every 30 s by a neurologist blinded to treatment allocation. We performed a multitaper spectral analysis of all electroencephalography data obtained from each participant. Brainstem reflexes were present in all eight patients in the slow infusion group, while being absent in all patients in the fast infusion group, at the moment of loss of consciousness (p = 0.010). An increase in alpha band power was observed before loss of consciousness only in participants allocated to the slow infusion group. Alpha band power emerged several minutes after the loss of consciousness in participants allocated to the fast infusion group. Our results show a predominance of 'bottom-up' mechanisms during fast infusion rates and 'top-down' mechanisms during slow infusion rates. The underlying mechanisms by which propofol induces loss of consciousness are potentially influenced by the speed of infusion.
Collapse
Affiliation(s)
- P Sepúlveda
- Department of Anaesthesiology, Clínica Alemana - UDD, Santiago de Chile
| | - L I Cortinez
- Department of Anaesthesia, School of Medicine, Pontificia Universidad Católica Santiago de Chile
| | - M Irani
- Department of Psychiatry and Division of Neuroscience, Pontificia Universidad Católica Santiago de Chile
| | - J I Egaña
- Department of Anaesthesiology and Peri-operative Medicine, Faculty of Medicine, Universidad de Chile
| | - V Contreras
- Department of Adult and Aging Health, School of Nursing, Pontificia Universidad Católica Santiago de Chile
| | - A Sánchez Corzo
- Department of Psychiatry and Division of Neuroscience, Pontificia Universidad Católica Santiago de Chile
| | - I Acosta
- Department of Neurology, Clínica Alemana Santiago de Chile
| | - R Sitaram
- Department of Psychiatry and Division of Neuroscience, Pontificia Universidad Católica Santiago de Chile.,Institute for Biological and Medical Engineering, Pontificia Universidad Católica Santiago de Chile.,Center for Brain-Machine Interfaces and Neuromodulation, Pontificia Universidad Católica Santiago de Chile
| |
Collapse
|
9
|
Grossman S, Gaziv G, Yeagle EM, Harel M, Mégevand P, Groppe DM, Khuvis S, Herrero JL, Irani M, Mehta AD, Malach R. Convergent evolution of face spaces across human face-selective neuronal groups and deep convolutional networks. Nat Commun 2019; 10:4934. [PMID: 31666525 PMCID: PMC6821842 DOI: 10.1038/s41467-019-12623-6] [Citation(s) in RCA: 50] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2018] [Accepted: 09/23/2019] [Indexed: 12/21/2022] Open
Abstract
The discovery that deep convolutional neural networks (DCNNs) achieve human performance in realistic tasks offers fresh opportunities for linking neuronal tuning properties to such tasks. Here we show that the face-space geometry, revealed through pair-wise activation similarities of face-selective neuronal groups recorded intracranially in 33 patients, significantly matches that of a DCNN having human-level face recognition capabilities. This convergent evolution of pattern similarities across biological and artificial networks highlights the significance of face-space geometry in face perception. Furthermore, the nature of the neuronal to DCNN match suggests a role of human face areas in pictorial aspects of face perception. First, the match was confined to intermediate DCNN layers. Second, presenting identity-preserving image manipulations to the DCNN abolished its correlation to neuronal responses. Finally, DCNN units matching human neuronal group tuning displayed view-point selective receptive fields. Our results demonstrate the importance of face-space geometry in the pictorial aspects of human face perception. Deep convolutional neural networks (DCNNs) are able to identify faces on par with humans. Here, the authors record neuronal activity from higher visual areas in humans and show that face-selective responses in the brain show similarity to those in the intermediate layers of the DCNN.
Collapse
Affiliation(s)
- Shany Grossman
- Department of Neurobiology, Weizmann Institute of Science, 76100, Rehovot, Israel
| | - Guy Gaziv
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, 76100, Rehovot, Israel
| | - Erin M Yeagle
- Department of Neurosurgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell and Feinstein Institute for Medical Research, Manhasset, NY, 11030, USA
| | - Michal Harel
- Department of Neurobiology, Weizmann Institute of Science, 76100, Rehovot, Israel
| | - Pierre Mégevand
- Department of Neurosurgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell and Feinstein Institute for Medical Research, Manhasset, NY, 11030, USA.,Neurology Division, Clinical Neuroscience Department, Geneva University Hospital and Faculty of Medicine, Geneva, 1205, Switzerland
| | - David M Groppe
- Department of Neurosurgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell and Feinstein Institute for Medical Research, Manhasset, NY, 11030, USA.,The Krembil Neuroscience Centre, Toronto, ON, M5T 2S8, Canada
| | - Simon Khuvis
- Department of Neurosurgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell and Feinstein Institute for Medical Research, Manhasset, NY, 11030, USA
| | - Jose L Herrero
- Department of Neurosurgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell and Feinstein Institute for Medical Research, Manhasset, NY, 11030, USA
| | - Michal Irani
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, 76100, Rehovot, Israel
| | - Ashesh D Mehta
- Department of Neurosurgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell and Feinstein Institute for Medical Research, Manhasset, NY, 11030, USA
| | - Rafael Malach
- Department of Neurobiology, Weizmann Institute of Science, 76100, Rehovot, Israel.
| |
Collapse
|
10
|
Irani M. “Blind” visual inference by composition. Pattern Recognit Lett 2019. [DOI: 10.1016/j.patrec.2017.10.021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
11
|
Haqghu M, Irani M, Gholami MR. Theoretical Study of Kinetics and Mechanism of Reactions of Hydroxylamine and Amineoxide Anion with Methyl Iodide in Gas and Aqueous Phases. Progress in Reaction Kinetics and Mechanism 2019. [DOI: 10.3184/146867807x227462] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
The kinetics and mechanism of the reactions of hydroxylamine and aminoxide anion with methyl iodide were studied with ab initio calculations, Monte-Carlo and QM/MM simulations in gas and aqueous phases. Geometrical parameters and charge calculations show that these reactions proceed through the SN2 (bimolecular nucleophilic displacement) mechanism only. The solvent effects on these reactions were studied by inserting water molecules in reaction media, Onsager model, Monte-Carlo and QM/MM simulations. Activation parameters indicate the expected variation in activation energy and rate coefficient in aqueous phase in comparison to the gas phase. The shift of potential energy barrier through the reactants or products for the studied reactions in the gas phase is in the opposite direction in comparison to the aqueous phase.
Collapse
Affiliation(s)
- M. Haqghu
- Department of Chemistry, Sharif University of Technology, P.O. BOX 11365-9516,Tehran, Iran
| | - M. Irani
- Department of Chemistry, Sharif University of Technology, P.O. BOX 11365-9516,Tehran, Iran
| | - M. R. Gholami
- Department of Chemistry, Sharif University of Technology, P.O. BOX 11365-9516,Tehran, Iran
| |
Collapse
|
12
|
Irani M, Parrella A, O'Neill C, Lu V, Choi D, Rosenwaks Z, Palermo G. In vitro neospermatogenesis of human induced pluripotent stem cells. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.1052] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
13
|
Irani M, Canon C, Robles A, Maddy B, Qin X, Zhang C, Xu K, Rosenwaks Z. The effect of gonadotropin dosage and duration of ovarian hyperstimulation on euploidy and live birth rates: an analysis of 12,298 trophectoderm biopsies. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.937] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
14
|
Lu V, Parrella A, Choi D, Irani M, O'Neill C, Rosenwaks Z, Palermo G. Differentiating mouse-induced pluripotent stem cells into male germ cells through embryoid bodies. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.1050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
15
|
Gunnala V, Canon C, Kong L, Wan J, Irani M, Chung P, Rosenwaks Z. Do blastulation rates correlate with embryo ploidy? a comparison of 1,552 IVF cycles with preimplantation genetic testing stratified by age and percent blastulation. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.1156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
16
|
Minis E, Athanasiou A, Nasioudis D, Irani M, Witkin S, Spandorfer S. Understanding the pathophysiology of OHSS: the role of TGF-B and SENG. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.932] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
17
|
Parrella A, Irani M, Rosenwaks Z, Palermo G. Understanding the role of cytoplasmic dismaturity on ICSI outcome. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.883] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
18
|
Minis E, Chervenak J, Irani M, Witkin S, Spandorfer S. Serum IGFBP-1 levels and IVF outcome. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.756] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
19
|
Minis E, Irani M, Athanasiou A, Witkin S, Spandorfer S. Serum IL-1β predicts ongoing pregnancy following IVF. Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.388] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
20
|
Stewart J, Irani M, Chervenak J, Chung P, Schattman G, Rosenwaks Z. Natural cycle frozen blastocyst transfer after a failed fresh embryo transfer: do we have to wait? Fertil Steril 2018. [DOI: 10.1016/j.fertnstert.2018.07.651] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
21
|
Gruber LZ, Haruvi A, Basri R, Irani M. Perceptual Dominance in Brief Presentations of Mixed Images: Human Perception vs. Deep Neural Networks. Front Comput Neurosci 2018; 12:57. [PMID: 30087604 PMCID: PMC6066547 DOI: 10.3389/fncom.2018.00057] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2018] [Accepted: 07/03/2018] [Indexed: 11/23/2022] Open
Abstract
Visual perception involves continuously choosing the most prominent inputs while suppressing others. Neuroscientists induce visual competitions in various ways to study why and how the brain makes choices of what to perceive. Recently deep neural networks (DNNs) have been used as models of the ventral stream of the visual system, due to similarities in both accuracy and hierarchy of feature representation. In this study we created non-dynamic visual competitions for humans by briefly presenting mixtures of two images. We then tested feed-forward DNNs with similar mixtures and examined their behavior. We found that both humans and DNNs tend to perceive only one image when presented with a mixture of two. We revealed image parameters which predict this perceptual dominance and compared their predictability for the two visual systems. Our findings can be used to both improve DNNs as models, as well as potentially improve their performance by imitating biological behaviors.
Collapse
Affiliation(s)
- Liron Z Gruber
- Department of Neurobiology, Weizmann Institute of Science, Rehovot, Israel
| | - Aia Haruvi
- Department of Neurobiology, Weizmann Institute of Science, Rehovot, Israel
| | - Ronen Basri
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
| | - Michal Irani
- Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
| |
Collapse
|
22
|
Irani M, Zaninovic N, Canon C, O’Neill C, Gunnala V, Zhan Q, Palermo G, Reichman D, Rosenwaks Z. A rationale for biopsying embryos reaching the morula stage on Day 6 in women undergoing preimplantation genetic testing for aneuploidy. Hum Reprod 2018; 33:935-941. [DOI: 10.1093/humrep/dey053] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/01/2018] [Accepted: 02/20/2018] [Indexed: 12/13/2022] Open
Affiliation(s)
- M Irani
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - N Zaninovic
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - C Canon
- Department of Obstetrics and Gynecology, Weill Cornell Medicine, 525 East 68th Street, New York, NY 10065, USA
| | - C O’Neill
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - V Gunnala
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - Q Zhan
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - G Palermo
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - D Reichman
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| | - Z Rosenwaks
- The Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine, Weill Cornell Medicine, 1305 York Avenue, 6th Floor, New York, NY 10021, USA
| |
Collapse
|
23
|
Irani M, Nasioudis D, Gunnala V, Witkin S, Spandorfer S. Serum levels of PTX3 and SFLT-1 predict the outcomes of frozen-thawed euploid embryo transfer cycles. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.118] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
24
|
Irani M, Canon C, O'Neill C, Gunnala V, Zaninovic N, Xu K, Reichman D, Rosenwaks Z. Should we biopsy embryos reaching morula stage on day 6 for patients undergoing preimplantation genetic screening? Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
25
|
Irani M, Gunnala V, Kligman I, Rosenwaks Z. The impact of the day of embryo transfer and type of transfer cycle on the incidence of ectopic pregnancy following IVF. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.1094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
26
|
O'Neill C, Irani M, Parrella A, Rosenwaks Z, Palermo G. Screening for germ cells in surgical specimen that fail to yield spermatozoa. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.930] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
27
|
Nasioudis D, Kreines F, Minis E, Irani M, Witkin S, Spandorfer S. Insulin-like growth factor-1 and soluble FMS-like tyrosine kinase-1 prospectively predict cancelled IVF cycles. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
28
|
Irani M, Nasioudis D, Witkin S, Spandorfer S. Higher serum levels of IGF-1 is associated with a higher rate of pregnancy loss following frozen-thawed euploid embryo transfer cycles. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.242] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
|
29
|
Kreines F, Nasioudis D, Minis E, Irani M, Witkin S, Spandorfer S. Serum interleukin-1β and IVF outcome: a prospective study. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
30
|
Gunnala V, Irani M, Schattman G, Rosenwaks Z. Liquid tumor patients show equivalent ovarian reserve and response to IVF stimulation compared to a solid tumor undergoing fertility preservation. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
31
|
Nasioudis D, Irani M, Minis E, Spandorfer S, Witkin S. Sera from women with ovarian hyperstimulation syndrome induce autophagy: new clues for susceptibility and pathophysiology. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.076] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
32
|
Irani M, Elder S, Kreines F, Gunnala V, James D, Reichman D, Rosenwaks Z. Should we measure progesterone level on the day of trigger before fresh embryo transfer? Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.1034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
33
|
Gunnala V, Irani M, Schattman G, Rosenwaks Z. BRCA mutation breast cancer patients show equivalent ovarian reserve and response to IVF stimulation compared to BRCA negative patients and other malignancies undergoing fertility preservation. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
34
|
Hancock K, Gunnala V, Irani M, Schattman G, Rosenwaks Z. Subsequent IVF cycle outcomes following a pregnancy loss: first analysis of interpregnancy interval in an IVF population. Fertil Steril 2017. [DOI: 10.1016/j.fertnstert.2017.07.1114] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
35
|
Irani M, Gunnala V, Kligman I, Rosenwaks Z. The success rate of intrauterine insemination after failed oocyte retrieval. Fertil Steril 2016. [DOI: 10.1016/j.fertnstert.2016.07.917] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
36
|
Irani M, Gunnala V, Rosenwaks Z, Spandorfer S. Obesity is associated with an increase in spontaneous abortion rate in young women undergoing IVF without affecting the aneuploidy rate. Fertil Steril 2016. [DOI: 10.1016/j.fertnstert.2016.07.768] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
37
|
Irani M, Robles A, Gunnala V, Rosenwaks Z, Spandorfer S. Unilateral salpingectomy and methotrexate are associated with similar recurrence rate of ectopic pregnancy in patients undergoing IVF. Fertil Steril 2016. [DOI: 10.1016/j.fertnstert.2016.07.049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
38
|
Irani M, Robles A, Gunnala V, Reichman D, Rosenwaks Z. Optimal parameters for determining the LH surge in natural cyclefrozen-thawed embryo transfers. Fertil Steril 2016. [DOI: 10.1016/j.fertnstert.2016.07.426] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
39
|
Irani M, Seifer D, Grazi R, Irani S, Tal R. Vitamin D decreases serum VEGF levels correlating with clinical improvement in vitamin D-deficient women with PCOS: a randomized placebo-controlled trial. Fertil Steril 2016. [DOI: 10.1016/j.fertnstert.2016.07.728] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
40
|
Irani M, Setton R, Gunnala V, Kligman I, Goldschlag D, Rosenwaks Z. Dose of human chorionic gonadotropin to trigger final oocyte maturation. Fertil Steril 2016. [DOI: 10.1016/j.fertnstert.2016.07.757] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
41
|
Irani M, Fisher N, Mor A, Bensinger G. Urinary retention and syndrome of inappropriate antidiuretic hormone secretion (SIADH) secondary to impacted gravid uterus. J Obstet Gynaecol Res 2016; 42:734-737. [DOI: 10.1111/jog.12963] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2015] [Revised: 12/10/2015] [Accepted: 01/07/2016] [Indexed: 11/29/2022]
Affiliation(s)
- M. Irani
- Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine; Weill Cornell Medical College; New York USA
| | - N. Fisher
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology; Maimonides Medical Center; Brooklyn New York USA
| | - A. Mor
- Department of Obstetrics and Gynecology; Maimonides Medical Center; Brooklyn New York USA
| | - G. Bensinger
- Division of Urogynecology, Department of Obstetrics and Gynecology; Maimonides Medical Center; Brooklyn New York USA
| |
Collapse
|
42
|
Tabari M, Ghazvinian K, Irani M, Molaei R. Effects of dietary supplementation of nettle root extract and pumpkin seed oil on production traits and intestinal microflora in broiler chickens. BJVM 2016. [DOI: 10.15547/bjvm.879] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
|
43
|
Irani M, Seifer D, Grazi R, Bhatt D, Julka N, Kalgi B, Irani S, Tal O, Tal R. Vitamin D supplementation decreases TGF beta-1 bioavailability correlating with clinical improvement in Vitamin D deficient women with PCOS: a randomized placebo-controlled trial. Fertil Steril 2015. [DOI: 10.1016/j.fertnstert.2015.07.324] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
44
|
Mor A, Tal R, Irani M, Garg D, Haberman S, McCalla S, Perlman J, Grazi R, Minkoff H. A simple and fast approach to confirm the presence of an intrauterine pregnancy. Fertil Steril 2015. [DOI: 10.1016/j.fertnstert.2015.07.1090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
|
45
|
Irani M, Kalgi B, Mor A, Kaliappan S, Garg D, Homel P, Grazi R. Cryopreservation technique and duration of storage affect pregnancy outcomes in frozen-thawed embryo transfer cycles. Fertil Steril 2015. [DOI: 10.1016/j.fertnstert.2015.07.608] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
46
|
Prabakar C, Irani M, Julka N, Bhatt D, Homel P, Saraf S, Bral P. What Your Patient Does Not Know: A Survey of Patient Knowledge about Surgical Approaches in Gynecology. J Minim Invasive Gynecol 2014. [DOI: 10.1016/j.jmig.2014.08.431] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
47
|
Irani M, Seifer D, Melzer K, Makarov J, Chavkin D, Grazi R. Is endometrial thickness on day of transfer a predictor of pregnancy rate in IVF? Fertil Steril 2014. [DOI: 10.1016/j.fertnstert.2014.07.996] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
48
|
Faktor A, Irani M. "Clustering by Composition"-Unsupervised Discovery of Image Categories. IEEE Trans Pattern Anal Mach Intell 2014; 36:1092-1106. [PMID: 26353273 DOI: 10.1109/tpami.2013.251] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
We define a "good image cluster" as one in which images can be easily composed (like a puzzle) using pieces from each other, while are difficult to compose from images outside the cluster. The larger and more statistically significant the pieces are, the stronger the affinity between the images. This gives rise to unsupervised discovery of very challenging image categories. We further show how multiple images can be composed from each other simultaneously and efficiently using a collaborative randomized search algorithm. This collaborative process exploits the "wisdom of crowds of images", to obtain a sparse yet meaningful set of image affinities, and in time which is almost linear in the size of the image collection. "Clustering-by-Composition" yields state-of-the-art results on current benchmark data sets. It further yields promising results on new challenging data sets, such as data sets with very few images (where a `cluster model' cannot be `learned' by current methods), and a subset of the PASCAL VOC data set (with huge variability in scale and appearance).
Collapse
|
49
|
|
50
|
Rezaeipour V, Fononi H, Irani M. Effects of dietary L-threonine and Saccharomyces cerevisiae on performance, intestinal morphology and immune response of broiler chickens. S AFR J ANIM SCI 2012. [DOI: 10.4314/sajas.v42i3.8] [Citation(s) in RCA: 24] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|