Corin F. Otesteanu

Corin F. Otesteanu

Auto-generated profile, based on publicly available information

Corin F. Otesteanu

ETH Zurich,Zurich,Switzerland

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
25 October 2021 in Cell Reports Methods
Verified
Journal Article
Open access
COCorin F. Otesteanu
Corin F. Otesteanu
MUMartina Ugrinic
Martina Ugrinic
GHGregor Holzner
Gregor Holzner
YCYun-Tsan Chang
Yun-Tsan Chang
CFChristina Fassnacht
Christina Fassnacht
MCManfred Claassen
Manfred Claassen
The application of machine learning approaches to imaging flow cytometry (IFC) data has the potential to transform the diagnosis of hematological diseases. However, the need for manually labeled single-cell images for machine learning model training has severely limited its clinical application. To address this, we present iCellCnn, a weakly supervised deep learning approach for label-free IFC-based blood diagnostics. We demonstrate the capability of iCellCnn to achieve diagnosis of Sézary syndrome (SS) from patient samples on the basis of bright-field IFC images of T cells obtained after fluorescence-activated cell sorting of human peripheral blood mononuclear cell specimens. With a sample size of four healthy donors and five SS patients, iCellCnn achieved a 100% classification accuracy. As iCellCnn is not restricted to the diagnosis of SS, we expect such weakly supervised approaches to tap the diagnostic potential of IFC by providing automatic data-driven diagnosis of diseases with so-far unknown morphological manifestations.

8 August 2019 in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Verified
Journal Article
Closed access
COCorin F. Otesteanu
Corin F. Otesteanu
BCBhaskara Rao Chintada
Bhaskara Rao Chintada
MRMarga B. Rominger
Marga B. Rominger
SSSergio Sanabria
Sergio Sanabria
OGOrcun Goksel
Orcun Goksel
Tissue biomechanical properties are known to be sensitive to pathological changes. Accordingly, various techniques have been developed to estimate tissue mechanical properties. Shear-wave elastography (SWE) measures shear-wave speed (SWS) in tissues, which can be related to shear modulus. Although viscosity or stress-strain nonlinearity may act as confounder of SWE, their explicit characterization may also provide additional information about tissue composition as a contrast modality. Viscosity can be related to frequency dispersion of SWS, which can be characterized using multi-frequency measurements, herein called spectral SWE (SSWE). Additionally, nonlinear shear modulus can be quantified and parameterized based on SWS changes with respect to applied stress, a phenomenon called acoustoelasticity (AE). In this work, we characterize the nonlinear parameters of tissue as a function of excitation frequency by utilizing both AE and SSWE together. For this, we apply incremental amounts of quasi-static stress on a medium, while imaging and quantifying SWS dispersion via SSWE. Results from phantom and ex vivo porcine liver experiments demonstrate the feasibility of measuring frequency-dependent nonlinear parameters using the proposed method. SWS propagation in porcine liver tissue was observed to change from 1.8 m/s at 100 Hz to 3.3 m/s at 700 Hz, while increasing by approximately 25% from a strain of 0% to 12% across these frequencies.

16 May 2018 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
COCorin F. Otesteanu
Corin F. Otesteanu
SSSergio Sanabria
Sergio Sanabria
OGOrcun Goksel
Orcun Goksel
Biomedical parameters of tissue can be important indicators for clinical diagnosis. One such parameter that reflects tissue stiffness is elasticity, the imaging of which is called elastography. In this work, we use displacements from harmonic excitations to solve the inverse problem of elasticity based on a finite element method (FEM) formulation. This leads to iterative solution of nonlinear and nonconvex problems. In this paper we show the importance and selection of viable initializations in numerical simulation studies, and propose techniques for the fusion of multiple initializations for ideal reconstructions of unknown tissue as well as combining information from excitations at multiple frequencies. Results show that our method leads up to 76% decrease in root-mean-squared error (RMSE) and 9.9 dB increase in contrast-to-noise ratio (CNR) in simulations with noise, when compared to conventional iterative FEM without multiple initializations and frequencies. As the wave patterns in individually selected frequencies may introduce artifacts, a joint inverse-problem solution of multi-frequency excitations is introduced as a robust solution, where CNR improvements of up to 11.9 dB are observed. We also present the methods on a tissuemimicking gelatin phantom study using mechanical excitation and ultrafast plane-wave ultrasound imaging, where RMSE was improved by up to 51%. An experiment of ablation via heating an ex-vivo bovine liver shows that reconstruction artifacts are reduced with our proposed method.

17 April 2018 in International Journal of Computer Assisted Radiology and Surgery
Verified
Journal Article
Closed access
PDF file
COCorin F. Otesteanu
Corin F. Otesteanu
VVValery Vishnevsky
Valery Vishnevsky
OGOrcun Goksel
Orcun Goksel

1 April 2016
Verified
Conference Paper
Closed access
COCorin F. Otesteanu
Corin F. Otesteanu
SSSergio Sanabria
Sergio Sanabria
OGOrcun Goksel
Orcun Goksel
Multi-frequency harmonic elastography is a technique that involves applying vibrations to tissues in order to measure their mechanical properties. High speed plane wave ultrasound imaging is used to image dynamic deformations produced by a voice coil actuator on a gelatin phantom with a hard inclusion mimicking a focal lesion (e.g. breast, liver). Tissue displacements are estimated from the echo data and used in a finite element inverse elasticity problem. Until now, mostly one or very few frequencies were used for tissue excitation which could lead to inconclusive or misleading results. In this paper we analyze a broad bandwidth of 100 Hz with a fine 5 Hz step and study the effect of the frequency excitation on the inversion of the inclusion geometry and stiffness ratio with respect to background. The results show the importance of using numerous frequencies for tissue excitation, as focal lesions could be "invisible" or have a deformed structure at certain frequencies.

1 September 2017
Verified
Conference Paper
Closed access
COCorin F. Otesteanu
Corin F. Otesteanu
BCBhaskara Rao Chintada
Bhaskara Rao Chintada
SSSergio Sanabria
Sergio Sanabria
MRMarga Rominger
Marga Rominger
EMEdoardo Mazza
Edoardo Mazza
OGOrcun Goksel
Orcun Goksel
Early detection of pathological processes is crucial for the prognosis and treatment of patients, which can be facilitated through studying tissue biomechanical properties. Shear wave elastography is a technique to estimate the shear modulus of tissue. Such measurements quantify elasticity linearized around an immediate state of local stress condition, under applied nature of excitation. Stress-strain is known to be nonlinearly related in tissues, and the quantification of such nonlinearity may be utilized to facilitate diagnostic and image analytic approaches. In this work, we compare different methods for quantifying such nonlinear relationships, in particular the estimation of elasticity parameters, including third (A) and fourth (D) order nonlinear elastic constants, from measurements. We study the fitness and robustness in approximating these parameters, and compare those in terms of tissue differentiation, applied to ex-vivo liver and muscle tissues.