no code implementations • 2 May 2024 • Liam Hazan, Gili Focht, Naama Gavrielov, Roi Reichart, Talar Hagopian, Mary-Louise C. Greer, Ruth Cytter Kuint, Dan Turner, Moti Freiman
Automatic conversion of free-text radiology reports into structured data using Natural Language Processing (NLP) techniques is crucial for analyzing diseases on a large scale.
no code implementations • 7 Apr 2024 • Shir Nitzan, Maya Gilad, Moti Freiman
Effective surgical planning for breast cancer hinges on accurately predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC).
1 code implementation • 6 Apr 2024 • Samah Khawaled, Moti Freiman
We introduce "NPB-REC", a non-parametric fully Bayesian framework, for MRI reconstruction from undersampled data with uncertainty estimation.
no code implementations • 6 Apr 2024 • Samah Khawaled, Simon K. Warfield, Moti Freiman
Furthermore, our approach exhibits significantly faster registration speed compared to conventional iterative methods ($0. 096$ sec.
no code implementations • 29 Jan 2024 • Hadar Hezi, Matan Gelber, Alexander Balabanov, Yosef E. Maruvka, Moti Freiman
Treatment approaches for colorectal cancer (CRC) are highly dependent on the molecular subtype, as immunotherapy has shown efficacy in cases with microsatellite instability (MSI) but is ineffective for the microsatellite stable (MSS) subtype.
1 code implementation • 13 Jan 2024 • Noga Kertes, Yael Zaffrani-Reznikov, Onur Afacan, Sila Kurugol, Simon K. Warfield, Moti Freiman
IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion.
no code implementations • 11 Sep 2023 • Jonathan Fhima, Jan Van Eijgen, Hana Kulenovic, Valérie Debeuf, Marie Vangilbergen, Marie-Isaline Billen, Heloïse Brackenier, Moti Freiman, Ingeborg Stalmans, Joachim A. Behar
Using active learning, we created a new DFI dataset containing 240 crowd-sourced manual A/V segmentations performed by fifteen medical students and reviewed by an ophthalmologist, and developed LUNet, a novel deep learning architecture for high resolution A/V segmentation.
1 code implementation • 22 Aug 2023 • Eyal Hanania, Ilya Volovik, Lilach Barkat, Israel Cohen, Moti Freiman
We compared PCMC-T1 to baseline deep-learning-based image registration approaches using a 5-fold experimental setup on a publicly available dataset of 210 patients.
no code implementations • 26 Mar 2023 • Hadar Hezi, Daniel Shats, Daniel Gurevich, Yosef E. Maruvka, Moti Freiman
We trained CNN models for CRC subtype classification that account for potential correlation between genomic variations within CRC subtypes and their corresponding cellular morphology patterns.
1 code implementation • 8 Dec 2022 • Hadas Ben-Atya, Moti Freiman
Deep neural network (DNN) based methods have been proposed to address the complex inverse problem of estimating $T_2$ distributions from MRI data, but they are not yet robust enough for clinical data with low Signal-to-Noise ratio (SNR) and are highly sensitive to distribution shifts such as variations in echo-times (TE) used during acquisition.
1 code implementation • 31 Aug 2022 • Nitzan Avidan, Moti Freiman
The goal of our work is to enhance the generalization capabilities of DNN methods for k-space interpolation by introducing `MA-RECON', an innovative mask-aware DNN architecture and associated training method.
1 code implementation • 22 Aug 2022 • Daniel Shats, Hadar Hezi, Guy Shani, Yosef E. Maruvka, Moti Freiman
However, the high resolution of WSI practically prevent direct classification of the entire WSI.
no code implementations • 22 Aug 2022 • Jonathan Fhima, Jan Van Eijgen, Moti Freiman, Ingeborg Stalmans, Joachim A. Behar
Discussion and future work: We will use active learning strategies to continue enlarging our retinal fundus dataset by including a more efficient process to select the images to be annotated and distribute them to annotators.
1 code implementation • 21 Aug 2022 • Yael Zaffrani-Reznikov, Onur Afacan, Sila Kurugol, Simon Warfield, Moti Freiman
Our approach couples a registration sub-network with a quantitative DWI model fitting sub-network.
1 code implementation • 8 Aug 2022 • Samah Khawaled, Moti Freiman
We demonstrated the added-value of our approach on the multi-coil brain MRI dataset, from the fastmri challenge, in comparison to the baseline E2E-VarNet with and without inference-time dropout.
no code implementations • 31 Jul 2022 • Jonathan Fhima, Jan Van Eijgen, Ingeborg Stalmans, Yevgeniy Men, Moti Freiman, Joachim A. Behar
Results: We built a fully automated vasculature biomarker toolbox based on DFI segmentations and provided a proof of usability to characterize the vascular changes in glaucoma.
1 code implementation • 12 Jun 2022 • Maya Gilad, Moti Freiman
We demonstrated the added-value of our PD-DWI model over conventional machine-learning approaches for pCR prediction from mp-MRI data using the publicly available Breast Multi-parametric MRI for prediction of NAC Response (BMMR2) challenge.
1 code implementation • 8 Jun 2022 • Noam Korngut, Elad Rotman, Onur Afacan, Sila Kurugol, Yael Zaffrani-Reznikov, Shira Nemirovsky-Rotman, Simon Warfield, Moti Freiman
SUPER-IVIM-DC has the potential to reduce the long acquisition times associated with IVIM analysis of DWI data and to provide clinically feasible bio-markers for non-invasive fetal lung maturity assessment.
1 code implementation • 16 Feb 2022 • Lilach Barkat, Moti Freiman, Haim Azhari
In order to evaluate the preservation of the anatomical features, the lesions in the ultrasonic images and the generated pseudo anatomical images were both automatically segmented and compared.
no code implementations • 25 Nov 2021 • Hadas Ben-Atya, Ori Rajchert, Liran Goshen, Moti Freiman
Automatic brain tumor segmentation from Magnetic Resonance Imaging (MRI) data plays an important role in assessing tumor response to therapy and personalized treatment stratification. Manual segmentation is tedious and subjective. Deep-learning-based algorithms for brain tumor segmentation have the potential to provide objective and fast tumor segmentation. However, the training of such algorithms requires large datasets which are not always available.
no code implementations • 19 Sep 2021 • Dar Arava, Mohammad Masarwy, Samah Khawaled, Moti Freiman
In the presence of motion, the different T1-weighted images are not aligned.
1 code implementation • 15 Aug 2021 • Samah Khawaled, Moti Freiman
The NPBDREG shows a better correlation of the predicted uncertainty with out-of-distribution data ($r>0. 95$ vs. $r<0. 5$) as well as a 7. 3%improvement in the registration accuracy (Dice score, $0. 74$ vs. $0. 69$, $p \ll 0. 01$), and 18% improvement in registration smoothness (percentage of folds in the deformation field, 0. 014 vs. 0. 017, $p \ll 0. 01$).
no code implementations • 10 Aug 2020 • Samah Khawaled, Moti Freiman
We demonstrated the added-value of our Basyesian unsupervised DL-based registration framework on the MNIST and brain MRI (MGH10) datasets in comparison to the VoxelMorph unsupervised DL-based image registration framework.
no code implementations • 25 Jun 2019 • Moti Freiman, Hannes Nickisch, Holger Schmitt, Pal Maurovich-Horvat, Patrick Donnelly, Mani Vembar, Liran Goshen
We introduce a functional for the learning of an optimal database for patch-based image segmentation with application to coronary lumen segmentation from coronary computed tomography angiography (CCTA) data.
no code implementations • 24 Jun 2019 • Moti Freiman, Hannes Nickisch, Sven Prevrhal, Holger Schmitt, Mani Vembar, Pál Maurovich-Horvat, Patrick Donnelly, Liran Goshen
Purpose: The goal of this study was to assess the potential added benefit of accounting for partial volume effects (PVE) in an automatic coronary lumen segmentation algorithm from coronary computed tomography angiography (CCTA).
no code implementations • 28 Feb 2019 • Moti Freiman, Ravindra Manjeshwar, Liran Goshen
Deep sparse auto-encoders with mixed structure regularization (MSR) in addition to explicit sparsity regularization term and stochastic corruption of the input data with Gaussian noise have the potential to improve unsupervised abnormality detection.