Sunil Kumar Yadav
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
Research Subjects
Sunil Kumar Yadav has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
Konrad Polthier
7 shared publicationsEric Zimmermann
Freie Universität Berlin
3 shared publications- Alexander Ulrich Brandt
Experimental and Clinical Research Center, Max Delbrück Center for Molecular Medicine and Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt‐Universität zu Berlin Berlin Germany
2 shared publications Friedemann Paul
Charite Universitatsmedizin Berlin (Germany)
2 shared publications- Konrad Polthier
Institute of Mathematics, Freie Universität Berlin, Berlin, Berlin Germany
2 shared publications Martin Skrodzki
Freie Universität Berlin
2 shared publications
Latest Publications
- Open Access
- 17 May 2022
- Published by MDPI AG in Journal of Imaging
- Vol. 8 (5) , 139
Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets
Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground–background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 μm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 μm when using the same gold standard segmentation approach, and 3.7 μm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes.
- 17 May 2022
- Published by MDPI AG in Journal of Imaging
- Vol. 8 (5) , 139
Open AccessIntraretinal Layer Segmentation Using Cascaded Compressed U-Nets
Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground–background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 μm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 μm when using the same gold standard segmentation approach, and 3.7 μm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes.
- 1 March 2021
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 86
Local Delaunay-based high fidelity surface reconstruction from 3D point sets
- 1 March 2021
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 86
Local Delaunay-based high fidelity surface reconstruction from 3D point sets
- Open Access
- 25 February 2021
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2021, 1-16
COVID-19 in Iran: Forecasting Pandemic Using Deep Learning
COVID-19 has led to a pandemic, affecting almost all countries in a few months. In this work, we applied selected deep learning models including multilayer perceptron, random forest, and different versions of long short-term memory (LSTM), using three data sources to train the models, including COVID-19 occurrences, basic information like coded country names, and detailed information like population, and area of different countries. The main goal is to forecast the outbreak in nine countries (Iran, Germany, Italy, Japan, Korea, Switzerland, Spain, China, and the USA). The performances of the models are measured using four metrics, including mean average percentage error (MAPE), root mean square error (RMSE), normalized RMSE (NRMSE), and . The best performance was found for a modified version of LSTM, called M-LSTM (winner model), to forecast the future trajectory of the pandemic in the mentioned countries. For this purpose, we collected the data from January 22 till July 30, 2020, for training, and from 1 August 2020 to 31 August 2020, for the testing phase. Through experimental results, the winner model achieved reasonably accurate predictions (MAPE, RMSE, NRMSE, and are 0.509, 458.12, 0.001624, and 0.99997, respectively). Furthermore, we stopped the training of the model on some dates related to main country actions to investigate the effect of country actions on predictions by the model.
- 25 February 2021
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2021, 1-16
Open AccessCOVID-19 in Iran: Forecasting Pandemic Using Deep Learning
COVID-19 has led to a pandemic, affecting almost all countries in a few months. In this work, we applied selected deep learning models including multilayer perceptron, random forest, and different versions of long short-term memory (LSTM), using three data sources to train the models, including COVID-19 occurrences, basic information like coded country names, and detailed information like population, and area of different countries. The main goal is to forecast the outbreak in nine countries (Iran, Germany, Italy, Japan, Korea, Switzerland, Spain, China, and the USA). The performances of the models are measured using four metrics, including mean average percentage error (MAPE), root mean square error (RMSE), normalized RMSE (NRMSE), and . The best performance was found for a modified version of LSTM, called M-LSTM (winner model), to forecast the future trajectory of the pandemic in the mentioned countries. For this purpose, we collected the data from January 22 till July 30, 2020, for training, and from 1 August 2020 to 31 August 2020, for the testing phase. Through experimental results, the winner model achieved reasonably accurate predictions (MAPE, RMSE, NRMSE, and are 0.509, 458.12, 0.001624, and 0.99997, respectively). Furthermore, we stopped the training of the model on some dates related to main country actions to investigate the effect of country actions on predictions by the model.
- 1 January 2021
- Published by Springer Nature
- p. 103-132
Surface Denoising Based on Normal Filtering in a Robust Statistics Framework
- 1 January 2021
- Published by Springer Nature
- p. 103-132
Surface Denoising Based on Normal Filtering in a Robust Statistics Framework
- Open Access
- 1 August 2020
- Published by Elsevier in Software Impacts
- Vol. 5
Normal voting tensor based points set denoising
- 1 August 2020
- Published by Elsevier in Software Impacts
- Vol. 5
Open AccessNormal voting tensor based points set denoising
- Open Access
Surface Denoising based on Normal Filtering in a Robust Statistics Framework
During a surface acquisition process using 3D scanners, noise is inevitable and an important step in geometry processing is to remove these noise components from these surfaces (given as points-set or triangulated mesh). The noise-removal process (denoising) can be performed by filtering the surface normals first and by adjusting the vertex positions according to filtered normals afterwards. Therefore, in many available denoising algorithms, the computation of noise-free normals is a key factor. A variety of filters have been introduced for noise-removal from normals, with different focus points like robustness against outliers or large amplitude of noise. Although these filters are performing well in different aspects, a unified framework is missing to establish the relation between them and to provide a theoretical analysis beyond the performance of each method. In this paper, we introduce such a framework to establish relations between a number of widely-used nonlinear filters for face normals in mesh denoising and vertex normals in point set denoising. We cover robust statistical estimation with M-smoothers and their application to linear and non-linear normal filtering. Although these methods originate in different mathematical theories - which include diffusion-, bilateral-, and directional curvature-based algorithms - we demonstrate that all of them can be cast into a unified framework of robust statistics using robust error norms and their corresponding influence functions. This unification contributes to a better understanding of the individual methods and their relations with each other. Furthermore, the presented framework provides a platform for new techniques to combine the advantages of known filters and to compare them with available methods.
Open AccessSurface Denoising based on Normal Filtering in a Robust Statistics Framework
During a surface acquisition process using 3D scanners, noise is inevitable and an important step in geometry processing is to remove these noise components from these surfaces (given as points-set or triangulated mesh). The noise-removal process (denoising) can be performed by filtering the surface normals first and by adjusting the vertex positions according to filtered normals afterwards. Therefore, in many available denoising algorithms, the computation of noise-free normals is a key factor. A variety of filters have been introduced for noise-removal from normals, with different focus points like robustness against outliers or large amplitude of noise. Although these filters are performing well in different aspects, a unified framework is missing to establish the relation between them and to provide a theoretical analysis beyond the performance of each method. In this paper, we introduce such a framework to establish relations between a number of widely-used nonlinear filters for face normals in mesh denoising and vertex normals in point set denoising. We cover robust statistical estimation with M-smoothers and their application to linear and non-linear normal filtering. Although these methods originate in different mathematical theories - which include diffusion-, bilateral-, and directional curvature-based algorithms - we demonstrate that all of them can be cast into a unified framework of robust statistics using robust error norms and their corresponding influence functions. This unification contributes to a better understanding of the individual methods and their relations with each other. Furthermore, the presented framework provides a platform for new techniques to combine the advantages of known filters and to compare them with available methods.
- Open Access
- 12 October 2018
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 23 (10) , 106004-13
Optic nerve head three-dimensional shape analysis
Many neurological and ophthalmological conditions affect the retina. Two landmark structures of this affection are the macula and the optic nerve head (ONH). Parameters describing the shape of these structures, especially 3-D parameters, are gaining more and more importance in understanding normative data and disease-specific changes, in form of additional information along with traditional quantitative ones. For example, in the case of the macula, several studies and approaches have already been published in order to provide a better insight into the definition of healthy structure and shape.1 2. 3. 4. – 5 ONH represents the part in which all retinal ganglion cell axons gather to leave the eye toward the brain. As such, investigating the ONH is central to the diagnosis of many disorders affecting the optic nerve like glaucoma,6 idiopathic intracranial hypertension (IIH),7,8 optic neuritis (ON),9,10 and optic neuropathies of other etiology, for example, in the context of multiple sclerosis (MS) or neuromyelitis optica spectrum disorders (NMOSD).11 12. – 13
- 12 October 2018
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 23 (10) , 106004-13
Open AccessOptic nerve head three-dimensional shape analysis
Many neurological and ophthalmological conditions affect the retina. Two landmark structures of this affection are the macula and the optic nerve head (ONH). Parameters describing the shape of these structures, especially 3-D parameters, are gaining more and more importance in understanding normative data and disease-specific changes, in form of additional information along with traditional quantitative ones. For example, in the case of the macula, several studies and approaches have already been published in order to provide a better insight into the definition of healthy structure and shape.1 2. 3. 4. – 5 ONH represents the part in which all retinal ganglion cell axons gather to leave the eye toward the brain. As such, investigating the ONH is central to the diagnosis of many disorders affecting the optic nerve like glaucoma,6 idiopathic intracranial hypertension (IIH),7,8 optic neuritis (ON),9,10 and optic neuropathies of other etiology, for example, in the context of multiple sclerosis (MS) or neuromyelitis optica spectrum disorders (NMOSD).11 12. – 13
- 1 August 2018
- Published by Elsevier in Computers & Graphics
- Vol. 74, 234-243
Constraint-based point set denoising using normal voting tensor and restricted quadratic error metrics
- 1 August 2018
- Published by Elsevier in Computers & Graphics
- Vol. 74, 234-243
Constraint-based point set denoising using normal voting tensor and restricted quadratic error metrics
- 20 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 25 (6) , 2304-2310
Robust and High Fidelity Mesh Denoising
This paper presents a simple and effective two-stage mesh denoising algorithm, where in the first stage, face normal filtering is done by using bilateral normal filtering in a robust statistics framework. Tukey's bi-weight function is used as similarity function in the bilateral weighting, which is a robust estimator and stops the diffusion at sharp edges to retain features and removes noise from flat regions effectively. In the second stage, an edge-weighted Laplace operator is introduced to compute a differential coordinate. This differential coordinate helps the algorithm to produce a high-quality mesh without any face normal flips and makes the method robust against high-intensity noise.
- 20 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 25 (6) , 2304-2310
Robust and High Fidelity Mesh Denoising
This paper presents a simple and effective two-stage mesh denoising algorithm, where in the first stage, face normal filtering is done by using bilateral normal filtering in a robust statistics framework. Tukey's bi-weight function is used as similarity function in the bilateral weighting, which is a robust estimator and stops the diffusion at sharp edges to retain features and removes noise from flat regions effectively. In the second stage, an edge-weighted Laplace operator is introduced to compute a differential coordinate. This differential coordinate helps the algorithm to produce a high-quality mesh without any face normal flips and makes the method robust against high-intensity noise.
- Open Access
Robust and High Fidelity Mesh Denoising
This paper presents a simple and effective two-stage mesh denoising algorithm, where in the first stage, the face normal filtering is done by using the bilateral normal filtering in the robust statistics framework. Tukey's bi-weight function is used as similarity function in the bilateral weighting, which is a robust estimator and stops the diffusion at sharp edges to retain features and removes noise from flat regions effectively. In the second stage, an edge weighted Laplace operator is introduced to compute a differential coordinate. This differential coordinate helps the algorithm to produce a high-quality mesh without any face normal flips and makes the method robust against high-intensity noise.
Open AccessRobust and High Fidelity Mesh Denoising
This paper presents a simple and effective two-stage mesh denoising algorithm, where in the first stage, the face normal filtering is done by using the bilateral normal filtering in the robust statistics framework. Tukey's bi-weight function is used as similarity function in the bilateral weighting, which is a robust estimator and stops the diffusion at sharp edges to retain features and removes noise from flat regions effectively. In the second stage, an edge weighted Laplace operator is introduced to compute a differential coordinate. This differential coordinate helps the algorithm to produce a high-quality mesh without any face normal flips and makes the method robust against high-intensity noise.