Sunil Kumar Gaire
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 Gaire has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Vadim Backman
Department of Biomedical Engineering, Northwestern University, Evanston, USA
4 shared publications - Leslie Ying
Department of Biomedical Engineering and Department of Electrical Engineering The State University of New York Buffalo New York USA
3 shared publications Ali Daneshkhah
Northwestern University
2 shared publications- Dong Liang
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
2 shared publications Emily Pujadas Liwag
Northwestern University
2 shared publications- Ethan Flowerday
School of Cyber Studies, The University of Tulsa, Tulsa, OK 74104, USA
2 shared publications
Latest Publications
- Open Access
A Robust Multivariate Thresholding Function for Sparse and Biomedical Signal Reconstruction
This paper presents a computationally efficient Multivariate Mixture Model Thresholding (MMMT) technique for sparse signal denoising and recovery, with the goal of improving data quality in modern sensing and biomedical systems. The proposed method extends classical thresholding approaches by modeling nonzero signal coefficients using a multivariate Gaussian mixture prior, thereby capturing cross-channel and intercomponent dependencies commonly observed in multi-sensor and physiological signals. The thresholding rule is analytically derived through maximum a posteriori (MAP) estimation within a majorization–minimization (MM) optimization framework, while the associated model parameters are adaptively estimated using an expectation–maximization (EM) algorithm. Experimental results on noisy sinusoidal signals and synthetic ECG data demonstrate that MMMT consistently achieves higher correlation with ground-truth signals and improved preservation of pulse amplitude and morphological characteristics compared with benchmark methods, including the -fused lasso and convex–non-convex (CNC) fused lasso. Quantitative evaluations based on correlation metrics, signal-to-noise ratio (SNR), and peak signal-to-noise ratio (PSNR) further confirm the effectiveness of the proposed approach. Owing to its scalability, robustness, and strong statistical interpretability, MMMT provides a promising framework for real-time ECG signal enhancement. Although the proposed framework is general and can be adapted to other biomedical modalities such as EEG, CT, and MRI, experimental validation in this study is limited to ECG signals.Open AccessA Robust Multivariate Thresholding Function for Sparse and Biomedical Signal Reconstruction
This paper presents a computationally efficient Multivariate Mixture Model Thresholding (MMMT) technique for sparse signal denoising and recovery, with the goal of improving data quality in modern sensing and biomedical systems. The proposed method extends classical thresholding approaches by modeling nonzero signal coefficients using a multivariate Gaussian mixture prior, thereby capturing cross-channel and intercomponent dependencies commonly observed in multi-sensor and physiological signals. The thresholding rule is analytically derived through maximum a posteriori (MAP) estimation within a majorization–minimization (MM) optimization framework, while the associated model parameters are adaptively estimated using an expectation–maximization (EM) algorithm. Experimental results on noisy sinusoidal signals and synthetic ECG data demonstrate that MMMT consistently achieves higher correlation with ground-truth signals and improved preservation of pulse amplitude and morphological characteristics compared with benchmark methods, including the -fused lasso and convex–non-convex (CNC) fused lasso. Quantitative evaluations based on correlation metrics, signal-to-noise ratio (SNR), and peak signal-to-noise ratio (PSNR) further confirm the effectiveness of the proposed approach. Owing to its scalability, robustness, and strong statistical interpretability, MMMT provides a promising framework for real-time ECG signal enhancement. Although the proposed framework is general and can be adapted to other biomedical modalities such as EEG, CT, and MRI, experimental validation in this study is limited to ECG signals. - 27 November 2024
- Published by Optica Publishing Group in Optics Express
- Vol. 32 (25) , 45052-45074
Deep learning-driven automatic nuclei segmentation of live-cell chromatin-sensitive partial wave spectroscopic microscopy imaging
Chromatin-sensitive partial wave spectroscopic (csPWS) microscopy offers a non-invasive glimpse into the mass density distribution of cellular structures at the nanoscale, leveraging the spectroscopic information. Such capability allows us to analyze the chromatin structure and organization and the global transcriptional state of the cell nuclei for the study of its role in carcinogenesis. Accurate segmentation of the nuclei in csPWS microscopy images is an essential step in isolating them for further analysis. However, manual segmentation is error-prone, biased, time-consuming, and laborious, resulting in disrupted nuclear boundaries with partial or over-segmentation. Here, we present an innovative deep-learning-driven approach to automate the accurate nuclei segmentation of label-free (without any exogenous fluorescent staining) live cell csPWS microscopy imaging data. Our approach, csPWS-seg, harnesses the convolutional neural networks-based U-Net model with an attention mechanism to automate the accurate cell nuclei segmentation of csPWS microscopy images. We leveraged the structural, physical, and biological differences between the cytoplasm, nucleus, and nuclear periphery to construct three distinct csPWS feature images for nucleus segmentation. Using these images of HCT116 cells, csPWS-seg achieved superior performance with a median intersection over union (IoU) of 0.80 and a Dice similarity coefficient (DSC) score of 0.89. The csPWS-seg outperformed the segmentation performance over several other commonly used deep learning-based segmentation models for biomedical imaging, such as U-Net, SE-U-Net, Mask R-CNN, and DeepLabV3+, marking a significant improvement in segmentation accuracy. Further, we analyzed the performance of our proposed model with four loss functions: binary cross-entropy loss, focal loss, Dice loss, and Jaccard loss separately, as well as a combination of all of these loss functions. The csPWS-seg with focal loss or a combination of these loss functions provided the same best results compared to other loss functions. The automatic and accurate nuclei segmentation offered by the csPWS-seg not only automates, accelerates, and streamlines csPWS data analysis but also enhances the reliability of subsequent chromatin analysis research, paving the way for more accurate diagnostics, treatment, and understanding of cellular mechanisms for carcinogenesis.
- 27 November 2024
- Published by Optica Publishing Group in Optics Express
- Vol. 32 (25) , 45052-45074
Deep learning-driven automatic nuclei segmentation of live-cell chromatin-sensitive partial wave spectroscopic microscopy imaging
Chromatin-sensitive partial wave spectroscopic (csPWS) microscopy offers a non-invasive glimpse into the mass density distribution of cellular structures at the nanoscale, leveraging the spectroscopic information. Such capability allows us to analyze the chromatin structure and organization and the global transcriptional state of the cell nuclei for the study of its role in carcinogenesis. Accurate segmentation of the nuclei in csPWS microscopy images is an essential step in isolating them for further analysis. However, manual segmentation is error-prone, biased, time-consuming, and laborious, resulting in disrupted nuclear boundaries with partial or over-segmentation. Here, we present an innovative deep-learning-driven approach to automate the accurate nuclei segmentation of label-free (without any exogenous fluorescent staining) live cell csPWS microscopy imaging data. Our approach, csPWS-seg, harnesses the convolutional neural networks-based U-Net model with an attention mechanism to automate the accurate cell nuclei segmentation of csPWS microscopy images. We leveraged the structural, physical, and biological differences between the cytoplasm, nucleus, and nuclear periphery to construct three distinct csPWS feature images for nucleus segmentation. Using these images of HCT116 cells, csPWS-seg achieved superior performance with a median intersection over union (IoU) of 0.80 and a Dice similarity coefficient (DSC) score of 0.89. The csPWS-seg outperformed the segmentation performance over several other commonly used deep learning-based segmentation models for biomedical imaging, such as U-Net, SE-U-Net, Mask R-CNN, and DeepLabV3+, marking a significant improvement in segmentation accuracy. Further, we analyzed the performance of our proposed model with four loss functions: binary cross-entropy loss, focal loss, Dice loss, and Jaccard loss separately, as well as a combination of all of these loss functions. The csPWS-seg with focal loss or a combination of these loss functions provided the same best results compared to other loss functions. The automatic and accurate nuclei segmentation offered by the csPWS-seg not only automates, accelerates, and streamlines csPWS data analysis but also enhances the reliability of subsequent chromatin analysis research, paving the way for more accurate diagnostics, treatment, and understanding of cellular mechanisms for carcinogenesis.
- Open Access
Deep Learning-driven Automatic Nuclei Segmentation of Label-free Live Cell Chromatin-sensitive Partial Wave Spectroscopic Microscopy Imaging
Chromatin-sensitive Partial Wave Spectroscopic (csPWS) microscopy offers a non-invasive glimpse into the mass density distribution of cellular structures at the nanoscale, leveraging the spectroscopic information. Such capability allows us to analyze the chromatin structure and organization and the global transcriptional state of the cell nuclei for the study of its role in carcinogenesis. Accurate segmentation of the nuclei in csPWS microscopy images is an essential step in isolating them for further analysis. However, manual segmentation is error-prone, biased, time-consuming, and laborious, resulting in disrupted nuclear boundaries with partial or over-segmentation. Here, we present an innovative deep-learning-driven approach to automate the accurate nuclei segmentation of label-free live cell csPWS microscopy imaging data. Our approach, csPWS-seg, harnesses the Convolutional Neural Networks-based U-Net model with an attention mechanism to automate the accurate cell nuclei segmentation of csPWS microscopy images. We leveraged the structural, physical, and biological differences between the cytoplasm, nucleus, and nuclear periphery to construct three distinct csPWS feature images for nucleus segmentation. Using these images of HCT116 cells, csPWS-seg achieved superior performance with a median Intersection over Union (IoU) of 0.80 and a Dice Similarity Coefficient (DSC) score of 0.88. The csPWS-seg overcame the segmentation performance over the baseline U-Net model and another attention-based model, SE-U-Net, marking a significant improvement in segmentation accuracy. Further, we analyzed the performance of our proposed model with four loss functions: binary cross-entropy loss, focal loss, dice loss, and Jaccard loss. The csPWS-seg with focal loss provided the best results compared to other loss functions. The automatic and accurate nuclei segmentation offered by the csPWS-seg not only automates, accelerates, and streamlines csPWS data analysis but also enhances the reliability of subsequent chromatin analysis research, paving the way for more accurate diagnostics, treatment, and understanding of cellular mechanisms for carcinogenesis.
Open AccessDeep Learning-driven Automatic Nuclei Segmentation of Label-free Live Cell Chromatin-sensitive Partial Wave Spectroscopic Microscopy Imaging
Chromatin-sensitive Partial Wave Spectroscopic (csPWS) microscopy offers a non-invasive glimpse into the mass density distribution of cellular structures at the nanoscale, leveraging the spectroscopic information. Such capability allows us to analyze the chromatin structure and organization and the global transcriptional state of the cell nuclei for the study of its role in carcinogenesis. Accurate segmentation of the nuclei in csPWS microscopy images is an essential step in isolating them for further analysis. However, manual segmentation is error-prone, biased, time-consuming, and laborious, resulting in disrupted nuclear boundaries with partial or over-segmentation. Here, we present an innovative deep-learning-driven approach to automate the accurate nuclei segmentation of label-free live cell csPWS microscopy imaging data. Our approach, csPWS-seg, harnesses the Convolutional Neural Networks-based U-Net model with an attention mechanism to automate the accurate cell nuclei segmentation of csPWS microscopy images. We leveraged the structural, physical, and biological differences between the cytoplasm, nucleus, and nuclear periphery to construct three distinct csPWS feature images for nucleus segmentation. Using these images of HCT116 cells, csPWS-seg achieved superior performance with a median Intersection over Union (IoU) of 0.80 and a Dice Similarity Coefficient (DSC) score of 0.88. The csPWS-seg overcame the segmentation performance over the baseline U-Net model and another attention-based model, SE-U-Net, marking a significant improvement in segmentation accuracy. Further, we analyzed the performance of our proposed model with four loss functions: binary cross-entropy loss, focal loss, dice loss, and Jaccard loss. The csPWS-seg with focal loss provided the best results compared to other loss functions. The automatic and accurate nuclei segmentation offered by the csPWS-seg not only automates, accelerates, and streamlines csPWS data analysis but also enhances the reliability of subsequent chromatin analysis research, paving the way for more accurate diagnostics, treatment, and understanding of cellular mechanisms for carcinogenesis.
- Open Access
- 24 May 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (06) , 066501-19
Deep learning-based spectroscopic single-molecule localization microscopy
Single-molecule localization microscopy (SMLM), exemplified by techniques, such as stochastic optical reconstruction microscopy (STORM),1 photoactivated localization microscopy (PALM),2,3 point accumulation for imaging in nanoscale topography (PAINT),4 and other variants,5,6 have revolutionized the field of microscopy by transcending the spatial resolution of conventional diffraction-limited microscopy. These super-resolution techniques thus enable the imaging of subcellular structures at a nanometer-level (up to ) resolution. Building upon wide-field imaging principles, SMLM methods exploit the ability to precisely determine the spatial coordinates of single fluorophores provided their point spread functions (PSFs) remain non-overlap and emit a sufficient number of photons.7 – 9 Recently, spectroscopic single-molecule localization microscopy (sSMLM) has emerged that utilizes additional spectral information, often overlooked in conventional SMLM imaging.10,11 In sSMLM, incorporating a dispersive optical component, such as a prism or grating, emission light from the sample is split into two imaging paths, both of which are captured using a single camera. The resulting image frame consists of a spatial image representing the spatial distribution of blinking events and a spectral image containing the corresponding emission spectra. These image frames undergo a computational process to determine the spatial localization position of the fluorophores and identify the corresponding distinct spectroscopic signatures (e.g., spectral peaks or centroids) associated with each blinking molecule. By correlating the spatial localization position with its associated emission spectra, it becomes possible to distinguish molecules within closer proximity compared to standard SMLM.- 24 May 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (06) , 066501-19
Open AccessDeep learning-based spectroscopic single-molecule localization microscopy
Single-molecule localization microscopy (SMLM), exemplified by techniques, such as stochastic optical reconstruction microscopy (STORM),1 photoactivated localization microscopy (PALM),2,3 point accumulation for imaging in nanoscale topography (PAINT),4 and other variants,5,6 have revolutionized the field of microscopy by transcending the spatial resolution of conventional diffraction-limited microscopy. These super-resolution techniques thus enable the imaging of subcellular structures at a nanometer-level (up to ) resolution. Building upon wide-field imaging principles, SMLM methods exploit the ability to precisely determine the spatial coordinates of single fluorophores provided their point spread functions (PSFs) remain non-overlap and emit a sufficient number of photons.7 – 9 Recently, spectroscopic single-molecule localization microscopy (sSMLM) has emerged that utilizes additional spectral information, often overlooked in conventional SMLM imaging.10,11 In sSMLM, incorporating a dispersive optical component, such as a prism or grating, emission light from the sample is split into two imaging paths, both of which are captured using a single camera. The resulting image frame consists of a spatial image representing the spatial distribution of blinking events and a spectral image containing the corresponding emission spectra. These image frames undergo a computational process to determine the spatial localization position of the fluorophores and identify the corresponding distinct spectroscopic signatures (e.g., spectral peaks or centroids) associated with each blinking molecule. By correlating the spatial localization position with its associated emission spectra, it becomes possible to distinguish molecules within closer proximity compared to standard SMLM. - 1 January 2023
- Published by Optica Publishing Group
- Vol. 7, IM4E.4
Simultaneous Multicolor Spectroscopic Single-molecule Localization Microscopy Image Reconstruction using Machine Learning
We present all machine learning-based reconstruction approach for simultaneous multicolor spectroscopic super-resolution microscopy. Machine learning is used for localization and spectral classification. Reconstruction of the simultaneous two-color imaging of the nanoruler sample with a mark-to-mark distance of 40 nm is presented.
- 1 January 2023
- Published by Optica Publishing Group
- Vol. 7, IM4E.4
Simultaneous Multicolor Spectroscopic Single-molecule Localization Microscopy Image Reconstruction using Machine Learning
We present all machine learning-based reconstruction approach for simultaneous multicolor spectroscopic super-resolution microscopy. Machine learning is used for localization and spectral classification. Reconstruction of the simultaneous two-color imaging of the nanoruler sample with a mark-to-mark distance of 40 nm is presented.
- Open Access
- 27 February 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 26 (02) , 026501-15
Accelerating 3D single-molecule localization microscopy using blind sparse inpainting
Significance: Single-molecule localization-based super-resolution microscopy has enabled the imaging of microscopic objects beyond the diffraction limit. However, this technique is limited by the requirements of imaging an extremely large number of frames of biological samples to generate a super-resolution image, thus requiring a longer acquisition time. Additionally, the processing of such a large image sequence leads to longer data processing time. Therefore, accelerating image acquisition and processing in single-molecule localization microscopy (SMLM) has been of perennial interest. Aim: To accelerate three-dimensional (3D) SMLM imaging by leveraging a computational approach without compromising the resolution. Approach: We used blind sparse inpainting to reconstruct high-density 3D images from low-density ones. The low-density images are generated using much fewer frames than usually needed, thus requiring a shorter acquisition and processing time. Therefore, our technique will accelerate 3D SMLM without changing the existing standard SMLM hardware system and labeling protocol. Results: The performance of the blind sparse inpainting was evaluated on both simulation and experimental datasets. Superior reconstruction results of 3D SMLM images using up to 10-fold fewer frames in simulation and up to 50-fold fewer frames in experimental data were achieved. Conclusions: We demonstrate the feasibility of fast 3D SMLM imaging leveraging a computational approach to reduce the number of acquired frames. We anticipate our technique will enable future real-time live-cell 3D imaging to investigate complex nanoscopic biological structures and their functions.
- 27 February 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 26 (02) , 026501-15
Open AccessAccelerating 3D single-molecule localization microscopy using blind sparse inpainting
Significance: Single-molecule localization-based super-resolution microscopy has enabled the imaging of microscopic objects beyond the diffraction limit. However, this technique is limited by the requirements of imaging an extremely large number of frames of biological samples to generate a super-resolution image, thus requiring a longer acquisition time. Additionally, the processing of such a large image sequence leads to longer data processing time. Therefore, accelerating image acquisition and processing in single-molecule localization microscopy (SMLM) has been of perennial interest. Aim: To accelerate three-dimensional (3D) SMLM imaging by leveraging a computational approach without compromising the resolution. Approach: We used blind sparse inpainting to reconstruct high-density 3D images from low-density ones. The low-density images are generated using much fewer frames than usually needed, thus requiring a shorter acquisition and processing time. Therefore, our technique will accelerate 3D SMLM without changing the existing standard SMLM hardware system and labeling protocol. Results: The performance of the blind sparse inpainting was evaluated on both simulation and experimental datasets. Superior reconstruction results of 3D SMLM images using up to 10-fold fewer frames in simulation and up to 50-fold fewer frames in experimental data were achieved. Conclusions: We demonstrate the feasibility of fast 3D SMLM imaging leveraging a computational approach to reduce the number of acquired frames. We anticipate our technique will enable future real-time live-cell 3D imaging to investigate complex nanoscopic biological structures and their functions.
- Open Access
- 1 September 2020
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 10 (9) , 1748-1762
Diagnostic interchangeability of deep convolutional neural networks reconstructed knee MR images: preliminary experience
Background: MRI acceleration using deep learning (DL) convolutional neural networks (CNNs) is a novel technique with great promise. Increasing the number of convolutional layers may allow for more accurate image reconstruction. Studies on evaluating the diagnostic interchangeability of DL reconstructed knee magnetic resonance (MR) images are scarce. The purpose of this study was to develop a deep CNN (DCNN) with an optimal number of layers for accelerating knee magnetic resonance imaging (MRI) acquisition by 6-fold and to test the diagnostic interchangeability and image quality of nonaccelerated images versus images reconstructed with a 15-layer DCNN or 3-layer CNN. Methods: For the feasibility portion of this study, 10 patients were randomly selected from the Osteoarthritis Initiative (OAI) cohort. For the interchangeability portion of the study, 40 patients were randomly selected from the OAI cohort. Three readers assessed meniscal and anterior cruciate ligament (ACL) tears and cartilage defects using DCNN, CNN, and nonaccelerated images. Image quality was subjectively graded as nondiagnostic, poor, acceptable, or excellent. Interchangeability was tested by comparing the frequency of agreement when readers used both accelerated and nonaccelerated images to frequency of agreement when readers only used nonaccelerated images. A noninferiority margin of 0.10 was used to ensure type I error ≤5% and power ≥80%. A logistic regression model using generalized estimating equations was used to compare proportions; 95% confidence intervals (CIs) were constructed. Results: DCNN and CNN images were interchangeable with nonaccelerated images for all structures, with excess disagreement values ranging from –2.5% [95% CI: (–6.1, 1.1)] to 3.0% [95% CI: (–0.1, 6.1)]. The quality of DCNN images was graded higher than that of CNN images but less than that of nonaccelerated images [excellent/acceptable quality: DCNN, 95% of cases (114/120); CNN, 60% (72/120); nonaccelerated, 97.5% (117/120)]. Conclusions: Six-fold accelerated knee images reconstructed with a DL technique are diagnostically interchangeable with nonaccelerated images and have acceptable image quality when using a 15-layer CNN.
- 1 September 2020
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 10 (9) , 1748-1762
Open AccessDiagnostic interchangeability of deep convolutional neural networks reconstructed knee MR images: preliminary experience
Background: MRI acceleration using deep learning (DL) convolutional neural networks (CNNs) is a novel technique with great promise. Increasing the number of convolutional layers may allow for more accurate image reconstruction. Studies on evaluating the diagnostic interchangeability of DL reconstructed knee magnetic resonance (MR) images are scarce. The purpose of this study was to develop a deep CNN (DCNN) with an optimal number of layers for accelerating knee magnetic resonance imaging (MRI) acquisition by 6-fold and to test the diagnostic interchangeability and image quality of nonaccelerated images versus images reconstructed with a 15-layer DCNN or 3-layer CNN. Methods: For the feasibility portion of this study, 10 patients were randomly selected from the Osteoarthritis Initiative (OAI) cohort. For the interchangeability portion of the study, 40 patients were randomly selected from the OAI cohort. Three readers assessed meniscal and anterior cruciate ligament (ACL) tears and cartilage defects using DCNN, CNN, and nonaccelerated images. Image quality was subjectively graded as nondiagnostic, poor, acceptable, or excellent. Interchangeability was tested by comparing the frequency of agreement when readers used both accelerated and nonaccelerated images to frequency of agreement when readers only used nonaccelerated images. A noninferiority margin of 0.10 was used to ensure type I error ≤5% and power ≥80%. A logistic regression model using generalized estimating equations was used to compare proportions; 95% confidence intervals (CIs) were constructed. Results: DCNN and CNN images were interchangeable with nonaccelerated images for all structures, with excess disagreement values ranging from –2.5% [95% CI: (–6.1, 1.1)] to 3.0% [95% CI: (–0.1, 6.1)]. The quality of DCNN images was graded higher than that of CNN images but less than that of nonaccelerated images [excellent/acceptable quality: DCNN, 95% of cases (114/120); CNN, 60% (72/120); nonaccelerated, 97.5% (117/120)]. Conclusions: Six-fold accelerated knee images reconstructed with a DL technique are diagnostically interchangeable with nonaccelerated images and have acceptable image quality when using a 15-layer CNN.
- 19 September 2016
- Published by SPIE-Intl Soc Optical Eng
- Vol. 9979, 99790D-99790D-9
OptoRadio: a method of wireless communication using orthogonal M-ary PSK (OMPSK) modulation
- 19 September 2016
- Published by SPIE-Intl Soc Optical Eng
- Vol. 9979, 99790D-99790D-9
OptoRadio: a method of wireless communication using orthogonal M-ary PSK (OMPSK) modulation