Major Research Areas/Interests/Projects - Bioinformatics

I. Biomedical Signal/Image/Video Processing and Analysis

Application of signal processing, image processing, computer vision and machine learning techniques to biomedical data - Magnetic Resonance (MR), Computed Tomography (CT), Positron Emission Tomography (PET), Single-Photon Emission Computed Tomography (SPECT), Optical Coherence Tomography (OCT), X-ray, Dual energy X-ray absorptiometry (DEXA), Ultrasound (US), Portable Ultrasound, Wireless Capsule Endoscopy, Colonoscopy, Histopathology, Confocal, Fluorescence, Magnetic Resonance Angiography (MRA), Fluorescein Angiogram, Color Fundus, Two-photon Microscopy, Mass Spectrometry Imaging (MSI), Matrix-assisted Laser Desorption/Ionization (MALDI), Mammography, Cryo-EM, cDNA Microarray images, Laryngeal High-Speed Videos, Electroencephalography (EEG), Electrocardiography (ECG), MR Elastography, Calcium Imaging, Fluorescence lifetime imaging microscopy (FLIM). Image reconstruction, compressed sensing, enhancement, noise removal, compression of endoscopic videos, image segmentation based on active contours, shape based (Shape from Shading, Structure from Motion) approaches for endoscopic images. Machine learning, and deep learning for biomedical image analysis - Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Generative Adversarial Network (GAN), Recurrent Neural Network (RNN), Encoder-Decoder, Transformers. Bioinformatics, visualization and interpretation of biomedical imaging data. Segmentation and quantitative image analysis for magnetic resonance, histopathological, fluorescence microscopy images. E-health, telemedicine, m-health related data processing. Computational neuroscience, transcranial direct current stimulation (tDCS), fMRI analysis. Clinical/federated learning implementation of machine learning, deep learning models for imaging and multimodal data, clinical informatics. Application of signal processing, image processing, computer vision and machine learning techniques to clinical and patient's video analysis. AI for CP/TBI patient's rehabilitation, gait pathology detection. Video-based action recognition, fall detection, motion analysis, optical flow.

Project pages:

CT : ICH, DEXA, Lung/Chest CT, Abdominal CT, DReCon, MOSeg

Endoscopy : MucosaSeg, 3D-SfS, Stamping, Illumination, CE-Polyps, Bleeding, Distortion, Compression, Summary, Colonopolyps, Stereo, Registration, Polypseg, Quality, Celiac, Tumor, Ulcer, ArcEndos, Chromoendoscopy - FICE, NBI

Histopathology : StromaSeg, Glioma, NucleiSeg, Ulcer, EsoCount, IBD/CD/UC, Liver Fibrosis, LungMAP, Breast Cancer

Microscopy : Denoising, Segmentation, Clustering, ConIFSeg, RF-HEp-2, HEp-2SegZoo, RetinalSeg, Confocal - Denoising, Deconvolution, Cryo-EM, IHC, FISH, MALDI-MS, ErythroNet

MRI : MAC-Multiphase segmentation, MSP-Mid saggital plane, Skull stripping, Symmetry, SIMMER, Bleeds, Denoising, iSPi

Ultrasound : Stiffness, PylStenNet, Denoising, Segmentation, AbsCellUSNet, PEchoNet

Video Analysis : CP/Gait Analysis, GMA, DLVD, 3D-Cell-Tracking

X-ray : PICCLineNet, TracNet, Denoising, Analysis, LungSeg, LungBoundary, TBScreen, Cardiomegaly, OrganSeg, CBXIR, DEXA

Selected publications:

  • I. N. Figueiredo, S. Prasath, Y.-H. R. Tsai, P. N. Figueiredo. Automatic detection and segmentation of colonic polyps in wireless capsule images. CAM Report 10-65, Department of Mathematics, University of California Los Angeles (UCLA), 2010.

  • P. N. Figueiredo, I. N. Figueiredo, S. Prasath and R. Tsai. Automatic polyp detection in PillCam COLON 2 capsule images and videos: Preliminary feasibility report. Diagnostic and Therapeutic Endoscopy, Vol. 2011, Article ID 182435, 16pp, 2011.

  • J. C. Moreno, V. B. S. Prasath, H. Proenca, K. Palaniappan. Fast and globally convex multiphase active contours for brain MRI segmentation. Computer Vision and Image Understanding, 125:237-250, 2014. [MAC]

  • P. Kalavathi, V. B. S. Prasath. Automatic segmentation of cerebral hemispheres in MR human head scans. International Journal of Imaging Systems and Technology - Neuroimaging and Brain Mapping, 26(1):15-23, 2016. [MSP]

  • P. Kalavathi, V. B. S. Prasath. Methods on skull stripping of MRI head scan images - A review. Journal of Digital Imaging, 29(3):365-397, 2016. [Skullstrip]

  • V. B. S. Prasath, Y. M. Kassim, Z. A. Oraibi, J.-B. Guiriec, A. Hafiane, K. Palaniappan. HEp-2 cell classification and segmentation using motif texture patterns and spatial features with random forests. International Contests on Pattern Recognition Techniques for Indirect Immunofluorescence Images Analysis, International Conference on Pattern Recognition (ICPR), Cancun, Mexico, Dec 2016. Proc. IEEE, pp. 90-95. [IIF-HEp2]

  • V. B. S. Prasath. Polyp detection and segmentation from video capsule endoscopy: A review. Journal of Imaging, 3(1), 2017. Preliminary Version at arXiv:1609.01915 [CE-Polyps]

  • A. Yonekura, H. Kawanaka, V. B. S. Prasath, B. J. Aronow, H. Takase. Automatic disease stage classification of glioblastoma multiforme histopathological images using deep convolutional neural network. Biomedical Engineering Letters, 8(3), 321-327, August 2018. [Glioma]

  • D. N. H. Thanh, V. B. S. Prasath, L. M. Hieu, N. N. Hien. Melanoma skin cancer detection method based on adaptive principal curvature, colour normalisation and feature extraction with the ABCD rule. Journal of Digital Imaging, 33(3), 574-585, June 2020.

  • T. Hayakawa, V. B. S. Prasath, H. Kawanaka, B. J. Aronow, S. Tsuruoka. Computational nuclei segmentation methods in digital pathology: A survey. Archives of Computational Methods in Engineering, 28(1), 1-13, January 2021. [NucleiSeg]

II. Machine Learning for Bioinformatics/Computational Biology

Application of machine/deep learning to single cell RNA sequence (scRNAseq), Assay for Transposase-Accessible Chromatin using sequence (ATAC-seq), etc. Analysis of high throughput sequencing genomics data (ChIP-Seq, DNase-Seq, and/or ATAC-Seq). Deep learning, explainable AI for computational biology problems - quality control (QC), clustering, denoising, imputation, trajectory inference, immunogenicity prediction, RNA binding protein prediction, transcription factor binding prediction, antimicrobial resistance prediction. Analysis of multiplexed imaging, mass spectrometry imaging (MSI), CODEX imaging, spatial transcriptomics in tandem with single-cell genomics data and in general multi-omics, and multi-modal analysis. Exploration of latent structures in single cell data, finding common embeddings/integration for mutimodal biological data. Automated cell population discovery, exploration of latent structures in single cell data, finding common embeddings/integration for mutimodal biological data.

Project pages:

  1. Imaging-based: Clustering

  2. Single-cell: DeepImmuno, CellDrift, scTriangulate, MaxATAC

  3. Metagenomics: MGS2AMR

Selected publications:

  • J. Zhang, Q. Wu, C. B. Johnson, G. Pham, J. M. Kinder, A. Olsson, A. Slaughter, M. May, B. Weinhaus, A. D'Alessandro, J. D. Engel, J. X. Jiang, J. M. Kofron, L. F. Huang, V. B. S. Prasath, S. S. Way, N. Salomonis, H. L. Grimes, D. Lucas. In situ mapping identifies distinct vascular niches for myelopoiesis. Nature, 590, 457-462, February 2021. [Clustering]

  • G. Li, B. Iyer, V. B. S. Prasath, Y. Ni, N. Salomonis. DeepImmuno: Deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity. Briefings in Bioinformatics, 22(6), November 2021. Code, online app. [DeepImmuno]

  • K. Jin, D. Schnell, G. Li, N. Salomonis, S. Prasath, R. Szczesniak, B. J. Aronow. CellDrift: Inferring perturbation responses in temporally-sampled single cell data. Briefings in Bioinformatics, 23(5), September 2022. Code [CellDrift]

  • G. Li, B. Song, H. Singh, V. B. S. Prasath, H. L. Grimes, N. Salomonis. scTriangulate, decision-level integration of uni- and multimodal single-cell data. Nature Communications, 14, 406, January 2023. [scTriangulate]

  • T. A Cazares, F. W. Rizvi, B. Iyer, X. Chen, M. Kotliar, J. A. Wayman, A. Bejjani, O. Donmez, B. Wronowski, S. Parameswaran, L. C. Kottyan, A. Barski, M. T. Weirauch, V. B. S. Prasath, E. R. Miraldi. maxATAC: Genome-scale transcription-factor binding prediction from ATAC-seq with deep neural networks. PLOS Computational Biology, 2023. Biorxiv:10.1101/2022.01.28.478235 [maxATAC]

III. Machine Learning for Applied Clinical Informatics

Application of natural language processing, signal processing, image processing, computer vision and machine learning techniques to clinical, heath, and medical informatics problems. AI for NICU/PICU/ICU/CICU data, Critical Care, Emergency Medicine, Sepsis, Bronchopulmonary Dysplasia. Healthcare NLP for EHR/EMR/ePHI/PHR/PRO Data - Unstructured text data analysis with ML/DL - Clinical data - MLDevOps + FHIR. AI for Healthcare and Clinical Implementation. AI for NICU/PICU/ICU/CICU.

Project pages:

  1. AI/NLP/Imaging for NICU: NLP-PICC, PICCLineNet, BPD, Sepsis, NPD

  2. EHR : RareDiseases, ASD

Selected publications:

  • M. Shah, D. Shu, V. B. S. Prasath, Y. Ni, A. Schapiro, K. Dufendach. Machine learning for detection of correct peripherally inserted central catheter tip position from radiology reports in infants. Applied Clinical Informatics, 12(04), 856-863, August 2021. [NLP-PICC]

  • M. Shah, D. Jain, V. B. S. Prasath, K. Dufendach. Artificial intelligence in bronchopulmonary dysplasia - Current research and unexplored frontiers. Pediatric Research, 2022.

Other Projects - Applied Mathematics - Imaging/Data Science

Note that these contain prior major research projects in the areas of Applied Mathematics, Image Processing, and Computer Vision 2004 to 2018 i.e. before the start of Prasath Lab @ CCHMC in March 2018. Although we continue to work on these areas the major focus of our lab are now in various Bio + Medical Informatics (BMI) areas.

I. Analysis & PDEs with Image Processing Applications

Nonlinear, anisotropic diffusion partial differential equations (PDEs), Weak/viscosity/dissipative/Young measure solutions, Perona-Malik type diffusion PDEs, variable exponent PDEs, p-Laplacian, p(t,x)-Laplacian, complex diffusion, higher order PDEs, adaptive PDEs and computational methods (finite differences, finite elements) for solving them are major themes. Linear, nonlinear scale space theory and applications - smoothing, denoising, deblurring, super-resolution, fusion, segmentation, decomposition.

Project pages:

  1. Mono-channel (Gray-scale) : CoupledPDEs, MTTV, AFBD, ABO4, Fractional, Infinity, Rinse, Ahana

  2. Multi-channel (Color, Multispectral, Hyperspectral) : MultiAD, VTV-denoise, CMAC, VarEx, MMIS, CEDzoo, WNOF

Selected publications:

  • V. B. S. Prasath, A. Singh. Multispectral image denoising by well-posed anisotropic diffusion with channel coupling. International Journal of Remote Sensing, 31(08):2091-2099, 2010. [MultiAD]

  • V. B. S. Prasath, A. Singh. Well-posed inhomogeneous nonlinear diffusion scheme for digital image denoising. Journal of Applied Mathematics, Vol. 2010, Article ID 763847, 15 pp, 2010.

  • V. B. S. Prasath, A. Singh. An adaptive anisotropic diffusion scheme for image restoration and selective smoothing. International Journal of Image and Graphics, 12(1):18pp, 2012.

  • V. B. S. Prasath, D. Vorotnikov. On a system of adaptive coupled PDEs for image restoration. Journal of Mathematical Imaging and Vision, 48(1):35-52, 2014. Preliminary Version at arXiv:1112.2904, and accompanying slides. [CoupledPDEs]

  • V. B. S. Prasath, D. Vorotnikov. Weighted and well-balanced anisotropic diffusion scheme for image denoising and restoration. Nonlinear Analysis: Real World Applications, 17:33-46, 2014.

  • V. B. S. Prasath, J. M. Urbano, D. Vorotnikov. Analysis of adaptive forward-backward diffusion flows with applications in image processing. Inverse Problems, 31, 105008 (30pp), 2015. Preprint 15-07, Department of Mathematics, University of Coimbra. [AFBD]

  • V. B. S. Prasath, J. C. Moreno. On convergent finite difference schemes for variational - PDE based image processing. Computational and Applied Mathematics, Jan 2017. Preliminary Version at arXiv:1310.7443.

  • V. B. S. Prasath, D. Vorotnikov. On time adaptive critical variable exponent vectorial diffusion flows and their applications in image processing I. Analysis. Nonlinear Analysis, 168:176-197, 2018. Preliminary Version at arXiv:1603.06337. [VarEx]

  • N. Salamat, M. M. S. Missen, V. B. S. Prasath. Recent developments in computational color image denoising with PDEs to deep learning: A review. Artificial Intelligence Review, 54(8): 6245-6276, December 2021.

  • N. Salamat, M. M. S. Missen, N. Akhtar, M. Mustahsan, V. B. S. Prasath. Color image restoration by filtering methods - A review. Soft Computing, 2023.

We organized the Mini-Symposium on Analysis of PDEs from Image processing at the SIAM Conference on Analysis of Partial Differential Equations 2013 Conference, Lake Buena Vista, FL, USA.

II. Variational Methods, Regularization Techniques

In this direction the primary focus is to regularize ill-posed problems arising in signal processing, image processing, computer vision, and machine learning. Total variation (TV), total generalized variation (TGV), higher order total variation (HOTV), L0, L1, and Lp optimization, elastic net, sparse representation, convex, non-convex regularization, optimization, energy minimization, and corresponding numerical schemes (dual minimization, split Bregman) are major thrust areas.

Project pages:

  1. Regularization: MTTV, MAC, CMAC, PIDTGV, SIMRES, Gradfit, M2AC, Modseg, CBseg, Fusion, OmniReg, TVzoo, L0z, Cartoon, Featurefit, REPAIR, Super, OCT

  2. Total variation: VTV-denoise, AdaptiveTV/wTV, Decomposition

Selected publications:

  • V. B. S. Prasath, A. Singh. A hybrid convex variational model for image restoration. Applied Mathematics and Computation, 215(10):3655-3664, 2010.

  • V. B. S. Prasath. A well-posed multiscale regularization scheme for digital image denoising. International Journal of Applied Mathematics and Computer Science, 21(4):769-777, 2011.

  • V. B. S. Prasath, D. Vorotnikov, R. Pelapur, Shani Jose, G. Seetharaman, K. Palaniappan. Multiscale Tikhonov-total variation image restoration using spatially varying edge coherence exponent. IEEE Transactions on Image Processing, 24(12):5220-5235, 2015. [MTTV]

  • J. C. Moreno, V. B. S. Prasath, J. C. Neves. Color image processing by vectorial total variation with gradient channels coupling. Inverse Problems and Imaging, 10(2):461-497, 2016. [VTV-denoise]

  • V. B. S. Prasath. Quantum noise removal in X-ray images with adaptive total variation regularization. Informatica, 28(3), 505--515, September 2017. [AdaptiveTV]

  • V. B. S. Prasath, R. Pelapur, G. Seetharaman, K. Palaniappan. Multiscale structure tensor for improved feature extraction and image regularization. IEEE Transactions on Image Processing, 28(12), 6198-6210, December 2019.

  • D. N. H. Thanh, V. B. S. Prasath, Le Minh Hieu, Sergey Dvoenko. An adaptive method for image restoration based on high-order total variation and inverse gradient. Signal, Image and Video Processing, 14(6), 1189-1197, September 2020.

  • E. H. S. Diop, A.-O. Boudraa, V. B. S. Prasath. Optimal nonlinear signal approximations based on piecewise constant functions. Circuits, Systems and Signal Processing, 39(5), 2673-2694, May 2020.

  • E. H. S. Diop, A. Ngom, V. B. S. Prasath. Signal approximations based on an nonlinear and optimal piecewise affine functions. Circuits, Systems, and Signal Processing, 2022.

III. Remote Sensing, Biometrics, Other Image Processing/Computer Vision Problems and Data Science Domains

Image speckle denoising, segmentation for SAR, PolSAR images. Road network extraction from aerial imagery. Wavelets, Shearlets for image processing. Regression analysis, Robust M-estimators, Discontinuity adaptive smoothing schemes and kernel smoothing. Image and data fusion, multi-focus fusion, multi-sensor fusion, sensor networks. Biometrics - ocular, periocular, fingerprint, iris, retina, face, palm print. Multi-view geometry, shape from X, segmentation, optical flow, mosaicing, blending, registration, point cloud processing, tracking, large scale 3D reconstruction for full motion video (FMV), wide area motion imagery (WAMI), video surveillance, summarization, event detection. DTM/DEM, edge detection, super-resolution, deblocking, decompression, saliency detection, watermarking, steganography, Kinect depth data processing, local binary patterns, registration, video data analysis. Feature analysis, deep learning for image processing and computer vision problems. Sensor networks with emphasize on visual sensors, internet of things (IoT), natural language processing (NLP), text mining, affective computing, sentiment analysis from text, social media data, emotion recognition from image data. Topological data analysis (TDA) for signals, imaging and biomedical informatics problems.

Project pages:

  1. Remote Sensing: Shadows, STLLT, PolSARSeg, Clouds, Roads, WAMI

  2. Biometrics : Periocular, Veil, V-sign, Fingerprint, Iris, Hands

  3. Image quality : MSID, BriCho

  4. Misc : Splineseg, CSANG, SSTEdges, LOHI, STEAD, TopGradED, ScaleInvED, RC-BA, GeLaDA, Weld, LSS3D, P3D, FashionableGAN, Entrans

Selected publications:

  • V. B. S. Prasath, A. Singh. Multichannel image restoration using combined channel information and robust M-estimator approach. International Journal of Tomography and Statistics, 12(F10):9-22, 2010.

  • V. B. S. Prasath, O. Haddad. Radar shadow detection in SAR images using DEM and projections, Journal Applied Remote Sensing, 8(1), 083628, 2014. Preliminary Version at arXiv:1309.1830, and accompanying datasets. [Shadows]

  • J. C. Moreno, V. B. S. Prasath, G. Santos, H. Proença. Robust periocular recognition by fusing sparse representations of color and geometry information. Journal of Signal Processing Systems. 82(3):403-417, 2016. [Periocular]

  • H. Aliakbarpour, V. B. S. Prasath, K. Palaniappan, G. Seetharaman, J. Dias. Heterogeneous multi-view information fusion: Review of 3-D reconstruction methods and a new registration with uncertainty modeling. IEEE Access, 4(1):8264-8285, 2016.

  • H. Aliakbarpour, J. F. Ferreira, V. B. S. Prasath, K. Palaniappan, G. Seetharaman, J. Dias. A probabilistic framework for 3D reconstruction using heterogeneous sensors. IEEE Sensors Journal, 17(9):2640-2641, 2017.

To be updated soon with more projects! meantime you can take a look at the publications page.