Mr. Varun Mannam Profile

Varun Mannam

at Univ of Notre Dame

SPIE Involvement:

Author

Area of Expertise:

Deep learning , computer vision , machine learning , image processing , autonomous driving , biomedical image processing

Websites:

Personal Website

Publications (7)

Proceedings Article | 25 April 2023 Presentation + Paper

3D time resolved multiphoton fluorescence lifetime imaging microscopy of nano-crystalline agricultural treatments on living plant tissue

Xiaotong Yuan, Varun Mannam, Scott Howard

Proceedings Volume 12384, 123840A (2023) https://doi.org/10.1117/12.2650736

KEYWORDS: Tissues, Agriculture, Fluorescence lifetime imaging, 3D image processing, Biological imaging, Biological samples, Multiphoton fluorescence microscopy, Fluorescence imaging, Proteins, Molecular imaging

Read Abstract +

SPIE Journal Paper | 14 March 2023 Open Access

Small training dataset convolutional neural networks for application-specific super-resolution microscopy

Varun Mannam, Scott Howard

JBO, Vol. 28, Issue 03, 036501, (March 2023) https://doi.org/10.1117/12.10.1117/1.JBO.28.3.036501

KEYWORDS: Education and training, Image analysis, Data modeling, Convolutional neural networks, Fluorescence microscopy, Gallium nitride, Point spread functions, Performance modeling, Lawrencium, Network architectures

Read Abstract +

SignificanceMachine learning (ML) models based on deep convolutional neural networks have been used to significantly increase microscopy resolution, speed [signal-to-noise ratio (SNR)], and data interpretation. The bottleneck in developing effective ML systems is often the need to acquire large datasets to train the neural network. We demonstrate how adding a “dense encoder-decoder” (DenseED) block can be used to effectively train a neural network that produces super-resolution (SR) images from conventional microscopy diffraction-limited (DL) images trained using a small dataset [15 fields of view (FOVs)].AimThe ML helps to retrieve SR information from a DL image when trained with a massive training dataset. The aim of this work is to demonstrate a neural network that estimates SR images from DL images using modifications that enable training with a small dataset.ApproachWe employ “DenseED” blocks in existing SR ML network architectures. DenseED blocks use a dense layer that concatenates features from the previous convolutional layer to the next convolutional layer. DenseED blocks in fully convolutional networks (FCNs) estimate the SR images when trained with a small training dataset (15 FOVs) of human cells from the Widefield2SIM dataset and in fluorescent-labeled fixed bovine pulmonary artery endothelial cells samples.ResultsConventional ML models without DenseED blocks trained on small datasets fail to accurately estimate SR images while models including the DenseED blocks can. The average peak SNR (PSNR) and resolution improvements achieved by networks containing DenseED blocks are ≈3.2 dB and 2 × , respectively. We evaluated various configurations of target image generation methods (e.g., experimentally captured a target and computationally generated target) that are used to train FCNs with and without DenseED blocks and showed that including DenseED blocks in simple FCNs outperforms compared to simple FCNs without DenseED blocks.ConclusionsDenseED blocks in neural networks show accurate extraction of SR images even if the ML model is trained with a small training dataset of 15 FOVs. This approach shows that microscopy applications can use DenseED blocks to train on smaller datasets that are application-specific imaging platforms and there is promise for applying this to other imaging modalities, such as MRI/x-ray, etc.

DOWNLOAD PAPER

Proceedings Article | 4 March 2022 Presentation + Paper

Deconvolution of fluorescence lifetime imaging microscopy (FLIM)

Varun Mannam, Xiaotong Yuan, Scott Howard

Proceedings Volume 11965, 1196508 (2022) https://doi.org/10.1117/12.2608910

KEYWORDS: Fluorescence lifetime imaging, Deconvolution, Microscopy, Luminescence, Convolution, Point spread functions, Multiphoton microscopy, Multiphoton fluorescence microscopy, Image processing, Distortion

Read Abstract +

Proceedings Article | 2 March 2022 Presentation + Paper

Low dosage 3D volume fluorescence microscopy imaging using compressive sensing

Varun Mannam, Jacob Brandt, Cody Smith, Scott Howard

Proceedings Volume 11966, 1196603 (2022) https://doi.org/10.1117/12.2607515

KEYWORDS: 3D image processing, Microscopy, Compressed sensing, Luminescence, In vivo imaging, Signal to noise ratio, Confocal microscopy, Reconstruction algorithms, Microscopes, 3D modeling

Read Abstract +

Proceedings Article | 5 March 2021 Presentation + Paper

Overcoming the fundamental limitation of frequency-domain fluorescence lifetime imaging microscopy spatial resolution

Xiaotong Yuan, Varun Mannam, Yide Zhang, Scott Howard

Proceedings Volume 11650, 116500M (2021) https://doi.org/10.1117/12.2577284

KEYWORDS: Fluorescence lifetime imaging, Microscopy, Super resolution, Spatial resolution, Luminescence, Stimulated emission depletion microscopy, Super resolution microscopy, Physics, Optical communications, Numerical simulations

Read Abstract +

Proceedings Article | 5 March 2021 Poster + Presentation + Paper

Convolutional neural network denoising in fluorescence lifetime imaging microscopy (FLIM)

Varun Mannam, Yide Zhang, Xiaotong Yuan, Takashi Hato, Pierre Dagher, Evan Nichols, Cody Smith, Kenneth Dunn, Scott Howard

Proceedings Volume 11648, 116481C (2021) https://doi.org/10.1117/12.2578574

KEYWORDS: Fluorescence lifetime imaging, Image segmentation, Microscopy, Denoising, In vivo imaging, Luminescence, Convolutional neural networks, Signal to noise ratio, Imaging systems, Signal processing

Read Abstract +

Proceedings Article | 5 March 2021 Presentation + Paper

Deep learning-based super-resolution fluorescence microscopy on small datasets

Varun Mannam, Yide Zhang, Xiaotong Yuan, Scott Howard

Proceedings Volume 11650, 116500O (2021) https://doi.org/10.1117/12.2578519

KEYWORDS: Super resolution, Microscopy, Luminescence, Organisms, Data modeling, X-rays, X-ray imaging, Visualization, Super resolution microscopy, Magnetic resonance imaging

Read Abstract +

Showing 5 of 7 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years