Dr. Prathyush Chirra Profile

Dr. Prathyush Chirra

SPIE Involvement:

Author

Publications (6)

Proceedings Article | 3 April 2023 Presentation + Paper

Integrating multi-plane and multi-region radiomic features to predict pathologic response to neoadjuvant chemoradiation in rectal cancers via pre-treatment MRI

Thomas DeSilvio, Leo Bao, Dhruv Seth, Prathyush Chirra, Sneha Singh, Atreya Sridharan, Murad Labbad, Katie Bingmer, Diana Jodeh, Eric Marderstein, Rajmohan Paspulati, David Liska, Kenneth Friedman, Smitha Krishnamurthi, Sharon Stein, Andrei Purysko, Satish Viswanath

Proceedings Volume 12466, 124660K (2023) https://doi.org/10.1117/12.2655787

KEYWORDS: Tumors, Radiomics, Magnetic resonance imaging, Cancer, Oncology, Feature extraction, Visualization, Performance modeling, Surgery, Rectum

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Deep hybrid convolutional wavelet networks: application to predicting response to chemoradiation in rectal cancers via MRI

Amir Reza Sadri, Thomas DeSilvio, Prathyush Chirra, Andrei Purysko, Rajmohan Paspulati, Kenneth Friedman, Smitha Krishnamurthi, David Liska, Sharon Stein, Satish Viswanath

Proceedings Volume 12033, 120330H (2022) https://doi.org/10.1117/12.2613035

KEYWORDS: Wavelets, Magnetic resonance imaging, Cancer, Tumors, 3D modeling, Network architectures, Neural networks, Data modeling, Oncology, Neurons

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Presentation + Paper

Identifying radiomic features associated with disease activity, patient outcomes, and serum phenotypes in pediatric Crohn's disease via MRI

Prathyush Chirra, Avani Muchhala, Katelin Amann, Kaajal Krishnan, Jacob Kurowski, Satish Viswanath

Proceedings Volume 12034, 120340V (2022) https://doi.org/10.1117/12.2613599

KEYWORDS: Feature extraction, Magnetic resonance imaging, Visualization, Inflammation, Surgery, Proteins, Feature selection, Control systems, Performance modeling, In vivo imaging

Read Abstract +

SPIE Journal Paper | 14 June 2019 Open Access

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

Prathyush Chirra, Patrick Leo, Michael Yim, B. Nicolas Bloch, Ardeshir R. Rastinehad, Andrei Purysko, Mark Rosen, Anant Madabhushi, Satish Viswanath

JMI, Vol. 6, Issue 02, 024502, (June 2019) https://doi.org/10.1117/12.10.1117/1.JMI.6.2.024502

KEYWORDS: Magnetic resonance imaging, Tumors, Prostate, Feature extraction, Scanners, Tissues, Prostate cancer, Computed tomography, Visualization, Magnetism

Read Abstract +

Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1- or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary based on differing acquisition protocols between institutions. We present the first empirical study of benchmarking five different radiomic feature families in terms of both reproducibility and discriminability in a multisite setting, specifically, for identifying prostate tumors in the peripheral zone on MRI. Our cohort comprised 147 patient T2-weighted MRI datasets from four different sites, all of which are first preprocessed to correct for acquisition-related artifacts such as bias field, differing voxel resolutions, and intensity drift (nonstandardness). About 406 three-dimensional voxel-wise radiomic features from five different families (gray, Haralick, gradient, Laws, and Gabor) were evaluated in a cross-site setting to determine (a) how reproducible they are within a relatively homogeneous nontumor tissue region and (b) how well they could discriminate tumor regions from nontumor regions. Our results demonstrate that a majority of the popular Haralick features are reproducible in over 99% of all cross-site comparisons, as well as achieve excellent cross-site discriminability (classification accuracy of ≈0.8). By contrast, a majority of Laws features are highly variable across sites (reproducible in <75 % of all cross-site comparisons) as well as resulting in low cross-site classifier accuracies (<0.6), likely due to a large number of noisy filter responses that can be extracted. These trends suggest that only a subset of radiomic features and associated parameters may be both reproducible and discriminable enough for use within machine learning classifier schemes.

DOWNLOAD PAPER

Proceedings Article | 8 March 2019 Paper

Region-specific fully convolutional networks for segmentation of the rectal wall on post-chemoradiation T2w MRI

Thomas DeSilvio, Jacob Antunes, Prathyush Chirra, Kaustav Bera, Jay Gollamudi, Raj Paspulati, Conor Delaney, Satish Viswanath

Proceedings Volume 10951, 1095134 (2019) https://doi.org/10.1117/12.2513055

KEYWORDS: Image segmentation, Magnetic resonance imaging, Tumors, Tissues, Cancer, CRTs, Surgery, Rectum, Image resolution, Visualization, Convolutional neural networks

Read Abstract +

Proceedings Article | 27 February 2018 Presentation + Paper

Empirical evaluation of cross-site reproducibility in radiomic features for characterizing prostate MRI

Prathyush Chirra, Patrick Leo, Michael Yim, B. Nicolas Bloch, Ardeshir Rastinehad, Andrei Purysko, Mark Rosen, Anant Madabhushi, Satish Viswanath

Proceedings Volume 10575, 105750B (2018) https://doi.org/10.1117/12.2293992

KEYWORDS: Magnetic resonance imaging, Prostate, Feature extraction, Computed tomography, Scanners, Tissues, Image resolution, Data acquisition, Magnetism, Machine learning

Read Abstract +

Showing 5 of 6 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