Sai Kiran Maryada
Publications
Recent publications and conference contributions. Click any title to view abstract.
Deep Learning-Based Estimation of Petrophysical Properties for Unconventional Shales from SEM Images
Authors: L. Livingstone, P. Yeturi, I. Cherukuri, D. Devegowda, M. Curtis, C. Rai, S.K. Maryada, et al.
ResNet50 feature embeddings from SEM images correlated with porosity, mineralogy, and elastic properties—enabling rapid, lower-cost petrophysical estimation from drill cuttings.
An Improved Data-Driven Method for the Prediction of Elastic Properties in Unconventional Shales from SEM Images Q1
Authors: S.K. Maryada, D. Devegowda, C. Rai, M. Curtis, D. Ebert, G. Danala
SEM texture/shape proxies + deep features with non-parametric regression to estimate elastic properties (e.g., Young’s modulus) across diverse formations.
Self-Supervised Learning Using Vision Transformer Architecture for Rock Image Segmentation
Authors: R.D. Mohammad, D. Devegowda, C. Rai, M. Curtis, S. Mudduluru, S.K. Maryada, et al.
ViT-based self-supervised segmentation of FIB-SEM images into 12 sub-classes grouped into organic/inorganic/pores—enabling large-scale microstructure analysis without labels.
An Improved Data-Driven Method for the Prediction of Elastic Properties in Unconventional Shales from SEM Images (Preprint)
Authors: M. Sai Kiran, D. Deepak, C. Mark, S.R. Chandra, E. David, D. Gopichandh
Preprint outlining SEM-based predictors and regression workflow for elastic property estimation.
Improving Medical Image Segmentation and Classification Using a Novel Joint Deep Learning Model
Authors: S. Mudduluru, S.K.R. Maryada, W.L. Booker, D.F. Hougen, B. Zheng
Joint segmentation + classification framework improving end-to-end clinical image understanding.
Application of Deep Learning to Optimize Computer-Aided-Detection and Diagnosis of Medical Images (Dissertation)
Author: S.K.R. Maryada
Dissertation on end-to-end CAD/CADx pipelines with deep learning for clinical imaging.
A Comparison of CAD Schemes Optimized Using Radiomics and Deep Transfer Learning Methods
Authors: G. Danala, S.K. Maryada, W. Islam, R. Faiz, M. Jones, Y. Qiu, B. Zheng
Head-to-head evaluation of radiomics vs. deep transfer learning pipelines for breast lesion classification.
Developing New Quantitative CT Image Markers to Predict Prognosis of Acute Ischemic Stroke Patients
Authors: G. Danala, B. Ray, M. Desai, M. Heidari, S. Mirniaharikandehei, S.K. Maryada, et al.
Introduces CT-derived quantitative markers to forecast outcomes in acute ischemic stroke.
Applying a Novel Two-Stage Deep-Learning Model to Improve Accuracy in Detecting Retinal Fundus Images
Authors: S.K.R. Maryada, W.L. Booker, G. Danala, C.A. Ha, S. Mudduluru, D.F. Hougen, et al.
Two-stage curation + classification pipeline boosts screening reliability from web-scale fundus imagery.
Comparison of Performance in Breast Lesions Classification Using Radiomics and Deep Transfer Learning: An Assessment Study
Authors: G. Danala, S.K. Maryada, H. Pham, W. Islam, M. Jones, B. Zheng
Assessment study benchmarking radiomics vs. deep transfer learning for breast lesions.
Developing Interactive Computer-Aided Detection Tools to Support Translational Clinical Research
Authors: G. Danala, S. Mirniaharikandehei, M. Jones, T. Gai, S.K. Maryada, D. Wu, et al.
Interactive CAD tools designed for translational study workflows and reader studies.
Applying Quantitative Radiographic Image Markers to Predict Clinical Complications after Aneurysmal Subarachnoid Hemorrhage: A Pilot Study
Authors: G. Danala, M. Desai, B. Ray, M. Heidari, S.K.R. Maryada, C.I. Prodan, B. Zheng
Quantitative CT markers linked to post-SAH complications and prognosis.
An Efficient Synthetic Data Generation Algorithm to Improve Efficacy of Deep Learning Models of Medical Images
Authors: S.K. Maryada, W.L. Booker, G. Danala, M. Jones, S. Mudduluru, H. Pham, et al.
Synthetic augmentation pipeline boosting downstream segmentation/classification performance.
Applying a Random Projection Algorithm to Optimize Machine Learning Model for Breast Lesion Classification Q1 (SJR 1.113)
Authors: M. Heidari, S. Lakshmivarahan, S. Mirniaharikandehei, G. Danala, S.K. Maryada, et al.
Random projections for dimensionality reduction improve ML efficiency and classification performance for breast imaging.
Observability Gramian and Its Role in the Placement of Observations in Dynamic Data Assimilation
Authors: S. Lakshmivarahan, J.M. Lewis, S.K.R. Maryada
Foundational chapter discussing observability Gramian and optimal sensor placement in data assimilation.
A New Interactive Visual-Aided Decision-Making Supporting Tool to Predict Severity of Acute Ischemic Stroke
Authors: G. Danala, S.K.R. Maryada, M. Heidari, B. Ray, M. Desai, B. Zheng
Visual analytics decision support tool for predicting stroke severity from imaging markers.
Placement of Observations for Variational Data Assimilation: Application to Burgers’ Equation and Seiche Phenomenon
Authors: J.M. Lewis, S. Lakshmivarahan, S. Maryada
Case studies on optimal observation placement for PDEs and hydrodynamic oscillations.