Prashnna K Gyawali



Contact

prashnna.gyawali@mail.wvu.edu
AERB (Room: 352)
           


Hi there!

I am an Assistant Professor at West Virginia University in the Lane Department of Computer Science and Electrical Engineering. Before my stint at WVU, I did my postdoctoral training at School of Medicine, Stanford University and completed my PhD in Computer Science from RIT .

My research focuses on building reliable and trustworthy AI systems with improved generalization and robustness, particularly in critical domains such as healthcare. I emphasize generalization (through self-supervised learning and foundation models), reliability (via out-of-distribution detection), and trustworthiness (through interpretability) as key pillars of my work.

NOTE: I am looking for motivated graduate students broadly interested in robust and explainable machine learning and its applications to health care. If you are excited about this line of research and would like to work with me, please read this before contacting me.

News

  • April 2025:New Our latest work, SPMat, is available on arXiv. SPMat is a foundation model for crystal structure materials and is trained using our novel supervised pretraining strategies with surrogate labels.
  • March 2025:New Our work AI Analysis for Ejection Fraction Estimation from 12-lead ECG has been accepted at Scientific Reports.
  • January 2025: 2 abstracts accepted in ARVO Annual Meeting 2025 (topic: 1. OCTA for dementia 2. EHR analysis for Diabetic Retinopathy).
  • October 2024: We presented 2 main conference papers, 2 workshop papers, and co-organized DEMI workshop at MICCAI (Marrakesh, Morroco).
  • September 2024: 2 papers accepted at ICMLA.
  • September 2024: Our work in Material Property Prediction has been accepted at Frontiers in Materials.
  • June 2024: 2 papers accepted at MICCAI.
  • August 2023: Started Machine Intelligence Lab (MIL@WVU).
  • June 2023: Joined West Virginia University as an Assitant Professor.
  • May 2021: Joined Stanford Univeristy as Postdoctoral Scholar (with Zihuai He and James Zou).
  • May 2021: Completed PhD from Rochester Institute of Technology.

Research

See Google Scholar Page for the complete lists, including recent preprints. * below indicates equal contribution

  • AI analysis for ejection fraction estimation from 12-lead ECG.
    Alina Devkota, Rukesh Prajapati, Amr El-Wakeel, Donald Adjeroh, Brijesh Patel, Prashnna Gyawali.
    Scientific Reports, 2025.
    Code

  • TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer's Disease Progression Analysis.
    Jacob Thrasher, Alina Devkota, Ahmed Tafti, Binod Bhattarai, Prashnna Gyawali.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2024.
    Code

  • CAR-MFL: Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalities.
    Pranav Poudel, Prashant Shrestha, Sanskar Amgain, Yash Raj Shrestha, Prashnna Gyawali, Binod Bhattarai.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2024.

  • Enhancing material property prediction with ensemble deep graph convolutional networks.
    Chowdhury Mohammad Abid Rahman, Ghadendra Bhandari, Nasser M Nasrabadi, Aldo Humberto Romero, Prashnna Gyawali.
    Frontiers in Materials (Computational Materials Science), 2024.

  • Can ai keep you safe? a study of large language models for phishing detection.
    Robin Chataut, Prashnna Kumar Gyawali, Yusuf Usman.
    IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC), 2024.

  • A deep-learning algorithm to classify skin lesions from mpox virus infection.
    Alexander H Thieme, Yuanning Zheng, Gautam Machiraju, Chris Sadee, Mirja Mittermaier, Maximilian Gertler, Jorge L Salinas, Krithika Srinivasan, Prashnna K Gyawali, Francisco Carrillo-Perez, Angelo Capodici, Maximilian Uhlig, Daniel Habenicht, Anastassia Löser, Maja Kohler, Maximilian Schuessler, David Kaul, Johannes Gollrad, Jackie Ma, Christoph Lippert, Kendall Billick, Isaac Bogoch, Tina Hernandez-Boussard, Pascal Geldsetzer, Olivier Gevaert.
    Nature Medicine, 2023.

  • Continual Unsupervised Disentangling of Self-Organizing Representations.
    Zhiyuan Li, Xiajun Jiang, Ryan Missel, Prashnna K Gyawali, Nilesh Kumar, Linwei Wang.
    International Conference on Learning Representations (ICLR), 2023.

  • Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation.
    Nilesh Kumar, Prashnna K Gyawali, Sandesh Ghimire, Linwei Wang.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2023.

  • GhostKnockoff inference empowers identification of putative causal variants in genome-wide association studies.
    Zihuai He, Linxi Liu, Michael E Belloy, Yann Le Guen, Aaron Sossin, Xiaoxia Liu, Xinran Qi, Shiyang Ma, Prashnna K Gyawali, Tony Wyss-Coray, Hua Tang, Chiara Sabatti, Emmanuel Candès, Michael D Greicius, Iuliana Ionita-Laza.
    Nature Communications, 2022.

  • Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators.
    Maryam Toloubidokhti, Nilesh Kumar, Zhiyuan Li, Prashnna K Gyawali, Brian Zenger, Wilson W Good, Rob S MacLeod, Linwei Wang.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2022.

  • Ensembling improves stability and power of feature selection for deep learning models.
    Prashnna K Gyawali, Xiaoxia Liu, James Zou, Zihuai He.
    Machine Learning in Computational Biology (MLCB), 2022.

  • Vela pulsar: single pulses analysis with machine learning techniques.
    Carlos O Lousto, Ryan Missel, Harshkumar Prajapati, Valentina Sosa Fiscella, Federico G López Armengol, Prashnna K Gyawali, Linwei Wang, Nathan D Cahill, Luciano Combi, Santiago del Palacio, Jorge A Combi, Guillermo Gancio, Federico García, Eduardo M Gutiérrez and Fernando Hauscarriaga.
    Monthly Notices of the Royal Astronomical Society, 2022.

  • Latent-optimization based Disease-aware Image Editing for Medical Image Augmentation.
    Aakash Saboo, Prashnna K Gyawali, Ankit Shukla, Neeraj Jain, Manoj Sharma and Linwei Wang.
    British Machine Vision Conference (BMVC), 2021.

  • Learning to Disentangle Inter-subject Anatomical Variations in Electrocardiographic Data.
    Prashnna K Gyawali, Jaideep Vitthal Murkute, Maryam Toloubidokhti, Xiajun Jiang, B. Milan Horacek, John Sapp and Linwei Wang.
    IEEE Transacations on Biomedical Engineering (TBE), 2021.
    Dataset

  • A hybrid machine learning approach to localizing the origin of ventricular tachycardia using 12-lead electrocardiograms.
    Ryan Missel, Prashnna K Gyawali, Jaideep Vitthal Murkute, Zhiyuan Li, Shijie Zhou, Amir AbdelWahab, Jason Davis, James Warren, John L Sapp and Linwei Wang.
    Computers in Biology and Medicine, 2020.

  • Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization.
    Prashnna K Gyawali, Sandesh Ghimire, Linwei Wang.
    IEEE International Conference on Data Mining (ICDM), 2020.
    Code

  • Semi-supervised Medical Image Classification with Global Latent Mixing.
    Prashnna K Gyawali, Sandesh Ghimire, Pradeep Bajracharya, Zhiyuan Li, Linwei Wang.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2020.
    Code

  • Learning Geometry-Dependent and Physics-Based Inverse Image Reconstruction.
    Xiajun Jiang, Sandesh Ghimire, Prashnna K Gyawali, Linwei Wang.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2020.

  • Progressive Learning and Disentanglement of Hierarchical Representations.
    Zhiyuan Li, Jaideep Vitthal Murkute, Prashnna K Gyawali, Linwei Wang.
    International Conference on Learning Representations (ICLR), 2020.

  • Sequential Factorized Autoencoder for Localizing the Origin of Ventricular Activation From 12-Lead Electrocardiograms.
    Prashnna K. Gyawali, B. Milan Horacek, John Sapp, Linwei Wang.
    IEEE Transacations on Biomedical Engineering (TBE), 2019.

  • Improving Disentangled Representation Learning with the Beta Bernoulli Process.
    Prashnna K Gyawali, Zhiyuan Li, Cameron Knight, Sandesh Ghimire, B. Milan Horacek, John Sapp, Linwei Wang.
    IEEE International Conference on Data Mining (ICDM), 2019.
    Code

  • Semi-Supervised Learning by Disentangling and Self-Ensembling over Stochastic Latent Space.
    Prashnna K Gyawali*, Zhiyuan Li*, Sandesh Ghimire, Linwei Wang.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2019.
    Code

  • Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences.
    Sandesh Ghimire, Prashnna K Gyawali, Jwala Dhamala, John Sapp, B. Milan Horacek, Linwei Wang.
    International Conference on Information Processing in Medical Imaging (IPMI), 2019.

  • Generative Modeling and Inverse Imaging of Cardiac Transmembrane Potential.
    Sandesh Ghimire, Jwala Dhamala, Prashnna K Gyawali, John Sapp, B. Milan Horacek, Linwei Wang.
    International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2018.

  • Automatic Coordinate Prediction of the Exit of Ventricular Tachycardia from 12-lead Electrocardiogram.
    Prashnna K Gyawali, Shuhang Chen, Huafeng Liu, B. Milan Horacek, John Sapp, Wang L.
    Computing in Cardiology (CinC), 2017. (Semifinalist for Young Investigator Award)

Advising

PhD students:

  • Chowdhury Mohammad Abid Rahman
  • Jacob Thrasher
  • Alina Devkota
  • Greg Murray
  • Shivam (co-advising with Prof. Yemunala Reddy)

MS students:

  • Rizwan Ahamed
  • Ahsan Habib Akash

Student Collaborators:

  • Nima Najafzadeh (PhD Student, WVU CS)

Teaching

  • CPE620 Deep Learning
    Instructor
    West Virginia University, Spring 2025.

  • EE565 Advanced Image Processing
    Instructor
    West Virginia University, Fall 2023, Fall 2024.

  • EE465 Digital Image Processing
    Instructor
    West Virginia University, Spring 2024.

  • Image Processing and Pattern Recognition
    Instructor
    Institute of Engineering, Tribhuwan University, 2015.