Submission information
Submission Number: 211
Submission ID: 5983
Submission UUID: 3e522921-7707-4df0-881b-543297cb5207
Submission URI: /form/project
Created: Tue, 01/27/2026 - 14:05
Completed: Tue, 01/27/2026 - 14:05
Changed: Tue, 01/27/2026 - 14:05
Remote IP address: 144.80.138.168
Submitted by: Andrew Zhou
Language: English
Is draft: No
Webform: Project
| Received Sent | 0 |
|---|---|
| Accept and Publish Sent | 0 |
| Project Title | Pennsylvania Science DMZ Undergraduate Research Program Proposal |
| Program | PA Science |
| Project Leader | Andrew Zhou |
| fzhou@iup.edu | |
| Mentor(s) | |
| Student-facilitator(s) | |
| Mentee(s) | |
| Project Description | AI-Based Cancer Imaging Analysis Andrew Zhou Department of Chemistry, Biochemistry, and Physics Indiana University of Pennsylvania Project Overview This project proposes a focused, data-intensive research effort centered on artificial intelligence (AI)–based analysis of cancer medical imaging data. The work will be conducted under faculty supervision and will engage an undergraduate student as the primary researcher, supported through the Pennsylvania Science DMZ program. The project aligns with the PA Science DMZ mission by leveraging advanced cyberinfrastructure, high-performance computing (HPC), and large-scale medical imaging datasets to develop and evaluate deep learning models for tumor detection and segmentation. Student Role and Training Objectives The undergraduate researcher will play a central role in implementing the AI imaging pipeline and will gain hands-on experience in medical image processing, machine learning model development, and computational experimentation using HPC resources. Training objectives include proficiency with open-source SimpleITK for image preprocessing, TensorFlow or PyTorch for model development, and best practices for reproducible, data-intensive research. Research Scope and Methodology The project will focus on a single imaging modality (CT or MRI) using publicly available datasets from The Cancer Imaging Archive (TCIA). Image preprocessing will include normalization, resampling, and basic quality control. Deep learning models will be trained for tumor detection and segmentation, and performance will be evaluated using standard metrics such as the Dice similarity coefficient, sensitivity, and specificity. Computational workloads will be executed using PA Science DMZ–enabled HPC resources to support scalable experimentation. Undergraduate Work Plan and Six-Month Schedule Monthly Milestones The first Month - Orientation to PA Science DMZ and HPC resources - Literature review on AI-based cancer imaging - Selection of TCIA dataset and imaging modality - Initial image preprocessing using SimpleITK The 2nd Month - Refinement of preprocessing workflow - Implementation of baseline deep learning models - Initial training runs and debugging on HPC systems - Documentation of workflows and datasets The 3rd Month - Model architecture refinement - Hyperparameter tuning and performance optimization - Expanded training using larger datasets - Interim evaluation and result analysis The 4th month - Final model training and validation - Quantitative performance assessment using clinical metrics - Error analysis and robustness checks - Finalize codebase and documentation The 5th month - Prepare figures, tables, and summaries of results - Draft poster or presentation materials - Final project report preparation - Identification of future research directions Stipend Justification A $3,000 undergraduate stipend is requested to support sustained student engagement from July through November 2026. The stipend compensates the student for consistent weekly research effort, technical skill development, and contribution to project deliverables. This support directly enables meaningful participation in data-intensive research activities aligned with the goals of the Pennsylvania Science DMZ program. |
| Project Deliverables | |
| Project Deliverables | |
| Student Research Computing Facilitator Profile | |
| Mentee Research Computing Profile | |
| Student Facilitator Programming Skill Level | |
| Mentee Programming Skill Level | |
| Project Institution | |
| Project Address | |
| Anchor Institution | |
| Preferred Start Date | |
| Start as soon as possible. | No |
| Project Urgency | Already behind3Start date is flexible |
| Expected Project Duration (in months) | |
| Launch Presentation | |
| Launch Presentation Date | |
| Wrap Presentation | |
| Wrap Presentation Date | |
| Project Milestones | |
| Github Contributions | |
| Planned Portal Contributions (if any) | |
| Planned Publications (if any) | |
| What will the student learn? | |
| What will the mentee learn? | |
| What will the Cyberteam program learn from this project? | |
| HPC resources needed to complete this project? | |
| Notes | |
| What is the impact on the development of the principal discipline(s) of the project? | |
| What is the impact on other disciplines? | |
| Is there an impact physical resources that form infrastructure? | |
| Is there an impact on the development of human resources for research computing? | |
| Is there an impact on institutional resources that form infrastructure? | |
| Is there an impact on information resources that form infrastructure? | |
| Is there an impact on technology transfer? | |
| Is there an impact on society beyond science and technology? | |
| Lessons Learned | |
| Overall results |