UWEC CERCA 2026: Full Schedule

arrow_back View All Dates

2:00pm CDT

Influence of Data Provenance on Anatomical Representations in Pancreas CT Segmentation Models

Tuesday April 28, 2026 2:00pm - 3:30pm CDT

Clinical imaging datasets for analysis of pancreatic cancer increasingly aggregate scans collected under heterogeneous workflows and annotation strategies. Deep learning models for medical image segmentation are typically evaluated using overlap metrics such as Dice scores, which assumes training data is drawn from heterogeneous distributions. While state-of-the-art segmentation frameworks such as nnU-Net achieve strong benchmark performance, little is known about how data provenance influences the anatomical representations learned by these models. Understanding these effects is critical for interpretability, robustness, and safe deployment in clinical settings. This project aims to investigate whether pancreas CT segmentation models trained on different data sources learn systematically different anatomical priors, even when standard accuracy metrics are similar. To evaluate these effects, we train multiple source-specific nnU-Net models on curated subsets of the PANORAMA pancreas dataset that reflect distinct data collection strategies. We will compare outputs via Dice scores and anatomical descriptors such as predicted volume, connected components, centroid location, spatial extent, and voxel-wise inter-model disagreement maps. Ongoing analysis aims to quantify these differences and demonstrate disagreement mapping as a computationally efficient proxy for anatomical uncertainty.

Presenters

Caleb Smock

University of Wisconsin - Eau Claire

Lando Dierkes

University of Wisconsin - Eau Claire

Faculty Mentor

Rahul Gomes

Computer Science, University of Wisconsin - Eau Claire

Tuesday April 28, 2026 2:00pm - 3:30pm CDT
Davies Center: Ojibwe Ballroom (330) 77 Roosevelt Ave, Eau Claire, WI 54701, USA

Spotlight on First-Year Research

Department Computer Science
College CAS

2:00pm CDT

Tracking the Real Time Movements of the Food Delivery KiwiBots using a Network of Low-Powered, WiFi-Enabled Devices

Tuesday April 28, 2026 2:00pm - 3:30pm CDT

Davies Center: Ojibwe Ballroom (330)

KiwiBots are food delivery robots which traverse the campus of UW-Eau Claire. Each robot gives off a unique WiFi signal which can be detected by WiFi chips. A network of strategically placed, low-powered embedded computers (ESP32) capture the signals of KiwiBots within WiFi range and transmit the data to a central server for triangulation. Using average speed and overlapping detection ranges, this project aims to track the real time movements of the KiwiBots across the UW-Eau Claire campus. Potential applications of this type of system can be used to track the movement of Bluetooth or WiFi enabled devices used by passersby (Bluetooth headphones and smartphones, for instance) for malicious purposes. By creating a realistic system which can effectively track the real-time movements of personal devices, we aim to advocate for strong legal and technical countermeasures against systems of this kind.

Presenters

Jack Hagen

University of Wisconsin - Eau Claire

Aiden Lee

University of Wisconsin - Eau Claire

Silas Eacret

Student Administrator at Blugold Center for High Performance Computing, University of Wisconsin - Eau Claire

Hello! I'm Silas. I enjoy breaking things, fixing the things, and then breaking more things in the process of fixing said things.

I'm currently employed part-time by the Blugold Center for High Performance Computing (https://hpc.uwec.edu) at UWEC as a Student Administrator. I help... Read More →

Yegeon Cho

University of Wisconsin - Eau Claire

Faculty Mentor

Mounika Vanamala

Computer Science, University of Wisconsin - Eau Claire

Tuesday April 28, 2026 2:00pm - 3:30pm CDT
Davies Center: Ojibwe Ballroom (330) 77 Roosevelt Ave, Eau Claire, WI 54701, USA

Spotlight on First-Year Research

Department Computer Science
College CAS

2:00pm CDT

2:00pm CDT

Get help with the event