Radiomics: The Application of Machine Learning Algorithms in Pancreatitis Detection
Session Number
CMPS(ai) 25
Advisor(s)
Dr. Ulas Bagci, Northwestern University
Discipline
Computer Science
Start Date
17-4-2025 11:25 AM
End Date
17-4-2025 11:40 AM
Abstract
Pediatric pancreatitis, along with other radiologically identifiable diseases, requires an early, accurate diagnosis for effective treatment. Machine Learning algorithms have become very effective in the radiology field, since radiologists focus on identifying patterns in radiology scans. However, because of the scarcity and large variance in data on pediatric pancreatitis, models to predict patient outcomes are both few and low accuracy.
This study aims to utilize a deep learning-based approach using convolutional neural networks (CNNs) for automated detection of pediatric pancreatitis with radiomics features extracted from Computed Tomography (CT) scans. By compiling datasets from all different ages, we are able to use deep learning and create a model with higher accuracy.
The model’s performance was evaluated using standard metrics such as accuracy, precision, recall, and the area under the receiver operating characteristic curve (AUC-ROC). Preliminary results show that our model can achieve high accuracy, demonstrating its ability to assist radiologists in diagnosing pediatric pancreatitis.
Radiomics: The Application of Machine Learning Algorithms in Pancreatitis Detection
Pediatric pancreatitis, along with other radiologically identifiable diseases, requires an early, accurate diagnosis for effective treatment. Machine Learning algorithms have become very effective in the radiology field, since radiologists focus on identifying patterns in radiology scans. However, because of the scarcity and large variance in data on pediatric pancreatitis, models to predict patient outcomes are both few and low accuracy.
This study aims to utilize a deep learning-based approach using convolutional neural networks (CNNs) for automated detection of pediatric pancreatitis with radiomics features extracted from Computed Tomography (CT) scans. By compiling datasets from all different ages, we are able to use deep learning and create a model with higher accuracy.
The model’s performance was evaluated using standard metrics such as accuracy, precision, recall, and the area under the receiver operating characteristic curve (AUC-ROC). Preliminary results show that our model can achieve high accuracy, demonstrating its ability to assist radiologists in diagnosing pediatric pancreatitis.