Authors :
RUTATINA RUTAGONYA Frank; Dr. Wilson Musoni
Volume/Issue :
Volume 8 - 2023, Issue 10 - October
Google Scholar :
https://tinyurl.com/yp7ezuen
Scribd :
https://tinyurl.com/mwrdct59
DOI :
https://doi.org/10.5281/zenodo.10099559
Abstract :
This study focuses on the importance of
detecting and diagnosing pancreatic tumors accurately
to improve patient outcomes. It explores the use of deep
learning algorithms, specifically convolutional neural
networks, for automated pancreas tumor detection
using CT scans. The CT images undergo preprocessing
steps such as noise reduction, normalization, and image
resampling. These preprocessed images are then used to
train a deep learning model that learns the
characteristics of pancreatic tumors.
The model is trained using a large dataset of
annotated CT images, consisting of both tumor-positive
and tumor-negative cases. Various optimization
techniques and loss functions are employed to maximize
the model's performance. The initial results show
promising outcomes, with the model achieving high
accuracy in pancreas tumor detection. Its sensitivity and
specificity are evaluated to assess its ability to correctly
identify tumor presence or absence. The model's
performance is further validated using independent
testing datasets to ensure its generalizability.
The study aims to develop an efficient and reliable
automated system for detecting pancreatic tumors by
leveraging deep learning techniques on CT images. This
approach has the potential to assist radiologists and
clinicians in early and accurate diagnosis of pancreatic
cancer, leading to timely treatment interventions and
improved patient outcomes.
This study focuses on the importance of
detecting and diagnosing pancreatic tumors accurately
to improve patient outcomes. It explores the use of deep
learning algorithms, specifically convolutional neural
networks, for automated pancreas tumor detection
using CT scans. The CT images undergo preprocessing
steps such as noise reduction, normalization, and image
resampling. These preprocessed images are then used to
train a deep learning model that learns the
characteristics of pancreatic tumors.
The model is trained using a large dataset of
annotated CT images, consisting of both tumor-positive
and tumor-negative cases. Various optimization
techniques and loss functions are employed to maximize
the model's performance. The initial results show
promising outcomes, with the model achieving high
accuracy in pancreas tumor detection. Its sensitivity and
specificity are evaluated to assess its ability to correctly
identify tumor presence or absence. The model's
performance is further validated using independent
testing datasets to ensure its generalizability.
The study aims to develop an efficient and reliable
automated system for detecting pancreatic tumors by
leveraging deep learning techniques on CT images. This
approach has the potential to assist radiologists and
clinicians in early and accurate diagnosis of pancreatic
cancer, leading to timely treatment interventions and
improved patient outcomes.
