Enhancing Segmentation of Abdominal Aortic Aneurysms in CT Images

This study concentrates on a potential strategy for improving Abdominal aortic aneurysms (AAAs) segmentation in CT imaging. The study's dataset included 19 CT images of healthy AAAs acquired from different patients. Ground-truth segmentations that matched the training data were also included. F...

Full description

Saved in:
Bibliographic Details
Published in2023 International Conference on Data Science and Network Security (ICDSNS) pp. 01 - 06
Main Authors Saleem Javeed, Abdul, K M, Veeresh, V N, Ganesh, Lavanya, Chunduri, B D, Parameshachari
Format Conference Proceeding
LanguageEnglish
Published IEEE 28.07.2023
Subjects
Online AccessGet full text
DOI10.1109/ICDSNS58469.2023.10245256

Cover

More Information
Summary:This study concentrates on a potential strategy for improving Abdominal aortic aneurysms (AAAs) segmentation in CT imaging. The study's dataset included 19 CT images of healthy AAAs acquired from different patients. Ground-truth segmentations that matched the training data were also included. For enhanced accuracy while segmenting AAA, the suggested technique integrates pre-processing, deep learning segmentation, and post-processing into a cohesive workflow. Convolutional neural networks (CNNs) are trained for deep learning segmentation using a U-Net architecture, and noise in input pictures is removed during pre-processing. This differs from the conventional habit of employing linear regression for image segmentation. The results were measured using the dice similarity coefficient, sensitivity, specificity, accuracy, recall, and F1 score. With a DSC of 0.81, sensitivity of 0.89, specificity of 0.97, accuracy of 0.86, recall of 0.89, and F1 score of 0.86, the suggested approach was proven to be successful in segmenting AAAs in CT images. The technique has shown potential in clinical settings for improving AAA diagnosis and treatment planning.
DOI:10.1109/ICDSNS58469.2023.10245256