# Modeling of Severity Classification Algorithm Using Abdominal Aortic Aneurysm Computed Tomography Image Segmentation Based on U-Net with Improved Noise Reduction Performance

## TL;DR

A new method combining a noise filter with U-Net improves the accuracy of identifying abdominal aortic aneurysms in CT scans, leading to better severity classification.

## Contribution

A median-modified Wiener filter is integrated with U-Net to enhance segmentation accuracy in noisy AAA CT images.

## Key findings

- The median-modified Wiener filter significantly improved U-Net segmentation performance on noisy AAA CT images.
- Hough circle-based classification achieved 100% sensitivity, precision, and accuracy after MMWF preprocessing.
- MMWF improved metrics like Dice score, Jaccard coefficient, and mean surface distance by over 30%.

## Abstract

What are the main findings?
The application of the median-modified Wiener filter
significantly improved the U-Net-based segmentation performance on abdominal
aortic aneurysm CT images with added Poisson–Gaussian noise.Segmentation quality directly influenced automated severity
classification performance. When MMWF was used as a preprocessing step, the
Hough circle-based classification achieved 100% sensitivity, precision, and
accuracy.

The application of the median-modified Wiener filter
significantly improved the U-Net-based segmentation performance on abdominal
aortic aneurysm CT images with added Poisson–Gaussian noise.

Segmentation quality directly influenced automated severity
classification performance. When MMWF was used as a preprocessing step, the
Hough circle-based classification achieved 100% sensitivity, precision, and
accuracy.

What is the implication of the main finding?
Integrating classical filtering methods into deep learning-based
segmentation pipelines can enhance robustness against noise without modifying
network architecture.Accurate segmentation via preprocessing contributes to more
reliable automated severity classification of AAAs, supporting improved
clinical decision-making in noisy imaging conditions.

Integrating classical filtering methods into deep learning-based
segmentation pipelines can enhance robustness against noise without modifying
network architecture.

Accurate segmentation via preprocessing contributes to more
reliable automated severity classification of AAAs, supporting improved
clinical decision-making in noisy imaging conditions.

Accurate segmentation of abdominal aortic aneurysm (AAA) from computed tomography (CT) images is critical for early diagnosis and treatment planning of vascular diseases. However, noise in CT images obscures vessel boundaries, reducing segmentation accuracy. U-Net is widely used for medical image segmentation, where noise removal is critical. This study applied various denoising filters for U-Net segmentation and classified the severity of segmented AAA images to evaluate accuracy. Poisson–Gaussian noise was added to AAA CT images, and then average, median, Wiener, and median-modified Wiener filters (MMWF) were applied. U-Net-based segmentation was performed, and the segmentation accuracy of the output images obtained per filter was quantitatively assessed. Furthermore, the Hough circle algorithm was applied to the segmented images for diameter measurement, enabling severity classification and evaluation of classification accuracy. MMWF application improved the Matthews correlation coefficient, Dice score, Jaccard coefficient, and mean surface distance by 31.09%, 34.25%, 53.99%, and 3.70%, respectively, compared with images with added noise. Moreover, classification based on the output images obtained after MMWF application demonstrated the highest accuracy, with sensitivity, precision, and accuracy reaching 100%. Thus, U-Net-based segmentation yields more accurate results when images are processed with the MMWF and analyzed using the Hough circle algorithm.