# Synthetic data generation with Worley–Perlin diffusion for robust subarachnoid hemorrhage detection in imbalanced CT Datasets

## TL;DR

This paper introduces a new model for generating realistic subarachnoid hemorrhage CT images to improve detection accuracy in imbalanced datasets.

## Contribution

The novel Worley–Perlin Diffusion Model (WPDM) generates high-quality SAH images, overcoming noise limitations in prior methods.

## Key findings

- WPDM improves classification accuracy in imbalanced datasets with varying imbalance ratios.
- A classifier using WPDM-generated samples achieved an F1-score of 0.857 on a 1:36 imbalance ratio.
- WPDM outperforms Gaussian and Simplex noise-based models in generating realistic SAH images.

## Abstract

In this paper, we propose a novel generative model to produce high-quality SAH samples, enhancing SAH CT detection performance in imbalanced datasets. Previous methods, such as cost-sensitive learning and previous diffusion models, suffer from overfitting or noise-induced distortion, limiting their effectiveness. Accurate SAH sample generation is crucial for better detection.

We propose the Worley–Perlin Diffusion Model (WPDM), leveraging Worley–Perlin noise to synthesize diverse, high-quality SAH images. WPDM addresses limitations of Gaussian noise (homogeneity) and Simplex noise (distortion), enhancing robustness for generating SAH images. Additionally, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\hbox {WPDM}_{\text {Fast}}$$\end{document}WPDMFast optimizes generation speed without compromising quality.

WPDM effectively improved classification accuracy in datasets with varying imbalance ratios. Notably, a classifier trained with WPDM-generated samples achieved an F1-score of 0.857 on a 1:36 imbalance ratio, surpassing the state of the art by 2.3 percentage points.

WPDM overcomes the limitations of Gaussian and Simplex noise-based models, generating high-quality, realistic SAH images. It significantly enhances classification performance in imbalanced settings, providing a robust solution for SAH CT detection.