Style-Aligned Image Composition for Robust Detection of Abnormal Cells in Cytopathology

TL;DR

This paper introduces a style-aligned image composition method to generate high-quality, style-preserved pathological images, significantly improving the robustness and accuracy of abnormal cell detection in cytopathology without additional training.

Contribution

The proposed SAIC method innovatively synthesizes style-aligned pathological images to enhance detection models, addressing data scarcity and style variability issues in cytopathology.

Findings

SAIC improves detection accuracy for tail categories and styles

Synthesized images enhance model robustness and generalizability

Method achieves high-quality, style-preserved image synthesis without extra training

Abstract

Challenges such as the lack of high-quality annotations, long-tailed data distributions, and inconsistent staining styles pose significant obstacles to training neural networks to detect abnormal cells in cytopathology robustly. This paper proposes a style-aligned image composition (SAIC) method that composes high-fidelity and style-preserved pathological images to enhance the effectiveness and robustness of detection models. Without additional training, SAIC first selects an appropriate candidate from the abnormal cell bank based on attribute guidance. Then, it employs a high-frequency feature reconstruction to achieve a style-aligned and high-fidelity composition of abnormal cells and pathological backgrounds. Finally, it introduces a large vision-language model to filter high-quality synthesis images. Experimental results demonstrate that incorporating SAIC-synthesized images effectively enhances the performance and robustness of abnormal cell detection for tail categories and styles, thereby improving overall detection performance. The comprehensive quality evaluation further confirms the generalizability and practicality of SAIC in clinical application scenarios. Our code will be released at https://github.com/Joey-Qi/SAIC.