Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection

TL;DR

This paper introduces a simulation-driven augmentation framework called Perturb-and-Restore to improve chromosomal anomaly detection by generating synthetic abnormal data, addressing data scarcity and imbalance issues.

Contribution

The novel Perturb-and-Restore framework combines structure perturbation, restoration simulation, and adaptive sampling to enhance deep learning performance on imbalanced chromosome anomaly datasets.

Findings

Achieved state-of-the-art detection performance with over 260,000 chromosome images.

Surpassed existing methods by approximately 9% in sensitivity and 14% in F1-score.

Effectively alleviated data imbalance with synthetic abnormal chromosome generation.

Abstract

Detecting structural chromosomal abnormalities is crucial for accurate diagnosis and management of genetic disorders. However, collecting sufficient structural abnormality data is extremely challenging and costly in clinical practice, and not all abnormal types can be readily collected. As a result, deep learning approaches face significant performance degradation due to the severe imbalance and scarcity of abnormal chromosome data. To address this challenge, we propose a Perturb-and-Restore (P&R), a simulation-driven structural augmentation framework that effectively alleviates data imbalance in chromosome anomaly detection. The P&R framework comprises two key components: (1) Structure Perturbation and Restoration Simulation, which generates synthetic abnormal chromosomes by perturbing chromosomal banding patterns of normal chromosomes followed by a restoration diffusion network that reconstructs continuous chromosome content and edges, thus eliminating reliance on rare abnormal samples; and (2) Energy-guided Adaptive Sampling, an energy score-based online selection strategy that dynamically prioritizes high-quality synthetic samples by referencing the energy distribution of real samples. To evaluate our method, we construct a comprehensive structural anomaly dataset consisting of over 260,000 chromosome images, including 4,242 abnormal samples spanning 24 categories. Experimental results demonstrate that the P&R framework achieves state-of-the-art (SOTA) performance, surpassing existing methods with an average improvement of 8.92% in sensitivity, 8.89% in precision, and 13.79% in F1-score across all categories.