基于频率感知图像恢复的自监督肝部病灶检测
Self-supervised Liver Lesion Detection Based on Frequency-aware Image Restoration
梁金鑫 1李炜 1唐郑熠 1李佐勇2
作者信息
- 1. 福建理工大学计算机科学与数学学院,福州 350118;福建省大数据挖掘与应用技术重点实验室,福州 350118
- 2. 闽江学院计算机与大数据学院,福州 350121;福建省信息处理与智能控制重点实验室,福州 350121
- 折叠
摘要
计算机断层扫描产生的肝部影像为医生进行肝部病灶区域发现提供了素材.但肝部病灶的人工检测严重依赖于医生的专业技能,且费时费力.现有的肝部病灶区域检测算法对细微病灶的检测效果欠佳.为此,本文提出了一种基于频率感知图像恢复的自监督肝部病灶检测算法.首先,此算法设计了一个基于合成异常的自监督任务,用于合成更加广泛且适宜的伪异常图像,从而缓解算法模型训练时异常数据不足的问题.其次,为了抑制重建网络对合成肝部异常的敏感性,设计了提取图像高频信息的模块,通过从图像的高频成分中恢复图像,以减轻重建网络对异常的不利泛化.最后,其采用权重衰减训练策略以训练分割子网络,减少训练前期的琐碎解问题,实现局部细微病灶的检测.在真实公开数据集上进行的大量实验表明,本文方法在肝部病灶检测任务中取得了领先的性能.
Abstract
Computed tomography(CT)scanning provides valuable material for detecting hepatic lesions in the liver.Manual detection of hepatic lesions is laborious and heavily relies on the expertise of physicians.Existing algorithms for liver lesion detection exhibit suboptimal performance in detecting subtle lesions.To address this issue,this study proposes a self-supervised liver lesion detection algorithm based on frequency-aware image restoration.Firstly,this algorithm designs a self-supervised task based on synthetic anomalies to generate a broader and more suitable set of pseudo-anomalous images,thereby alleviating the issue of insufficient abnormal data during model training.Secondly,to suppress the sensitivity of the reconstructed network to synthetic liver anomalies,a module is designed to extract high-frequency information from images.By restoring the images from their high-frequency components,the adverse generalization of the reconstructed network to anomalies is mitigated.Lastly,the algorithm adopts weight decay to train the segmented sub-networks,reducing the occurrence of trivial solutions during the early stages of training and enabling the detection of local and subtle lesions.Extensive experiments conducted on publicly available real datasets demonstrate that the proposed method achieves state-of-the-art performance in liver lesion detection.
关键词
异常检测/肝脏CT/自监督学习/合成数据Key words
anomaly detection/liver CT/self-supervised learning(SSL)/synthetic data引用本文复制引用
出版年
2024
NETL
NSTL
万方数据