使用支持向量数据描述的向量量化变异自动编码器的肺部 CT 图像异常检测方案。

IF 1.7 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Zhihui Gao, Ryohei Nakayama, Akiyoshi Hizukuri, Shoji Kido
{"title":"使用支持向量数据描述的向量量化变异自动编码器的肺部 CT 图像异常检测方案。","authors":"Zhihui Gao, Ryohei Nakayama, Akiyoshi Hizukuri, Shoji Kido","doi":"10.1007/s12194-024-00851-5","DOIUrl":null,"url":null,"abstract":"<p><p>This study aims to develop an anomaly-detection scheme for lesions in CT images. Our database consists of lung CT images obtained from 1500 examinees. It includes 1200 normal and 300 abnormal cases. In this study, SVDD (Support Vector Data Description) mapping the normal latent variables into a hypersphere as small as possible on the latent space is introduced to VQ-VAE (Vector Quantized-Variational Auto-Encoder). VQ-VAE with SVDD is constructed from two encoders, two decoders, and an embedding space. The first encoder compresses the input image into the latent-variable map, whereas the second encoder maps the normal latent variables into a hypersphere as small as possible. The first decoder then up-samples the mapped latent variables into a latent-variable map with the original size. The second decoder finally reconstructs the input image from the latent-variable map replaced by the embedding representations. The data of each examinee is classified as abnormal or normal based on the anomaly score defined as the combination of the difference between the input image and the reconstructed image and the distance between the latent variables and the center of the hypersphere. The area under the ROC curve for VQ-VAE with SVDD was 0.76, showing an improvement when compared with the conventional VAE (0.63, p < .001). VQ-VAE with SVDD developed in this study can yield higher anomaly-detection accuracy than the conventional VAE. The proposed method is expected to be useful for identifying examinees with lesions and reducing interpretation time in CT screening.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Anomaly detection scheme for lung CT images using vector quantized variational auto-encoder with support vector data description.\",\"authors\":\"Zhihui Gao, Ryohei Nakayama, Akiyoshi Hizukuri, Shoji Kido\",\"doi\":\"10.1007/s12194-024-00851-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>This study aims to develop an anomaly-detection scheme for lesions in CT images. Our database consists of lung CT images obtained from 1500 examinees. It includes 1200 normal and 300 abnormal cases. In this study, SVDD (Support Vector Data Description) mapping the normal latent variables into a hypersphere as small as possible on the latent space is introduced to VQ-VAE (Vector Quantized-Variational Auto-Encoder). VQ-VAE with SVDD is constructed from two encoders, two decoders, and an embedding space. The first encoder compresses the input image into the latent-variable map, whereas the second encoder maps the normal latent variables into a hypersphere as small as possible. The first decoder then up-samples the mapped latent variables into a latent-variable map with the original size. The second decoder finally reconstructs the input image from the latent-variable map replaced by the embedding representations. The data of each examinee is classified as abnormal or normal based on the anomaly score defined as the combination of the difference between the input image and the reconstructed image and the distance between the latent variables and the center of the hypersphere. The area under the ROC curve for VQ-VAE with SVDD was 0.76, showing an improvement when compared with the conventional VAE (0.63, p < .001). VQ-VAE with SVDD developed in this study can yield higher anomaly-detection accuracy than the conventional VAE. The proposed method is expected to be useful for identifying examinees with lesions and reducing interpretation time in CT screening.</p>\",\"PeriodicalId\":46252,\"journal\":{\"name\":\"Radiological Physics and Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-10-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiological Physics and Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s12194-024-00851-5\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiological Physics and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s12194-024-00851-5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

本研究旨在开发一种针对 CT 图像中病变的异常检测方案。我们的数据库由 1500 名受检者的肺部 CT 图像组成。其中包括 1200 个正常病例和 300 个异常病例。在这项研究中,SVDD(支持向量数据描述)被引入到 VQ-VAE(向量量化变量自动编码器)中,将正常潜变量映射到潜空间上尽可能小的超球中。带有 SVDD 的 VQ-VAE 由两个编码器、两个解码器和一个嵌入空间构成。第一个编码器将输入图像压缩为潜变量映射,而第二个编码器则将正常潜变量映射为尽可能小的超球。然后,第一个解码器将映射的潜变量向上采样到具有原始大小的潜变量映射中。第二个解码器最后根据被嵌入表示替换的潜变量图重建输入图像。每个受检者的数据会根据异常分数被分为异常和正常,异常分数的定义是输入图像和重建图像之间的差值与潜变量和超球中心之间距离的组合。带有 SVDD 的 VQ-VAE 的 ROC 曲线下面积为 0.76,与传统的 VAE 相比有所提高(0.63,p<0.05)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Anomaly detection scheme for lung CT images using vector quantized variational auto-encoder with support vector data description.

This study aims to develop an anomaly-detection scheme for lesions in CT images. Our database consists of lung CT images obtained from 1500 examinees. It includes 1200 normal and 300 abnormal cases. In this study, SVDD (Support Vector Data Description) mapping the normal latent variables into a hypersphere as small as possible on the latent space is introduced to VQ-VAE (Vector Quantized-Variational Auto-Encoder). VQ-VAE with SVDD is constructed from two encoders, two decoders, and an embedding space. The first encoder compresses the input image into the latent-variable map, whereas the second encoder maps the normal latent variables into a hypersphere as small as possible. The first decoder then up-samples the mapped latent variables into a latent-variable map with the original size. The second decoder finally reconstructs the input image from the latent-variable map replaced by the embedding representations. The data of each examinee is classified as abnormal or normal based on the anomaly score defined as the combination of the difference between the input image and the reconstructed image and the distance between the latent variables and the center of the hypersphere. The area under the ROC curve for VQ-VAE with SVDD was 0.76, showing an improvement when compared with the conventional VAE (0.63, p < .001). VQ-VAE with SVDD developed in this study can yield higher anomaly-detection accuracy than the conventional VAE. The proposed method is expected to be useful for identifying examinees with lesions and reducing interpretation time in CT screening.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Radiological Physics and Technology
Radiological Physics and Technology RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-
CiteScore
3.00
自引率
12.50%
发文量
40
期刊介绍: The purpose of the journal Radiological Physics and Technology is to provide a forum for sharing new knowledge related to research and development in radiological science and technology, including medical physics and radiological technology in diagnostic radiology, nuclear medicine, and radiation therapy among many other radiological disciplines, as well as to contribute to progress and improvement in medical practice and patient health care.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信