Yongyi Shi, Chuang Niu, Amber L. Simpson, Bruno De Man, Richard Do, Ge Wang
{"title":"利用生成扩散先验进行基于 CT 的肝脏肿瘤异常检测","authors":"Yongyi Shi, Chuang Niu, Amber L. Simpson, Bruno De Man, Richard Do, Ge Wang","doi":"arxiv-2408.00092","DOIUrl":null,"url":null,"abstract":"CT is a main modality for imaging liver diseases, valuable in detecting and\nlocalizing liver tumors. Traditional anomaly detection methods analyze\nreconstructed images to identify pathological structures. However, these\nmethods may produce suboptimal results, overlooking subtle differences among\nvarious tissue types. To address this challenge, here we employ generative\ndiffusion prior to inpaint the liver as the reference facilitating anomaly\ndetection. Specifically, we use an adaptive threshold to extract a mask of\nabnormal regions, which are then inpainted using a diffusion prior to\ncalculating an anomaly score based on the discrepancy between the original CT\nimage and the inpainted counterpart. Our methodology has been tested on two\nliver CT datasets, demonstrating a significant improvement in detection\naccuracy, with a 7.9% boost in the area under the curve (AUC) compared to the\nstate-of-the-art. This performance gain underscores the potential of our\napproach to refine the radiological assessment of liver diseases.","PeriodicalId":501378,"journal":{"name":"arXiv - PHYS - Medical Physics","volume":"21 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CT-based Anomaly Detection of Liver Tumors Using Generative Diffusion Prior\",\"authors\":\"Yongyi Shi, Chuang Niu, Amber L. Simpson, Bruno De Man, Richard Do, Ge Wang\",\"doi\":\"arxiv-2408.00092\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"CT is a main modality for imaging liver diseases, valuable in detecting and\\nlocalizing liver tumors. Traditional anomaly detection methods analyze\\nreconstructed images to identify pathological structures. However, these\\nmethods may produce suboptimal results, overlooking subtle differences among\\nvarious tissue types. To address this challenge, here we employ generative\\ndiffusion prior to inpaint the liver as the reference facilitating anomaly\\ndetection. Specifically, we use an adaptive threshold to extract a mask of\\nabnormal regions, which are then inpainted using a diffusion prior to\\ncalculating an anomaly score based on the discrepancy between the original CT\\nimage and the inpainted counterpart. Our methodology has been tested on two\\nliver CT datasets, demonstrating a significant improvement in detection\\naccuracy, with a 7.9% boost in the area under the curve (AUC) compared to the\\nstate-of-the-art. This performance gain underscores the potential of our\\napproach to refine the radiological assessment of liver diseases.\",\"PeriodicalId\":501378,\"journal\":{\"name\":\"arXiv - PHYS - Medical Physics\",\"volume\":\"21 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Medical Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.00092\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Medical Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.00092","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
CT-based Anomaly Detection of Liver Tumors Using Generative Diffusion Prior
CT is a main modality for imaging liver diseases, valuable in detecting and
localizing liver tumors. Traditional anomaly detection methods analyze
reconstructed images to identify pathological structures. However, these
methods may produce suboptimal results, overlooking subtle differences among
various tissue types. To address this challenge, here we employ generative
diffusion prior to inpaint the liver as the reference facilitating anomaly
detection. Specifically, we use an adaptive threshold to extract a mask of
abnormal regions, which are then inpainted using a diffusion prior to
calculating an anomaly score based on the discrepancy between the original CT
image and the inpainted counterpart. Our methodology has been tested on two
liver CT datasets, demonstrating a significant improvement in detection
accuracy, with a 7.9% boost in the area under the curve (AUC) compared to the
state-of-the-art. This performance gain underscores the potential of our
approach to refine the radiological assessment of liver diseases.