{"title":"利用变分自编码器的光声断层成像深度学习","authors":"Teemu Sahlström, T. Tarvainen","doi":"10.1117/12.2670860","DOIUrl":null,"url":null,"abstract":"In Photoacoustic Tomography (PAT), the aim is to estimate the initial pressure distribution based on measured ultrasound data. While several approaches utilizing deep learning for PAT have been proposed, many of these do not provide estimates on the reliability of the reconstruction. In this work, we propose a deep learning approach for the Bayesian inverse problem for PAT based on the uncertainty quantification variational autoencoder. The approach enables simultaneous image reconstruction and reliability estimation.","PeriodicalId":278089,"journal":{"name":"European Conference on Biomedical Optics","volume":"7 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning in photoacoustic tomography utilizing variational autoencoders\",\"authors\":\"Teemu Sahlström, T. Tarvainen\",\"doi\":\"10.1117/12.2670860\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In Photoacoustic Tomography (PAT), the aim is to estimate the initial pressure distribution based on measured ultrasound data. While several approaches utilizing deep learning for PAT have been proposed, many of these do not provide estimates on the reliability of the reconstruction. In this work, we propose a deep learning approach for the Bayesian inverse problem for PAT based on the uncertainty quantification variational autoencoder. The approach enables simultaneous image reconstruction and reliability estimation.\",\"PeriodicalId\":278089,\"journal\":{\"name\":\"European Conference on Biomedical Optics\",\"volume\":\"7 1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Conference on Biomedical Optics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1117/12.2670860\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Conference on Biomedical Optics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.2670860","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deep learning in photoacoustic tomography utilizing variational autoencoders
In Photoacoustic Tomography (PAT), the aim is to estimate the initial pressure distribution based on measured ultrasound data. While several approaches utilizing deep learning for PAT have been proposed, many of these do not provide estimates on the reliability of the reconstruction. In this work, we propose a deep learning approach for the Bayesian inverse problem for PAT based on the uncertainty quantification variational autoencoder. The approach enables simultaneous image reconstruction and reliability estimation.