Diffeomorphic Lung Registration Using Deep CNNs and Reinforced Learning.

Image analysis for moving organ, breast, and thoracic images : third International Workshop, RAMBO 2018, fourth International Workshop, BIA 2018, and first International Workshop, TIA 2018, held in conjunction with MICCAI 2018, Granada,... Pub Date : 2018-09-01 Epub Date: 2018-09-12 DOI:10.1007/978-3-030-00946-5_28

Jorge Onieva Onieva, Berta Marti-Fuster, María Pedrero de la Puente, Raúl San José Estépar

{"title":"Diffeomorphic Lung Registration Using Deep CNNs and Reinforced Learning.","authors":"Jorge Onieva Onieva, Berta Marti-Fuster, María Pedrero de la Puente, Raúl San José Estépar","doi":"10.1007/978-3-030-00946-5_28","DOIUrl":null,"url":null,"abstract":"<p><p>Image registration is a well-known problem in the field of medical imaging. In this paper, we focus on the registration of chest inspiratory and expiratory computed tomography (CT) scans from the same patient. Our method recovers the diffeomorphic elastic displacement vector field (DVF) by jointly regressing the direct and the inverse transformation. Our architecture is based on the RegNet network but we implement a reinforced learning strategy that can accommodate a large training dataset. Our results show that our method performs with a lower estimation error for the same number of epochs than the RegNet approach.</p>","PeriodicalId":93006,"journal":{"name":"Image analysis for moving organ, breast, and thoracic images : third International Workshop, RAMBO 2018, fourth International Workshop, BIA 2018, and first International Workshop, TIA 2018, held in conjunction with MICCAI 2018, Granada,...","volume":"11040 ","pages":"284-294"},"PeriodicalIF":0.0000,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/978-3-030-00946-5_28","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image analysis for moving organ, breast, and thoracic images : third International Workshop, RAMBO 2018, fourth International Workshop, BIA 2018, and first International Workshop, TIA 2018, held in conjunction with MICCAI 2018, Granada,...","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/978-3-030-00946-5_28","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2018/9/12 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 10

Abstract

Image registration is a well-known problem in the field of medical imaging. In this paper, we focus on the registration of chest inspiratory and expiratory computed tomography (CT) scans from the same patient. Our method recovers the diffeomorphic elastic displacement vector field (DVF) by jointly regressing the direct and the inverse transformation. Our architecture is based on the RegNet network but we implement a reinforced learning strategy that can accommodate a large training dataset. Our results show that our method performs with a lower estimation error for the same number of epochs than the RegNet approach.

Abstract Image

查看原文本刊更多论文

基于深度cnn和强化学习的异胚肺配准。

图像配准是医学成像领域中一个众所周知的问题。在本文中，我们着重于注册胸部吸气和呼气的计算机断层扫描(CT)从同一患者。该方法通过对正变换和逆变换的联合回归，恢复了微分同构弹性位移向量场。我们的架构是基于RegNet网络的，但我们实现了一个强化的学习策略，可以容纳一个大的训练数据集。结果表明，在相同的epoch数下，我们的方法比RegNet方法具有更低的估计误差。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Image analysis for moving organ, breast, and thoracic images : third International Workshop, RAMBO 2018, fourth International Workshop, BIA 2018, and first International Workshop, TIA 2018, held in conjunction with MICCAI 2018, Granada,...

自引率

0.00%

发文量