改进基于神经辐射场的医学图像合成中的姿态精度和几何形状。

Medical physics Pub Date : 2025-04-14 DOI:10.1002/mp.17832
Twaha Kabika, Cai Hongsen, Zhu Hongling, Dong Jingxian, Zhang Siyuan, Mingyue Ding, Deng Xianbo, Hou Wenguang, Wang Yan
{"title":"改进基于神经辐射场的医学图像合成中的姿态精度和几何形状。","authors":"Twaha Kabika, Cai Hongsen, Zhu Hongling, Dong Jingxian, Zhang Siyuan, Mingyue Ding, Deng Xianbo, Hou Wenguang, Wang Yan","doi":"10.1002/mp.17832","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Neural radiance field (NeRF) models have garnered significant attention for their impressive ability to synthesize high-quality novel scene views from posed 2D images. Recently, the MedNeRF algorithm was developed to render complete computed tomography (CT) projections from a single or a few x-ray images further. Despite this advancement, MedNeRF struggles with accurate pose reconstruction, crucial for radiologists during image analysis, leading to blurry geometry in the generated outputs.</p><p><strong>Purpose: </strong>Motivated by these challenges, our research aims to address MedNeRF's limitations in pose accuracy and image clarity. Specifically, we seek to improve the pose accuracy of reconstructed images and enhance the generated output's anatomical detail and quality.</p><p><strong>Methods: </strong>We propose a novel pose-aware discriminator that estimates pose differences between generated and real patches, ensuring accurate poses and deeper anatomical structures in generated images. We enhance volumetric rendering from single-view x-rays by introducing a customized distortion adaptive loss function and present the HTDataset, a new dataset pair that better mimics machine-generated x-rays, offering clearer anatomical depictions with reduced noise.</p><p><strong>Results: </strong>Our method successfully renders images with correct poses and high fidelity, outperforming existing state-of-the-art methods. The results demonstrate superior performance in both qualitative and quantitative metrics.</p><p><strong>Conclusions: </strong>The proposed approach addresses the pose reconstruction challenge in MedNeRF, enhances the anatomical detail, and reduces noise in generated images. The use of HTDataset and the innovative discriminator structure lead to significant improvements in the accuracy and quality of the rendered images, setting a new benchmark in the field.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improving pose accuracy and geometry in neural radiance field-based medical image synthesis.\",\"authors\":\"Twaha Kabika, Cai Hongsen, Zhu Hongling, Dong Jingxian, Zhang Siyuan, Mingyue Ding, Deng Xianbo, Hou Wenguang, Wang Yan\",\"doi\":\"10.1002/mp.17832\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Neural radiance field (NeRF) models have garnered significant attention for their impressive ability to synthesize high-quality novel scene views from posed 2D images. Recently, the MedNeRF algorithm was developed to render complete computed tomography (CT) projections from a single or a few x-ray images further. Despite this advancement, MedNeRF struggles with accurate pose reconstruction, crucial for radiologists during image analysis, leading to blurry geometry in the generated outputs.</p><p><strong>Purpose: </strong>Motivated by these challenges, our research aims to address MedNeRF's limitations in pose accuracy and image clarity. Specifically, we seek to improve the pose accuracy of reconstructed images and enhance the generated output's anatomical detail and quality.</p><p><strong>Methods: </strong>We propose a novel pose-aware discriminator that estimates pose differences between generated and real patches, ensuring accurate poses and deeper anatomical structures in generated images. We enhance volumetric rendering from single-view x-rays by introducing a customized distortion adaptive loss function and present the HTDataset, a new dataset pair that better mimics machine-generated x-rays, offering clearer anatomical depictions with reduced noise.</p><p><strong>Results: </strong>Our method successfully renders images with correct poses and high fidelity, outperforming existing state-of-the-art methods. The results demonstrate superior performance in both qualitative and quantitative metrics.</p><p><strong>Conclusions: </strong>The proposed approach addresses the pose reconstruction challenge in MedNeRF, enhances the anatomical detail, and reduces noise in generated images. The use of HTDataset and the innovative discriminator structure lead to significant improvements in the accuracy and quality of the rendered images, setting a new benchmark in the field.</p>\",\"PeriodicalId\":94136,\"journal\":{\"name\":\"Medical physics\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-04-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1002/mp.17832\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1002/mp.17832","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

背景:神经辐射场(NeRF)模型因其从2D图像合成高质量新场景视图的令人印象深刻的能力而获得了极大的关注。最近,MedNeRF算法被开发出来,可以进一步从单个或几张x射线图像中绘制完整的计算机断层扫描(CT)投影。尽管取得了这一进步,但MedNeRF仍在努力实现准确的姿态重建,这对放射科医生在图像分析过程中至关重要,导致生成的输出中几何形状模糊。目的:在这些挑战的激励下,我们的研究旨在解决MedNeRF在姿态准确性和图像清晰度方面的局限性。具体来说,我们寻求提高重建图像的姿态精度,增强生成的输出的解剖细节和质量。方法:我们提出了一种新的姿态感知鉴别器,用于估计生成图像和真实图像之间的姿态差异,确保生成图像中的准确姿态和更深层次的解剖结构。我们通过引入定制的畸变自适应损失函数来增强单视图x射线的体积渲染,并提出HTDataset,这是一个新的数据集对,可以更好地模拟机器生成的x射线,提供更清晰的解剖描述,降低噪声。结果:我们的方法成功地呈现出正确的姿态和高保真度的图像,优于现有的最先进的方法。结果表明,在定性和定量指标优越的性能。结论:所提出的方法解决了MedNeRF中的姿态重建挑战,增强了解剖细节,并降低了生成图像中的噪声。利用HTDataset和创新的鉴别器结构,显著提高了渲染图像的精度和质量,在该领域树立了新的标杆。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Improving pose accuracy and geometry in neural radiance field-based medical image synthesis.

Background: Neural radiance field (NeRF) models have garnered significant attention for their impressive ability to synthesize high-quality novel scene views from posed 2D images. Recently, the MedNeRF algorithm was developed to render complete computed tomography (CT) projections from a single or a few x-ray images further. Despite this advancement, MedNeRF struggles with accurate pose reconstruction, crucial for radiologists during image analysis, leading to blurry geometry in the generated outputs.

Purpose: Motivated by these challenges, our research aims to address MedNeRF's limitations in pose accuracy and image clarity. Specifically, we seek to improve the pose accuracy of reconstructed images and enhance the generated output's anatomical detail and quality.

Methods: We propose a novel pose-aware discriminator that estimates pose differences between generated and real patches, ensuring accurate poses and deeper anatomical structures in generated images. We enhance volumetric rendering from single-view x-rays by introducing a customized distortion adaptive loss function and present the HTDataset, a new dataset pair that better mimics machine-generated x-rays, offering clearer anatomical depictions with reduced noise.

Results: Our method successfully renders images with correct poses and high fidelity, outperforming existing state-of-the-art methods. The results demonstrate superior performance in both qualitative and quantitative metrics.

Conclusions: The proposed approach addresses the pose reconstruction challenge in MedNeRF, enhances the anatomical detail, and reduces noise in generated images. The use of HTDataset and the innovative discriminator structure lead to significant improvements in the accuracy and quality of the rendered images, setting a new benchmark in the field.

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
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信