文献速递神经头颈CT

超高分辨率光子计数探测器CT结合专用去噪卷积神经网络提升颞骨成像

Ultra-High-Resolution Photon-Counting-Detector CT with a Dedicated Denoising Convolutional Neural Network for Enhanced Temporal Bone Imaging.
PubMed 文献 · AJNR Am J Neuroradiol · 2025-06-03

本研究在双源光子计数探测器CT上训练去噪卷积神经网络,用于超高清颞骨成像中以最锐利核重建的图像;该网络在20例测试病例中降低噪声并保持分辨率,Hr96-CNN图像整体质量评分高于常规Hr84-QIR3和Hr96-QIR3(P < .001),读者对镫骨足板、砧锤关节和蜗轴三个结构的显示均更偏好Hr96-CNN。

要点

  • Hr96-CNN较Hr96-QIR3噪声降低80%,较Hr84-QIR3降低50%,同时保持高分辨率。
  • Hr96-CNN图像整体质量评分高于Hr84-QIR3和Hr96-QIR3(P < .001)。
  • 读者对蜗轴、镫骨足板和砧锤关节三个结构的显示均更偏好Hr96-CNN。

核心结论

  • 所提出的卷积神经网络显著降低了超高清光子计数探测器CT的图像噪声,使最锐利核得以使用,该组合大幅提升了诊断图像质量和解剖结构可视化。

研究设计与样本

  • 经机构审查委员会批准,去噪卷积神经网络在6例临床颞骨成像病例(1885幅图像)上训练,并在20例独立病例上测试,使用双源光子计数探测器CT(NAEOTOM Alpha)。

关键影像表现/征象

  • Hr96-CNN较Hr96-QIR3噪声降低80%,较Hr84-QIR3噪声降低50%,同时保持高分辨率。
  • 与同核常规方法Hr96-QIR3相比,Hr96-CNN显著降低图像噪声(从204.63 HU降至47.35 HU),结构相似性指数从0.72提升至0.99。
  • Hr96-CNN图像整体质量评分高于Hr84-QIR3和Hr96-QIR3(P < .001)。
  • 读者对蜗轴、镫骨足板和砧锤关节三个结构的显示均更偏好Hr96-CNN。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND AND PURPOSE: Ultra-high-resolution (UHR) photon-counting-detector (PCD) CT improves image resolution but increases noise, necessitating the use of smoother reconstruction kernels that reduce resolution below the 0.125-mm maximum spatial resolution. A denoising convolutional neural network (CNN) was developed to reduce noise in images reconstructed with the available sharpest reconstruction kernel while preserving resolution for enhanced temporal bone visualization to address this issue.

MATERIALS AND METHODS: With institutional review board approval, the CNN was trained on 6 patient cases of clinical temporal bone imaging (1885 images) and tested on 20 independent cases using a dual-source PCD-CT (NAEOTOM Alpha). Images were reconstructed using quantum iterative reconstruction at strength 3 (QIR3) with both a clinical routine kernel (Hr84) and the sharpest available head kernel (Hr96). The CNN was applied to images reconstructed with Hr96 and QIR1 kernel. For each case, three series of images (Hr84-QIR3, Hr96-QIR3, and Hr96-CNN) were randomized for review by 2 neuroradiologists assessing the overall quality and delineating the modiolus, stapes footplate, and incudomallear joint.

RESULTS: The CNN reduced noise by 80% compared with Hr96-QIR3 and by 50% relative to Hr84-QIR3, while maintaining high resolution. Compared with the conventional method at the same kernel (Hr96-QIR3), Hr96-CNN significantly decreased image noise (from 204.63 to 47.35 HU) and improved its structural similarity index (from 0.72 to 0.99). Hr96-CNN images ranked higher than Hr84-QIR3 and Hr96-QIR3 in overall quality (P < .001). Readers preferred Hr96-CNN for all 3 structures.

CONCLUSIONS: The proposed CNN significantly reduced image noise in UHR PCD-CT, enabling the use of the sharpest kernel. This combination greatly enhanced diagnostic image quality and anatomic visualization.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Chang S, Benson JC, Lane JI, et al. Ultra-High-Resolution Photon-Counting-Detector CT with a Dedicated Denoising Convolutional Neural Network for Enhanced Temporal Bone Imaging. AJNR Am J Neuroradiol. 2025. PMID: 39528299. doi:10.3174/ajnr.A8572

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。