Scholarlink

Purpose <p>To reveal the effectiveness of image correction using a conditional generative adversarial network for sparse-view cone-beam computed tomography (CBCT) images, we generated pseudo-CBCT images with data projection angles ranging from 1° to 20° from CT images and evaluated the image quality and tumor shape reproducibility.</p> Methods <p>Cone beam projection was simulated using multi-slice CT images with the ray summation method, and pseudo-CBCT images were reconstructed for 15 patients. These projections were collected at each rotation angle of 1º– 20º to acquire a sparse-view CBCT image. The dataset comprised paired sparse pseudo-CBCT and original CT images. Overall, 14 and one cases were used in the training and validation datasets, respectively. The structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were calculated to evaluate image quality, and the Dice index evaluated tumor shape similarity in the corrected CBCT images.</p> Results <p>The sparse-view CBCT image quality improved, resembling the original CT images. SSIM increased from an average of 0.11 to 0.80, and PSNR improved from 9.50 to 21.2 dB. The dice index improved from 0.79 to 0.82. However, data acquisition at larger sparse projection angles resulted in a blurring of reconstructed tumor shapes, indicating limitations in maintaining structural fidelity.</p> Conclusion <p>Conditional generative adversarial networks-based correction significantly improves the image quality and tumor shape reproducibility of sparse-view CBCT images. However, higher projection angles result in structural blurring, suggesting limitations in maintaining tumor shape integrity at larger angles.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Image Quality and Tumor Shape Correction in Sparse Projection Cone-Beam CT Using Conditional Generative Adversarial Networks

  • 期刊论文

  • 发表日期：

    2025年2月19日

查看全文
  • Sae Kamiyama,
  • Keisuke Usui,
  • Kenta Suga,
  • Hiroto Adachi,
  • Akihiro Arita,
  • Hajime Sakamoto,
  • Shinsuke Kyogoku,
  • Hiroyuki Daida

摘要

Purpose

To reveal the effectiveness of image correction using a conditional generative adversarial network for sparse-view cone-beam computed tomography (CBCT) images, we generated pseudo-CBCT images with data projection angles ranging from 1° to 20° from CT images and evaluated the image quality and tumor shape reproducibility.

Methods

Cone beam projection was simulated using multi-slice CT images with the ray summation method, and pseudo-CBCT images were reconstructed for 15 patients. These projections were collected at each rotation angle of 1º– 20º to acquire a sparse-view CBCT image. The dataset comprised paired sparse pseudo-CBCT and original CT images. Overall, 14 and one cases were used in the training and validation datasets, respectively. The structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were calculated to evaluate image quality, and the Dice index evaluated tumor shape similarity in the corrected CBCT images.

Results

The sparse-view CBCT image quality improved, resembling the original CT images. SSIM increased from an average of 0.11 to 0.80, and PSNR improved from 9.50 to 21.2 dB. The dice index improved from 0.79 to 0.82. However, data acquisition at larger sparse projection angles resulted in a blurring of reconstructed tumor shapes, indicating limitations in maintaining structural fidelity.

Conclusion

Conditional generative adversarial networks-based correction significantly improves the image quality and tumor shape reproducibility of sparse-view CBCT images. However, higher projection angles result in structural blurring, suggesting limitations in maintaining tumor shape integrity at larger angles.