Scholarlink

Background <p>Conventional <sup>123</sup>I-ioflupane dopamine-transporter SPECT requires 25–40&#xa0;min of acquisition, causing patient discomfort and limiting throughput. This study assessed whether deep-learning (DL) reconstruction can yield diagnostic-quality images from a 5-min scan.</p> Methods <p>We retrospectively analysed 207 studies (1035 slices) obtained between April 2018 and June 2020. After cropping to 64 × 64 striatal regions, 600, 185 and 250 images from 120, 37 and 50 patients were used for training, validation and testing. Six convolutional architectures—U-Net (one–five depths), V-Net, U-Net +  + , R2U-Net, Attention U-Net and TransUNet—were trained to translate 5-min into virtual 25-min images. Image quality was assessed with peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), analysed by Friedman and Dunn–Holm tests. A blinded reader study involved three nuclear medicine physicians grading 50 cases (100 striata) on a four-point scale; agreement with the 25-min consensus was measured by weighted κ and intra-/inter-observer intraclass correlation coefficients (ICC).</p> Results <p>All DL reconstructions significantly outperformed raw 5-min images in PSNR and SSIM (p &lt; 0.01). The four-layer U-Net achieved the highest quality (PSNR 32.7 ± 1.7&#xa0;dB, SSIM 0.842 ± 0.069), ≈1.8&#xa0;dB and 0.13 higher than baseline, and statistically indistinguishable from 25-min images (<i>p</i> &gt; 0.05). Reader concordance improved from fair with baseline (κ = 0.29–0.41) to substantial with the four-layer U-Net (κ = 0.62–0.70); intra-reader ICC was 0.84–0.93 and inter-reader ICC 0.73–0.75.</p> Conclusions <p>A compact four-layer U-Net restores diagnostic fidelity to 5-min <sup>123</sup>I-ioflupane SPECT, enabling an 80% reduction in scan time without loss of quantitative metrics or interpretability. DL-accelerated protocols may enhance comfort, reduce motion artefacts and increase throughput, warranting prospective multicentre validation.</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

Accelerating imaging: deep learning for enhanced 123I-ioflupane SPECT efficiency

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月18日

查看全文
  • Yoshinobu Ishiwata,
  • Keiichi Horie,
  • Kazuhiro Aritome,
  • Ryo Aoki,
  • Hitoshi Iizuka,
  • Shinjiro Aso,
  • Yuka Takeuchi,
  • Yuka Misumi,
  • Akira Haga,
  • Shingo Kato,
  • Tsuneo Yamashiro,
  • Shoko Takano,
  • Daisuke Utsunomiya

摘要

Background

Conventional 123I-ioflupane dopamine-transporter SPECT requires 25–40 min of acquisition, causing patient discomfort and limiting throughput. This study assessed whether deep-learning (DL) reconstruction can yield diagnostic-quality images from a 5-min scan.

Methods

We retrospectively analysed 207 studies (1035 slices) obtained between April 2018 and June 2020. After cropping to 64 × 64 striatal regions, 600, 185 and 250 images from 120, 37 and 50 patients were used for training, validation and testing. Six convolutional architectures—U-Net (one–five depths), V-Net, U-Net +  + , R2U-Net, Attention U-Net and TransUNet—were trained to translate 5-min into virtual 25-min images. Image quality was assessed with peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), analysed by Friedman and Dunn–Holm tests. A blinded reader study involved three nuclear medicine physicians grading 50 cases (100 striata) on a four-point scale; agreement with the 25-min consensus was measured by weighted κ and intra-/inter-observer intraclass correlation coefficients (ICC).

Results

All DL reconstructions significantly outperformed raw 5-min images in PSNR and SSIM (p < 0.01). The four-layer U-Net achieved the highest quality (PSNR 32.7 ± 1.7 dB, SSIM 0.842 ± 0.069), ≈1.8 dB and 0.13 higher than baseline, and statistically indistinguishable from 25-min images (p > 0.05). Reader concordance improved from fair with baseline (κ = 0.29–0.41) to substantial with the four-layer U-Net (κ = 0.62–0.70); intra-reader ICC was 0.84–0.93 and inter-reader ICC 0.73–0.75.

Conclusions

A compact four-layer U-Net restores diagnostic fidelity to 5-min 123I-ioflupane SPECT, enabling an 80% reduction in scan time without loss of quantitative metrics or interpretability. DL-accelerated protocols may enhance comfort, reduce motion artefacts and increase throughput, warranting prospective multicentre validation.