Scholarlink

Background <p>Clinical evaluation of Artificial Intelligence (AI)-based Precise Image (PI) algorithm in brain imaging remains limited. PI is a&#xa0;deep-learning reconstruction (DLR) technique that reduces image noise while maintaining a&#xa0;familiar Filtered Back Projection (FBP)-like appearance at low doses. This study aims to compare PI, Iterative Reconstruction (IR), and FBP—in improving image quality and enhancing lesion detection in 1.0 mm thin-slice brain computed tomography (CT) images.</p> Methods <p>A&#xa0;retrospective analysis was conducted on brain non-contrast CT scans from August to September 2024 at our institution. Each scan was reconstructed using four methods: routine 5.0 mm FBP (Group&#xa0;A), thin-slice 1.0 mm FBP (Group&#xa0;B), thin-slice 1.0 mm&#xa0;IR (Group&#xa0;C), and thin-slice 1.0 mm PI (Group&#xa0;D). Subjective image quality was assessed by two radiologists using a&#xa0;4- or 5‑point Likert scale. Objective metrics included contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), and image noise across designated regions of interest (ROIs).</p> Results <p>60&#xa0;patients (65.47 years ± 18.40; 29&#xa0;males and 31&#xa0;females) were included. Among these, 39&#xa0;patients had lesions, primarily low-density lacunar infarcts. Thin-slice PI images demonstrated the lowest image noise and artifacts, alongside the highest CNR and SNR values (<i>p</i> &lt; 0.001) compared to Groups&#xa0;A,&#xa0;B, and C.&#xa0;Subjective assessments revealed that both PI and IR provided significantly improved image quality over routine FBP (<i>p</i> &lt; 0.05). Specifically, Group&#xa0;D (PI) achieved superior lesion conspicuity and diagnostic confidence, with a&#xa0;100% detection rate for lacunar lesions, outperforming Groups B and&#xa0;A.</p> Conclusions <p>PI reconstruction significantly enhances image quality and lesion detectability in thin-slice brain CT scans compared to IR and FBP, suggesting its potential as a&#xa0;new clinical standard.</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

Thin-Slice Brain CT Image Quality and Lesion Detection Evaluation in Deep Learning Reconstruction Algorithm

  • 期刊论文

  • 发表日期：

    2025年7月23日

查看全文
  • Jiali Sun,
  • Hui Yao,
  • Tailin Han,
  • Yan Wang,
  • Le Yang,
  • Xizhe Hao,
  • Su Wu

摘要

Background

Clinical evaluation of Artificial Intelligence (AI)-based Precise Image (PI) algorithm in brain imaging remains limited. PI is a deep-learning reconstruction (DLR) technique that reduces image noise while maintaining a familiar Filtered Back Projection (FBP)-like appearance at low doses. This study aims to compare PI, Iterative Reconstruction (IR), and FBP—in improving image quality and enhancing lesion detection in 1.0 mm thin-slice brain computed tomography (CT) images.

Methods

A retrospective analysis was conducted on brain non-contrast CT scans from August to September 2024 at our institution. Each scan was reconstructed using four methods: routine 5.0 mm FBP (Group A), thin-slice 1.0 mm FBP (Group B), thin-slice 1.0 mm IR (Group C), and thin-slice 1.0 mm PI (Group D). Subjective image quality was assessed by two radiologists using a 4- or 5‑point Likert scale. Objective metrics included contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), and image noise across designated regions of interest (ROIs).

Results

60 patients (65.47 years ± 18.40; 29 males and 31 females) were included. Among these, 39 patients had lesions, primarily low-density lacunar infarcts. Thin-slice PI images demonstrated the lowest image noise and artifacts, alongside the highest CNR and SNR values (p < 0.001) compared to Groups A, B, and C. Subjective assessments revealed that both PI and IR provided significantly improved image quality over routine FBP (p < 0.05). Specifically, Group D (PI) achieved superior lesion conspicuity and diagnostic confidence, with a 100% detection rate for lacunar lesions, outperforming Groups B and A.

Conclusions

PI reconstruction significantly enhances image quality and lesion detectability in thin-slice brain CT scans compared to IR and FBP, suggesting its potential as a new clinical standard.