Scholarlink

Objectives <p>To evaluate the benefits of an automated deep learning-based tool (RTLI-DM) for early detection of radiation-induced temporal lobe injury (RTLI) on MRI.</p> Materials and methods <p>A total of 396 RTLI and 3181 non-RTLI patients were retrospectively included from a cohort of 6483 NPC patients who underwent radiotherapy and MRI follow-ups at four hospitals from January 2010 to June 2021. We developed and validated an automated RTLI-DM using the initial abnormal MRI of RTLI patients and the final MRI of non-RTLI patients. The RTLI-DM consists of a bilateral temporal lobe segmentation model based on Unet++ and a diagnostic model based on a modified DenseNet-121 network. The multi-reader study was conducted to compare the performance of four radiologists (two trainees, and two experienced readers) in interpreting images without and with RTLI-DM assistance. Sensitivity, specificity, false positives (FPs), and false negatives (FNs) were compared between two reading sessions.</p> Results <p>Assisted reading with RTLI-DM significantly improve the sensitivity (60.5% [95% CI: 53.6–67.0%] vs 83.5% [95% CI: 77.7–88.0%]; 79.5% [95% CI: 73.3–84.5%] vs 91.5% [95% CI: 86.7–94.7%]) and FNs (0.395 vs 0.165; 0.205 vs 0.085) for both trainees and experienced readers, although there is a slight decrease in specificity (99.0% [95% CI: 96.2–100%] vs 93.0% [95% CI: 88.5–95.9%]) and increase in FPs (0.01 vs 0.07) for trainees (<i>p</i> &lt; 0.05). The averaged time for assisted reading is reduced by 29 s, compared with unassisted reading.</p> Conclusion <p>For early detection of RTLI on MRI, the RTLI-DM assistant significantly improved the diagnostic performance of radiologists while reducing the reading time.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis> <i>RTLI is usually asymptomatic in its initial stage, which contributes to the challenges of early diagnosis</i>.</p> <p><Emphasis Type="BoldItalic">Findings</Emphasis> <i>The effectiveness of the RTLI detection model (RTLI-DM) as a diagnostic aid is evident, particularly in enhancing the detection of subtle lesions</i>.</p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis> <i>The RTLI-DM can significantly improve radiologists’ diagnostic efficiency and accuracy in the early detection of RTLI in clinical workflows, but still requires validation when in clinical applications</i>.</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

Automated deep learning-assisted early detection of radiation-induced temporal lobe injury on MRI: a multicenter retrospective analysis

  • 期刊论文

  • 发表日期：

    2025年3月7日

查看全文
  • Fangxue Yang,
  • Rong Hu,
  • Jing Hu,
  • Linmei Zhao,
  • Youming Zhang,
  • Yitao Mao,
  • Jingyi Tang,
  • Sai Li,
  • Jiaqi He,
  • Ruiting Chen,
  • Jiuqing Guo,
  • Weiwei Zhang,
  • Liping Zhu,
  • Xiao Jiao,
  • Shulin Liu,
  • Guanghua Luo,
  • Hong Zhou,
  • Xiangjun Fang,
  • Haijun Zheng,
  • Lang Li,
  • Zaide Han,
  • Zhicheng Jiao,
  • Harrison X. Bai,
  • Junfeng Li,
  • Weihua Liao

摘要

Objectives

To evaluate the benefits of an automated deep learning-based tool (RTLI-DM) for early detection of radiation-induced temporal lobe injury (RTLI) on MRI.

Materials and methods

A total of 396 RTLI and 3181 non-RTLI patients were retrospectively included from a cohort of 6483 NPC patients who underwent radiotherapy and MRI follow-ups at four hospitals from January 2010 to June 2021. We developed and validated an automated RTLI-DM using the initial abnormal MRI of RTLI patients and the final MRI of non-RTLI patients. The RTLI-DM consists of a bilateral temporal lobe segmentation model based on Unet++ and a diagnostic model based on a modified DenseNet-121 network. The multi-reader study was conducted to compare the performance of four radiologists (two trainees, and two experienced readers) in interpreting images without and with RTLI-DM assistance. Sensitivity, specificity, false positives (FPs), and false negatives (FNs) were compared between two reading sessions.

Results

Assisted reading with RTLI-DM significantly improve the sensitivity (60.5% [95% CI: 53.6–67.0%] vs 83.5% [95% CI: 77.7–88.0%]; 79.5% [95% CI: 73.3–84.5%] vs 91.5% [95% CI: 86.7–94.7%]) and FNs (0.395 vs 0.165; 0.205 vs 0.085) for both trainees and experienced readers, although there is a slight decrease in specificity (99.0% [95% CI: 96.2–100%] vs 93.0% [95% CI: 88.5–95.9%]) and increase in FPs (0.01 vs 0.07) for trainees (p < 0.05). The averaged time for assisted reading is reduced by 29 s, compared with unassisted reading.

Conclusion

For early detection of RTLI on MRI, the RTLI-DM assistant significantly improved the diagnostic performance of radiologists while reducing the reading time.

Key Points

Question RTLI is usually asymptomatic in its initial stage, which contributes to the challenges of early diagnosis.

Findings The effectiveness of the RTLI detection model (RTLI-DM) as a diagnostic aid is evident, particularly in enhancing the detection of subtle lesions.

Clinical relevance The RTLI-DM can significantly improve radiologists’ diagnostic efficiency and accuracy in the early detection of RTLI in clinical workflows, but still requires validation when in clinical applications.