Scholarlink

Background <p>The artificial intelligence-assisted ASPECTS (AI-ASPECTS) system has become an increasingly common tool in clinical practice for assessing acute ischemic stroke (AIS). However, current AI-ASPECTS implementations still rely on the conventional expert-evaluation framework, which uses a simplified two-slice atlas and arbitrarily selected lesion-load thresholds. Our study aimed to develop a refined AI-assisted ASPECTS (Ref-AI-ASPECTS) framework featuring a seamless &amp; whole middle cerebral artery (MCA) territory atlas and region-specific, optimally determined lesion-load thresholds, and comprehensively evaluate the performance of this framework across various clinical scenarios for AIS.</p> Methods <p>We enrolled a cohort of 7,655 AIS patients from eleven centers. Modified atlas was created by expanding conventional atlas based on full MCA territory. Ref-AI-ASPECTS with modified atlas and specific lesion-load thresholds was established using a genetic algorithm. The clinical utility of Ref-AI-ASPECTS was assessed by comparing it to the conventional framework (Con-AI-ASPECTS) in terms of correlation with NIHSS scores on admission, dichotomized prediction of mRS at 3 months, and consistency with expert scoring across the training DWI data, external DWI data, expanded CT data, and real-world prospective DWI data.</p> Results <p>The Ref-AI-ASPECTS frameworks with modified atlas and specific lesion-load thresholds (2% to 29%) achieved correlation coefficients (<i>r</i>) of −0.414/−0.438/−0.375 and AUC values of 0.665/0.723/0.707 in the training/internal validation/external validation sets, surpassing both Con-AI- (<i>r</i>: −0.336/−0.402/−0.331; AUC: 0.615/0.654/0.654) and expert-ASPECTS (<i>r</i>: −0.196/−0.206/−0.173; AUC: 0.600/0.641/0.644) (all <i>P</i> &lt; 0.01). The intraclass correlation coefficients for expert- and Ref-AI-ASPECTS were 0.82 and 0.81 in the training and external validation DWI sets, respectively, exceeding those of expert- and Con-AI-ASPECTS (0.69/0.67; both <i>P</i> &lt; 0.01). These improvements were consistently validated across expanded CT datasets (AUC: 0.696 and 0.679) and in a real-world prospective cohort (AUC: 0.710).</p> Conclusions <p>The Ref-AI-ASPECTS framework outperformed conventional approaches in evaluating baseline neurological deficits and predicting functional outcomes in AIS. Our findings support the potential for its wider implementation in AI-ASPECTS systems. Prospective external real‑world validation remains necessary.</p> Trial registration <p>ClinicalTrials.gov Identifier: NCT04775147; chictr.org.cn Identifier: ChiCTR2400092230</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

Refined AI-ASPECTS with modified atlas and lesion-load thresholds: advancing acute ischemic stroke imaging and prognostic prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月3日

查看全文
  • Liang Jiang,
  • Xin Deng,
  • Changcheng Li,
  • Yi Zhou,
  • Hongjie Huang,
  • Qiang Xu,
  • Zehong Cao,
  • Ziwei Nie,
  • Xiaoqing Cheng,
  • Yinghua Shi,
  • Mingyang Peng,
  • Qiwen Deng,
  • Xiangming Fang,
  • Changjie Pan,
  • Jing Ye,
  • Zhen Jiang,
  • Caifeng Guo,
  • Dante Mantini,
  • Zhongxiang Ding,
  • Guangming Lu,
  • Feng Shi,
  • Xindao Yin,
  • Shukui Wang,
  • Wusheng Zhu,
  • Zhiqiang Zhang,
  • Lulu Xiao,
  • Zhiwen Geng,
  • Zheng Dai,
  • Changjie Pan,
  • Min Zhang,
  • Zhiliang Guo,
  • Caifeng Guo,
  • Ting Hu

摘要

Background

The artificial intelligence-assisted ASPECTS (AI-ASPECTS) system has become an increasingly common tool in clinical practice for assessing acute ischemic stroke (AIS). However, current AI-ASPECTS implementations still rely on the conventional expert-evaluation framework, which uses a simplified two-slice atlas and arbitrarily selected lesion-load thresholds. Our study aimed to develop a refined AI-assisted ASPECTS (Ref-AI-ASPECTS) framework featuring a seamless & whole middle cerebral artery (MCA) territory atlas and region-specific, optimally determined lesion-load thresholds, and comprehensively evaluate the performance of this framework across various clinical scenarios for AIS.

Methods

We enrolled a cohort of 7,655 AIS patients from eleven centers. Modified atlas was created by expanding conventional atlas based on full MCA territory. Ref-AI-ASPECTS with modified atlas and specific lesion-load thresholds was established using a genetic algorithm. The clinical utility of Ref-AI-ASPECTS was assessed by comparing it to the conventional framework (Con-AI-ASPECTS) in terms of correlation with NIHSS scores on admission, dichotomized prediction of mRS at 3 months, and consistency with expert scoring across the training DWI data, external DWI data, expanded CT data, and real-world prospective DWI data.

Results

The Ref-AI-ASPECTS frameworks with modified atlas and specific lesion-load thresholds (2% to 29%) achieved correlation coefficients (r) of −0.414/−0.438/−0.375 and AUC values of 0.665/0.723/0.707 in the training/internal validation/external validation sets, surpassing both Con-AI- (r: −0.336/−0.402/−0.331; AUC: 0.615/0.654/0.654) and expert-ASPECTS (r: −0.196/−0.206/−0.173; AUC: 0.600/0.641/0.644) (all P < 0.01). The intraclass correlation coefficients for expert- and Ref-AI-ASPECTS were 0.82 and 0.81 in the training and external validation DWI sets, respectively, exceeding those of expert- and Con-AI-ASPECTS (0.69/0.67; both P < 0.01). These improvements were consistently validated across expanded CT datasets (AUC: 0.696 and 0.679) and in a real-world prospective cohort (AUC: 0.710).

Conclusions

The Ref-AI-ASPECTS framework outperformed conventional approaches in evaluating baseline neurological deficits and predicting functional outcomes in AIS. Our findings support the potential for its wider implementation in AI-ASPECTS systems. Prospective external real‑world validation remains necessary.

Trial registration

ClinicalTrials.gov Identifier: NCT04775147; chictr.org.cn Identifier: ChiCTR2400092230