文献速递神经头颈CTMR

深度学习模型在非增强CT上检测创伤性脑损伤及NIRIS分级的验证:一项多阅片者研究,结果有前景且存在改进空间

Validation of a deep learning model for traumatic brain injury detection and NIRIS grading on non-contrast CT: a multi-reader study with promising results and opportunities for improvement.
PubMed 文献 · Neuroradiology · 2023-06-03

该回顾性多阅片者研究纳入100例疑似创伤性脑损伤且接受非增强CT扫描的患者,评估深度学习模型icobrain tbi 5.0版与8名不同年资阅片者(神经放射学主治、fellow、住院医师及神经外科主治、住院医师)在NIRIS评分、中线移位、占位效应、出血性病灶、脑积水等方面的判读一致性。模型成功分类77例扫描,与金标准呈中等一致性,在NIRIS 0-2与3-4分类中特异度0.88、阳性预测值0.96;受训者与主治医师准确率最高(0.95)。模型作为辅助工具可改善受训者与金标准的一致性,但多数情况下主治医师评估仍更优,模型需进一步改进优化以提升临床效用。

要点

  • DL模型icobrain tbi 5.0与金标准、受训者及主治医师均呈中等一致性。
  • 模型分类NIRIS 0-2与3-4时特异度0.88、阳性预测值0.96。
  • 受训者与主治医师准确率最高(0.95),多数情况下主治医师评估仍更优。

核心结论

  • DL模型在某些方面优于受训者,但多数情况下主治医师评估仍更优;作为辅助工具可改善受训者NIRIS评分与金标准的一致性;模型在分类部分TBI CT影像常见数据元素方面有高潜力,但需进一步改进优化以提升临床效用。

研究设计与样本

  • 回顾性多阅片者研究,纳入100例疑似TBI并接受NCCT扫描的患者,8名不同年资阅片者独立评估,并与icobrain tbi 5.0版DL模型比较;金标准由研究阅片者共识结合临床、实验室及随访影像(NCCT和MRI)确定。

关键影像表现/征象

  • DL模型成功分类77例扫描,中位年龄48岁,未纳入组中位年龄44.5岁,纳入组中位年龄48岁。
  • DL模型在量化出血性病灶体积时平均差异6.0 mL(95%CI -68.32至80.22)。
  • DL模型在量化中线移位时平均差异1.4 mm(95%CI -3.4至6.2)。

诊断标准与关键数值

  • DL模型将NIRIS评分分类为0-2或3-4时,特异度0.88,阳性预测值0.96。
  • 受训者与主治医师准确率最高(0.95)。
  • DL模型在分类各种TBI CT影像常见数据元素方面的性能与受训者和主治医师相当。

临床应用与阅片要点

  • DL模型作为辅助工具可改善受训者NIRIS评分与金标准的一致性。
  • DL模型在出血性病灶体积及中线移位量化方面与金标准存在差异,95%CI较宽。
  • 作者认为模型在分类部分TBI CT影像常见数据元素方面有高潜力,但需进一步改进优化以提升临床效用。

局限性

  • DL模型仅成功分类77/100例扫描。
  • 出血性病灶体积量化的平均差异95%CI较宽(-68.32至80.22 mL)。
  • 中线移位量化的平均差异95%CI较宽(-3.4至6.2 mm)。
  • 作者指出模型需进一步改进和优化以提升临床效用。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: This study aimed to assess and externally validate the performance of a deep learning (DL) model for the interpretation of non-contrast computed tomography (NCCT) scans of patients with suspicion of traumatic brain injury (TBI).

METHODS: This retrospective and multi-reader study included patients with TBI suspicion who were transported to the emergency department and underwent NCCT scans. Eight reviewers, with varying levels of training and experience (two neuroradiology attendings, two neuroradiology fellows, two neuroradiology residents, one neurosurgery attending, and one neurosurgery resident), independently evaluated NCCT head scans. The same scans were evaluated using the version 5.0 of the DL model icobrain tbi. The establishment of the ground truth involved a thorough assessment of all accessible clinical and laboratory data, as well as follow-up imaging studies, including NCCT and magnetic resonance imaging, as a consensus amongst the study reviewers. The outcomes of interest included neuroimaging radiological interpretation system (NIRIS) scores, the presence of midline shift, mass effect, hemorrhagic lesions, hydrocephalus, and severe hydrocephalus, as well as measurements of midline shift and volumes of hemorrhagic lesions. Comparisons using weighted Cohen's kappa coefficient were made. The McNemar test was used to compare the diagnostic performance. Bland-Altman plots were used to compare measurements.

RESULTS: One hundred patients were included, with the DL model successfully categorizing 77 scans. The median age for the total group was 48, with the omitted group having a median age of 44.5 and the included group having a median age of 48. The DL model demonstrated moderate agreement with the ground truth, trainees, and attendings. With the DL model's assistance, trainees' agreement with the ground truth improved. The DL model showed high specificity (0.88) and positive predictive value (0.96) in classifying NIRIS scores as 0-2 or 3-4. Trainees and attendings had the highest accuracy (0.95). The DL model's performance in classifying various TBI CT imaging common data elements was comparable to that of trainees and attendings. The average difference for the DL model in quantifying the volume of hemorrhagic lesions was 6.0 mL with a wide 95% confidence interval (CI) of - 68.32 to 80.22, and for midline shift, the average difference was 1.4 mm with a 95% CI of - 3.4 to 6.2.

CONCLUSION: While the DL model outperformed trainees in some aspects, attendings' assessments remained superior in most instances. Using the DL model as an assistive tool benefited trainees, improving their NIRIS score agreement with the ground truth. Although the DL model showed high potential in classifying some TBI CT imaging common data elements, further refinement and optimization are necessary to enhance its clinical utility.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Jiang, Ozkara, Creeden, et al. Validation of a deep learning model for traumatic brain injury detection and NIRIS grading on non-contrast CT: a multi-reader study with promising results and opportunities for improvement. Neuroradiology. 2023. PMID: 37269414. doi:10.1007/s00234-023-03170-5

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。