文献速递腹部CT

评估机器学习模型早期检测胰腺导管腺癌的稳健性:利用图像扰动方法评估其对图像采集和影像组学流程变化的适应能力

Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods.
PubMed 文献 · Abdom Radiol (NY) · 2024-01-04

本研究评估基于影像组学的支持向量机模型在诊断前CT上检测视觉隐匿性胰腺导管腺癌的稳健性,通过18种算法生成的扰动模拟图像噪声、旋转、体素重采样、灰度离散化和胰腺分割变化。模型在未扰动测试子集上准确率92.2%、AUC 0.98,在多数临床相关变化下性能保持稳健,但噪声增至3σ时敏感度降至80%(p=0.02)。结论认为模型在广泛临床相关变化范围内具有稳健性。

要点

  • 模型在未扰动测试子集(n=128)上准确率92.2%、AUC 0.98,正确分类45例诊断前CT中的43例和83例正常胰腺对照CT中的75例。
  • 噪声增至3σ时模型敏感度降至80%(p=0.02),其余噪声水平下性能未受影响。
  • 图像旋转(p=0.99)、体素重采样(p=0.25-0.31)、灰度级bin宽度32(p=0.31-0.99)以及胰腺边界腐蚀/膨胀至4像素(p=0.12-0.34)下性能与未扰动测试子集相当。

核心结论

  • 模型在广泛临床相关图像采集和影像组学流程变化范围内对视觉隐匿性胰腺导管腺癌检测保持稳健性能。

研究设计与样本

  • 研究论文;评估基于影像组学的支持向量机模型,在128例测试子集(45例诊断前CT、83例正常胰腺对照CT)上引入18种算法生成扰动,比较模型性能与未扰动测试子集。

诊断标准与关键数值

  • 未扰动测试子集上模型准确率92.2%、AUC 0.98;噪声3σ时敏感度80%(p=0.02);图像旋转p=0.99、体素重采样p=0.25-0.31、灰度级bin宽度32 p=0.31-0.99、胰腺边界腐蚀/膨胀至4像素p=0.12-0.34。

局限性

  • 原文未报告局限性。

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: To evaluate robustness of a radiomics-based support vector machine (SVM) model for detection of visually occult PDA on pre-diagnostic CTs by simulating common variations in image acquisition and radiomics workflow using image perturbation methods.

METHODS: Eighteen algorithmically generated-perturbations, which simulated variations in image noise levels (σ, 2σ, 3σ, 5σ), image rotation [both CT image and the corresponding pancreas segmentation mask by 45° and 90° in axial plane], voxel resampling (isotropic and anisotropic), gray-level discretization [bin width (BW) 32 and 64)], and pancreas segmentation (sequential erosions by 3, 4, 6, and 8 pixels and dilations by 3, 4, and 6 pixels from the boundary), were introduced to the original (unperturbed) test subset (n = 128; 45 pre-diagnostic CTs, 83 control CTs with normal pancreas). Radiomic features were extracted from pancreas masks of these additional test subsets, and the model's performance was compared vis-a-vis the unperturbed test subset.

RESULTS: The model correctly classified 43 out of 45 pre-diagnostic CTs and 75 out of 83 control CTs in the unperturbed test subset, achieving 92.2% accuracy and 0.98 AUC. Model's performance was unaffected by a three-fold increase in noise level except for sensitivity declining to 80% at 3σ (p = 0.02). Performance remained comparable vis-a-vis the unperturbed test subset despite variations in image rotation (p = 0.99), voxel resampling (p = 0.25-0.31), change in gray-level BW to 32 (p = 0.31-0.99), and erosions/dilations up to 4 pixels from the pancreas boundary (p = 0.12-0.34).

CONCLUSION: The model's high performance for detection of visually occult PDA was robust within a broad range of clinically relevant variations in image acquisition and radiomics workflow.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Mukherjee S, Korfiatis P, Patnam NG, et al. Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods. Abdom Radiol (NY). 2024. PMID: 38175255. doi:10.1007/s00261-023-04127-1

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。