Department of Radiology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, X-ray Level 2, Headley Way, Headington, Oxford, OX3 9DU, UK.
Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Headley Way, Headington, Oxford, OX3 9DU, UK.
Eur Radiol. 2022 Aug;32(8):5330-5338. doi: 10.1007/s00330-022-08635-4. Epub 2022 Mar 3.
To determine if predictions of the Lung Cancer Prediction convolutional neural network (LCP-CNN) artificial intelligence (AI) model are analogous to the Brock model.
In total, 10,485 lung nodules in 4660 participants from the National Lung Screening Trial (NLST) were analysed. Both manual and automated nodule measurements were inputted into the Brock model, and this was compared to LCP-CNN. The performance of an experimental AI model was tested after ablating imaging features in a manner analogous to removing predictors from the Brock model. First, the nodule was ablated leaving lung parenchyma only. Second, a sphere of the same size as the nodule was implanted in the parenchyma. Third, internal texture of both nodule and parenchyma was ablated.
Automated axial diameter (AUC 0.883) and automated equivalent spherical diameter (AUC 0.896) significantly improved the accuracy of Brock when compared to manual measurement (AUC 0.873), although not to the level of the LCP-CNN (AUC 0.936). Ablating nodule and parenchyma texture (AUC 0.915) led to a small drop in AI predictive accuracy, as did implanting a sphere of the same size as the nodule (AUC 0.889). Ablating the nodule leaving parenchyma only led to a large drop in AI performance (AUC 0.717).
Feature ablation is a feasible technique for understanding AI model predictions. Nodule size and morphology play the largest role in AI prediction, with nodule internal texture and background parenchyma playing a limited role. This is broadly analogous to the relative importance of morphological factors over clinical factors within the Brock model.
• Brock lung cancer risk prediction accuracy was significantly improved using automated axial or equivalent spherical measurements of lung nodule diameter, when compared to manual measurements. • Predictive accuracy was further improved by using the Lung Cancer Prediction convolutional neural network, an artificial intelligence-based model which obviates the requirement for nodule measurement. • Nodule size and morphology are important factors in artificial intelligence lung cancer risk prediction, with nodule texture and background parenchyma contributing a small, but measurable, role.
确定肺癌预测卷积神经网络（LCP-CNN）人工智能（AI）模型的预测是否与 Brock 模型类似。
对来自国家肺癌筛查试验（NLST）的 4660 名参与者的 10485 个肺结节进行分析。将手动和自动结节测量值输入 Brock 模型，并与 LCP-CNN 进行比较。通过类似于从 Brock 模型中删除预测因子的方式对实验性 AI 模型的性能进行了测试。首先，将结节消融仅留下肺实质。其次，在实质中植入与结节大小相同的球体。第三，消融结节和实质的内部纹理。
与手动测量相比（AUC 0.873），自动轴向直径（AUC 0.883）和自动等效球形直径（AUC 0.896）显著提高了 Brock 的准确性，尽管不如 LCP-CNN（AUC 0.936）。消融结节和实质纹理（AUC 0.915）会导致 AI 预测准确性略有下降，植入与结节大小相同的球体也会导致（AUC 0.889）。仅消融结节留下肺实质会导致 AI 性能大幅下降（AUC 0.717）。
特征消融是理解 AI 模型预测的一种可行技术。结节大小和形态在 AI 预测中起着最大的作用，而结节内部纹理和背景实质则起着有限的作用。这与 Brock 模型中形态因素相对于临床因素的相对重要性大致相似。
与手动测量相比，使用肺结节直径的自动轴向或等效球形测量值可显著提高 Brock 肺癌风险预测的准确性。
通过使用人工智能模型 Lung Cancer Prediction Convolutional Neural Network（LCP-CNN），可以进一步提高预测准确性，该模型无需进行结节测量。
结节大小和形态是人工智能肺癌风险预测的重要因素，结节纹理和背景实质的作用较小，但可测量。
