Committee on Medical Physics, Department of Radiology, The University of Chicago, 5841 S Maryland Avenue, MC2026, Chicago, 60637, USA.
Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, 10029, USA.
Sci Rep. 2023 Jan 21;13(1):1187. doi: 10.1038/s41598-023-27549-9.
In addition to lung cancer, other thoracic abnormalities, such as emphysema, can be visualized within low-dose CT scans that were initially obtained in cancer screening programs, and thus, opportunistic evaluation of these diseases may be highly valuable. However, manual assessment for each scan is tedious and often subjective, thus we have developed an automatic, rapid computer-aided diagnosis system for emphysema using attention-based multiple instance deep learning and 865 LDCTs. In the task of determining if a CT scan presented with emphysema or not, our novel Transfer AMIL approach yielded an area under the ROC curve of 0.94 ± 0.04, which was a statistically significant improvement compared to other methods evaluated in our study following the Delong Test with correction for multiple comparisons. Further, from our novel attention weight curves, we found that the upper lung demonstrated a stronger influence in all scan classes, indicating that the model prioritized upper lobe information. Overall, our novel Transfer AMIL method yielded high performance and provided interpretable information by identifying slices that were most influential to the classification decision, thus demonstrating strong potential for clinical implementation.
除了肺癌，在最初用于癌症筛查计划的低剂量 CT 扫描中，还可以观察到其他胸部异常，如肺气肿。因此，对这些疾病进行机会性评估可能具有很高的价值。然而，对每个扫描进行手动评估既繁琐又主观，因此我们已经开发了一种使用基于注意力的多实例深度学习和 865 个 LDCT 的肺气肿自动快速计算机辅助诊断系统。在确定 CT 扫描是否存在肺气肿的任务中，我们的新型 Transfer AMIL 方法在 ROC 曲线下的面积为 0.94 ± 0.04，与我们在研究中使用 Delong 测试校正多重比较评估的其他方法相比，这是一个具有统计学意义的改进。此外，从我们的新型注意力权重曲线中，我们发现上肺在所有扫描类别中都表现出更强的影响，这表明该模型优先考虑上叶信息。总体而言，我们的新型 Transfer AMIL 方法具有出色的性能，并通过识别对分类决策最有影响的切片来提供可解释的信息，因此具有很强的临床应用潜力。
