Department of Applied Bioengineering, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Republic of Korea.
ClariPi Research, Seoul, Republic of Korea.
PLoS One. 2022 Sep 29;17(9):e0275531. doi: 10.1371/journal.pone.0275531. eCollection 2022.
We propose a deep learning-assisted overscan decision algorithm in chest low-dose computed tomography (LDCT) applicable to the lung cancer screening. The algorithm reflects the radiologists' subjective evaluation criteria according to the Korea institute for accreditation of medical imaging (KIAMI) guidelines, where it judges whether a scan range is beyond landmarks' criterion. The algorithm consists of three stages: deep learning-based landmark segmentation, rule-based logical operations, and overscan determination. A total of 210 cases from a single institution (internal data) and 50 cases from 47 institutions (external data) were utilized for performance evaluation. Area under the receiver operating characteristic (AUROC), accuracy, sensitivity, specificity, and Cohen's kappa were used as evaluation metrics. Fisher's exact test was performed to present statistical significance for the overscan detectability, and univariate logistic regression analyses were performed for validation. Furthermore, an excessive effective dose was estimated by employing the amount of overscan and the absorbed dose to effective dose conversion factor. The algorithm presented AUROC values of 0.976 (95% confidence interval [CI]: 0.925-0.987) and 0.997 (95% CI: 0.800-0.999) for internal and external dataset, respectively. All metrics showed average performance scores greater than 90% in each evaluation dataset. The AI-assisted overscan decision and the radiologist's manual evaluation showed a statistically significance showing a p-value less than 0.001 in Fisher's exact test. In the logistic regression analysis, demographics (age and sex), data source, CT vendor, and slice thickness showed no statistical significance on the algorithm (each p-value > 0.05). Furthermore, the estimated excessive effective doses were 0.02 ± 0.01 mSv and 0.03 ± 0.05 mSv for each dataset, not a concern within slight deviations from an acceptable scan range. We hope that our proposed overscan decision algorithm enables the retrospective scan range monitoring in LDCT for lung cancer screening program, and follows an as low as reasonably achievable (ALARA) principle.
我们提出了一种适用于肺癌筛查的深度学习辅助的胸部低剂量 CT（LDCT）过扫决策算法。该算法根据韩国医学影像认证协会（KIAMI）指南反映了放射科医生的主观评估标准，判断扫描范围是否超出了标志点的标准。该算法由三个阶段组成：基于深度学习的标志点分割、基于规则的逻辑运算和过扫判断。利用一个机构的 210 例（内部数据）和 47 个机构的 50 例（外部数据）进行性能评估。接收者操作特征曲线下面积（AUROC）、准确性、敏感度、特异性和 Cohen's kappa 被用作评估指标。Fisher 精确检验用于过扫检测的统计学意义，单变量逻辑回归分析用于验证。此外，通过过扫量和吸收剂量与有效剂量转换系数来估计过量有效剂量。该算法在内部数据集和外部数据集中的 AUROC 值分别为 0.976（95%置信区间[CI]：0.925-0.987）和 0.997（95% CI：0.800-0.999）。在每个评估数据集的所有指标中，表现得分均大于 90%。人工智能辅助的过扫决策和放射科医生的手动评估在 Fisher 精确检验中显示出统计学意义（p 值小于 0.001）。在逻辑回归分析中，年龄、性别、数据来源、CT 供应商和层厚对算法无统计学意义（每个 p 值大于 0.05）。此外，每个数据集的估计过量有效剂量分别为 0.02±0.01 mSv 和 0.03±0.05 mSv，在可接受的扫描范围略有偏差内，这并不令人担忧。我们希望我们提出的过扫决策算法能够实现肺癌筛查 LDCT 的回顾性扫描范围监测，并遵循合理可行的最低（ALARA）原则。
