Universidad de los Andes, Cra 1 N 18A-12, Bogota, 111711, Colombia.
Med Biol Eng Comput. 2020 Aug;58(8):1803-1815. doi: 10.1007/s11517-020-02197-7. Epub 2020 Jun 5.
Lung cancer is the deadliest cancer worldwide. It has been shown that early detection using low-dose computer tomography (LDCT) scans can reduce deaths caused by this disease. We present a general framework for the detection of lung cancer in chest LDCT images. Our method consists of a nodule detector trained on the LIDC-IDRI dataset followed by a cancer predictor trained on the Kaggle DSB 2017 dataset and evaluated on the IEEE International Symposium on Biomedical Imaging (ISBI) 2018 Lung Nodule Malignancy Prediction test set. Our candidate extraction approach is effective to produce accurate candidates with a recall of 99.6%. In addition, our false positive reduction stage classifies successfully the candidates and increases precision by a factor of 2000. Our cancer predictor obtained a ROC AUC of 0.913 and was ranked 1st place at the ISBI 2018 Lung Nodule Malignancy Prediction challenge. Graphical abstract.
肺癌是全球最致命的癌症。已经证明，使用低剂量计算机断层扫描（LDCT）扫描进行早期检测可以降低这种疾病导致的死亡。我们提出了一种用于胸部 LDCT 图像中肺癌检测的通用框架。我们的方法包括在 LIDC-IDRI 数据集上训练的结节检测器，以及在 Kaggle DSB 2017 数据集上训练的癌症预测器，并在 2018 年 IEEE 国际生物医学成像研讨会（ISBI）的肺结节恶性预测测试集上进行评估。我们的候选物提取方法能够有效地生成召回率为 99.6%的准确候选物。此外，我们的假阳性减少阶段成功地对候选物进行了分类，并将精度提高了 2000 倍。我们的癌症预测器获得了 0.913 的 ROC AUC，并在 2018 年 ISBI 肺结节恶性预测挑战赛中排名第一。
