Zhao Wei, Sun Yingli, Kuang Kaiming, Yang Jiancheng, Li Ge, Ni Bingbing, Jiang Yingjia, Jiang Bo, Liu Jun, Li Ming
Department of Radiology, The Second Xiangya Hospital, Central South University, Changsha 410011, China.
Department of Radiology, Huadong Hospital, Fudan University, Shanghai 200040, China.
Cancers (Basel). 2022 Jul 28;14(15):3675. doi: 10.3390/cancers14153675.
To investigate the value of the deep learning method in predicting the invasiveness of early lung adenocarcinoma based on irregularly sampled follow-up computed tomography (CT) scans. In total, 351 nodules were enrolled in the study. A new deep learning network based on temporal attention, named Visual Simple Temporal Attention (ViSTA), was proposed to process irregularly sampled follow-up CT scans. We conducted substantial experiments to investigate the supplemental value in predicting the invasiveness using serial CTs. A test set composed of 69 lung nodules was reviewed by three radiologists. The performance of the model and radiologists were compared and analyzed. We also performed a visual investigation to explore the inherent growth pattern of the early adenocarcinomas. Among counterpart models, ViSTA showed the best performance (AUC: 86.4% vs. 60.6%, 75.9%, 66.9%, 73.9%, 76.5%, 78.3%). ViSTA also outperformed the model based on Volume Doubling Time (AUC: 60.6%). ViSTA scored higher than two junior radiologists (accuracy of 81.2% vs. 75.4% and 71.0%) and came close to the senior radiologist (85.5%). Our proposed model using irregularly sampled follow-up CT scans achieved promising accuracy in evaluating the invasiveness of the early stage lung adenocarcinoma. Its performance is comparable with senior experts and better than junior experts and traditional deep learning models. With further validation, it can potentially be applied in clinical practice.
探讨深度学习方法在基于不规则采样的随访计算机断层扫描（CT）预测早期肺腺癌侵袭性方面的价值。本研究共纳入351个结节。提出了一种基于时间注意力的新型深度学习网络，称为视觉简单时间注意力（ViSTA），用于处理不规则采样的随访CT扫描。我们进行了大量实验，以研究使用系列CT预测侵袭性的补充价值。由69个肺结节组成的测试集由三名放射科医生进行评估。对模型和放射科医生的表现进行了比较和分析。我们还进行了视觉研究，以探索早期腺癌的内在生长模式。在同类模型中，ViSTA表现最佳（AUC：86.4%，而其他模型分别为60.6%、75.9%、66.9%、73.9%、76.5%、78.3%）。ViSTA也优于基于体积倍增时间的模型（AUC：60.6%）。ViSTA的得分高于两名初级放射科医生（准确率分别为81.2%，而初级放射科医生为75.4%和71.0%），并接近高级放射科医生（85.5%）。我们提出的使用不规则采样随访CT扫描的模型在评估早期肺腺癌侵袭性方面取得了有前景的准确率。其表现与高级专家相当，优于初级专家和传统深度学习模型。经过进一步验证，它有可能应用于临床实践。
