Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, People's Republic of China.
Department of Radiology, The First Affiliated Hospital of Army Military Medical University, Chongqing, 400038, People's Republic of China.
Eur Radiol. 2023 Dec;33(12):8879-8888. doi: 10.1007/s00330-023-09857-w. Epub 2023 Jul 1.
To develop a deep learning (DL) method that can determine the Liver Imaging Reporting and Data System (LI-RADS) grading of high-risk liver lesions and distinguish hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT.
This retrospective study included 1049 patients with 1082 lesions from two independent hospitals that were pathologically confirmed as HCC or non-HCC. All patients underwent a four-phase CT imaging protocol. All lesions were graded (LR 4/5/M) by radiologists and divided into an internal (n = 886) and external cohort (n = 196) based on the examination date. In the internal cohort, Swin-Transformer based on different CT protocols were trained and tested for their ability to LI-RADS grading and distinguish HCC from non-HCC, and then validated in the external cohort. We further developed a combined model with the optimal protocol and clinical information for distinguishing HCC from non-HCC.
In the test and external validation cohorts, the three-phase protocol without pre-contrast showed κ values of 0.6094 and 0.4845 for LI-RADS grading, and its accuracy was 0.8371 and 0.8061, while the accuracy of the radiologist was 0.8596 and 0.8622, respectively. The AUCs in distinguishing HCC from non-HCC were 0.865 and 0.715 in the test and external validation cohorts, while those of the combined model were 0.887 and 0.808.
The Swin-Transformer based on three-phase CT protocol without pre-contrast could feasibly simplify LI-RADS grading and distinguish HCC from non-HCC. Furthermore, the DL model have the potential in accurately distinguishing HCC from non-HCC using imaging and highly characteristic clinical data as inputs.
The application of deep learning model for multiphase CT has proven to improve the clinical applicability of the Liver Imaging Reporting and Data System and provide support to optimize the management of patients with liver diseases.
• Deep learning (DL) simplifies LI-RADS grading and helps distinguish hepatocellular carcinoma (HCC) from non-HCC. • The Swin-Transformer based on the three-phase CT protocol without pre-contrast outperformed other CT protocols. • The Swin-Transformer provide help in distinguishing HCC from non-HCC by using CT and characteristic clinical information as inputs.
开发一种深度学习（DL）方法，能够根据多期 CT 确定高危肝脏病变的 Liver Imaging Reporting and Data System（LI-RADS）分级，并区分肝细胞癌（HCC）与非 HCC。
这项回顾性研究纳入了来自两家独立医院的 1049 名患者的 1082 个病灶，这些病灶均经病理证实为 HCC 或非 HCC。所有患者均行四期 CT 成像方案检查。由放射科医生对所有病灶进行分级（LR 4/5/M），并根据检查日期将其分为内部队列（n=886）和外部队列（n=196）。在内部队列中，基于不同 CT 方案的 Swin-Transformer 进行训练和测试，以评估其对 LI-RADS 分级和区分 HCC 与非 HCC 的能力，并在外部队列中进行验证。我们进一步开发了一种结合最佳方案和临床信息的联合模型，用于区分 HCC 与非 HCC。
在测试和外部验证队列中，不包括平扫的三期方案的 κ 值分别为 0.6094 和 0.4845，其准确性分别为 0.8371 和 0.8061，而放射科医生的准确性分别为 0.8596 和 0.8622。在测试和外部验证队列中，区分 HCC 与非 HCC 的 AUC 分别为 0.865 和 0.715，而联合模型的 AUC 分别为 0.887 和 0.808。
基于不包括平扫的三期 CT 方案的 Swin-Transformer 可简化 LI-RADS 分级并区分 HCC 与非 HCC。此外，该深度学习模型具有使用影像学和高度特征性临床数据作为输入来准确区分 HCC 与非 HCC 的潜力。
深度学习模型在多期 CT 中的应用已被证明可提高 Liver Imaging Reporting and Data System 的临床适用性，并为优化肝病患者的管理提供支持。
•深度学习（DL）简化了 LI-RADS 分级并有助于区分肝细胞癌（HCC）与非 HCC。•基于不包括平扫的三期 CT 方案的 Swin-Transformer 优于其他 CT 方案。•Swin-Transformer 通过将 CT 和特征性临床信息作为输入来帮助区分 HCC 与非 HCC。
