Department of Scientific Research, The People's Hospital of Yubei District of Chongqing city, Chongqing, 401120, China.
School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.
J Cancer Res Clin Oncol. 2024 Oct 3;150(10):443. doi: 10.1007/s00432-024-05977-y.
Liver cancer is a significant cause of cancer-related mortality worldwide and requires tailored treatment strategies for different types. However, preoperative accurate diagnosis of the type presents a challenge. This study aims to develop an automatic diagnostic model based on multi-phase contrast-enhanced CT (CECT) images to distinguish between hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and normal individuals.
We designed a Hierarchical Long Short-Term Memory (H-LSTM) model, whose core components consist of a shared image feature extractor across phases, an internal LSTM for each phase, and an external LSTM across phases. The internal LSTM aggregates features from different layers of 2D CECT images, while the external LSTM aggregates features across different phases. H-LSTM can handle incomplete phases and varying numbers of CECT image layers, making it suitable for real-world decision support scenarios. Additionally, we applied phase augmentation techniques to process multi-phase CECT images, improving the model's robustness.
The H-LSTM model achieved an overall average AUROC of 0.93 (0.90, 1.00) on the test dataset, with AUROC for HCC classification reaching 0.97 (0.93, 1.00) and for ICC classification reaching 0.90 (0.78, 1.00). Comprehensive validation in scenarios with incomplete phases was performed, with the H-LSTM model consistently achieving AUROC values over 0.9.
The proposed H-LSTM model can be employed for classification tasks involving incomplete phases of CECT images in real-world scenarios, demonstrating high performance. This highlights the potential of AI-assisted systems in achieving accurate diagnosis and treatment of liver cancer. H-LSTM offers an effective solution for processing multi-phase data and provides practical value for clinical diagnostics.
肝癌是全球癌症相关死亡的重要原因，需要针对不同类型制定针对性的治疗策略。然而，术前准确诊断类型是一个挑战。本研究旨在开发一种基于多期增强 CT（CECT）图像的自动诊断模型，以区分肝细胞癌（HCC）、肝内胆管癌（ICC）和正常个体。
我们设计了一种分层长短期记忆（H-LSTM）模型，其核心组件包括跨期共享图像特征提取器、每个期的内部 LSTM 和跨期的外部 LSTM。内部 LSTM 聚合来自 2D CECT 图像不同层的特征，而外部 LSTM 聚合来自不同期的特征。H-LSTM 可以处理不完整的期和不同数量的 CECT 图像层，使其适用于现实世界的决策支持场景。此外，我们应用了相位增强技术来处理多期 CECT 图像，提高了模型的鲁棒性。
H-LSTM 模型在测试数据集上的总体平均 AUROC 为 0.93（0.90，1.00），HCC 分类的 AUROC 达到 0.97（0.93，1.00），ICC 分类的 AUROC 达到 0.90（0.78，1.00）。在不完整相位的场景中进行了全面验证，H-LSTM 模型始终达到超过 0.9 的 AUROC 值。
所提出的 H-LSTM 模型可用于处理现实场景中 CECT 图像不完整相位的分类任务，表现出高性能。这突出了人工智能辅助系统在实现肝癌准确诊断和治疗方面的潜力。H-LSTM 为处理多期数据提供了有效的解决方案，为临床诊断提供了实用价值。
