Saad Maliazurina, He Shenghua, Thorstad Wade, Gay Hiram, Barnett Daniel, Zhao Yujie, Ruan Su, Wang Xiaowei, Li Hua
Department of Bioengineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA. She is now with the MD Anderson Cancer Center, Houston, TX, USA.
Department of Computer Science and Engineering, Washington University, Saint louis, MO, USA.
IEEE Trans Radiat Plasma Med Sci. 2022 Feb;6(2):231-244. doi: 10.1109/trpms.2021.3104297. Epub 2021 Aug 12.
Predicting early in treatment whether a tumor is likely to be responsive is a difficult yet important task to support clinical decision-making. Studies have shown that multimodal biomarkers could provide complementary information and lead to more accurate treatment outcome prognosis than unimodal biomarkers. However, the prognosis accuracy could be affected by multimodal data heterogeneity and incompleteness. The small-sized and imbalance datasets also bring additional challenges for training a designed prognosis model. In this study, a modular framework employing multimodal biomarkers for cancer treatment outcome prediction was proposed. It includes four modules of synthetic data generation, deep feature extraction, multimodal feature fusion, and classification to address the challenges described above. The feasibility and advantages of the designed framework were demonstrated through an example study, in which the goal was to stratify oropharyngeal squamous cell carcinoma (OPSCC) patients with low- and high-risks of treatment failures by use of positron emission tomography (PET) image data and microRNA (miRNA) biomarkers. The superior prognosis performance and the comparison with other methods demonstrated the efficiency of the proposed framework and its ability of enabling seamless integration, validation and comparison of various algorithms in each module of the framework. The limitation and future work was discussed as well.
在治疗早期预测肿瘤是否可能产生反应是一项艰巨但重要的任务，有助于支持临床决策。研究表明，多模态生物标志物可以提供补充信息，并且比单模态生物标志物能更准确地预测治疗结果。然而，预后准确性可能会受到多模态数据的异质性和不完整性的影响。小规模和不平衡的数据集也给训练设计好的预后模型带来了额外的挑战。在本研究中，提出了一个使用多模态生物标志物进行癌症治疗结果预测的模块化框架。它包括合成数据生成、深度特征提取、多模态特征融合和分类四个模块，以应对上述挑战。通过一个实例研究证明了所设计框架的可行性和优势，该实例研究的目标是利用正电子发射断层扫描（PET）图像数据和微小RNA（miRNA）生物标志物对治疗失败风险低和高的口咽鳞状细胞癌（OPSCC）患者进行分层。优越的预后性能以及与其他方法的比较证明了所提出框架的有效性，以及它能够在框架的每个模块中实现各种算法的无缝集成、验证和比较。同时也讨论了该研究的局限性和未来工作。
