Pham Tuan D, Ravi Vinayakumar, Luo Bin, Fan Chuanwen, Sun Xiao-Feng
Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar 34754, Saudi Arabia.
Department of Biomedical and Clinical Sciences, Linköping University, 58183 Linköping, Sweden.
Explor Target Antitumor Ther. 2023;4(1):1-16. doi: 10.37349/etat.2023.00119. Epub 2023 Feb 7.
The process of biomarker discovery is being accelerated with the application of artificial intelligence (AI), including machine learning. Biomarkers of diseases are useful because they are indicators of pathogenesis or measures of responses to therapeutic treatments, and therefore, play a key role in new drug development. Proteins are among the candidates for biomarkers of rectal cancer, which need to be explored using state-of-the-art AI to be utilized for prediction, prognosis, and therapeutic treatment. This paper aims to investigate the predictive power of Ras homolog family member B (RhoB) protein in rectal cancer.
This study introduces the integration of pretrained convolutional neural networks and support vector machines (SVMs) for classifying biopsy samples of immunohistochemical expression of protein RhoB in rectal-cancer patients to validate its biologic measure in biopsy. Features of the immunohistochemical expression images were extracted by the pretrained networks and used for binary classification by the SVMs into two groups of less and more than 5-year survival rates.
The fusion of neural search architecture network (NASNet)-Large for deep-layer feature extraction and classifier using SVMs provided the best average classification performance with a total accuracy = 85%, prediction of survival rate of more than 5 years = 90%, and prediction of survival rate of less than 5 years = 75%.
The finding obtained from the use of AI reported in this study suggest that RhoB expression on rectal-cancer biopsy can be potentially used as a biomarker for predicting survival outcomes in rectal-cancer patients, which can be informative for clinical decision making if the patient would be recommended for preoperative therapy.
随着包括机器学习在内的人工智能（AI）的应用，生物标志物发现的进程正在加速。疾病生物标志物很有用，因为它们是发病机制的指标或对治疗反应的衡量标准，因此在新药开发中发挥着关键作用。蛋白质是直肠癌生物标志物的候选者之一，需要使用最先进的人工智能进行探索，以用于预测、预后和治疗。本文旨在研究Ras同源家族成员B（RhoB）蛋白在直肠癌中的预测能力。
本研究引入了预训练卷积神经网络和支持向量机（SVM）的整合，用于对直肠癌患者蛋白质RhoB免疫组化表达的活检样本进行分类，以验证其在活检中的生物学指标。免疫组化表达图像的特征由预训练网络提取，并用于由支持向量机进行二分类，分为生存率大于和小于5年的两组。
用于深层特征提取的神经搜索架构网络（NASNet）-Large与使用支持向量机的分类器相融合，提供了最佳的平均分类性能，总准确率 = 85%，5年以上生存率预测 = 90%，5年以下生存率预测 = 75%。
本研究报告中使用人工智能获得的结果表明，直肠癌活检中的RhoB表达有可能作为预测直肠癌患者生存结果的生物标志物，如果患者被推荐进行术前治疗，这对临床决策可能具有参考价值。
