Artificial image objects for classification of breast cancer biomarkers with transcriptome sequencing data and convolutional neural network algorithms

• Published in: Breast cancer research : BCR 2021-10, Vol.23 (1), p.96-96, Article 96
• Main Authors: Chen, Xiangning, Chen, Daniel G, Zhao, Zhongming, Balko, Justin M, Chen, Jingchun
• Format: Article
• Language: English
• Subjects: Algorithms; Antibodies; Artificial image object; Artificial intelligence; Automation; Biological markers; Biomarkers; Biomarkers, Tumor - genetics; Breast cancer; Breast cancer biomarker classification; Breast Neoplasms - diagnosis; Breast Neoplasms - genetics; Breast Neoplasms - pathology; Cable television broadcasting industry; Cancer therapies; Classification; Convolutional neural network; Data mining; Databases, Genetic; Datasets; Female; Gene expression; Genomics; Humans; Image Interpretation, Computer-Assisted; Ki-67 Antigen - genetics; Machine learning; Machine learning algorithm; Medical imaging equipment; Medical prognosis; Medical research; Medicine, Experimental; Neural networks; Neural Networks, Computer; Performance evaluation; Reproducibility of Results; Ribonucleic acid; RNA; RNA sequencing; Survival; Survival Analysis; Transcriptome; Transcriptomes
• ISSN: 1465-542X; 1465-5411; 1465-542X
• DOI: 10.1186/s13058-021-01474-z

Transcriptome sequencing has been broadly available in clinical studies. However, it remains a challenge to utilize these data effectively for clinical applications due to the high dimension of the data and the highly correlated expression between individual genes. We proposed a method to transform RNA sequencing data into artificial image objects (AIOs) and applied convolutional neural network (CNN) algorithms to classify these AIOs. With the AIO technique, we considered each gene as a pixel in an image and its expression level as pixel intensity. Using the GSE96058 (n = 2976), GSE81538 (n = 405), and GSE163882 (n = 222) datasets, we created AIOs for the subjects and designed CNN models to classify biomarker Ki67 and Nottingham histologic grade (NHG). With fivefold cross-validation, we accomplished a classification accuracy and AUC of 0.821 ± 0.023 and 0.891 ± 0.021 for Ki67 status. For NHG, the weighted average of categorical accuracy was 0.820 ± 0.012, and the weighted average of AUC was 0.931 ± 0.006. With GSE96058 as training data and GSE81538 as testing data, the accuracy and AUC for Ki67 were 0.826 ± 0.037 and 0.883 ± 0.016, and that for NHG were 0.764 ± 0.052 and 0.882 ± 0.012, respectively. These results were 10% better than the results reported in the original studies. For Ki67, the calls generated from our models had a better power for prediction of survival as compared to the calls from trained pathologists in survival analyses. We demonstrated that RNA sequencing data could be transformed into AIOs and be used to classify Ki67 status and NHG with CNN algorithms. The AIO method could handle high-dimensional data with highly correlated variables, and there was no need for variable selection. With the AIO technique, a data-driven, consistent, and automation-ready model could be developed to classify biomarkers with RNA sequencing data and provide more efficient care for cancer patients.