Value of genomics- and radiomics-based machine learning models in the identification of breast cancer molecular subtypes: a systematic review and meta-analysis

Routine molecular applications and recent advances in breast cancer diagnostics

Cancer stands as one of the most common and lethal diseases, imposing a substantial burden on global mortality rates. Breast cancer is distinct from other forms of cancer in which it is the primary cause of death for women. Early detection of breast cancer can significantly lower the risk of mortality, improving the prognosis for those who are affected. The death rate of breast cancer has been steadily rising, according to epidemiological data, especially since the COVID-19 pandemic. This emphasizes the necessity of sensitive and precise technologies that can be utilized in early breast cancer diagnosis. In this process, biomarkers play a pivotal role by facilitating the early detection and diagnosis of breast cancer. Currently, a wide variety of cancer biomarkers have been identified, improving the accuracy of cancer diagnosis. These biomarkers can be applied in liquid biopsies as well as on solid tissues. In the context of breast cancer, biomarkers are particularly valuable for determining who is predisposed to the disease, predicting prognosis at the time of diagnosis, and selecting the best course of therapy. This review comprehensively explores the recently developed gene-based biomarkers from biofluids that are used in the context of breast cancer, as well as the conventional and cutting-edge techniques that have been employed for breast cancer diagnosis.

Omics Technologies Improving Breast Cancer Research and Diagnostics

Breast cancer (BC) has yielded approximately 2.26 million new cases and has caused nearly 685,000 deaths worldwide in the last two years, making it the most common diagnosed cancer type in the world. BC is an intricate ecosystem formed by both the tumor microenvironment and malignant cells, and its heterogeneity impacts the response to treatment. Biomedical research has entered the era of massive omics data thanks to the high-throughput sequencing revolution, quick progress and widespread adoption. These technologies-liquid biopsy, transcriptomics, epigenomics, proteomics, metabolomics, pharmaco-omics and artificial intelligence imaging-could help researchers and clinicians to better understand the formation and evolution of BC. This review focuses on the findings of recent multi-omics-based research that has been applied to BC research, with an introduction to every omics technique and their applications for the different BC phenotypes, biomarkers, target therapies, diagnosis, treatment and prognosis, to provide a comprehensive overview of the possibilities of BC research.

Characterization of Breast Tumors from MR Images Using Radiomics and Machine Learning Approaches

Determining histological subtypes, such as invasive ductal and invasive lobular carcinomas (IDCs and ILCs) and immunohistochemical markers, such as estrogen response (ER), progesterone response (PR), and the HER2 protein status is important in planning breast cancer treatment. MRI-based radiomic analysis is emerging as a non-invasive substitute for biopsy to determine these signatures. We explore the effectiveness of radiomics-based and CNN (convolutional neural network)-based classification models to this end. T1-weighted dynamic contrast-enhanced, contrast-subtracted T1, and T2-weighted MR images of 429 breast cancer tumors from 323 patients are used. Various combinations of input data and classification schemes are applied for ER⁺ vs. ER^-, PR⁺ vs. PR^-, HER2⁺ vs. HER2^-, and IDC vs. ILC classification tasks. The best results were obtained for the ER⁺ vs. ER^- and IDC vs. ILC classification tasks, with their respective AUCs reaching 0.78 and 0.73 on test data. The results with multi-contrast input data were generally better than the mono-contrast alone. The radiomics and CNN-based approaches generally exhibited comparable results. ER and IDC/ILC classification results were promising. PR and HER2 classifications need further investigation through a larger dataset. Better results by using multi-contrast data might indicate that multi-parametric quantitative MRI could be used to achieve more reliable classifiers.