Breast cancer is the most commonly diagnosed cancer type worldwide. Overexpression of human epidermal growth factor receptor 2 (HER2) is an important subtype of breast cancer and results in an increased risk of recurrence and metastasis in patients. At present, immunohistochemistry (IHC) is used to detect the expression of HER2 in breast cancer tissues as the golden standard. However, IHC has some shortcomings, such as large subjective impact, long time consumption, expensive reagents, etc. In this paper, a combined morphological and spectroscopic diagnostic method based on label-free surface-enhanced Raman scattering (SERS) for HER2 expression in breast cancer is proposed. It can not only quantitively detect HER2 expression in breast cancer tissues by spectroscopic measurements but also give morphological images reflecting the distribution of HER2 in tissues. The results show that the consistency between this method and IHC is 95% and achieves the annotation of tumor regions on tissue sections. This method is time-consuming, quantifiable, intuitive, scalable, and easy to understand. Combined with deep learning approaches, it is expected to promote the development of clinical detection and diagnosis technology for breast cancer and other cancers.

No abstract

The outbreak of COVID-19 has spread worldwide, causing great damage to the global economy. Raman spectroscopy is expected to become a rapid and accurate method for the detection of coronavirus. A classification method of coronavirus spike proteins by Raman spectroscopy based on deep learning was implemented. A Raman spectra dataset of the spike proteins of five coronaviruses (including MERS-CoV, SARS-CoV, SARS-CoV-2, HCoVHKU1, and HCoV-OC43) was generated to establish the neural network model for classification. Even for rapidly acquired spectra with a low signal-to-noise ratio, the average accuracy exceeded 97%. An interpretive analysis of the classification results of the neural network was performed, which indicated that the differences in spectral characteristics captured by the neural network were consistent with the experimental analysis. The interpretative analysis method provided a valuable reference for identifying complex Raman spectra using deep-learning techniques. Our approach exhibited the potential to be applied in clinical practice to identify COVID-19 and other coronaviruses, and it can also be applied to other identification problems such as the identification of viruses or chemical agents, as well as in industrial areas such as oil and gas exploration.