Rapid, label-free histopathological diagnosis of liver cancer based on Raman spectroscopy and deep learning

Abstract

Biopsy is the recommended standard for pathological diagnosis of liver carcinoma. However, this method usually requires sectioning and staining, and well-trained pathologists to interpret tissue images. Here, we utilize Raman spectroscopy to study human hepatic tissue samples, developing and validating a workflow for in vitro and intraoperative pathological diagnosis of liver cancer. We distinguish carcinoma tissues from adjacent non-tumour tissues in a rapid, non-disruptive, and label-free manner by using Raman spectroscopy combined with deep learning, which is validated by tissue metabolomics. This technique allows for detailed pathological identification of the cancer tissues, including subtype, differentiation grade, and tumour stage. 2D/3D Raman images of unprocessed human tissue slices with submicrometric resolution are also acquired based on visualization of molecular composition, which could assist in tumour boundary recognition and clinicopathologic diagnosis. Lastly, the potential for a portable handheld Raman system is illustrated during surgery for real-time intraoperative human liver cancer diagnosis.

Raman spectroscopy in chronic heart failure diagnosis based on human skin analysis

“…These data have not been considered in the present study and potentially can influence the obtained results, thus, more studies combining optical analysis and chemical evaluation of skin tissues are required in the future. In addition, implementation of neural network classifiers for spectral data analysis can contribute to a more accurate performance of optical analysis [5,[49][50][51][52][53][54][55]. Nevertheless, the achieved performance of the proposed approach is sufficient for clinical setting, which makes it a potential basis for monitoring the health status of patients with CHF disease.…”

Bioinspired porous three-coordinated single-atom Fe nanozyme with oxidase-like activity for tumor visual identification via glutathione

“…Analysis of the tumor area in clinical practice enables the identifications of the boundary between tumor and normal tissue and the site of surgical resection 51 . The tumor microenvironment usually expresses an excess of GSH in comparison with the health counterparts.…”

Small molecule metabolites: discovery of biomarkers and therapeutic targets

“… 13 – 16 Discovery and identification of small molecule metabolites or metabolic pathway alterations is useful for understanding the pathophysiology of diseases, and help identify therapeutic targets. 17 – 27 Metabolome represent the upstream input from environment and downstream output of genome, the collection of bioactive small molecule metabolites including nucleotides, carbohydrates, amino acid, and fatty acid, has used for discovery of early prediction and diagnosis biomarkers of diseases that insight into the best use of interventions. 28 – 35 Endogenous metabolites could provide unique metabolic insights into the mechanistic basis and therapeutic targets of disease and also leads to personalized metabolic phenotype.…”