Diagnosis of normal and malignant human gastric tissue samples by FTIR spectra combined with mathematical models

Rapid diagnosis of celiac disease based on plasma Raman spectroscopy combined with deep learning

Celiac Disease (CD) is a primary malabsorption syndrome resulting from the interplay of genetic, immune, and dietary factors. CD negatively impacts daily activities and may lead to conditions such as osteoporosis, malignancies in the small intestine, ulcerative jejunitis, and enteritis, ultimately causing severe malnutrition. Therefore, an effective and rapid differentiation between healthy individuals and those with celiac disease is crucial for early diagnosis and treatment. This study utilizes Raman spectroscopy combined with deep learning models to achieve a non-invasive, rapid, and accurate diagnostic method for celiac disease and healthy controls. A total of 59 plasma samples, comprising 29 celiac disease cases and 30 healthy controls, were collected for experimental purposes. Convolutional Neural Network (CNN), Multi-Scale Convolutional Neural Network (MCNN), Residual Network (ResNet), and Deep Residual Shrinkage Network (DRSN) classification models were employed. The accuracy rates for these models were found to be 86.67%, 90.76%, 86.67% and 95.00%, respectively. Comparative validation results revealed that the DRSN model exhibited the best performance, with an AUC value and accuracy of 97.60% and 95%, respectively. This confirms the superiority of Raman spectroscopy combined with deep learning in the diagnosis of celiac disease.

Differentiation of Salivary Gland and Salivary Gland Tumor Tissue via Raman Imaging Combined with Multivariate Data Analysis

Salivary gland tumors (SGTs) are a relevant, highly diverse subgroup of head and neck tumors whose entity determination can be difficult. Confocal Raman imaging in combination with multivariate data analysis may possibly support their correct classification. For the analysis of the translational potential of Raman imaging in SGT determination, a multi-stage evaluation process is necessary. By measuring a sample set of Warthin tumor, pleomorphic adenoma and non-tumor salivary gland tissue, Raman data were obtained and a thorough Raman band analysis was performed. This evaluation revealed highly overlapping Raman patterns with only minor spectral differences. Consequently, a principal component analysis (PCA) was calculated and further combined with a discriminant analysis (DA) to enable the best possible distinction. The PCA-DA model was characterized by accuracy, sensitivity, selectivity and precision values above 90% and validated by predicting model-unknown Raman spectra, of which 93% were classified correctly. Thus, we state our PCA-DA to be suitable for parotid tumor and non-salivary salivary gland tissue discrimination and prediction. For evaluation of the translational potential, further validation steps are necessary.

The Convergence of FTIR and EVs: Emergence Strategy for Non-Invasive Cancer Markers Discovery

In conjunction with imaging analysis, pathology-based assessments of biopsied tissue are the gold standard for diagnosing solid tumors. However, the disadvantages of tissue biopsies, such as being invasive, time-consuming, and labor-intensive, have urged the development of an alternate method, liquid biopsy, that involves sampling and clinical assessment of various bodily fluids for cancer diagnosis. Meanwhile, extracellular vesicles (EVs) are circulating biomarkers that carry molecular profiles of their cell or tissue origins and have emerged as one of the most promising biomarkers for cancer. Owing to the biological information that can be obtained through EVs' membrane surface markers and their cargo loaded with biomolecules such as nucleic acids, proteins, and lipids, EVs have become useful in cancer diagnosis and therapeutic applications. Fourier-transform infrared spectroscopy (FTIR) allows rapid, non-destructive, label-free molecular profiling of EVs with minimal sample preparation. Since the heterogeneity of EV subpopulations may result in complicated FTIR spectra that are highly diverse, computational-assisted FTIR spectroscopy is employed in many studies to provide fingerprint spectra of malignant and non-malignant samples, allowing classification with high accuracy, specificity, and sensitivity. In view of this, FTIR-EV approach carries a great potential in cancer detection. The progression of FTIR-based biomarker identification in EV research, the rationale of the integration of a computationally assisted approach, along with the challenges of clinical translation are the focus of this review.

Identification of hepatocellular carcinoma and paracancerous tissue based on the peak area in FTIR microspectroscopy

Hepatocellular carcinoma (HCC) is one of the most common primary hepatic malignancies across the world. The annual incidence and death rates have increased at the highest rate of all cancers in recent years. Surgical resection is a potentially curative option for solitary HCC or unilobar disease without evidence of metastases or vascular invasion. This study focuses on the molecular differences between the HCC foci and paracancerous tissues and provides some valuable biomarkers based on the vibrational spectrum. Fourier transform infrared (FTIR) spectroscopy is a non-invasive and qualitative and semi-quantitative analysis technique that has been widely applied for the identification of macromolecular changes in biological tissues. In this study, the FTIR spectra of the HCC foci and the paracancerous tissues were recorded separately, and ten areas under the absorption peaks of all the specimens were calculated. The result demonstrates that the areas of protein-related absorption peaks at 1398 cm^-1, 1548 cm^-1, 1654 cm^-1 and 3070 cm^-1 may be the key indicators of the two different regions. After coupling with the classification algorithms of k-nearest neighbor (KNN), random forest (RF) and support vector machine (SVM), it was found that SVM with an RBF kernel performed best with the AUC (area under the ROC curve) reaching 0.997, and the performance was better than the feature based on the full spectrum. This reveals that the peak area-based FTIR spectra combined with the SVM algorithm may be a promising tool in identifying the HCC foci and the paracancerous tissues.

FTIR microspectroscopic study of biomacromolecular changes in As2O3 induced MGC803 cells apoptosis

It is well-known that As₂O₃ has significant anticancer effects, however, little is known regarding its mechanism for treating gastric cancer. Thus, we investigated biomacromolecular (DNA, proteins and lipids) changes of human gastric cancer cell line MGC803 to further understand As₂O₃-induced apoptosis. Conventional methods showed the increase of the apoptosis rate, the decrease of mitochondrial membrane potential (MMP), the accumulation of reactive oxygen species (ROS) and the changes of apoptotic proteins, etc. Fourier transform infrared (FTIR) microspectroscopy sensitively recognized overall biomacromolecular changes caused by the above: Peak-area ratios indicated the content/structure changes in DNA, proteins and lipids. Principle component analysis (PCA) revealed significant changes in intracellular DNA concentration and structure. This study suggests that As₂O₃ may exert anti-gastric cancer effect by altering intracellular biomacromolecules especially DNA.