Development and comparative assessment of Raman spectroscopic classification algorithms for lesion discrimination in stereotactic breast biopsies with microcalcifications

Physicochemical understanding of biomineralization by molecular vibrational spectroscopy: From mechanism to nature

The process and mechanism of biomineralization and relevant physicochemical properties of mineral crystals are remarkably sophisticated multidisciplinary fields that include biology, chemistry, physics, and materials science. The components of the organic matter, structural construction of minerals, and related mechanical interaction, etc., could help to reveal the unique nature of the special mineralization process. Herein, the paper provides an overview of the biomineralization process from the perspective of molecular vibrational spectroscopy, including the physicochemical properties of biomineralized tissues, from physiological to applied mineralization. These physicochemical characteristics closely to the hierarchical mineralization process include biological crystal defects, chemical bonding, atomic doping, structural changes, and content changes in organic matter, along with the interface between biocrystals and organic matter as well as the specific mechanical effects for hardness and toughness. Based on those observations, the special physiological properties of mineralization for enamel and bone, as well as the possible mechanism of pathological mineralization and calcification such as atherosclerosis, tumor micro mineralization, and urolithiasis are also reviewed and discussed. Indeed, the clearly defined physicochemical properties of mineral crystals could pave the way for studies on the mechanisms and applications.

Artificial intelligence-aided rapid and accurate identification of clinical fungal infections by single-cell Raman spectroscopy

Integrating artificial intelligence and new diagnostic platforms into routine clinical microbiology laboratory procedures has grown increasingly intriguing, holding promises of reducing turnaround time and cost and maximizing efficiency. At least one billion people are suffering from fungal infections, leading to over 1.6 million mortality every year. Despite the increasing demand for fungal diagnosis, current approaches suffer from manual bias, long cultivation time (from days to months), and low sensitivity (only 50% produce positive fungal cultures). Delayed and inaccurate treatments consequently lead to higher hospital costs, mobility and mortality rates. Here, we developed single-cell Raman spectroscopy and artificial intelligence to achieve rapid identification of infectious fungi. The classification between fungi and bacteria infections was initially achieved with 100% sensitivity and specificity using single-cell Raman spectra (SCRS). Then, we constructed a Raman dataset from clinical fungal isolates obtained from 94 patients, consisting of 115,129 SCRS. By training a classification model with an optimized clinical feedback loop, just 5 cells per patient (acquisition time 2 s per cell) made the most accurate classification. This protocol has achieved 100% accuracies for fungal identification at the species level. This protocol was transformed to assessing clinical samples of urinary tract infection, obtaining the correct diagnosis from raw sample-to-result within 1 h.

Combining derivative Raman with autofluorescence to improve the diagnosis performance of echinococcosis

Echinococcosis is a zoonotic parasitic disease transmitted by animals and distributed all over the world. There is no standardized and widely accepted treatment method, and early and accurate diagnosis is crucial for the prevention and cure of echinococcosis. Here, we explored the feasibility of using derivative Raman in combination with autofluorescence (AF) to improve the diagnosis performance of echinococcosis. The spectra of serum samples from patients with echinococcosis, as well as healthy volunteers, were recorded at 633 nm excitation. The normalized mean Raman spectra showed that there is a decrease in the relative amounts of β carotene and phenylalanine and an increase in the percentage of tryptophan, tyrosine, and glutamic acid contents in the serum of echinococcosis patients as compared to that of healthy subjects. Then, principal components analysis (PCA), combined with linear discriminant analysis (LDA), were adopted to distinguish echinococcosis patients from healthy volunteers. Based on the area under the ROC curve (AUC) value, the derivative Raman + AF spectral data set achieved the optimal results. The AUC value was improved by 0.08 for derivative Raman + AF (AUC = 0.98), compared to Raman alone. The results demonstrated that the fusion of derivative Raman and AF could effectively improve the performance of the diagnostic model, and this technique has great application potential in the clinical screening of echinococcosis.

Rapid identification of cervical adenocarcinoma and cervical squamous cell carcinoma tissue based on Raman spectroscopy combined with multiple machine learning algorithms

Cervical cancer has a long latency, and early screening greatly reduces mortality. In this study, cervical adenocarcinoma and cervical squamous cell carcinoma tissue data were collected by Raman spectroscopy, and then, the adaptive iteratively reweighted penalized least squares (airPLS) algorithm and Vancouver Raman algorithm (VRA) were used to subtract the background of the collected data. The following five feature extraction algorithms were applied: partial least squares (PLS), principal component analysis (PCA), kernel principal component analysis (KPCA), isometric feature mapping (isomap) and locally linear embedding (LLE). The k-nearest neighbour (KNN), extreme learning machine (ELM), decision tree (DT), backpropagation neural network (BP), genetic optimization backpropagation neural network (GA-BP) and linear discriminant analysis (LDA) classification models were then established through the features extracted by different feature extraction algorithms. In total, 30 types of classification models were established in this experiment. This research includes eight good models, airPLS-PLS-KNN, airPLS-PLS-ELM, airPLS-PLS-GA-BP, airPLS-PLS-BP, airPLS-PLS-LDA, airPLS-PCA-KNN, airPLS-PCA-LDA, and VRA-PLS-KNN, whose diagnostic accuracy was 96.3 %, 95.56 %, 95.06 %, 94.07 %, 92.59 %, 85.19 %, 85.19 % and 85.19 %, respectively. The experimental results showed that the model established in this article is simple to operate and highly accurate and has a good reference value for the rapid screening of cervical cancer.

Raman spectroscopy as a non-invasive diagnostic technique for endometriosis

Endometriosis is a condition in which the endometrium, the layer of tissue that usually covers the inside of the uterus, grows outside the uterus. One of its severe effects is sub-fertility. The exact reason for endometriosis is still unknown and under investigation. Tracking the symptoms is not sufficient for diagnosing the disease. A successful diagnosis can only be made using laparoscopy. During the disease, the amount of some molecules (i.e., proteins, antigens) changes in the blood. Raman spectroscopy provides information about biochemicals without using dyes or external labels. In this study, Raman spectroscopy is used as a non-invasive diagnostic method for endometriosis. The Raman spectra of 94 serum samples acquired from 49 patients and 45 healthy individuals were compared for this study. Principal Component Analysis (PCA), k- Nearest Neighbors (kNN), and Support Vector Machines (SVM) were used in the analysis. According to the results (using 80 measurements for training and 14 measurements for the test set), it was found that kNN-weighted gave the best classification model with sensitivity and specificity values of 80.5% and 89.7%, respectively. Testing the model with unseen data yielded a sensitivity value of 100% and a specificity value of 100%. To the best of our knowledge, this is the first study in which Raman spectroscopy was used in combination with PCA and classification algorithms as a non-invasive method applied on blood sera for the diagnosis of endometriosis.

Rapid and non-invasive screening of high renin hypertension using Raman spectroscopy and different classification algorithms

This study presents a rapid and non-invasive method to screen high renin hypertension using serum Raman spectroscopy combined with different classification algorithms. The serum samples taken from 24 high renin hypertension patients and 22 non-high renin hypertension samples were measured in this experiment. Tentative assignments of the Raman peaks in the measured serum spectra suggested specific biomolecular changes between the groups. Principal component analysis (PCA) was first used for feature extraction and reduced the dimension of high-dimension spectral data. Then, support vector machine (SVM), linear discriminant analysis (LDA) and k-nearest neighbor (KNN) algorithms were employed to establish the discriminant diagnostic models. The accuracies of 93.5%, 93.5% and 89.1% were obtained from PCA-SVM, PCA-LDA and PCA-KNN models, respectively. The results from our study demonstrate that the serum Raman spectroscopy technique combined with multivariate statistical methods have great potential for the screening of high renin hypertension. This technique could be used to develop a portable, rapid, and non-invasive device for screening high renin hypertension.

Rapid identification of staphylococci by Raman spectroscopy

Clinical treatment of the infections caused by various staphylococcal species differ depending on the actual cause of infection. Therefore, it is necessary to develop a fast and reliable method for identification of staphylococci. Raman spectroscopy is an optical method used in multiple scientific fields. Recent studies showed that the method has a potential for use in microbiological research, too. Our work here shows a possibility to identify staphylococci by Raman spectroscopy. We present a method that enables almost 100% successful identification of 16 of the clinically most important staphylococcal species directly from bacterial colonies grown on a Mueller-Hinton agar plate. We obtained characteristic Raman spectra of 277 staphylococcal strains belonging to 16 species from a 24-hour culture of each strain grown on the Mueller-Hinton agar plate using the Raman instrument. The results show that it is possible to distinguish among the tested species using Raman spectroscopy and therefore it has a great potential for use in routine clinical diagnostics.

Detection of Genomic DNA Damage from Radiated Nasopharyngeal Carcinoma Cells Using Surface-Enhanced Raman Spectroscopy (SERS)

Structural changes and chemical modifications in DNA during interactions with X-ray radiation are still not clear within 48 h of incubation. We investigate genomic DNA from the radiated CNE2 cell line within 48 h of incubation using surface-enhanced Raman spectroscopy (SERS). Multivariate methods including principal component analysis (PCA) and random forest are proposed to explore the statistical significance before and after radiation. Our results show that intensities of several bands change after radiation, which indicates backbone damage and base-unstacking. Biological effects from DNA damage repairing process may be simultaneously stimulated and different from incubation time. Under doses of 10 Gy (with 24 and 48 h of incubation) and 20 Gy (with 48 h of incubation), the relative contents of C against T and A against G deviate obviously from the control level. Statistical results strengthen significantly the idea that modification in DNA bases is associated with the disruption of base-stacking in the DNA duplex. Our findings provide vital information for radiation-induced the DNA damage at the molecular level, which may provide insight into the effect and mechanism of anticarcinogens in tumor therapy.

Pursuing shell-isolated nanoparticle-enhanced Raman spectroscopy (SHINERS) for concomitant detection of breast lesions and microcalcifications

Although tissue staining followed by morphologic identification remains the gold standard for diagnosis of most cancers, such determinations relying solely on morphology are often hampered by inter- and intra-observer variability. Vibrational spectroscopic techniques, in contrast, offer objective markers for diagnoses and can afford disease detection prior to alterations in cellular and extracellular architecture by furnishing a rapid "omics"-like view of the biochemical status of the probed specimen. Here, we report a classification approach to concomitantly detect microcalcification status and local pathological state in breast tissue, featuring a combination of vibrational spectroscopy that focuses on the tumor and its microenvironment, and multivariate data analysis of spectral markers reflecting molecular expression. We employ the unprecedented sensitivity and exquisite molecular specificity offered by Au@SiO2 shell-isolated nanoparticle-enhanced Raman spectroscopy (SHINERS) to probe the presence of calcified deposits and distinguish between normal breast tissues, fibroadenoma, atypical ductal hyperplasia, ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (IDC). By correlating the spectra with the corresponding histologic assessment, we developed partial least squares-discriminant analysis derived decision algorithm that provides excellent diagnostic power in the fresh frozen sections (overall accuracy of 99.4% and 93.6% using SHINs for breast lesions with and without microcalcifications, respectively). The performance of this decision algorithm is competitive with or supersedes that of analogous algorithms employing spontaneous Raman spectroscopy while enabling facile detection due to the considerably higher intensity of SHINERS. Our results pave the way for rapid tissue spectral pathology measurements using SHINERS that can offer a novel stain-free route to accurate and economical diagnoses without human interpretation.

Raman spectroscopic sensing of carbonate intercalation in breast microcalcifications at stereotactic biopsy

Microcalcifications are an early mammographic sign of breast cancer and frequent target for stereotactic biopsy. Despite their indisputable value, microcalcifications, particularly of the type II variety that are comprised of calcium hydroxyapatite deposits, remain one of the least understood disease markers. Here we employed Raman spectroscopy to elucidate the relationship between pathogenicity of breast lesions in fresh biopsy cores and composition of type II microcalcifications. Using a chemometric model of chemical-morphological constituents, acquired Raman spectra were translated to characterize chemical makeup of the lesions. We find that increase in carbonate intercalation in the hydroxyapatite lattice can be reliably employed to differentiate benign from malignant lesions, with algorithms based only on carbonate and cytoplasmic protein content exhibiting excellent negative predictive value (93–98%). Our findings highlight the importance of calcium carbonate, an underrated constituent of microcalcifications, as a spectroscopic marker in breast pathology evaluation and pave the way for improved biopsy guidance.

Anatomy of noise in quantitative biological Raman spectroscopy

Raman spectroscopy is a fundamental form of molecular spectroscopy that is widely used to investigate structures and properties of molecules using their vibrational transitions. It relies on inelastic scattering of monochromatic laser light irradiating the specimen. After appropriate filtering the scattered light is dispersed onto a detector to determine the shift from the excitation wavelength, which appears in the form of characteristic spectral patterns. The technique can investigate biological samples and provide real-time diagnosis of diseases. However, despite its intrinsic advantages of specificity and minimal perturbation, the Raman scattered light is typically very weak and limits applications of Raman spectroscopy due to measurement (im)precision, driven by inherent noise in the acquired spectra. In this article, we review the principal noise sources that impact quantitative biological Raman spectroscopy. Further, we discuss how such noise effects can be reduced by innovative changes in the constructed Raman system and appropriate signal processing methods.

Application of Raman spectroscopy to identify microcalcifications and underlying breast lesions at stereotactic core needle biopsy

Microcalcifications are a feature of diagnostic significance on a mammogram and a target for stereotactic breast needle biopsy. Here, we report development of a Raman spectroscopy technique to simultaneously identify microcalcification status and diagnose the underlying breast lesion, in real-time, during stereotactic core needle biopsy procedures. Raman spectra were obtained ex vivo from 146 tissue sites from fresh stereotactic breast needle biopsy tissue cores from 33 patients, including 50 normal tissue sites, 77 lesions with microcalcifications, and 19 lesions without microcalcifications, using a compact clinical system. The Raman spectra were modeled on the basis of the breast tissue components, and a support vector machine framework was used to develop a single-step diagnostic algorithm to distinguish normal tissue, fibrocystic change (FCC), fibroadenoma, and breast cancer, in the absence and presence of microcalcifications. This algorithm was subjected to leave-one-site-out cross-validation, yielding a positive predictive value, negative predictive value, sensitivity, and specificity of 100%, 95.6%, 62.5%, and 100% for diagnosis of breast cancer (with or without microcalcifications) and an overall accuracy of 82.2% for classification into specific categories of normal tissue, FCC, fibroadenoma, or breast cancer (with and without microcalcifications). Notably, the majority of breast cancers diagnosed are ductal carcinoma in situ (DCIS), the most common lesion associated with microcalcifications, which could not be diagnosed using previous Raman algorithm(s). Our study shows the potential of Raman spectroscopy to concomitantly detect microcalcifications and diagnose associated lesions, including DCIS, and thus provide real-time feedback to radiologists during such biopsy procedures, reducing nondiagnostic and false-negative biopsies.

Raman imaging at biological interfaces: applications in breast cancer diagnosis

BACKGROUND

One of the most important areas of Raman medical diagnostics is identification and characterization of cancerous and noncancerous tissues. The methods based on Raman scattering has shown significant potential for probing human breast tissue to provide valuable information for early diagnosis of breast cancer. A vibrational fingerprint from the biological tissue provides information which can be used to identify, characterize and discriminate structures in breast tissue, both in the normal and cancerous environment.

RESULTS

The paper reviews recent progress in understanding structure and interactions at biological interfaces of the human tissue by using confocal Raman imaging and IR spectroscopy. The important differences between the noncancerous and cancerous human breast tissues were found in regions characteristic for vibrations of carotenoids, fatty acids, proteins, and interfacial water. Particular attention was paid to the role played by unsaturated fatty acids and their derivatives as well as carotenoids and interfacial water.

CONCLUSIONS

We demonstrate that Raman imaging has reached a clinically relevant level in regard to breast cancer diagnosis applications. The results presented in the paper may have serious implications on understanding mechanisms of interactions in living cells under realistically crowded conditions of biological tissue.