Raman spectroscopy differentiates squamous cell carcinoma (SCC) from normal skin following treatment with a high-powered CO2 laser

Transfer Contrastive Learning for Raman Spectroscopy Skin Cancer Tissue Classification

Using Raman spectroscopy (RS) signals for skin cancer tissue classification has recently drawn significant attention, because of its non-invasive optical technique, which uses molecular structures and conformations within biological tissue for diagnosis. In reality, RS signals are noisy and unstable for training machine learning models. The scarcity of tissue samples also makes it challenging to learn reliable deep-learning networks for clinical usages. In this paper, we advocate a Transfer Contrasting Learning Paradigm (TCLP) to address the scarcity and noisy characteristics of the RS for skin cancer tissue classification. To overcome the challenge of limited samples, TCLP leverages transfer learning to pre-train deep learning models using RS data from similar domains (but collected from different RS equipments for other tasks). To tackle the noisy nature of the RS signals, TCLP uses contrastive learning to augment RS signals to learn reliable feature representation to represent RS signals for final classification. Experiments and comparisons, including statistical tests, demonstrate that TCLP outperforms existing deep learning baselines for RS signal-based skin cancer tissue classification.

Studying on the in vivo pathological evolution of spinal cord injury with the rat model by the method of integrated multispectral imaging and Raman spectroscopy

Spinal cord injury (SCI) is a debilitating neurological and pathological condition that results in significant impairments in motor, sensory, and autonomic functions. By integrating multispectral imaging (MSI) with Raman spectroscopy, a label-free optical methodology was developed for achieving a non-invasive in vivo understanding on the pathological features of SCI evolution. Under the guidance of captured the spectral imaging data cube with a rigid endoscope based MSI system, a special designed fiber probe passed through the instrumental channel for acquiring the finger-print spectral information from compression rat SCI models. After identifying the main visual features of injured spinal cord tissue in all Sham, 0-, 3- and 7-days post injury (0 DPI, 3 DPI, and 7 DPI) groups, the blood volume and oxygen content were visualized to describe hemorrhage, hypoxia and inflammatory state after acute injury. The averaged reflectance spectra, which were deduced from MSI data cubes, were utilized for describing oxygen saturation and hemoglobin concentration in living tissue. The results of Raman spectroscopy addressed complex compositional and conformational phenomena during SCI progression, correlated with the well-known event like neuronal apoptosis, hemorrhage, demyelination, and even the upregulation of chondroitin sulfate proteoglycans (CSPGs). A principal component analysis and linear discriminate algorithm (PCA-LDA) based discriminate model was introduced for categorizing spectral features in different injury stages, which was applicable for intraoperative interpretations on the complex pathological courses of SCI and therapeutic outcomes.

Portable System for In-Clinic Differentiation of Skin Cancers from Benign Skin Lesions and Inflammatory Dermatoses

The exquisite sensitivity of Raman spectroscopy for detecting biomolecular changes in skin cancer has previously been explored; however, this mostly required analysis of excised tissue samples using bulky, immobile laboratory instrumentation. In this study, the technique was translated for clinical use with a portable Raman system and customized fiber optic probe and applied to differentiation of skin cancers from benign lesions and inflammatory dermatoses. The aim was to provide an easy-to-use, easy-to-manage assessment tool for clinicians to use in their daily patient examination routine to perform rapid Raman measurements of skin lesions in vivo. Using this system, >867 spectra were measured in vivo from 330 patients with a wide variety of different benign skin lesions (n = 603), inflammatory dermatoses (n = 140), and skin cancers (n = 124). Ethnicities represented were 70% European; 16% Asian; 6% Māori; 5% Pacific people; and 4% Middle East, Latin American, and African. Accurate differentiation of skin cancers from benign lesions and inflammatory dermatoses was achieved using partial least squares discriminant analysis, with area under curve for the receiver operator curves for external validation sets ranging from 0.916 to 0.958. This study shows evidence for robust clinical translation of Raman spectroscopy for rapid, accurate diagnosis of skin cancer.

Research trends and hotspot analysis of fractional carbon dioxide laser: A bibliometric and visualized analysis via Citespace

INTRODUCTION

There is limited basic research on carbon dioxide (CO₂ ) fractional laser, indicating blind spots in CO₂ fractional laser treatment of certain diseases. This study aimed to organize previous literature, summarize the current research, and speculate on possible future development.

METHODS

We searched document data on fractional CO₂ lasers from the Web of Science core collection database and retrieved 928 articles from 2004 to 2021. CiteSpace software was used to analyze the main institutions, authors, subject hotspots, and research frontiers in global CO₂ fractional laser research.

RESULTS

The results revealed that 928 related papers were published in the past 18 years (2004-2021), and the number has increased annually. The publications were written by 3239 authors from 626 institutions in 60 countries/regions. The United States (US) dominates this field (312 documents), followed by Italy (289), and South Korea (88). Lasers in Surgery and Medicine is the journal with the most publications and citations, and Uebelhoer is the central author. The main research hotspots include vulvovaginal atrophy, fractional photothermolysis, keloids, drug delivery, gene expressions, facial acne scarring, resurfacing, vitiligo, and photo damage.

CONCLUSION

Using CiteSpace, this paper draws a map of authors, institutions, and keywords in fractional CO₂ laser from 2004 to 2021; summarizes the main authors, institutions, research hotspots, and cutting-edge topics of global fractional CO₂ laser technology in recent years; and summarizes the current application status of global fractional CO₂ laser in disease treatment. It also provides new ideas for the future application and research of fractional CO₂ lasers.

Matrix Effectors in the Pathogenesis of Keratinocyte-Derived Carcinomas

Basal cell carcinoma (BCC) and cutaneous squamous cell carcinoma (cSCC), referred to as keratinocyte carcinomas, are skin cancer with the highest incidence. BCCs, rarely metastasize; whereas, though generally not characterized by high lethality, approximately 2–4% of primary cSCCs metastasize with patients exhibiting poor prognosis. The extracellular matrix (ECM) serves as a scaffold that provides structural and biological support to cells in all human tissues. The main components of the ECM, including fibrillar proteins, proteoglycans (PGs), glycosaminoglycans (GAGs), and adhesion proteins such as fibronectin, are secreted by the cells in a tissue-specific manner, critical for the proper function of each organ. The skin compartmentalization to the epidermis and dermis compartments is based on a basement membrane (BM), a highly specialized network of ECM proteins that separate and unify the two compartments. The stiffness and assembly of BM and tensile forces affect tumor progenitors' invasion at the stratified epithelium's stromal border. Likewise, the mechanical properties of the stroma, e.g., stiffness, are directly correlated to the pathogenesis of the keratinocyte carcinomas. Since the ECM is a pool for various growth factors, cytokines, and chemokines, its' intense remodeling in the aberrant cancer tissue milieu affects biological functions, such as angiogenesis, adhesion, proliferation, or cell motility by regulating specific signaling pathways. This review discusses the structural and functional modulations of the keratinocyte carcinoma microenvironment. Furthermore, we debate how ECM remodeling affects the pathogenesis of these skin cancers.

Deep learning data augmentation for Raman spectroscopy cancer tissue classification

Recently, Raman Spectroscopy (RS) was demonstrated to be a non-destructive way of cancer diagnosis, due to the uniqueness of RS measurements in revealing molecular biochemical changes between cancerous vs. normal tissues and cells. In order to design computational approaches for cancer detection, the quality and quantity of tissue samples for RS are important for accurate prediction. In reality, however, obtaining skin cancer samples is difficult and expensive due to privacy and other constraints. With a small number of samples, the training of the classifier is difficult, and often results in overfitting. Therefore, it is important to have more samples to better train classifiers for accurate cancer tissue classification. To overcome these limitations, this paper presents a novel generative adversarial network based skin cancer tissue classification framework. Specifically, we design a data augmentation module that employs a Generative Adversarial Network (GAN) to generate synthetic RS data resembling the training data classes. The original tissue samples and the generated data are concatenated to train classification modules. Experiments on real-world RS data demonstrate that (1) data augmentation can help improve skin cancer tissue classification accuracy, and (2) generative adversarial network can be used to generate reliable synthetic Raman spectroscopic data.

Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning

Early-stage detection of cutaneous melanoma can vastly increase the chances of cure. Excision biopsy followed by histological examination is considered the gold standard for diagnosing the disease, but requires long high-cost processing time, and may be biased, as it involves qualitative assessment by a professional. In this paper, we present a new machine learning approach using raw data for skin Raman spectra as input. The approach is highly efficient for classifying benign versus malignant skin lesions (AUC 0.98, 95% CI 0.97-0.99). Furthermore, we present a high-performance model (AUC 0.97, 95% CI 0.95-0.98) using a miniaturized spectral range (896-1039 cm^-1), thus demonstrating that only a single fragment of the biological fingerprint Raman region is needed for producing an accurate diagnosis. These findings could favor the future development of a cheaper and dedicated Raman spectrometer for fast and accurate cancer diagnosis.

Raman spectroscopy combined with multivariate analysis to study the biochemical mechanism of lung cancer microwave ablation

Lung cancer is the leading cause of death in cancer patients, and microwave ablation (MWA) has been extensively used in clinical treatment. In this study, we characterized the spectra of MWA-treated and untreated lung squamous cell carcinoma (LSCC) tissues, as well as healthy lung tissue, and conducted a preliminary analysis of spectral variations associated with MWA treatment. The results of characteristic spectral analysis of different types of tissues indicated that MWA treatment induces an increase in the content of nucleic acids, proteins, and lipid components in lung cancer tissues. The discriminant model based on the principal component analysis - linear discriminant analysis (PCA-LDA) algorithm together with leave-one-out cross validation (LOOCV) method yield the sensitivities of 90%, 80%, and 96%, and specificities of 86.2%, 93.8%, and 100% among untreated and MWA-treated cancerous tissue, and healthy lung tissue, respectively. These results indicate that Raman spectroscopy combined with multivariate analysis techniques can be used to explore the biochemical response mechanism of cancerous tissue to MWA therapy.

Diagnosis accuracy of Raman spectroscopy in colorectal cancer: A PRISMA-compliant systematic review and meta-analysis

BACKGROUND

The clinical significance of Raman spectroscopy (RS) in colorectal cancer (CRC) patients still remains underestimated. We performed this meta-analysis to elucidate the diagnostic value in CRC patients.

METHODS

We systematically searched electronic databases for published articles. Fixed effect model and random effect model were used to calculate the pooled sensitivity, specificity, diagnostic accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR) and positive posttest probability (PPP) of CRC. Meta-regression and subgroup analysis were conducted to assess potential source of heterogeneity. We also used Egger linear regression tests to assess risk of publication bias.

RESULTS

Thirteen studies had been included (679 patients: 186 with premalignant lesions and 493 with malignant lesions). The pooled sensitivity, specificity, diagnostic accuracy, PLR, NLR, DOR and PPP for CRC screening using RS were 0.94 (0.92-0.96), 0.94 (0.88-0.97), 0.96 (0.94-0.98), 16.44 (7.80-34.63), 0.062 (0.043-0.090), 263.65 (99.03-701.96) and 86%, respectively.

CONCLUSION

RS is a potentially useful tool for future CRC screening. It also offers potentially early detection for CRC patients.

Accuracy of Raman spectroscopy in discrimination of nasopharyngeal carcinoma from normal samples: a systematic review and meta-analysis

OBJECTIVES

The aim of this review was to systematically evaluate the diagnostic accuracy of Raman spectroscopy (RS) in the identification of nasopharyngeal carcinomas from normal nasopharyngeal tissue.

METHODS

We searched six databases (PubMed, Embase, Cochrane Library, Web of Science, Scopus and CNKI) up to September 2018 for all published studies that assessed the diagnostic accuracy of RS in the detection of nasopharyngeal carcinomas. Non-qualifying studies were screened out in accordance with the specified exclusion criteria and relevant information about the diagnostic performance of RS extracted. A random effects model was adopted to calculate the pooled sensitivity, specificity, positive and negative likelihood ratios (PLR and NLR, respectively), diagnostic threshold and diagnostic odds ratio (DOR). Additionally, we conducted a summary receiver-operating characteristic (SROC) curve analysis and threshold analysis, reporting area under the curve (AUC) to evaluate the overall performance of RS.

RESULTS

Three studies examined RS analysis in vivo, the pooled sensitivity and specificity of RS of which were 0.90 and 0.91, respectively, with an AUC of 0.9617. Eighteen studies assessed ex vivo samples, for which RS exhibited particularly high accuracy for the analysis of blood plasma.

CONCLUSIONS

RS was demonstrated to be a reliable technique for the detection of nasopharyngeal carcinoma with high accuracy, but additional studies are required to improve its performance and expand its application in ex vivo detection.

Screening and staging for non-small cell lung cancer by serum laser Raman spectroscopy

OBJECTIVE

Lung cancer is the leading cause of cancer-related death worldwide. Current clinical screening methods to detect lung cancer are expensive and associated with many complications. Raman spectroscopy is a spectroscopic technique that offers a convenient method to gain molecular information about biological samples. In this study, we measured the serum Raman spectral intensity of healthy volunteers and patients with different stages of non-small cell lung cancer. The purpose of this study was to evaluate the application of serum laser Raman spectroscopy as a low cost alternative method in the screening and staging of non-small cell lung cancer (NSCLC).

METHODS

The Raman spectra of the sera of peripheral venous blood were measured with a LabRAM HR 800 confocal Micro Raman spectrometer for individuals from five groups including 14 healthy volunteers (control group), 23 patients with stage I NSCLC (stage I group), 24 patients with stage II NSCLC (stage II group), 19 patients with stage III NSCLC (stage III group), 11 patients with stage IV NSCLC (stage IV group). Each serum sample was measured 3 times at different spots and the average spectra represented the signal of Raman spectra in each case. The Raman spectrum signal data of the five groups were statistically analyzed by analysis of variance (ANOVA), principal component analysis (PCA), linear discriminant analysis (LDA), and cross-validation.

RESULTS

Raman spectral intensity was sequentially reduced in serum samples from control group, stage I group, stage II group and stage III/IV group. The strongest peak intensity was observed in the control group, and the weakest one was found in the stage III/IV group at bands of 848 cm^-1, 999 cm^-1, 1152 cm^-1, 1446 cm^-1 and 1658 cm^-1 (P < 0.05). Linear discriminant analysis showed that the sensitivity to identify healthy people, stage I, stage II, and stage III/IV NSCLC was 86%, 65%, 75%, and 87%, respectively; the specificity was 95%, 94%, 88%, and 93%, respectively; and the overall accuracy rate was 92% (71/77).

CONCLUSION

The laser Raman spectroscopy can effectively identify patients with stage I, stage II or stage III/IV Non-Small Cell Lung cancer using patient serum samples.

Accuracy of Raman spectroscopy for differentiating skin cancer from normal tissue

BACKGROUND

Raman spectroscopy could be applied to distinguish tumor from normal tissues. This meta-analysis assessed the accuracy of Raman spectroscopy in differentiating skin cancer from normal tissue.

METHODS

PubMed, Embase, Cochrane Library, and CNKI were searched to identify suitable studies before Februray 4th, 2018. We estimated the pooled sensitivity, specificity, positive, and negative likelihood ratios, diagnostic odds ratio, and constructed summary receiver-operating characteristics curves to identify the accuracy of Raman spectroscopy in differentiating skin cancer from normal tissue.

RESULTS

A total of 12 studies with 2461 spectra were included. For basal cell skin cancer (BCC) ex vivo detection, the pooled sensitivity and specificity were 0.99 (95% confidence interval [CI] 0.97-0.99) and 0.96 (95% CI 0.95-0.97), respectively. The area under the curve (AUC) was 0.9837. For BCC in vivo detection, the pooled sensitivity and specificity were 0.69 (95% CI 0.61-0.76) and 0.85 (95% CI 0.82-0.87), respectively. The AUC was 0.9213. For melanoma (MM) ex vivo detection, the pooled sensitivity and specificity were 1.00 (95% CI 0.91-1.00) and 0.98 (95% CI 0.95-1.00), respectively. The AUC was 0.9914. For MM in vivo detection, the sensitivity (0.93) and the specificity (0.96) balanced relatively well. For squamous cell skin cancer (SCC) ex vivo detection, the pooled sensitivity and specificity were 0.96 (95% CI 0.81-1.00) and 1.00 (95% CI 0.92-1.00), respectively. For SCC in vivo detection, the sensitivity was 0.81 (95% CI 0.70-0.90) and the specificity was 0.89 (95% CI 0.86-0.91).

CONCLUSION

This meta-analysis suggested that Raman spectroscopy could be an effective and accurate tool for differentiating BCC, MM, SCC from normal tissue, which would assist us in the diagnosis and treatment of skin cancer.

Collagen disruption as a marker for basal cell carcinoma in presurgical margin detection

INTRODUCTION AND OBJECTIVE

Nonmelanoma skin cancers (NMSCs) are the most common malignancies in the United States. Surgery is the most common treatment for these tumors, but pre-operative identification of surgical margins is challenging. The objective in this study was to determine whether optical polarization imaging (OPI) could be used prior to surgery to detect the extent of subclinical tumor spread by monitoring disruption in collagen.

MATERIALS AND METHODS

OPI is a non-invasive and rapid imaging modality that highlights the structure of dermal collagen. OPI was used preoperatively at wavelengths of 440 and 640 nm to perform imaging of NMSCs on six patients scheduled to undergo Mohs surgery for biopsy-proven basal cell carcinoma. This pilot study did not alter the course of routine MMS for any of the patients. The surgeon was blinded from the preoperative imaging results and completed the entire procedure without relying on the new technology. The study was conducted in an outpatient surgical setting. Patients over 18 years of age with biopsy-proven basal cell carcinoma participated.

RESULTS AND CONCLUSION

OPI accurately predicted the presence or absence of tumor at the surgical margin in six out of six cases, as confirmed on histology. OPI may allow efficient surgical planning by identifying tumor extension beyond visibly involved skin. Lasers Surg. Med. 50:902-907, 2018. © 2018 Wiley Periodicals, Inc.

Rapid and accurate intraoperative pathological diagnosis by artificial intelligence with deep learning technology

Frozen section is widely used for intraoperative pathological diagnosis (IOPD), which is essential for intraoperative decision making. However, frozen section suffers from some drawbacks, such as time consuming and high misdiagnosis rate. Recently, artificial intelligence (AI) with deep learning technology has shown bright future in medicine. We hypothesize that AI with deep learning technology could help IOPD, with a computer trained by a dataset of intraoperative lesion images. Evidences supporting our hypothesis included the successful use of AI with deep learning technology in diagnosing skin cancer, and the developed method of deep-learning algorithm. Large size of the training dataset is critical to increase the diagnostic accuracy. The performance of the trained machine could be tested by new images before clinical use. Real-time diagnosis, easy to use and potential high accuracy were the advantages of AI for IOPD. In sum, AI with deep learning technology is a promising method to help rapid and accurate IOPD.

Label-free discrimination of different stage nasopharyngeal carcinoma tissue based on Raman spectroscopy

The present study aimed to evaluate a label-free tissue test for the detection of nasopharyngeal carcinoma (NPC) at early and advanced stages using Raman spectroscopy (RS). RS measurements were performed to acquire high quality Raman spectra on two groups of tissue samples: One group consists of 30 NPC patients at the early stages (I-II), and the other group is 46 NPC patients at the advanced stages (III-IV). Tentative assignment of Raman bands showed specific biomolecular changes associated with cancer development. Furthermore, effective diagnostic algorithms based on principal components analysis (PCA) and linear discriminant analysis (LDA) were applied for distinguishing Raman spectra of nasopharyngeal tissues from different stages, yielding a diagnostic sensitivity of 70% and a specificity of 78%. This exploratory work suggests that RS in conjunction with the PCA-LDA algorithms provides good diagnostic ability for the early and the advanced staged NPC tissues, and RS has enormous potential for the non-invasive detection of early and advanced stage NPC.