Spectroscopic identification of benign (follicular adenoma) and cancerous lesions (follicular thyroid carcinoma) in thyroid tissues

Raman spectroscopy with an improved support vector machine for discrimination of thyroid and parathyroid tissues

The objective of this study was to discriminate thyroid and parathyroid tissues using Raman spectroscopy combined with an improved support vector machine (SVM) algorithm. In thyroid surgery, there is a risk of inadvertently removing the parathyroid glands. At present, there is a lack of research on using Raman spectroscopy to discriminate parathyroid and thyroid tissues. In this article, samples were obtained from 43 individuals with thyroid and parathyroid tissues for Raman spectroscopy analysis. This study employed partial least squares (PLS) to reduce dimensions of data, and three optimization algorithms are used to improve the classification accuracy of SVM algorithm model in spectral analysis. The results show that PLS-GA-SVM algorithm has higher diagnostic accuracy and better reliability. The sensitivity of this algorithm is 94.67% and the accuracy is 94.44%. It can be concluded that Raman spectroscopy combined with the PLS-GA-SVM diagnostic algorithm has significant potential for discriminating thyroid and parathyroid tissues.

Expression data of FOS and JUN genes and FTIR spectra provide diagnosis of thyroid carcinoma

We explore the feasibility of using FOS and JUN gene expression and ATR-FTIR for diagnosis of thyroid cancer. For the study, 38 samples (6 non-neoplastic (NN), 10 papillary thyroid carcinoma (PTC), 7 follicular thyroid carcinoma (FTC), and 15 benign tumors (BT) were subjected to RNA extraction followed by quantitative real time PCR (qRT-PCR) and 30 samples (5 NN, 9 PTC, 5 FTC, and 11 BT) were used for Attenuated Total Reflectance - Fourier Transform Infrared (ATR-FTIR) followed by multivariate analysis. Of the above, 20 samples were used for both gene expression and ATR-FTIR studies. We found FOS and JUN expression in malignant tumor samples to be significantly lower than NN and benign. ATR-FIR after multivariate analysis could identify the difficult to diagnose FTC with 93 % efficiency. Overall, results suggest the diagnostic potential of molecular biology techniques combined with ATR-FTIR spectroscopy in differentiated thyroid carcinomas (PTC and FTC) and BT.

Raman Spectroscopy as a Potential Adjunct of Thyroid Nodule Evaluation: A Systematic Review

The incidence of thyroid nodules (TNs) is estimated at 36.5% and 23% in females and males, respectively. A single thyroid nodule is usually detected during ultrasound assessment in patients with symptoms of thyroid dysfunction or neck mass. TNs are classified as benign tumours (non-malignant hyperplasia), benign neoplasms (e.g., adenoma, a non-invasive follicular tumour with papillary nuclear features) or malignant carcinomas (follicular cell-derived or C-cell derived). The differential diagnosis is based on fine-needle aspiration biopsies and cytological assessment (which is burdened with the bias of subjectivity). Raman spectroscopy (RS) is a laser-based, semiquantitative technique which shows for oscillations of many chemical groups in one label-free measurement. RS, through the assessment of chemical content, gives insight into tissue state which, in turn, allows for the differentiation of disease on the basis of spectral characteristics. The purpose of this study was to report if RS could be useful in the differential diagnosis of TN. The Web of Science, PubMed, and Scopus were searched from the beginning of the databases up to the end of June 2023. Two investigators independently screened key data using the terms "Raman spectroscopy" and "thyroid". From the 4046 records found initially, we identified 19 studies addressing the differential diagnosis of TNs applying the RS technique. The lasers used included 532, 633, 785, 830, and 1064 nm lines. The thyroid RS investigations were performed at the cellular and/or tissue level, as well as in serum samples. The accuracy of papillary thyroid carcinoma detection is approx. 90%. Furthermore, medullary, and follicular thyroid carcinoma can be detected with up to 100% accuracy. These results might be biased with low numbers of cases in some research and overfitting of models as well as the reference method. The main biochemical changes one can observe in malignancies are as follows: increase of protein, amino acids (like phenylalanine, tyrosine, and tryptophan), and nucleic acid content in comparison with non-malignant TNs. Herein, we present a review of the literature on the application of RS in the differential diagnosis of TNs. This technique seems to have powerful application potential in thyroid tumour diagnosis.

Detection of breast cancer by ATR-FTIR spectroscopy using artificial neural networks

In this study, three (3) neural networks (NN) were designed to discriminate between malignant (n = 78) and benign (n = 88) breast tumors using their respective attenuated total reflection Fourier transform infrared (ATR-FTIR) spectral data. A proposed NN-based sensitivity analysis was performed to determine the most significant IR regions that distinguished benign from malignant samples. The result of the NN-based sensitivity analysis was compared to the obtained results from FTIR visual peak identification. In training each NN models, a 10-fold cross validation was performed and the performance metrics-area under the curve (AUC), accuracy, positive predictive value (PPV), specificity rate (SR), negative predictive value (NPV), and recall rate (RR)-were averaged for comparison. The NN models were compared to six (6) machine learning models-logistic regression (LR), Naïve Bayes (NB), decision trees (DT), random forest (RF), support vector machine (SVM) and linear discriminant analysis (LDA)-for benchmarking. The NN models were able to outperform the LR, NB, DT, RF, and LDA for all metrics; while only surpassing the SVM in accuracy, NPV and SR. The best performance metric among the NN models was 90.48% ± 10.30% for AUC, 96.06% ± 7.07% for ACC, 92.18 ± 11.88% for PPV, 94.19 ± 10.57% for NPV, 89.04% ± 16.75% for SR, and 94.34% ± 10.54% for RR. Results from the proposed sensitivity analysis were consistent with the visual peak identification. However, unlike the FTIR visual peak identification method, the NN-based method identified the IR region associated with C-OH C-OH group carbohydrates as significant. IR regions associated with amino acids and amide proteins were also determined as possible sources of variability. In conclusion, results show that ATR-FTIR via NN is a potential diagnostic tool. This study also suggests a possible more specific method in determining relevant regions within a sample's spectrum using NN.

Metabolic Profile Characterization of Different Thyroid Nodules Using FTIR Spectroscopy: A Review

Thyroid cancer’s incidence has increased in the last decades, and its diagnosis can be a challenge. Further and complementary testing based in biochemical alterations may be important to correctly identify thyroid cancer and prevent unnecessary surgery. Fourier-transform infrared (FTIR) spectroscopy is a metabolomic technique that has already shown promising results in cancer metabolome analysis of neoplastic thyroid tissue, in the identification and classification of prostate tumor tissues and of breast carcinoma, among others. This work aims to gather and discuss published information on the ability of FTIR spectroscopy to be used in metabolomic studies of the thyroid, including discriminating between benign and malignant thyroid samples and grading and classifying different types of thyroid tumors.

Diagnosis of endometriosis using endometrioma volume and vibrational spectroscopy with multivariate methods as a noninvasive method

Endometriomas are typically an advanced form of endometriosis that leads to the formation of scar tissue, adhesions, and an inflammatory reaction. There is no certain serum marker for the diagnosis of endometriosis. This study aims to research the correlation between the amount of peaks corresponding to proteins and lipids with the volume of endometrioma and determine the chemical structure of blood serum collected from women suffering from endometriosis patients with endometrioma and healthy subjects using Fourier Transform Infrared (FTIR) spectroscopy. FTIR spectroscopy is used as a non-invasive diagnostic technique for the discrimination of endometriosis women with endometrioma and control blood sera. The FTIR spectra of 100 serum samples acquired from 50 patients and 50 healthy individuals were used for this study. For this purpose, multivariate analyses such as Principal Component Analysis (PCA), Partial Last Square analysis (PLS) with Variables Importance in Projection (VIP), and probability models, were performed. Our results showed that FTIR range 1500 cm^-1 and 1700 cm^-1 and around 2700 cm^-1 - 3000 cm^-1, regions may be used for the diagnosis of endometriosis. Also, we find that proteins and lipids fraction increase with the volume of endometrioma. Moreover, PLS and VIP analysis suggested that lipids could be helpful in the diagnosis of endometriosis women with endometrioma.

Primary squamous cell carcinoma of the thyroid: a case report

Primary squamous cell carcinoma of the thyroid (PSCCT) is a rare and rapidly progressive malignancy that carries a poor prognosis. PSCCT is easily misdiagnosed as acute thyroiditis or as another thyroid malignancy. We have reported a 76-year-old woman who presented with progressive neck pain for 1 month. Thyroid function tests revealed subclinical thyrotoxicosis. Ultrasound disclosed a solid nodule with calcification in the right thyroid lobe. Laboratory findings included neutrophilic leukocytosis and an elevated erythrocyte sedimentation rate. The patient's condition was diagnosed as subacute thyroiditis, and she was treated with cefixime and ibuprofen. However, her treatment response was poor. She was then treated with oral prednisone. Her neck pain gradually resolved. The patient subsequently developed dysphagia, choking, dyspnea, and dysphonia with an insidious onset. Further examinations including computed tomography and painless gastroscopy revealed that the volume of the thyroid gland had increased significantly, extending to the anterior superior mediastinum. The trachea and esophagus were stenotic because of external compression. Partial thyroidectomy and tracheotomy were performed under extracorporeal membrane oxygenation. The diagnosis of PSCCT was established via histopathology and immunohistochemistry.

Discrimination of malignant from benign thyroid lesions through neural networks using FTIR signals obtained from tissues

The current gold standard in cancer diagnosis-the microscopic examination of hematoxylin and eosin (H&E)-stained biopsies-is prone to bias since it greatly relies on visual examination. Hence, there is a need to develop a more sensitive and specific method for diagnosing cancer. Here, Fourier transform infrared (FTIR) spectroscopy of thyroid tumors (n = 164; 76 malignant, 88 benign) was performed and five (5) neural network (NN) models were designed to discriminate the obtained spectral data. PCA-LDA was used as classical benchmark for comparison. Each NN model was evaluated using a stratified 10-fold cross-validation method to avoid overfitting, and the performance metrics-accuracy, area under the curve (AUC), positive predictive value (PPV), negative predictive value (NPV), specificity rate (SR), and recall rate (RR)-were averaged for comparison. All NN models were able to perform excellently as classifiers, and all were able to surpass the LDA model in terms of accuracy. Among the NN models, the RNN model performed best, having an AUC of 95.29% ± 6.08%, an accuracy of 98.06% ± 2.87%, a PPV of 98.57% ± 4.52%, a NPV of 93.18% ± 7.93%, a SR value of 98.89% ± 3.51%, and a RR value of 91.25% ± 10.29%. The RNN model outperformed the LDA model for all metrics except for the AUC, NPV, and RR. In conclusion, NN-based tools were able to predict thyroid cancer based on infrared spectroscopy of tissues with a high level of diagnostic performance in comparison to the gold standard.

Malignant and benign thyroid nodule differentiation through the analysis of blood plasma with terahertz spectroscopy

The liquid and lyophilized blood plasma of patients with benign or malignant thyroid nodules and healthy individuals were studied by terahertz (THz) time-domain spectroscopy and machine learning. The blood plasma samples from malignant nodule patients were shown to have higher absorption. The glucose concentration and miRNA-146b level were correlated with the sample's absorption at 1 THz. A two-stage ensemble algorithm was proposed for the THz spectra analysis. The first stage was based on the Support Vector Machine with a linear kernel to separate healthy and thyroid nodule participants. The second stage included additional data preprocessing by Ornstein-Uhlenbeck kernel Principal Component Analysis to separate benign and malignant thyroid nodule participants. Thus, the distinction of malignant and benign thyroid nodule patients through their lyophilized blood plasma analysis by terahertz time-domain spectroscopy and machine learning was demonstrated.

Objective analysis of collagen organization in thyroid nodule capsules using second harmonic generation microscopy images and the Hough transform

Papillary carcinoma is the most prevalent type of thyroid cancer. Its diagnosis requires accurate and subjective analyses from expert pathologists. Here we propose a method based on the Hough transform (HT) to detect and objectively quantify local structural differences in collagen thyroid nodule capsules. Second harmonic generation (SHG) microscopy images were acquired on non-stained histological sections of capsule fragments surrounding the healthy thyroid gland and benign and tumoral/malignant nodules. The HT was applied to each SHG image to extract numerical information on the organization of the collagen architecture in the tissues under analysis. Results show that control thyroid capsule samples present a non-organized structure composed of wavy collagen distribution with local orientations. On the opposite, in capsules surrounding malignant nodules, a remodeling of the collagen network takes place and local undulations disappear, resulting in an aligned pattern with a global preferential orientation. The HT procedure was able to quantitatively differentiate thyroid capsules from capsules surrounding papillary thyroid carcinoma (PTC) nodules. Moreover, the algorithm also reveals that the collagen arrangement of the capsules surrounding benign nodules significantly differs from both the thyroid control and PTC nodule capsules. Combining SHG imaging with the HT results thus in an automatic and objective tool to discriminate between the pathological modifications that affect the capsules of thyroid nodules across the progressions of PTC, with potential to be used in clinical settings to complement current state-of-the-art diagnostic methods.

Thyroid cancer diagnosis by Raman spectroscopy

Over the last 50 years, the incidence of human thyroid cancer disease has seen a significative increment. This comes along with an even higher increment of surgery, since, according to the international guidelines, patients are sometimes addressed to surgery also when the fine needle aspiration gives undetermined cytological diagnosis. As a matter of fact, only 30% of the thyroid glands removed for diagnostic purpose have a post surgical histological report of malignancy: this implies that about 70% of the patients have suffered an unnecessary thyroid removal. Here we show that Raman spectroscopy investigation of thyroid tissues provides reliable cancer diagnosis. Healthy tissues are consistently distinguished from cancerous ones with an accuracy of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\sim $$\end{document}∼ 90%, and the three cancer typology with highest incidence are clearly identified. More importantly, Raman investigation has evidenced alterations suggesting an early stage of transition of adenoma tissues into cancerous ones. These results suggest that Raman spectroscopy may overcome the limits of current diagnostic tools.

The Spectroscopic Similarity between Breast Cancer Tissues and Lymph Nodes Obtained from Patients with and without Recurrence: A Preliminary Study

Lymph nodes (LNs) play a very important role in the spread of cancer cells. Moreover, it was noticed that the morphology and chemical composition of the LNs change in the course of cancer development. Therefore, finding and monitoring similarities between these characteristics of the LNs and tumor tissues are essential to improve diagnostics and therapy of this dreadful disease. In the present study, we used Raman and Fourier transform infrared (FTIR) spectroscopies to compare the chemical composition of the breast cancer tissues and LNs collected from women without (I group-4 patients) and with (II group-4 patients) recurrence. It was shown that the similarity of the chemical composition of the breast tissues and LNs is typical for the II group of the patients. The average Raman spectrum of the breast cancer tissues from the I group was not characterized by vibrations in the 800-1000 cm^-1 region originating from collagen and carbohydrates, which are typical for tumor-affected breast tissues. At the same time, this spectrum contains peaks at 1029 cm^-1, corresponding to PO^2- from DNA, RNA and phospholipids, and 1520 cm^-1, which have been observed in normal breast tissues before. It was shown that Raman bands of the average LN spectrum of the II group associated with proteins and carbohydrates are more intensive than those of the breast tissues spectrum. The intensity of the Raman spectra collected from the samples of the II group is almost three times higher compared to the I group. The vibrations of carbohydrates and amide III are much more intensive in the II group's case. The Raman spectra of the breast cancer tissues and LNs of the II group's samples do not contain bands (e.g., 1520 cm^-1) found in the Raman spectra of the normal breast tissues elsewhere. FTIR spectra of the LNs of the I group's women showed a lower level of vibrations corresponding to functional group building nucleic acid, collagen, carbohydrates, and proteins in comparison with the breast cancer tissues. Pearson's correlation test showed positive and more significant interplay between the nature of the breast tissues and LN spectra obtained for the II group of patients than that in the I group's spectra. Moreover, principal component analysis (PCA) showed that it is possible to distinguish Raman and FTIR spectra of the breast cancer tissues and LNs collected from women without recurrence of the disease.

Simultaneous FTIR and Raman Spectroscopy in Endometrial Atypical Hyperplasia and Cancer

Currently, endometrial carcinoma (EC) is the most common genital cancer in high-income countries. Some types of endometrial hyperplasia (EH) may be progressing to this malignancy. The diagnosis of EC and EH is based on time consuming histopathology evaluation, which is subjective and causes discrepancies in reassessment. Therefore, there is a need to create methods of objective evaluation allowing the diagnosis of early changes. The study aimed to simultaneously asses Fourier Transform Infrared (FTIR) and Raman spectroscopy combined with multidimensional analysis to identify the tissues of endometrial cancer, atypical hyperplasia and the normal control group, and differentiate them. The results of FTIR and Raman spectroscopy revealed quantitative and qualitative changes in the nucleic acid and protein in the groups of cancer and atypical hyperplasia, in comparison with the control group. Changes in the lipid region were also observed in Raman spectra. Pearson correlation coefficient demonstrated a statistically significant correlation between Raman spectra for the cancer and atypical hyperplasia groups (0.747, p < 0.05) and for atypical hyperplasia and the controls (0.507, p < 0.05), while FTIR spectra demonstrated a statistically significant positive correlation for the same group as in Raman data and for the control and cancer groups (0.966, p < 0.05). To summarize, the method of spectroscopy enables differentiation of atypical hyperplasia and endometrial cancer tissues from the physiological endometrial tissue.

Multi-Reader Multi-Case Study for Performance Evaluation of High-Risk Thyroid Ultrasound with Computer-Aided Detection

Physicians use sonographic characteristics as a reference for the possible diagnosis of thyroid cancers. The purpose of this study was to investigate whether physicians were more effective in their tentative diagnosis based on the information provided by a computer-aided detection (CAD) system. A computer compared software-defined and physician-adjusted tumor loci. A multicenter, multireader, and multicase (MRMC) study was designed to compare clinician performance without and with the use of CAD. Interobserver variability was also analyzed. Excellent, satisfactory, and poor segmentations were observed in 25.3%, 58.9%, and 15.8% of nodules, respectively. There were 200 patients with 265 nodules in the study set. Nineteen physicians scored the malignancy potential of the nodules. The average area under the curve (AUC) of all readers was 0.728 without CAD and significantly increased to 0.792 with CAD. The average standard deviation of the malignant potential score significantly decreased from 18.97 to 16.29. The mean malignant potential score significantly decreased from 35.01 to 31.24 for benign cases. With the CAD system, an additional 7.6% of malignant nodules would be suggested for further evaluation, and biopsy would not be recommended for an additional 10.8% of benign nodules. The results demonstrated that applying a CAD system would improve clinicians’ interpretations and lessen the variability in diagnosis. However, more studies are needed to explore the use of the CAD system in an actual ultrasound diagnostic situation where much more benign thyroid nodules would be seen.

Towards development of a novel universal medical diagnostic method: Raman spectroscopy and machine learning

This review summarizes recent progress made using Raman spectroscopy and machine learning for potential universal medical diagnostic applications.