Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis

Diagnostic accuracy of artificial intelligence assisted clinical imaging in the detection of oral potentially malignant disorders and oral cancer: a systematic review and meta-analysis

BACKGROUND

The objective of this study is to examine the application of artificial intelligence (AI) algorithms in detecting oral potentially malignant disorders (OPMD) and oral cancerous lesions, and to evaluate the accuracy variations among different imaging tools employed in these diagnostic processes.

MATERIALS AND METHODS

A systematic search was conducted in four databases: Embase, Web of Science, PubMed, and Scopus. The inclusion criteria included studies using machine learning algorithms to provide diagnostic information on specific oral lesions, prospective or retrospective design, and inclusion of OPMD. Sensitivity and specificity analyses were also required. Forest plots were generated to display overall diagnostic odds ratio (DOR), sensitivity, specificity, negative predictive values, and summary receiver operating characteristic (SROC) curves. Meta-regression analysis was conducted to examine potential differences among different imaging tools.

RESULTS

The overall DOR for AI-based screening of OPMD and oral mucosal cancerous lesions from normal mucosa was 68.438 (95% CI= [39.484-118.623], I2 =86%). The area under the SROC curve was 0.938, indicating excellent diagnostic performance. AI-assisted screening showed a sensitivity of 89.9% (95% CI= [0.866-0.925]; I2 =81%), specificity of 89.2% (95% CI= [0.851-0.922], I2 =79%), and a high negative predictive value of 89.5% (95% CI= [0.851-0.927], I2 =96%). Meta-regression analysis revealed no significant difference among the three image tools. After generating a GOSH plot, the DOR was calculated to be 49.30, and the area under the SROC curve was 0.877. Additionally, sensitivity, specificity, and negative predictive value were 90.5% (95% CI [0.873-0.929], I2 =4%), 87.0% (95% CI [0.813-0.912], I2 =49%) and 90.1% (95% CI [0.860-0.931], I2 =57%), respectively. Subgroup analysis showed that clinical photography had the highest diagnostic accuracy.

CONCLUSIONS

AI-based detection using clinical photography shows a high DOR and is easily accessible in the current era with billions of phone subscribers globally. This indicates that there is significant potential for AI to enhance the diagnostic capabilities of general practitioners to the level of specialists by utilizing clinical photographs, without the need for expensive specialized imaging equipment.

High-sensitive and rapid electrochemical detection of miRNA-31 in saliva using Cas12a-based 3D nano-harvester with improved trans-cleavage efficiency

Salivary miRNA-31 is a reliable diagnostic marker for early-stage oral squamous cell carcinoma (OSCC), but accurate detection of miRNA-31 in saliva samples is a challenge because of its low level and high sequence homology. The CRISPR/Cas12a system has the exceptional potential to enable simple nucleic acid analysis but suffers from low speed and sensitivity. To achieve rapid and high-sensitive detection of miRNA-31 using the CRISPR/Cas12a system, a Cas12a-based nano-harvester activated by a polymerase-driven DNA walker, named as dual 3D nanorobots, was developed. The target walked rapidly on the surface of DNA hairpin-modified magnetic nanoparticles driven by DNA polymerase, generating numerous double-strand DNA (dsDNA). Then, the Cas12a bound to the generated dsDNA for activating its trans-cleavage activity, forming 3D nano-harvester. Subsequently, the harvester cut and released methylene blue-labeled DNA hairpins immobilized on the sensing interface, leading to the change in electrochemical signal. We found that the trans-cleavage activity of the harvester was higher than the conventional CRISPR/Cas12a system. The developed dual 3D nanorobots could enable rapid (detection time within 60 min), high-sensitive (detection limit of femtomolar), and specific analysis of miRNA-31 in saliva samples. Thus, our established electrochemical biosensing strategy has great potential for early diagnosis of OSCC.

Oral Cancer Prediction Using a Probability Neural Network (PNN)

OBJECTIVE

In India, usually, oral cancer is mostly identified at a progressive stage of malignancy. Hence, we are motivated to identify oral cancer in its early stages, which helps to increase the lifetime of the patient, but this early detection is also more challenging.

METHODS

The proposed research work uses a probabilistic neural network (PNN) for the prediction of oral malignancy. The recommended work uses PNN along with the discrete wavelet transform to predict the cancer cells accurately. The classification accuracy of the PNN model is 80%, and hence this technique is best for the prediction of oral cancer.

RESULT

Due to heterogeneity in the appearance of oral lesions, it is difficult to identify the cancer region. This research work explores the different computer vision techniques that help in the prediction of oral cancer.

CONCLUSION

Oral screening is important in making a decision about oral lesions and also in avoiding delayed referrals, which reduces mortality rates.

Identification of Healthy Tissue from Malignant Tissue in Surgical Margin Using Raman Spectroscopy in Oral Cancer Surgeries

Accurate identification of tissue types in surgical margins is essential for ensuring the complete removal of cancerous cells and minimizing the risk of recurrence. The objective of this study was to explore the clinical utility of Raman spectroscopy for the detection of oral squamous cell carcinoma (OSCC) in both tumor and healthy tissues obtained from surgical resection specimens during surgery. This study enrolled a total of 64 patients diagnosed with OSCC. Among the participants, approximately 50% of the cases were classified as the most advanced stage, referred to as T4. Raman experiments were conducted on cryopreserved tissue samples collected from patients diagnosed with OSCC. Prominent spectral regions containing key oral biomarkers were analyzed using the partial least squares-support vector machine (PLS-SVM) method, which is a powerful multivariate analysis technique for discriminant analysis. This approach effectively differentiated OSCC tissue from non-OSCC tissue, achieving a sensitivity of 95.7% and a specificity of 93.3% with 94.7% accuracy. In the current study, Raman analysis of fresh tissue samples showed that OSCC tissues contained significantly higher levels of nucleic acids, proteins, and several amino acids compared to the adjacent healthy tissues. In addition to differentiating between OSCC and non-OSCC tissues, we have also explored the potential of Raman spectroscopy in classifying different stages of OSCC. Specifically, we have investigated the classification of T1, T2, T3, and T4 stages based on their Raman spectra. These findings emphasize the importance of considering both stage and subsite factors in the application of Raman spectroscopy for OSCC analysis. Future work will focus on expanding our tissue sample collection to better comprehend how different subsites influence the Raman spectra of OSCC at various stages, aiming to improve diagnostic accuracy and aid in identifying tumor-free margins during surgical interventions.

Autofluorescence Image-Guided Endoscopy in the Management of Upper Aerodigestive Tract Tumors

At this juncture, autofluorescence and narrow-band imaging have resurfaced in the medicine arena in parallel with current technology advancement. The emergence of newly developed optical instrumentation in addition to the discovery of new fluorescence biomolecules have contributed to a refined management of diseases and tumors, especially in the management of upper aerodigestive tract tumors. The advancement in multispectral imaging and micro-endoscopy has also escalated the trends further in the setting of the management of this tumor, in order to gain not only the best treatment outcomes but also facilitate early tumor diagnosis. This includes the usage of autofluorescence endoscopy for screening, diagnosis and treatment of this tumor. This is crucial, as microtumoral deposit at the periphery of the gross tumor can be only assessed via an enhanced endoscopy and even more precisely with autofluorescence endoscopic techniques. Overall, with this new technique, optimum management can be achieved for these patients. Hence, the treatment outcomes can be improved and patients are able to attain better prognosis and survival.

Applicability of autofluorescence and fluorescent probes in the trans-surgical of oral carcinomas: A systematic review

Oral cancer represents an important health problem, as it is the sixth most common type of cancer in the world and is associated with high rates of morbidity and mortality. The treatment considered the gold standard for this type of tumor is surgical resection with negative margins, with a distance of at least 5 mm from the tumor. This procedure is strongly associated with local control and disease-specific survival, however, in many cases, large amounts of healthy tissue are removed, resulting in surgical defects, compromising various functions and directly affecting the individual's quality of life. From this perspective, this systematic review aimed to evaluate the use of autofluorescence and fluorescent probes as potential adjuvant techniques to facilitate the delineation of surgical margins for oral cancers. A comprehensive search was performed in Pubmed, Scopus, Web of Science, LIVIVO, Embase, ProQuest Open Access Dissertations & Theses, Open Access Theses and Dissertations, and DART Europe databases, where 1948 articles were found. After the different stages of critical evaluation, 15 articles were selected, eligible for the inclusion criteria. Of these, 7 articles used autofluorescence, 7 used fluorescent probes and 1 article used both methods. As for autofluorescence, the most used device was the VELScope, and indocyanine green was the most used probe. Compared to histopathology, autofluorescence did not obtain significant and/or superiors results. In contrast to fluorescent probes that, most articles showed a good performance of margins during surgical resection, making them a promising alternative. However, it is still necessary to carry out the analysis of more articles, with more significant samples and sensitivity and specificity data to qualify the results.

Field validation of deep learning based Point-of-Care device for early detection of oral malignant and potentially malignant disorders

Early detection of oral cancer in low-resource settings necessitates a Point-of-Care screening tool that empowers Frontline-Health-Workers (FHW). This study was conducted to validate the accuracy of Convolutional-Neural-Network (CNN) enabled m(mobile)-Health device deployed with FHWs for delineation of suspicious oral lesions (malignant/potentially-malignant disorders). The effectiveness of the device was tested in tertiary-care hospitals and low-resource settings in India. The subjects were screened independently, either by FHWs alone or along with specialists. All the subjects were also remotely evaluated by oral cancer specialist/s. The program screened 5025 subjects (Images: 32,128) with 95% (n = 4728) having telediagnosis. Among the 16% (n = 752) assessed by onsite specialists, 20% (n = 102) underwent biopsy. Simple and complex CNN were integrated into the mobile phone and cloud respectively. The onsite specialist diagnosis showed a high sensitivity (94%), when compared to histology, while telediagnosis showed high accuracy in comparison with onsite specialists (sensitivity: 95%; specificity: 84%). FHWs, however, when compared with telediagnosis, identified suspicious lesions with less sensitivity (60%). Phone integrated, CNN (MobileNet) accurately delineated lesions (n = 1416; sensitivity: 82%) and Cloud-based CNN (VGG19) had higher accuracy (sensitivity: 87%) with tele-diagnosis as reference standard. The results of the study suggest that an automated mHealth-enabled, dual-image system is a useful triaging tool and empowers FHWs for oral cancer screening in low-resource settings.

Raman Spectral Characterization of Urine for Rapid Diagnosis of Acute Kidney Injury

Acute kidney injury (AKI) is a common syndrome characterized by various etiologies and pathophysiologic processes that deteriorate kidney function. The aim of this study is to identify potential biomarkers in the urine of non-acute kidney injury (non-AKI) and AKI patients through Raman spectroscopy (RS) to predict the advancement in complications and kidney failure. Selected spectral regions containing prominent peaks of renal biomarkers were subjected to partial least squares linear discriminant analysis (PLS-LDA). This discriminant analysis classified the AKI patients from non-AKI subjects with a sensitivity and specificity of 97% and 100%, respectively. In this study, the RS measurements of urine specimens demonstrated that AKI had significantly higher nitrogenous compounds, porphyrin, tryptophan and neopterin when compared with non-AKI. This study’s specific spectral information can be used to design an in vivo RS approach for the detection of AKI diseases.

Machine learning in point-of-care automated classification of oral potentially malignant and malignant disorders: a systematic review and meta-analysis

Machine learning (ML) algorithms are becoming increasingly pervasive in the domains of medical diagnostics and prognostication, afforded by complex deep learning architectures that overcome the limitations of manual feature extraction. In this systematic review and meta-analysis, we provide an update on current progress of ML algorithms in point-of-care (POC) automated diagnostic classification systems for lesions of the oral cavity. Studies reporting performance metrics on ML algorithms used in automatic classification of oral regions of interest were identified and screened by 2 independent reviewers from 4 databases. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. 35 studies were suitable for qualitative synthesis, and 31 for quantitative analysis. Outcomes were assessed using a bivariate random-effects model following an assessment of bias and heterogeneity. 4 distinct methodologies were identified for POC diagnosis: (1) clinical photography; (2) optical imaging; (3) thermal imaging; (4) analysis of volatile organic compounds. Estimated AUROC across all studies was 0.935, and no difference in performance was identified between methodologies. We discuss the various classical and modern approaches to ML employed within identified studies, and highlight issues that will need to be addressed for implementation of automated classification systems in screening and early detection.

Applications of Laser-Induced Fluorescence in Medicine

Fluorescence is the most sensitive spectroscopic method of analysis and fluorescence methods. However, classical analysis requires sampling. There are new needs for real-time analyses of biological materials, without the need for sampling. This article presents examples of proprietary applications of laser-induced fluorescence (LIF) in medicine with such methods. A classic example is the analysis of photosensitizers using the photodynamic treatment method (PDT). The level and kinetics of accumulation and excretion of sensitizers in the body are examined, as well as the optimal exposure time after the application of compounds. The LIF method is also used to analyze endogenous fluorophores; it has been used to detect neoplasms, e.g., lung cancer or gynecological and dermatological diseases. Furthermore, it is used for the diagnosis of early stages of tooth decay or detection of fungi. The article will present the construction of sensors based on the LIF method—fiber laser spectrometers and investigated fluorescence spectra in individual applications. Examples of fluorescence imaging, e.g., dermatological, and dental diagnostics and measuring systems will be presented. The advantage of the method is it has greater sensitivity and easily detects lesions early compared to the methods used in observing the material in reflected light.

Developing an Algorithm for Discriminating Oral Cancerous and Normal Tissues Using Raman Spectroscopy

The aim of this study was to investigate the clinical potential of Raman spectroscopy (RS) in detecting oral squamous cell carcinoma (OSCC) in tumor and healthy tissues in surgical resection specimens during surgery. Raman experiments were performed on cryopreserved specimens from patients with OSCC. Univariate and multivariate analysis was performed based on the fingerprint region (700-1800 cm-1) of the Raman spectra. One hundred thirty-one ex-vivo Raman experiments were performed on 131 surgical resection specimens obtained from 67 patients. The principal component analysis (PCA) and partial least square (PLS) methods with linear discriminant analysis (LDA) were applied on an independent validation dataset. Both models were able to differentiate between the tissue types, but PLS-LDA showed 100% accuracy, sensitivity, and specificity. In this study, Raman measurements of fresh resection tissue specimens demonstrated that OSCC had significantly higher nucleic acid, protein, and several amino acid contents than adjacent healthy tissues. The specific spectral information obtained in this study can be used to develop an in vivo Raman spectroscopic method for the tumor-free resection boundary during surgery.

Autofluorescence imaging of Barrett's esophageal lesions with additional transformation into spatial images of green autofluorescence intensity

BACKGROUND

 Early diagnosis of patients with Barrett's esophagus is required to  implement appropriate treatment to prevent neoplastic disease development. In  this work, we examined the usefulness of autofluorescence imaging as a method to increase the sensitivity of targeted biopsy under numerical color value control with  the additional conversion of autofluorescence images into spatial green autofluorescence intensity images.

METHODS

148 patients were included in the study. Autofluorescence imaging was used in each endoscopic examination. The obtained images of lesions were transformed with Image Pro PLUS 5.0.2 software to show the points of lesions with the highest values of numerical color value and the lowest green intensity. The obtained results were analyzed statistically using Statistica 8.0 software. Mann-Whitney U test was used to compare red to green ratio, red fluorescence intensity and green color intensity between the examined groups of lesions.

RESULTS

 Thanks to targeted biopsy under the control of red to green ratio factor and green autofluorescence intensity, this imaging method's sensitivity was also increased in all studied stages of histopathological dysplasia in Barrett's esophagus. In total analysis, the sensitivity of tri-modal imaging with the analysis of green autofluorescence intensity was almost 97%. The spatial maps of autofluorescence intensity significantly improved the effectiveness of biopsies performed to take tissue samples for a histopathological examination compared to white light endoscopy. The extension of autofluorescence to spatial autofluorescence intensity maps significantly reduced the percentage of false-negative results.

CONCLUSIONS

 The study results indicate that autofluorescence imaging allows for assessing the extent of dysplasia lesions and determining the margin of healthy and pathologically effected tissues. Our team's method to convert autofluorescence images into spatial images of green autofluorescence intensity further increased the sensitivity of the study.

Machine-Learning Assisted Discrimination of Precancerous and Cancerous from Healthy Oral Tissue Based on Multispectral Autofluorescence Lifetime Imaging Endoscopy

Multispectral autofluorescence lifetime imaging (maFLIM) can be used to clinically image a plurality of metabolic and biochemical autofluorescence biomarkers of oral epithelial dysplasia and cancer. This study tested the hypothesis that maFLIM-derived autofluorescence biomarkers can be used in machine-learning (ML) models to discriminate dysplastic and cancerous from healthy oral tissue. Clinical widefield maFLIM endoscopy imaging of cancerous and dysplastic oral lesions was performed at two clinical centers. Endoscopic maFLIM images from 34 patients acquired at one of the clinical centers were used to optimize ML models for automated discrimination of dysplastic and cancerous from healthy oral tissue. A computer-aided detection system was developed and applied to a set of endoscopic maFLIM images from 23 patients acquired at the other clinical center, and its performance was quantified in terms of the area under the receiver operating characteristic curve (ROC-AUC). Discrimination of dysplastic and cancerous from healthy oral tissue was achieved with an ROC-AUC of 0.81. This study demonstrates the capabilities of widefield maFLIM endoscopy to clinically image autofluorescence biomarkers that can be used in ML models to discriminate dysplastic and cancerous from healthy oral tissue. Widefield maFLIM endoscopy thus holds potential for automated in situ detection of oral dysplasia and cancer.

Fluorescence Guided Surgery

Fluorescence guided surgery (FGS) is an imaging technique that allows the surgeon to visualise different structures and types of tissue during a surgical procedure that may not be as visible under white light conditions. Due to the many potential advantages of fluorescence guided surgery compared to more traditional clinical imaging techniques such as its higher contrast and sensitivity, less subjective use, and ease of instrument operation, the research interest in fluorescence guided surgery continues to grow over various key aspects such as fluorescent probe development and surgical system development as well as its potential clinical applications. This review looks to summarise some of the emerging opportunities and developments that have already been made in fluorescence guided surgery in recent years while highlighting its advantages as well as limitations that need to be overcome in order to utilise the full potential of fluorescence within the surgical environment.

Correlation between Autofluorescence Intensity and Histopathological Features in Non-Melanoma Skin Cancer: An Ex Vivo Study

Simple Summary

Non-melanoma skin cancers (NMSC) are the most prevalent neoplasms worldwide, especially in the Caucasian population. Radical surgical excision is considered the therapeutic gold standard, while incomplete tumor removal is invariably associated with recurrence and the need for reintervention. Autofluorescence (AF) spectroscopy has recently been investigated for early diagnosis of NMSC and assessment of tumor margins. Understanding changes in AF intensity in association with peculiar histological features could improve the diagnostic accuracy of skin fluorescence spectroscopy. The main goal of our work was to investigate the correlation between the intensity of cutaneous AF and the histopathological features of NMSC. The intensity of fluorescence emission in tissues obtained from NMSC samples was approximately 4 times lower than that in healthy conditions. In fact, mean AF intensity for BCC group was 4.5 and 4.4 for SCCs, with further variability being recorded according to histopathologic subtypes. Histopathological features such as hyperkeratosis, neoangiogenesis, fibrosis and elastosis are statistically associated with a decrease in AF intensity. Our data suggest that such tissue alterations could be responsible for the difference in AF emission between neoplastic and healthy tissue. These results support the potential application of AF as a useful non-invasive diagnostic tool for NMSCs.

Abstract

Non-melanoma skin cancer (NMSC) is the most common malignant tumor affecting fair-skinned people. Increasing incidence rates of NMSC have been reported worldwide, which is an important challenge in terms of public health management. Surgical excision with pre-operatively identified margins is one of the most common and effective treatment strategies. Incomplete tumor removal is associated with a very high risk of recurrence and re-excision. Biological tissues can absorb and re-emit specific light wave-lengths, detectable through spectrophotometric devices. Such a phenomenon is known as autofluorescence (AF). AF spectroscopy has been widely explored for non-invasive, early detection of NMSC as well as for evaluation of surgical margins before excision. Fluorescence-aided diagnosis is based on differences in spectral characteristics between healthy and neoplastic skin. Understanding the biological basis of such differences and correlating AF intensity to histological features could improve the diagnostic accuracy of skin fluorescence spectroscopy. The primary objective of the present pre-clinical ex vivo study is to investigate the correlation between the intensity of cutaneous AF and the histopathological features of NMSC. Ninety-eight lesions suggestive for NMSCs were radically excised from 75 patients (46 M; 29 F; mean age: 79 years). After removal, 115 specific reference points on lesions (“cases”; 59 on BBC, 53 on SCC and 3 on other lesions) and on peri-lesional healthy skin (controls; 115 healthy skin) were identified and marked through suture stitches. Such reference points were irradiated at 400–430 nm wavelength, and resulting emission AF spectra were acquired through spectrophotometry. For each case, AFIR (autofluorescence intensity ratio) was measured as the ratio between the number of photons emitted at a wavelength ranging between 450 and 700 nm (peak: 500 nm) in the healthy skin and that was captured in the pathological tissue. At the histological level, hyperkeratosis, neoangiogenesis, cellular atypia, epithelial thickening, fibrosis and elastosis were quantified by light microscopy and were assessed through a previously validated grading system. Statistical correlation between histologic variables and AFIR was calculated through linear regression. Spectrometric evaluation was performed on 230 (115 cases + 115 controls) reference points. The mean AFIR for BCC group was 4.5, while the mean AFIR for SCC group was 4.4 and the fluorescence peaks at 500 nm were approximately 4 times lower (hypo-fluorescent) in BCCs and in SCCs than in healthy skin. Histological variables significantly associated with alteration of AFIR were fibrosis and elastosis (p < 0.05), neoangiogenesis, hyperkeratosis and epithelial thickening. Cellular atypia was not significantly associated with alteration of AFIR. The intensity of fluorescence emission in neoplastic tissues was approximately 4 times lower than that in healthy tissues. Histopathological features such as hyperkeratosis, neoangiogenesis, fibrosis and elastosis are statistically associated with the decrease in AFIR. We hypothesize that such tissue alterations are among the possible biophysical and biochemical bases of difference in emission AF between neoplastic and healthy tissue. The results of the present evaluation highlighted the possible usefulness of autofluorescence as diagnostic, non-invasive and real-time tool for NMSCs.

Band-Selection of a Portal LED-Induced Autofluorescence Multispectral Imager to Improve Oral Cancer Detection

This aim of this study was to find effective spectral bands for the early detection of oral cancer. The spectral images in different bands were acquired using a self-made portable light-emitting diode (LED)-induced autofluorescence multispectral imager equipped with 365 and 405 nm excitation LEDs, emission filters with center wavelengths of 470, 505, 525, 532, 550, 595, 632, 635, and 695 nm, and a color image sensor. The spectral images of 218 healthy points in 62 healthy participants and 218 tumor points in 62 patients were collected in the ex vivo trials at China Medical University Hospital. These ex vivo trials were similar to in vivo because the spectral images of anatomical specimens were immediately acquired after the on-site tumor resection. The spectral images associated with red, blue, and green filters correlated with and without nine emission filters were quantized by four computing method, including summated intensity, the highest number of the intensity level, entropy, and fractional dimension. The combination of four computing methods, two excitation light sources with two intensities, and 30 spectral bands in three experiments formed 264 classifiers. The quantized data in each classifier was divided into two groups: one was the training group optimizing the threshold of the quantized data, and the other was validating group tested under this optimized threshold. The sensitivity, specificity, and accuracy of each classifier were derived from these tests. To identify the influential spectral bands based on the area under the region and the testing results, a single-layer network learning process was used. This was compared to conventional rules-based approaches to show its superior and faster performance. Consequently, four emission filters with the center wavelengths of 470, 505, 532, and 550 nm were selected by an AI-based method and verified using a rule-based approach. The sensitivities of six classifiers using these emission filters were more significant than 90%. The average sensitivity of these was about 96.15%, the average specificity was approximately 69.55%, and the average accuracy was about 82.85%.

A Cytological Study Enlightening the Unseen Effects of Concomitant Chemoradiotherapy in Contralateral Normal Buccal Mucosa of Oral Squamous Cell Carcinoma Patients

Background/objectives In patients receiving concomitant chemoradiotherapy (CCRT) as a treatment for oral squamous cell carcinoma (OSCC), cytological changes were seen not only in neoplastic epithelial cells but the non-neoplastic epithelial cells are also affected, resulting in cytopathological atypical changes. The present study was designed to observe oral epithelial atypical cytopathologic changes induced in contralateral normal buccal mucosa in OSCC patients receiving CCRT. Methods The study included 150 patients with OSCC treated by CCRT whose details were collected from the Institute of Nuclear Medicine and Oncology Lahore (INMOL) Hospital Lahore. Cytological smears were obtained from the contralateral normal buccal mucosa of OSCC patients. The serial scrape smears were taken before, immediately after, on the 17th day (mid of treatment), and at the end of CCRT, whereas 20 patients were taken as normal healthy controls and were not exposed to CCRT. The smears were stained with hematoxylin and eosin and Papanicolaou stain. SPSS version 20 (Armonk, NY: IBM Corp.) was used for statistical analysis and p > 0.05 was considered to be significant. Results CCRT-induced oral epithelial atypical cytological changes were predominantly noted at end of therapy (19.7%) in the contralateral normal buccal mucosa. Nuclear atypia features were higher on the 17th day and end of treatment; whereas, epithelial atypia was mainly observed on the 17th day of CCRT (40%). A highly significant association was observed between epithelial atypia and radio-chemotherapy dose (p = 0.045), between CCRT-induced epithelial atypical cytological changes and days of treatment (p = 0.001), and between days of CCRT and nuclear atypia (0.000) accordingly. Atypia was not observed in any control group. Conclusion Varying degrees of oral epithelial atypical cytological changes may occur in otherwise normal contralateral mucosa of the patients receiving CCRT.

Novel Quantitative Analysis Using Optical Imaging (VELscope) and Spectroscopy (Raman) Techniques for Oral Cancer Detection

In this study, we developed a novel quantitative analysis method to enhance the detection capability for oral cancer screening. We combined two different optical techniques, a light-based detection technique (visually enhanced lesion scope) and a vibrational spectroscopic technique (Raman spectroscopy). Materials and methods: Thirty-five oral cancer patients who went through surgery were enrolled. Thirty-five cancer lesions and thirty-five control samples with normal oral mucosa (adjacent to the cancer lesion) were analyzed. Thirty-five autofluorescence images and 70 Raman spectra were taken from 35 cancer and 35 control group cryopreserved samples. The normalized intensity and heterogeneity of the 70 regions of interest (ROIs) were calculated along with 70 averaged Raman spectra. Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) were used with principal component analysis (PCA) to differentiate the cancer and control groups (normal). The classifications rates were validated using two different validation methods, leave-one-out cross-validation (LOOCV) and k-fold cross-validation. Results: The cryopreserved normal and tumor tissues were differentiated using the PCA-LDA and PCA-QDA models. The PCA-LDA of Raman spectroscopy (RS) had 82.9% accuracy, 80% sensitivity, and 85.7% specificity, while ROIs on the autofluorescence images were differentiated with 90% accuracy, 100% sensitivity, and 80% specificity. The combination of two optical techniques differentiated cancer and normal group with 97.14% accuracy, 100% sensitivity, and 94.3% specificity. Conclusion: In this study, we combined the data of two different optical techniques. Furthermore, PCA-LDA and PCA-QDA quantitative analysis models were used to differentiate tumor and normal groups, creating a complementary pathway for efficient tumor diagnosis. The error rates of RS and VELcope analysis were 17.10% and 10%, respectively, which was reduced to 3% when the two optical techniques were combined.

Healthcare Professional in the Loop (HPIL): Classification of Standard and Oral Cancer-Causing Anomalous Regions of Oral Cavity Using Textural Analysis Technique in Autofluorescence Imaging

Oral mucosal lesions (OML) and oral potentially malignant disorders (OPMDs) have been identified as having the potential to transform into oral squamous cell carcinoma (OSCC). This research focuses on the human-in-the-loop-system named Healthcare Professionals in the Loop (HPIL) to support diagnosis through an advanced machine learning procedure. HPIL is a novel system approach based on the textural pattern of OML and OPMDs (anomalous regions) to differentiate them from standard regions of the oral cavity by using autofluorescence imaging. An innovative method based on pre-processing, e.g., the Deriche-Canny edge detector and circular Hough transform (CHT); a post-processing textural analysis approach using the gray-level co-occurrence matrix (GLCM); and a feature selection algorithm (linear discriminant analysis (LDA)), followed by k-nearest neighbor (KNN) to classify OPMDs and the standard region, is proposed in this paper. The accuracy, sensitivity, and specificity in differentiating between standard and anomalous regions of the oral cavity are 83%, 85%, and 84%, respectively. The performance evaluation was plotted through the receiver operating characteristics of periodontist diagnosis with the HPIL system and without the system. This method of classifying OML and OPMD areas may help the dental specialist to identify anomalous regions for performing their biopsies more efficiently to predict the histological diagnosis of epithelial dysplasia.