Tumor histoculture captures the dynamic interactions between tumor and immune components in response to anti-PD1 in head and neck cancer.

Dynamic interactions within the tumor micro-environment drive patient response to immune checkpoint inhibitors. Existing preclinical models lack true representation of this complexity. Using a Head and Neck cancer patient derived TruTumor histoculture platform, the response spectrum of 70 patients to anti-PD1 treatment is investigated in this study. With a subset of 55 patient samples, multiple assays to characterize T-cell reinvigoration and tumor cytotoxicity are performed. Based on levels of these two response parameters, patients are stratified into five sub-cohorts, with the best responder and non-responder sub-cohorts falling at extreme ends of the spectrum. The responder sub-cohort exhibits high T-cell reinvigoration, high tumor cytotoxicity with T-cells homing into the tumor upon treatment whereas immune suppression and tumor progression pathways are pre-dominant in the non-responders. Some moderate responders benefit from combination of anti-CTLA4 with anti-PD1, which is evident from better cytotoxic T-cell: T-regulatory cell ratio and enhancement of tumor cytotoxicity. Baseline and on-treatment gene expression signatures from this study stratify responders and non-responders in unrelated clinical datasets.

Contrasting clinical outcomes and socio-economic impact of young versus elderly-onset oral squamous cell carcinoma, a novel health economic analysis.

OBJECTIVES: The incidence of young-onset oral squamous cell carcinoma (OSCC) is growing, even among non-smokers/drinkers. The effects of adverse histopathological features on long-term oncologic outcomes between the young and old are controversial and confounded by significant heterogeneity. Few studies have evaluated the socio-economic impact of premature mortality from OSCC. Our study seeks to quantify these differences and their economic impact on society. MATERIALS AND METHODS: Four hundred and seventy-eight young (<45 years) and 1660 old patients (≥45 years) with OSCC were studied. Logistic regression determined predictors of recurrence and death. Survival analysis was calculated via the Kaplan-Meier method. A separate health economic analysis was conducted for India and Singapore. Years of Potential Productive Life Lost (YPPLL) were estimated with the Human Capital Approach, and premature mortality cost was derived using population-level data. RESULTS: Adverse histopathological features were seen more frequently in young OSCC: PNI (42.9% vs. 35%, p = 0.002), LVI (22.4% vs. 17.3%, p = 0.013) and ENE (36% vs. 24.5%, p < 0.001). Although 5-year OS/DSS were similar, the young cohort had received more intensive adjuvant therapy (CCRT 26.9% vs. 16.6%, p < 0.001). Among Singaporean males, the premature mortality cost per death was US $396,528, and per YPPLL was US $45,486. This was US $397,402 and US $38,458 for females. Among Indian males, the premature mortality cost per death was US $30,641, and per YPPLL was US $595. This was US $ 21,038 and US $305 for females. CONCLUSION: Young-onset OSCC is an aggressive disease, mitigated by the ability to receive intensive adjuvant treatment. From our loss of productivity analysis, the socio-economic costs from premature mortality are substantial. Early cancer screening and educational outreach campaigns should be tailored to this cohort. Alongside, more funding should be diverted to genetic research, developing novel biomarkers and improving the efficacy of adjuvant treatment in OSCC.

Improving accuracy in nodal staging of oral cancer: Proposal of a new system.

BACKGROUND: Despite introduction of extranodal extension (ENE) into the AJCC 8th edition of oral cancer staging, previous criticisms persist, such as limited discrimination between sub-stages and doubtful prognostic value of contralateral nodal disease. The purpose of this study was to compare our novel nodal staging system, based on the number of positive nodes and ENE, to the AJCC staging system in surgically treated patients. METHODS: Retrospective analysis of 4710 patients with oral squamous cell carcinoma (OSCC) treated with surgery±adjuvant therapy in 8 institutions in Australia, North America and Asia. With overall survival (OS) and disease specific survival (DSS) as endpoint, the prognostic performance of AJCC 8th and 7th editions were compared using hazard consistency, hazard discrimination, likelihood difference and balance. RESULTS: Our new nodal staging system (PN) a progressive and linear increase in hazard ratio (HR) from pN0 to pN3, with good separation of Kaplan Meier curves. Using the predetermined criteria for evaluation of a staging system, our proposed staging model outperformed AJCC 8th and 7th editions in prediction of OS and DSS. CONCLUSION: PN was the lymph node staging system that provided the most accurate prediction of OS and DSS for patients in our cohort of OSCC. Additionally, it can be easily adopted, addresses the shortcomings of the existing systems and should be considered for future editions of the TNM staging system.

Inter-observer agreement among specialists in the diagnosis of oral potentially malignant disorders and oral cancer using store-and-forward technology.

OBJECTIVES: Oral cancer is a leading cause of morbidity and mortality. Screening and mobile Health (mHealth)-based approach facilitates early detection remotely in a resource-limited settings. Recent advances in eHealth technology have enabled remote monitoring and triage to detect oral cancer in its early stages. Although studies have been conducted to evaluate the diagnostic efficacy of remote specialists, to our knowledge, no studies have been conducted to evaluate the consistency of remote specialists. The aim of this study was to evaluate interobserver agreement between specialists through telemedicine systems in real-world settings using store-and-forward technology. MATERIALS AND METHODS: The two remote specialists independently diagnosed clinical images (n=822) from image archives. The onsite specialist diagnosed the same participants using conventional visual examination, which was tabulated. The diagnostic accuracy of two remote specialists was compared with that of the onsite specialist. Images that were confirmed histopathologically were compared with the onsite diagnoses and the two remote specialists. RESULTS: There was moderate agreement (k= 0.682) between two remote specialists and (k= 0.629) between the onsite specialist and two remote specialists in the diagnosis of oral lesions. The sensitivity and specificity of remote specialist 1 were 92.7% and 83.3%, respectively, and those of remote specialist 2 were 95.8% and 60%, respectively, each compared with histopathology. CONCLUSION: The diagnostic accuracy of the two remote specialists was optimal, suggesting that "store and forward" technology and telehealth can be an effective tool for triage and monitoring of patients. CLINICAL RELEVANCE: Telemedicine is a good tool for triage and enables faster patient care in real-world settings.

CD44-SNA1 integrated cytopathology for delineation of high grade dysplastic and neoplastic oral lesions.

The high prevalence of oral potentially-malignant disorders exhibits diverse severity and risk of malignant transformation, which mandates a Point-of-Care diagnostic tool. Low patient compliance for biopsies underscores the need for minimally-invasive diagnosis. Oral cytology, an apt method, is not clinically applicable due to a lack of definitive diagnostic criteria and subjective interpretation. The primary objective of this study was to identify and evaluate the efficacy of biomarkers for cytology-based delineation of high-risk oral lesions. A comprehensive systematic review and meta-analysis of biomarkers recognized a panel of markers (n: 10) delineating dysplastic oral lesions. In this observational cross sectional study, immunohistochemical validation (n: 131) identified a four-marker panel, CD44, Cyclin D1, SNA-1, and MAA, with the best sensitivity (>75%; AUC>0.75) in delineating benign, hyperplasia, and mild-dysplasia (Low Risk Lesions; LRL) from moderate-severe dysplasia (High Grade Dysplasia: HGD) along with cancer. Independent validation by cytology (n: 133) showed that expression of SNA-1 and CD44 significantly delineate HGD and cancer with high sensitivity (>83%). Multiplex validation in another cohort (n: 138), integrated with a machine learning model incorporating clinical parameters, further improved the sensitivity and specificity (>88%). Additionally, image automation with SNA-1 profiled data set also provided a high sensitivity (sensitivity: 86%). In the present study, cytology with a two-marker panel, detecting aberrant glycosylation and a glycoprotein, provided efficient risk stratification of oral lesions. Our study indicated that use of a two-biomarker panel (CD44/SNA-1) integrated with clinical parameters or SNA-1 with automated image analysis (Sensitivity >85%) or multiplexed two-marker panel analysis (Sensitivity: >90%) provided efficient risk stratification of oral lesions, indicating the significance of biomarker-integrated cytopathology in the development of a Point-of-care assay.

Inter-observer agreement among specialists in the diagnosis of Oral Potentially Malignant Disorders and Oral Cancer using Store-and-Forward technology.

Oral Cancer is one of the most common causes of morbidity and mortality. Screening and mobile Health (mHealth) based approach facilitates remote early detection of Oral cancer in a resource-constrained settings. The emerging eHealth technology has aided specialist reach to rural areas enabling remote monitoring and triaging to downstage Oral cancer. Though the diagnostic accuracy of the remote specialist has been evaluated, there are no studies evaluating the consistency among the remote specialists, to the best of our knowledge. The purpose of the study was to evaluate the interobserver agreement between the specialists through telemedicine systems in real-world settings using store and forward technology. Two remote specialists independently diagnosed the clinical images from image repositories, and the diagnostic accuracy was compared with onsite specialist and histopathological diagnosis when available. Moderate agreement (k = 0.682) between two remote specialists and (k = 0.629) between the onsite specialist and two remote specialists in diagnosing oral lesions. The sensitivity and specificity of remote specialist 1 were 92.7% and 83.3%, whereas remote specialist 2 was 95.8% and 60%, respectively, compared to histopathology. The store and forward technology and telecare can be effective tools in triaging and surveillance of patients.

Interpretable and Reliable Oral Cancer Classifier with Attention Mechanism and Expert Knowledge Embedding via Attention Map.

Convolutional neural networks have demonstrated excellent performance in oral cancer detection and classification. However, the end-to-end learning strategy makes CNNs hard to interpret, and it can be challenging to fully understand the decision-making procedure. Additionally, reliability is also a significant challenge for CNN based approaches. In this study, we proposed a neural network called the attention branch network (ABN), which combines the visual explanation and attention mechanisms to improve the recognition performance and interpret the decision-making simultaneously. We also embedded expert knowledge into the network by having human experts manually edit the attention maps for the attention mechanism. Our experiments have shown that ABN performs better than the original baseline network. By introducing the Squeeze-and-Excitation (SE) blocks to the network, the cross-validation accuracy increased further. Furthermore, we observed that some previously misclassified cases were correctly recognized after updating by manually editing the attention maps. The cross-validation accuracy increased from 0.846 to 0.875 with the ABN (Resnet18 as baseline), 0.877 with SE-ABN, and 0.903 after embedding expert knowledge. The proposed method provides an accurate, interpretable, and reliable oral cancer computer-aided diagnosis system through visual explanation, attention mechanisms, and expert knowledge embedding.

Isolated Infratemporal Fossa Desmoid Fibromatosis: A Rare Case Report and Review of Literature.

Desmoid fibromatosis (DF) arising from musculoaponeurotic structures rarely affects the head and neck region with the abdomen being the most common site of origin. These are benign tumors with locally infiltrative nature usually presenting as painless swellings that are rapidly growing. The infratemporal fossa DF is an extremely rare location with few clinical reports. This article discusses the management of a 2-year-old child with DF of the infratemporal fossa (ITF) along with literature review.

Exploring uncertainty measures in convolutional neural network for semantic segmentation of oral cancer images.

Significance: Oral cancer is one of the most prevalent cancers, especially in middle- and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output. Aim: We aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions. Approach: This work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists. Results: The proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings. Conclusions: Our study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model's prediction can be improved.

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.

Establishment and characterization of novel autologous pair cell lines from two Indian non­habitual tongue carcinoma patients.

Oral tongue squamous cell carcinoma (OTSCC) is one of the major causes of fatality in India due to very high percentage of patients with habits of smoking and chewing tobacco and associated products. Being highly heterogeneous in nature, every patient poses a different challenge clinically. To understand disease progression in an improved way, knowledge of cross­talk between tumor stroma and the tumor cells becomes indispensable. Patient­derived in vitro cell line models are helpful to understand the complexity of diseases. However, they have very low efficiency of establishment from the tumor samples, particularly the cancer­associated fibroblasts (CAFs). In the present study, two novel autologous pairs were immortalized spontaneously from non­habitual, HPV­positive patients, who presented with OTSCC. The epithelial and fibroblast cell lines had typical polygonal and spindle­shaped morphology, respectively. Positive staining with epithelial specific Pan­cytokeratin (PanCK) and fibroblast specific protein (FSP­1) further confirmed their epithelial and fibroblast origin. Unique Short Tandem Repeat (STR) profile of the cultures confirmed their novelty, while the similarity of the STR profiles between the epithelial and fibroblast cells from the same patient, confirmed their autologous nature. DNA analysis revealed aneuploidy of the established cultures. An increase in the tumorigenic potential of the established epithelial cultures upon treatment with CAF­conditioned medium proved the 'CAF­ness' of the established fibroblast cells. The established cultures are the first of their kind which would serve as a useful platform in understanding the tumor­stroma cross­talk in tongue cancer progression.

Thyroglobulin Levels in Patients who have Undergone Hemithyroidectomy for Differentiated Thyroid Cancer. An Assessment of Levels and Trends at a Tertiary Referral Centre.

Subramanian Kannan Serum thyroglobulin (Tg) and thyroglobulin antibody (TgAb) levels are used to monitor patients with differentiated thyroid cancer (DTC) after total thyroidectomy with or without radioiodine (RAI) ablation. However, they are also measured in patients who are treated with thyroid lobectomy (TL)/hemithyroidectomy (HT). Data on the levels of Tg and its trend in those undergoing TL/HT is sparse in India. We reviewed retrospective data of DTC patients who underwent TL/HT and were followed-up with postoperative Tg levels between 2015 and 2020. Out of 247 patients, 17 had undergone either TL or HT, which included papillary thyroid cancer ( n = 12), follicular thyroid cancer ( n = 4), and noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) in 1 patient. All patients with DTC had tumor size < 4 cm (T1/2, clinical N0, Mx). The median follow-up was 15 months (range, 1-125) and the median Tg level was 7.5 ng/mL (interquartile range [IQR]; 3.6, 7.5) and ranged from 0.9 to 36.7 ng/mL. The median thyroid-stimulating hormone (TSH) level was 2.03 IU/L (IQR; 1.21, 3.59) and it ranged from 0.05 to 8.54 IU/L. As of last follow-up, none of them underwent completion thyroidectomy; however, eight patients had a decline in Tg ranging from 8 to 64%, four patients had increase in Tg ranging from 14 to 145%, three patients had stable Tg, and one of them had an increase in TgAb titers. As per American Thyroid Association (ATA) response-to-treatment category, six patients had indeterminate response, five patients had biochemical incomplete response, four patients had excellent response, and two did not have follow-up Tg and TgAb levels. While absolute values of Tg were well below 30 ng/mL in almost all patients with HT/TL, the Tg trends were difficult to predict, and only 23% of patients were able to satisfy the criteria for "excellent response" on follow-up. We suggest keeping this factor in mind in follow-up and while counselling for HT in patients with low-risk DTC.

Risk Stratification in Oral Cancer: A Novel Approach.

Background: Oral squamous cell carcinoma (OSCC) is a common head and neck cancer with high morbidity and mortality. Currently, treatment decisions are guided by TNM staging, which omits important negative prognosticators such as lymphovascular invasion, perineural invasion (PNI), and histologic differentiation. We proposed nomogram models based on adverse pathological features to identify candidates suitable for treatment escalation within each risk group according to the National Comprehensive Cancer Network (NCCN) guidelines. Methods: Anonymized clinicopathologic data of OSCC patients from 5 tertiary healthcare institutions in Asia were divided into 3 risk groups according to the NCCN guidelines. Within each risk group, nomograms were built to predict overall survival based on histologic differentiation, histologic margin involvement, depth of invasion (DOI), extranodal extension, PNI, lymphovascular, and bone invasion. Nomograms were internally validated with precision-recall analysis and the Kaplan-Meier survival analysis. Results: Low-risk patients with positive pathological nodal involvement and/or positive PNI should be considered for adjuvant radiotherapy. Intermediate-risk patients with gross bone invasion may benefit from concurrent chemotherapy. High-risk patients with positive margins, high DOI, and a high composite score of histologic differentiation, PNI, and the American Joint Committee on Cancer (AJCC) 8th edition T staging should be considered for treatment escalation to experimental therapies in clinical trials. Conclusion: Nomograms built based on prognostic adverse pathological features can be used within each NCCN risk group to fine-tune treatment decisions for OSCC patients.

Incorporation of adverse features in advanced oral cancer improves precision in staging and patient prognostication.

BACKGROUND: Despite revised staging criteria, stratification of patients with advanced oral squamous cell carcinoma (OSCC) remains difficult. Well-established features like perineural invasion (PNI), differentiation, and lymphovascular-invasion (LVI) are controversial, and hence omitted from staging. We endeavor to better stratify this cohort by identifying predictors of survival in advanced OSCC (T3-4). METHODS: Seven hundred and forty-two patients with T3-4 OSCC underwent surgery from 2006 to 2013. Cox regression was performed to determine predictors of overall survival (OS). RESULTS: OS was adversely impacted by PNI (p = 0.046), LVI (p = 0.038), moderate/poor differentiation (p = 0.001), close/involved surgical margins (p = 0.002), pT (p = 0.034), and pN (p < 0.001). The cumulative number of adverse histopathological features predicted poorer OS; HR 2.64 (CI 1.42-4.90) for one adverse feature and HR 4.23 (CI 2.34-7.67) for ≥2. CONCLUSION: In advanced OSCC, stratification with histopathologic risk factors can predict survival even in maximally treated patients; adjuvant therapies are unable to entirely mitigate this risk. Incorporation of adverse features into future editions of TNM can improve precision in staging and identify candidates for treatment escalation.

Interpretable deep learning approach for oral cancer classification using guided attention inference network.

SIGNIFICANCE: Convolutional neural networks (CNNs) show the potential for automated classification of different cancer lesions. However, their lack of interpretability and explainability makes CNNs less than understandable. Furthermore, CNNs may incorrectly concentrate on other areas surrounding the salient object, rather than the network's attention focusing directly on the object to be recognized, as the network has no incentive to focus solely on the correct subjects to be detected. This inhibits the reliability of CNNs, especially for biomedical applications. AIM: Develop a deep learning training approach that could provide understandability to its predictions and directly guide the network to concentrate its attention and accurately delineate cancerous regions of the image. APPROACH: We utilized Selvaraju et al.'s gradient-weighted class activation mapping to inject interpretability and explainability into CNNs. We adopted a two-stage training process with data augmentation techniques and Li et al.'s guided attention inference network (GAIN) to train images captured using our customized mobile oral screening devices. The GAIN architecture consists of three streams of network training: classification stream, attention mining stream, and bounding box stream. By adopting the GAIN training architecture, we jointly optimized the classification and segmentation accuracy of our CNN by treating these attention maps as reliable priors to develop attention maps with more complete and accurate segmentation. RESULTS: The network's attention map will help us to actively understand what the network is focusing on and looking at during its decision-making process. The results also show that the proposed method could guide the trained neural network to highlight and focus its attention on the correct lesion areas in the images when making a decision, rather than focusing its attention on relevant yet incorrect regions. CONCLUSIONS: We demonstrate the effectiveness of our approach for more interpretable and reliable oral potentially malignant lesion and malignant lesion classification.

Bayesian deep learning for reliable oral cancer image classification.

In medical imaging, deep learning-based solutions have achieved state-of-the-art performance. However, reliability restricts the integration of deep learning into practical medical workflows since conventional deep learning frameworks cannot quantitatively assess model uncertainty. In this work, we propose to address this shortcoming by utilizing a Bayesian deep network capable of estimating uncertainty to assess oral cancer image classification reliability. We evaluate the model using a large intraoral cheek mucosa image dataset captured using our customized device from high-risk population to show that meaningful uncertainty information can be produced. In addition, our experiments show improved accuracy by uncertainty-informed referral. The accuracy of retained data reaches roughly 90% when referring either 10% of all cases or referring cases whose uncertainty value is greater than 0.3. The performance can be further improved by referring more patients. The experiments show the model is capable of identifying difficult cases needing further inspection.

Classification of imbalanced oral cancer image data from high-risk population.

SIGNIFICANCE: Early detection of oral cancer is vital for high-risk patients, and machine learning-based automatic classification is ideal for disease screening. However, current datasets collected from high-risk populations are unbalanced and often have detrimental effects on the performance of classification. AIM: To reduce the class bias caused by data imbalance. APPROACH: We collected 3851 polarized white light cheek mucosa images using our customized oral cancer screening device. We use weight balancing, data augmentation, undersampling, focal loss, and ensemble methods to improve the neural network performance of oral cancer image classification with the imbalanced multi-class datasets captured from high-risk populations during oral cancer screening in low-resource settings. RESULTS: By applying both data-level and algorithm-level approaches to the deep learning training process, the performance of the minority classes, which were difficult to distinguish at the beginning, has been improved. The accuracy of "premalignancy" class is also increased, which is ideal for screening applications. CONCLUSIONS: Experimental results show that the class bias induced by imbalanced oral cancer image datasets could be reduced using both data- and algorithm-level methods. Our study may provide an important basis for helping understand the influence of unbalanced datasets on oral cancer deep learning classifiers and how to mitigate.

Validation of a Point-of-Care Optical Coherence Tomography Device with Machine Learning Algorithm for Detection of Oral Potentially Malignant and Malignant Lesions.

Non-invasive strategies that can identify oral malignant and dysplastic oral potentially-malignant lesions (OPML) are necessary in cancer screening and long-term surveillance. Optical coherence tomography (OCT) can be a rapid, real time and non-invasive imaging method for frequent patient surveillance. Here, we report the validation of a portable, robust OCT device in 232 patients (lesions: 347) in different clinical settings. The device deployed with algorithm-based automated diagnosis, showed efficacy in delineation of oral benign and normal (n = 151), OPML (n = 121), and malignant lesions (n = 75) in community and tertiary care settings. This study showed that OCT images analyzed by automated image processing algorithm could distinguish the dysplastic-OPML and malignant lesions with a sensitivity of 95% and 93%, respectively. Furthermore, we explored the ability of multiple (n = 14) artificial neural network (ANN) based feature extraction techniques for delineation high grade-OPML (moderate/severe dysplasia). The support vector machine (SVM) model built over ANN, delineated high-grade dysplasia with sensitivity of 83%, which in turn, can be employed to triage patients for tertiary care. The study provides evidence towards the utility of the robust and low-cost OCT instrument as a point-of-care device in resource-constrained settings and the potential clinical application of device in screening and surveillance of oral cancer.

Mobile-based oral cancer classification for point-of-care screening.

SIGNIFICANCE: Oral cancer is among the most common cancers globally, especially in low- and middle-income countries. Early detection is the most effective way to reduce the mortality rate. Deep learning-based cancer image classification models usually need to be hosted on a computing server. However, internet connection is unreliable for screening in low-resource settings. AIM: To develop a mobile-based dual-mode image classification method and customized Android application for point-of-care oral cancer detection. APPROACH: The dataset used in our study was captured among 5025 patients with our customized dual-modality mobile oral screening devices. We trained an efficient network MobileNet with focal loss and converted the model into TensorFlow Lite format. The finalized lite format model is ∼16.3 MB and ideal for smartphone platform operation. We have developed an Android smartphone application in an easy-to-use format that implements the mobile-based dual-modality image classification approach to distinguish oral potentially malignant and malignant images from normal/benign images. RESULTS: We investigated the accuracy and running speed on a cost-effective smartphone computing platform. It takes ∼300 ms to process one image pair with the Moto G5 Android smartphone. We tested the proposed method on a standalone dataset and achieved 81% accuracy for distinguishing normal/benign lesions from clinically suspicious lesions, using a gold standard of clinical impression based on the review of images by oral specialists. CONCLUSIONS: Our study demonstrates the effectiveness of a mobile-based approach for oral cancer screening in low-resource settings.