Search

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.

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.

In a rural block in North East India, community health workers (CHW) empowered with a mobile phone-based application screened a total of 2,686 participants for Oral Potentially Malignant Lesions (OPMLs), and an oral medicine specialist recommended treatment remotely. Independent risk factors were determined using independent multiple logistic regression models. Nearly 700 (26%) participants were identified with OPMLs. The sensitivity, specificity, positive predictive values, negative predictive values and accuracy of the CHW was 70.3, 88.4, 66.8, 89.9% and 83.7% respectively. Male gender, married status, smokeless tobacco, paan, areca-nut and alcohol consumption were independent predictors of OPMLs, the burden of which in North East India can be attributed to the high consumption of tobacco and non-tobacco products. Such programmes, with the recommendations from remote specialists, will facilitate early detection in remote settings.

Oral cancer is usually preceded by oral potentially malignant disorders (OPMDs) and early detection can downstage the disease. The majority of OPMDs are asymptomatic in early stages and can be detected on routine oral examination. Though only a proportion of OPMDs may transform to oral squamous cell carcinoma (OSCC), they may serve as a surrogate clinical lesion to identify individuals at risk of developing OSCC. Currently, there is a scarcity of scientific evidence on specific interventions and management of OPMDs and there is no consensus regarding their management. A consensus meeting with a panel of experts was convened to frame guidelines for clinical practices and recommendations for management strategies for OPMDs. A review of literature from medical databases was conducted to provide the best possible evidence and provide recommendations in management of OPMDs.

SignificanceOral 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.AimWe 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.ApproachThis 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.ResultsThe 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.ConclusionsOur 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.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.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.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.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.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.

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.

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.

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.

Simple Summary Early detection is crucial towards improving survival in patients diagnosed with oral cancer. Non-invasive strategies equivalent to histology diagnosis are extremely valuable in oral cancer screening and early detection in resource-constrained settings. Optical coherence tomography (OCT), an optical biopsy technique enables real-time imaging with periodic surveillance and capability to image architectural features of the tissues. We report that while OCT system delineates oral pre-cancer and cancer with more than 90% sensitivity, integration, with artificial neural network-based analysis efficiently identifies high-risk, oral pre-cancer (83%). This study provides evidence that the robust, low-cost system was effective as a point-of-care device in resource-constrained settings. The high accuracy and portability signify widespread clinical application in oral cancer screening and/or surveillance. Abstract 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.

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.

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.

Background: Early detection of oral cancer in low-resource settings necessitates a robust, Point-of-Care screening tool that can empower Frontline-Health-Workers (FHW) for triaging high-risk populations. This study was conducted to validate the accuracy of Artificial-Neural-Network (ANN) enabled m(mobile)-Health device deployed with FHWs. Methods: The dual-imaging device enables white-light as well as auto-fluorescence imaging with both a wide and focused view. The effectiveness of the device was tested in tertiary-care/dental hospitals and low-resource settings of South/North-East India. Demographics and clinical details were documented in the device, and the subjects were screened independently, either by FHWs or along with specialists, in addition to a remote evaluation by oral cancer specialists. Simple and complex ANN were built using the images for classification of oral-potentially-malignant/malignant lesions and integrated into the mobile phone/cloud. The specialist diagnoses were compared with the histopathology, FHW, and ANN-based diagnosis to evaluate the efficacy of the oral cancer detection program. Findings: The program screened 5025 subjects with 95% (n=4728) having tele-diagnosis. Among the 16% (n=752) assessed by onsite specialists, biopsy was advised for 515, out of which 20% (n=102) underwent biopsy. The onsite specialist diagnosis showed high sensitivity (94%) and moderate specificity (72%) when compared to histology diagnosis, while tele-diagnosis showed high accuracy when compared with onsite specialists (sensitivity: 95%; specificity: 84%). FHWs, when compared with tele-diagnosis, identified suspicious lesions with less sensitivity (60%). Further, the efficacy of the FHWs in delineating suspicious lesions correlated (r= 0·80) with their prior experience in the project. The ANN (MobileNet) integrated with the phone for a real-time diagnosis could accurately delineate lesions (n=1416; sensitivity: 82%), while the cloud-based ANN (VGG19) had higher accuracy (sensitivity: 87%) when compared to tele-diagnosis. Interpretation: This study suggests that an automated mHealth-enabled dual-image system could prove a useful triaging tool, empowering FHWs towards accurate screening in low-resource settings. Clinical Trial: The study protocol was registered in the Clinical Trial Registry of the Indian Council of Medical Research (CTRI/2019/11/022167). Funding: This study is primarily funded by the National Institutes of Health (NIH), USA grants (UH2EB022623, UH3CA239682). This work is also supported by LAMMP NIH/NIBIB P41EB05890, Arnold and Mabel Beckman Foundation, California Tobacco-Related Diseases Program: T31IR1825. Declaration of Interest: We declare no competing interests. Ethical Approval: Institutional Ethics Committee approvals were obtained from the three nodal centers- The KLE Society’s Institute of Dental Sciences (KLE; ECR/887/Inst/KA/2016), Bengaluru, India, Christian Institute of Health Sciences and Research (CIHSR; EC/NEW/INST/2020/782), Dimapur, Nagaland, India, and Mazumdar Shaw Medical Center (MSMC; NNH/MEC-CL-2016-394), Bengaluru, India prior to the initiation of the clinical trial.

Oral cancer is one of the most common malignant tumors. There are 354,864 new cases and 177,384 death per year globally according to Globocan 2018 report. Most of the cases are in low- and middle-income countries that lack trained specialists and health services, of which India accounts for approximately one-third of the new cases and two-fifth deaths. Point-of-care oral screening tool to enable early diagnosis is urgently needed. We developed a dual-mode intraoral oral cancer screening platform and an automatic classification algorithm for oral dysplasia and malignancy images using deep learning.

We use both data- and algorithm-level methods to improve the neural network performance of oral cancer image classification with imbalanced multi-class dataset captured from high-risk populations during oral cancer screening.

We will report a mobile-based dual-mode image classification method for oral cancer detection in low-resource settings.

Standard deep learning algorithms for clinical image classification are unable to understand their confidence in a decision. We developed a Bayesian deep network could estimate uncertainty to assess the reliability of oral cancer image classification.

Purpose: Hounsfield unit (HU) provides a quantitative evaluation of bone density. The assessment of bone density is essential for successful treatment plan. Although, multislice computed tomography (MSCT) is considered as gold standard in evaluating bone density, cone-beam computed tomography (CBCT) is frequently used in dentomaxillofacial imaging due to lower radiation dose, less complex device, and images with satisfactory resolution. Aims and Objectives: The aim of this study is to determine and compare the gray value and HU value of hypodense and hyperdense structures on CBCT and MSCT, respectively. The study also evaluated and compared the gray values in different field of views within CBCT. Materials and Methods: A total of 20 dry human mandibles were obtained. The gray values and HU values of hypodense structures (extraction socket, inferior alveolar canal, and mental foramen) and hyperdense structures (enamel, cancellous, and cortical bone) were evaluated and compared between CBCT and MSCT images, respectively. The obtained data were statistically analyzed. Statistical Analysis: One-way analyses of variance, ANOVA F-test. Results: The gray value for hypodense structures in large volume CBCT scans resembled the HU value. The study showed statistically significant difference (P

Oral cancer is a growing health issue in low- and middle-income countries due to betel quid, tobacco, and alcohol use and in younger populations of middle- and high-income communities due to the prevalence of human papillomavirus. The described point-of-care, smartphone-based intraoral probe enables autofluorescence imaging and polarized white light imaging in a compact geometry through the use of a USB-connected camera module. The small size and flexible imaging head improves on previous intraoral probe designs and allows imaging the cheek pockets, tonsils, and base of tongue, the areas of greatest risk for both causes of oral cancer. Cloud-based remote specialist and convolutional neural network clinical diagnosis allow for both remote community and home use. The device is characterized and preliminary field-testing data are shared.

Background: The global incidence of oral cancer occurs in low-resource settings. Community-based oral screening is a strategic step toward downstaging oral cancer by early diagnosis. The mobile health (mHealth) program is a technology-based platform, steered with the aim to assess the use of mHealth by community health workers (CHWs) in the identification of oral mucosal lesions. MATERIALS AND METHODS: mHealth is a mobile phone-based oral cancer-screening program in a workplace setting. The participants were screened by two CHWs, followed by an assessment by an oral medicine specialist. A mobile phone-based questionnaire that included the risk assessment was distributed among participants. On specialist recommendation an oral surgeon performed biopsy on participants. The diagnosis by onsite specialist that was confirmed by histopathology was considered as gold standard. All individuals received the standard treatment protocol. A remote oral medicine specialist reviewed the uploaded data in Open Medical Record System. Sensitivity, specificity, positive and negative predictive values were calculated. Inter-rater agreement was analyzed with Cohen's kappa coefficient (κ) test, and the diagnostic ability of CHWs, onsite specialist, and remote specialist was illustrated using receiver operating characteristic curve. RESULTS: CHWs identified oral lesions in 405 (11.8%) individuals; the onsite specialist identified oral lesions in 394 (11.4%) individuals; and the remote specialist diagnosed oral lesions in 444 (13%). The inter-rater agreement between the CHW and the onsite specialist showed almost perfect agreement with the κ score of 0.92, and a substantial agreement between CHW and remote specialist showed a score of 0.62. The sensitivity, specificity, positive and negative predictive values of CHWs in the identification of oral lesion were 84.7, 97.6, 84.8, and 97.7%, respectively. CONCLUSION: The trained CHWs can aid in identifying oral potentially malignant disorders and they can be utilized in oral cancer-screening program mHealth effectively.

Background To determine the effectiveness of a mobile phone–based remote oral cancer surveillance program (Oncogrid) connecting primary care dental practitioners and frontline health care workers (FHW) with oral cancer specialists. Methods The study population (N = 3,440) included a targeted cohort (n = 2,000) and an opportunistic cohort (n = 1,440) screened by FHW and dental professionals, respectively. The authors compared the screening efficacy in both groups, with specialist diagnosis considered the reference standard. The outcomes measured were lesion detection and capture of interpretable images of the oral cavity. Results In the targeted cohort, among 51 of 81 (61%) interpretable images, 23 of 51 (45%) of the lesions were confirmed by specialists, while the opportunistic cohort showed 100% concordance with the specialists (106 of 106). Sixty-two of 129 (48%) of the recommended patients underwent biopsy; 1 of 23 (4%) were in the targeted cohort, and 61 of 106 (57%) were in the opportunistic cohort. Ninety percent of the lesions were confirmed to be malignant or potentially malignant. Conclusions The mobile health–based approach adopted in this study aided remote early detection of oral cancer by primary care dental practitioners in a resource-constrained setting. Further optimization of this program is required to adopt the system for FHW. Evaluation of its efficacy in a larger population is also warranted. Practical Implications The increased efficiency of early detection by dentists, when assisted by a remote mobile health–based approach, is a step toward a more effective oral cancer screening program.

With the goal to screen high-risk populations for oral cancer in low- and middle-income countries (LMICs), we have developed a low-cost, portable, easy to use smartphone-based intraoral dual-modality imaging platform. In this paper we present an image classification approach based on autofluorescence and white light images using deep learning methods. The information from the autofluorescence and white light image pair is extracted, calculated, and fused to feed the deep learning neural networks. We have investigated and compared the performance of different convolutional neural networks, transfer learning, and several regularization techniques for oral cancer classification. Our experimental results demonstrate the effectiveness of deep learning methods in classifying dual-modal images for oral cancer detection.

Author(s): Birur, N Praveen; Patrick, Sanjana; Bajaj, Suchitra; Raghavan, Shubhasini; Suresh, Amritha; Sunny, Sumsum P; Chigurupati, Radhika; Wilder-Smith, Petra; Gurushanth, Keerthi; Gurudath, Shubha; Rao, Pratima; Kuriakose, Moni A | Abstract: AimThe incidence of oral cancer is high in India, which can be reduced by early detection. We aimed to empower frontline health care providers (FHP) for early detection and connect specialist to rural population through mHealth.Materials and methodsWe provided training to FHPs in examination of oral cavity, use of mobile phone for image capture, and risk factor analysis. The FHPs were selected from different cohorts in resource-constrained settings. The workflow involved screening of high-risk individuals in door-to-door and workplace settings, and capture of images of suspected lesions. Uploaded data were interpreted and recommendation was sent by specialist from a remote location. Their recommendation was intimated to FHPs who arranged for further action. Two more initiatives, one for multiple dental schools and another for private practitioners, were undertaken.ResultsDuring the period from 2010 to 2018, 42,754 subjects have been screened, and 5,406 subjects with potentially malignant disorders have been identified. The prevalence of potentially malignant disorders varied from 0.8 to 62% at different cohorts; 516 biopsies have been performed at remote locations.ConclusionConnecting specialists to rural population was made possible through the use of mobile health. Trained FHP were able to reach out to the population. Electronic data capture facilitated efficient follow-up. The program was very cost-effective with screening completed under $1 per person.Clinical significanceIn view of the high incidence of oral cancer in India, and the resource-constrained settings, mobile health paves the way for better access to specialist care for the rural population.

Oral cancer is a rising health issue in many low and middle income countries (LMIC). Proposed is an implementation of autofluorescence imaging (AFI) and white light imaging (WLI) on a smartphone platform providing inexpensive early detection of cancerous conditions in the oral cavity. Interchangeable modules allow both whole mouth imaging for an overview of the patients’ oral health and an intraoral imaging probe for localized information. Custom electronics synchronize image capture and external LED operation for the excitation of tissue fluorescence. A custom Android application captures images and an image processing algorithm provides likelihood estimates of cancerous conditions. Finally, all data can be uploaded to a cloud server where a convolutional neural network classifies the images and a remote specialist can provide diagnosis and triage instructions.

Oral cancer is a growing health issue in a number of low- and middle-income countries (LMIC), particularly in South and Southeast Asia. The described dual-modality, dual-view, point-of-care oral cancer screening device, developed for high-risk populations in remote regions with limited infrastructure, implements autofluorescence imaging (AFI) and white light imaging (WLI) on a smartphone platform, enabling early detection of pre-cancerous and cancerous lesions in the oral cavity with the potential to reduce morbidity, mortality, and overall healthcare costs. Using a custom Android application, this device synchronizes external light-emitting diode (LED) illumination and image capture for AFI and WLI. Data is uploaded to a cloud server for diagnosis by a remote specialist through a web app, with the ability to transmit triage instructions back to the device and patient. Finally, with the on-site specialist's diagnosis as the gold-standard, the remote specialist and a convolutional neural network (CNN) were able to classify 170 image pairs into 'suspicious' and 'not suspicious' with sensitivities, specificities, positive predictive values, and negative predictive values ranging from 81.25% to 94.94%.

AimGlobally, India accounts for the highest number of oral cancer cases. The survival rates are about 30% lower than those in developing countries. The main reason for these dismal figures is the late presentation of patients. In order to downstage oral cancer in such a scenario, screening and diagnosis at an early stage is warranted. A pragmatic approach is needed for an oral cancer screening program, hence a mobile health (mHealth) approach was used. In this approach, health workers were empowered with mobile phones with decision-based algorithm. Risk stratification of tobacco habit enables us to identify lesions associated with particular habits.Materials and methodsA specific cohort of factory employees who predominantly had pure tobacco chewing habit was chosen to examine the effect of pure tobacco on oral mucosa. One thousand three hundred and fifty-seven subjects were screened in two phases. In the first phase, habits and oral lesions were identified and photographed. The photographs were remotely diagnosed by an oral medicine specialist and those subjects requiring biopsy were recalled for phase II. Cytology and biopsy were performed in phase II.ResultsThe predominant habit was smokeless tobacco (SLT), in 582 subjects. The most commonly encountered lesion was tobacco pouch keratosis seen in 397 subjects. Biopsy was performed for 71 subjects, most cases showed hyperkeratosis and mild dysplasia. One subject had moderate dysplasia.ConclusionThere was minimal alteration of tissues in our study subjects, which can be considered as low-risk. Use of mHealth empowered frontline healthcare workers to identify subjects with lesions and enabled remote diagnosis by specialist in resource-constrained settings.Clinical significanceUse of mHealth enabled us have an electronic record of subject details. This data shall be used for a planned follow-up of the same cohort after 3 years.How to cite this articleDesai R, Birur P, Bajaj S, Shubhasini AR, Bhanushree R, Shubha G, Keerthi G, Tiwari V, Patrick S, Hegde U, Shetty S, Nagabhushan V, Kankanala S, Shah S. Smokeless Tobacco-associated Lesions: A Mobile Health Approach. J Contemp Dent Pract 2015;16(10):813-818.