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

Development and Evaluation of an Automated Multimodal Mobile Detection of Oral Cancer Imaging System to Aid in Risk-Based Management of Oral Mucosal Lesions

Oral cancer is a major global health problem. It is commonly diagnosed at an advanced stage, although often preceded by clinically visible oral mucosal lesions, termed oral potentially malignant disorders, which are associated with an increased risk of oral cancer development. There is an unmet clinical need for effective screening tools to assist front-line healthcare providers to determine which patients should be referred to an oral cancer specialist for evaluation. This study reports the development and evaluation of the mobile detection of oral cancer (mDOC) imaging system and an automated algorithm that generates a referral recommendation from mDOC images. mDOC is a smartphone-based autofluorescence and white light imaging tool that captures images of the oral cavity. Data were collected using mDOC from a total of 332 oral sites in a study of 29 healthy volunteers and 120 patients seeking care for an oral mucosal lesion. A multimodal image classification algorithm was developed to generate a recommendation of "refer" or "do not refer" from mDOC images using expert clinical referral decision as the ground truth label. A referral algorithm was developed using cross-validation methods on 80% of the dataset and then retrained and evaluated on a separate holdout test set. Referral decisions generated in the holdout test set had a sensitivity of 93.9% and a specificity of 79.3% with respect to expert clinical referral decisions. The mDOC system has the potential to be utilized in community physicians' and dentists' offices to help identify patients who need further evaluation by an oral cancer specialist. Prevention Relevance: Our research focuses on improving the early detection of oral precancers/cancers in primary dental care settings with a novel mobile platform that can be used by front-line providers to aid in assessing whether a patient has an oral mucosal condition that requires further follow-up with an oral cancer specialist.

Integrating artificial intelligence with smartphone-based imaging for cancer detection in vivo

Cancer is a major global health challenge, accounting for nearly one in six deaths worldwide. Early diagnosis significantly improves survival rates and patient outcomes, yet in resource-limited settings, the scarcity of medical resources often leads to late-stage diagnosis. Integrating artificial intelligence (AI) with smartphone-based imaging systems offers a promising solution by providing portable, cost-effective, and widely accessible tools for early cancer detection. This paper introduces advanced smartphone-based imaging systems that utilize various imaging modalities for in vivo detection of different cancer types and highlights the advancements of AI for in vivo cancer detection in smartphone-based imaging. However, these compact smartphone systems face challenges like low imaging quality and restricted computing power. The use of advanced AI algorithms to address the optical and computational limitations of smartphone-based imaging systems provides promising solutions. AI-based cancer detection also faces challenges. Transparency and reliability are critical factors in gaining the trust and acceptance of AI algorithms for clinical application, explainable and uncertainty-aware AI breaks the black box and will shape the future AI development in early cancer detection. The challenges and solutions for improving AI accuracy, transparency, and reliability are general issues in AI applications, the AI technologies, limitations, and potentials discussed in this paper are applicable to a wide range of biomedical imaging diagnostics beyond smartphones or cancer-specific applications. Smartphone-based multimodal imaging systems and deep learning algorithms for multimodal data analysis are also growing trends, as this approach can provide comprehensive information about the tissue being examined. Future opportunities and perspectives of AI-integrated smartphone imaging systems will be to make cutting-edge diagnostic tools more affordable and accessible, ultimately enabling early cancer detection for a broader population.

Artificial Intelligence in Oral Cancer: A Comprehensive Scoping Review of Diagnostic and Prognostic Applications

Background/Objectives: Oral cancer, the sixth most common cancer worldwide, is linked to smoke, alcohol, and HPV. This scoping analysis summarized early-onset oral cancer diagnosis applications to address a gap. Methods: A scoping review identified, selected, and synthesized AI-based oral cancer diagnosis, screening, and prognosis literature. The review verified study quality and relevance using frameworks and inclusion criteria. A full search included keywords, MeSH phrases, and Pubmed. Oral cancer AI applications were tested through data extraction and synthesis. Results: AI outperforms traditional oral cancer screening, analysis, and prediction approaches. Medical pictures can be used to diagnose oral cancer with convolutional neural networks. Smartphone and AI-enabled telemedicine make screening affordable and accessible in resource-constrained areas. AI methods predict oral cancer risk using patient data. AI can also arrange treatment using histopathology images and address data heterogeneity, restricted longitudinal research, clinical practice inclusion, and ethical and legal difficulties. Future potential includes uniform standards, long-term investigations, ethical and regulatory frameworks, and healthcare professional training. Conclusions: AI may transform oral cancer diagnosis and treatment. It can develop early detection, risk modelling, imaging phenotypic change, and prognosis. AI approaches should be standardized, tested longitudinally, and ethical and practical issues related to real-world deployment should be addressed.

Holistic Approach for the Early Detection of Oral Cancer: A Comprehensive Training Module

Objectives

Oral cancer is significantly high in India, and screening is an effective approach to downstage the disease. Educating Community Health Workers (CHWs) on early oral cancer detection is an effective step toward reducing the burden and serves as a first step toward facilitating the transfer of knowledge. Therefore, the purpose of this hands-on education was to equip CHWs with insight on the advanced diagnostics, preventive techniques, and innovations for the early detection of oral cancer.

Materials and Methods

A total of 178 participants were trained in two groups: Group 1 received training for screening and primary prevention, while group 2 received training on updates in recent diagnostic adjuncts and innovations, AI-enabled point-of-care diagnostics, and essential patient care in management of Oral Potentially Malignant Disorders (OPMDs). Pre- and post-assessment questionnaires were used to evaluate the participants.

Results

The knowledge assessment scores between the pre- and post-tests showed a statistically significant difference (p < 0.001), with rise in mean score of 3.99 from baseline. Six months following training, knowledge retention revealed a statistically significant difference (p < 0.001) in the participants' ability to recall the information.

Conclusion

A well-structured training module can create awareness, impart knowledge and upskill the CHWs for early detection of oral cancer. Retraining of CHWs is required for knowledge retention post-training.

Label-free assessment of the transformation zone using multispectral diffuse optical imaging toward early detection of cervical cancer

The assessment of the transformation zone is a critical step toward diagnosis of cervical cancer. This work involves the development of a portable, label-free transvaginal multispectral diffuse optical imaging (MDOI) imaging probe to estimate the transformation zone. The images were acquired from N = 5 (N = 1 normal, N = 2 premalignant, and N = 2 malignant) patients. Key parameters such as spectral contrast ratio (ρ) at 545 and 450 nm were higher in premalignant (0.29, 0.25 for 450 nm and 0.30, 0.17 for 545 nm) as compared to the normal patients (0.13 and 0.14 for 450 and 545 nm, respectively). The threshold for the spectral intensity ratio R610/R450 and R610/R545 can also be used as a marker to correlate with the new and original squamous columnar junction (SCJ), respectively. The pilot study highlights the use of new markers such as spectral contrast ratio (ρ) and spectral intensity ratio (R610/R450 and R610/R545) images.

The association between referral by specialists in oral diagnosis on survival rates of patients with oral cancer: A retrospective cohort study

BACKGROUND

To assess the influence of diagnosis and referral provided by specialists in oral diagnosis on disease-free survival and overall survival of patients with oral cancer.

METHODS

A cohort of 282 patients with oral cancer treated at a regional cancer hospital from 1998 to 2016 was analyzed retrospectively. The referral register of the patients was analyzed and assigned to two groups: (1) those referred by oral diagnosis specialists (n = 129), or (2) those referred by nonspecialized professionals (n = 153). The cancer treatment evolution was assessed from the patients' records, and the outcome was registered concerning cancer recurrence and death. Sociodemographic and clinicopathological variables were explored as predictors of disease-free survival and overall survival.

RESULTS

Group 1 exhibited lower T stages and a reduced incidence of regional and distant metastases. Surgery was performed in 75.2% of cases in Group 1, while in Group 2, the rate was 60.8%. Advanced T stages and regional metastases reduced the feasibility of surgery. Higher TNM stages and tumor recurrence were associated with decreased disease-free survival, while surgical intervention was a protective factor. Higher TNM stage had a negative impact on the overall survival.

CONCLUSION

Specialized oral diagnosis did not directly impact disease-free survival and overall survival and did not influence the indication of surgery in oral cancer; however, it was associated with the diagnosis of early tumors and better prognosis.

An Update on the Use of Artificial Intelligence in Digital Pathology for Oral Epithelial Dysplasia Research

INTRODUCTION

Oral epithelial dysplasia (OED) is a precancerous histopathological finding which is considered the most important prognostic indicator for determining the risk of malignant transformation into oral squamous cell carcinoma (OSCC). The gold standard for diagnosis and grading of OED is through histopathological examination, which is subject to inter- and intra-observer variability, impacting accurate diagnosis and prognosis. The aim of this review article is to examine the current advances in digital pathology for artificial intelligence (AI) applications used for OED diagnosis.

MATERIALS AND METHODS

We included studies that used AI for diagnosis, grading, or prognosis of OED on histopathology images or intraoral clinical images. Studies utilizing imaging modalities other than routine light microscopy (e.g., scanning electron microscopy), or immunohistochemistry-stained histology slides, or immunofluorescence were excluded from the study. Studies not focusing on oral dysplasia grading and diagnosis, e.g., to discriminate OSCC from normal epithelial tissue were also excluded.

RESULTS

A total of 24 studies were included in this review. Nineteen studies utilized deep learning (DL) convolutional neural networks for histopathological OED analysis, and 4 used machine learning (ML) models. Studies were summarized by AI method, main study outcomes, predictive value for malignant transformation, strengths, and limitations.

CONCLUSION

ML/DL studies for OED grading and prediction of malignant transformation are emerging as promising adjunctive tools in the field of digital pathology. These adjunctive objective tools can ultimately aid the pathologist in more accurate diagnosis and prognosis prediction. However, further supportive studies that focus on generalization, explainable decisions, and prognosis prediction are needed.

Use of digital strategies in the diagnosis of oral squamous cell carcinoma: a scoping review

Telediagnosis uses information and communication technologies to support diagnosis, shortening geographical distances. It helps make decisions about various oral lesions. The objective of this scoping review was to map the existing literature on digital strategies to assist in the diagnosis of oral squamous cell carcinoma. this review was structured based on the 5-stage methodology proposed by Arksey and O'Malley, the Joanna Briggs Institute Manual for Evidence Synthesis and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews. The methods were registered on the Open Science Framework. The research question was: What digital strategies have been used to assist in the diagnosis of oral squamous cell carcinoma? The search was conducted on PubMed/MEDLINE, Scopus, Web of Science, Embase, and ScienceDirect. Inclusion criteria comprised studies on telediagnosis, teleconsultation or teleconsultation mediated by a professional and studies in English, without date restrictions. The search conducted in June 2023 yielded 1,798 articles, from which 16 studies were included. Telediagnosis was reported in nine studies, involving data screening through applications, clinical images from digital cameras, mobile phones or artificial intelligence. Histopathological images were reported in four studies. Both, telediagnosis and teleconsultation, were mentioned in seven studies, utilizing images and information submission services to platforms, WhatsApp or applications. One study presented teleconsultations involving slides and another study introduced teleconsultation mediated by a professional. Digital strategies telediagnosis and teleconsultations enable the histopathological diagnosis of oral cancer through clinical or histopathological images. The higher the observed diagnostic agreement, the better the performance of the strategy.

Classification of Mobile-Based Oral Cancer Images Using the Vision Transformer and the Swin Transformer

Oral cancer, a pervasive and rapidly growing malignant disease, poses a significant global health concern. Early and accurate diagnosis is pivotal for improving patient outcomes. Automatic diagnosis methods based on artificial intelligence have shown promising results in the oral cancer field, but the accuracy still needs to be improved for realistic diagnostic scenarios. Vision Transformers (ViT) have outperformed learning CNN models recently in many computer vision benchmark tasks. This study explores the effectiveness of the Vision Transformer and the Swin Transformer, two cutting-edge variants of the transformer architecture, for the mobile-based oral cancer image classification application. The pre-trained Swin transformer model achieved 88.7% accuracy in the binary classification task, outperforming the ViT model by 2.3%, while the conventional convolutional network model VGG19 and ResNet50 achieved 85.2% and 84.5% accuracy. Our experiments demonstrate that these transformer-based architectures outperform traditional convolutional neural networks in terms of oral cancer image classification, and underscore the potential of the ViT and the Swin Transformer in advancing the state of the art in oral cancer image analysis.

Accuracy of Remote Examination for Detecting Potentially Malignant Oral Lesions: A Systematic Review and Meta-Analysis

Objective: We aimed to investigate the accuracy of remote examination by photographs compared to in-person clinical examination for detecting potentially malignant oral lesions (PMOLs). Methods: The Reporting Guide and Guidelines for Writing Systematic Reviews (Preferred Reporting Items for Systematic Reviews and Meta-Analysis [PRISMA]) guided the reporting of findings. The search was conducted by two independent reviewers in six databases with no language restriction until November 2022. The Population, Test-Index, Reference Standard, Outcome and Study Design (PIROS) strategy guided the eligibility criteria, and studies with adult patients (P) examined remotely (I) and in-person (R) to verify the detection of PMOLs (O) were considered. The methodological quality was assessed by QUADAS-2, and the certainty of the evidence was measured by the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE). Results: A total of 769 files were identified. After removing duplicates and reading titles and abstracts, 16 were read in full, from which 6 articles then comprised the qualitative synthesis. The oral clinical examination was the reference standard in four studies. Five studies presented high risk of bias in at least one assessment domain. A high probability of detection of PMOL by remote examination (97.37%) was observed for the three studies included in the meta-analysis, which presented high heterogeneity among them. The certainty of evidence for the outcome was considered very low. Conclusions: Remote tools for detecting PMOLs may be feasible and assertive, but new studies are required to incorporate them into clinical practice. Clinical Relevance: Remote examination for the detection of PMOLs has the potential to favoring the early diagnosis of malignant lesions.

Optical imaging for screening and early cancer diagnosis in low-resource settings

Low-cost optical imaging technologies have the potential to reduce inequalities in healthcare by improving the detection of pre-cancer or early cancer and enabling more effective and less invasive treatment. In this Review, we summarise technologies for in vivo widefield, multi-spectral, endoscopic, and high-resolution optical imaging that could offer affordable approaches to improve cancer screening and early detection at the point-of-care. Additionally, we discuss approaches to slide-free microscopy, including confocal imaging, lightsheet microscopy, and phase modulation techniques that can reduce the infrastructure and expertise needed for definitive cancer diagnosis. We also evaluate how machine learning-based algorithms can improve the accuracy and accessibility of optical imaging systems and provide real-time image analysis. To achieve the potential of optical technologies, developers must ensure that devices are easy to use; the optical technologies must be evaluated in multi-institutional, prospective clinical tests in the intended setting; and the barriers to commercial scale-up in under-resourced markets must be overcome. Therefore, test developers should view the production of simple and effective diagnostic tools that are accessible and affordable for all countries and settings as a central goal of their profession.

Screening for HPV-Related Oropharyngeal Cancer in Gay and Bisexual Men: Acceptability and Predicting Possible Use of "Oral Selfies" by Smartphone as a Secondary Prevention Approach

Oropharyngeal cancers (OPCa) caused by HPV have emerged as one of the leading causes of malignancies caused by HPV infection. They are also significantly more likely to occur in males and in people with a history of oral sex with multiple partners. Gay and bisexual men are disproportionately affected by HPV-positive oropharyngeal cancers. We studied 1699 gay and bisexual men on 2 major dating sites in the US to assess their knowledge about HPV-related OPCa, attitudes toward screening for it, beliefs about oropharyngeal cancer screening based on the Health Belief Model, and attitudes toward possible screening approaches for OPCa. Knowledge on a 12-item scale was low, with a median of 5 items correct: 72% knew of the benefits of HPV vaccination. Significant predictors of needing OPCa screening included perception of risk for OPCa, seeing it as severe, having lower barriers, fewer reasons to avoid screening, higher knowledge, and being HPV vaccinated were significant predictors, explaining half the total variance. Most participants would accept routine, virtual/online doctor or dental appointments, and over half would accept an in-person screening. Nearly two-thirds stated that they would accept getting checked for OPCa if they could do self-screening at home, and half were prepared to use an online screening tool or app, where they could take an "oral selfie" and send it to a healthcare provider for examination. One-third stated that they would trust the results of a home screening completed by themselves and posted to a website equally as cancer screening completed online by a healthcare provider. Data indicate that despite low OPCA knowledge levels, the risk of HPV-associated OPCa was known. Being at personal risk and having knowledge of disease severity had 70% of the sample thinking about, or preparing to get, screening. Self-screening by a smartphone "oral selfie" transmitted to a screening website was acceptable to many gay and bisexual men, and online screening by a doctor or dentist was acceptable to most. OPCa screening in this population using electronic technology, together with the increasing incidence of HPV-associated OPCa in gay and bisexual men, brings together an opportunity to detect OPCa early.

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.

Optical imaging technologies for in vivo cancer detection in low-resource settings

Cancer continues to affect underserved populations disproportionately. Novel optical imaging technologies, which can provide rapid, non-invasive, and accurate cancer detection at the point of care, have great potential to improve global cancer care. This article reviews the recent technical innovations and clinical translation of low-cost optical imaging technologies, highlighting the advances in both hardware and software, especially the integration of artificial intelligence, to improve in vivo cancer detection in low-resource settings. Additionally, this article provides an overview of existing challenges and future perspectives of adapting optical imaging technologies into clinical practice, which can potentially contribute to novel insights and programs that effectively improve cancer detection in low-resource settings.

Deep Learning Techniques and Imaging in Otorhinolaryngology-A State-of-the-Art Review

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology.

Role of digital health in coordinating patient care in a hub-and-spoke hierarchy of cancer care facilities: a scoping review

Background

Coordinating cancer care is complicated due to the involvement of multiple service providers which often leads to fragmentation. The evolution of digital health has led to the development of technology-enabled models of healthcare delivery. This scoping review provides a comprehensive summary of the use of digital health in coordinating cancer care via hub-and-spoke models.

Methods

A scoping review of the literature was undertaken using the framework developed by Arksey and O'Malley. Research articles published between 2010 and 2022 were retrieved from four electronic databases (PubMed/MEDLINE, Web of Sciences, Cochrane Reviews and Global Health Library). The preferred reporting items for systematic reviews and meta-analyses extension for the scoping reviews (PRISMA-ScR) checklist were followed to present the findings.

Result

In total, 311 articles were found of which 7 studies that met the inclusion criteria were included. The use of videoconferencing was predominant across all the studies. The number of spokes varied across the studies ranging from 1 to 63. Three studies aimed to evaluate the impact on access to cancer care among patients, two studies were related to capacity building of the health care workers at the spoke sites, one study was based on a peer review of radiotherapy plans, and one study was related to risk assessment and patient navigation. The introduction of digital health led to reduced travel time and waiting period for patients, and standardisation of radiotherapy plans at spokes. Tele-mentoring intervention aimed at capacity-building resulted in higher confidence and increased knowledge among the spoke learners.

Conclusion

There is limited evidence for the role of digital health in the hub-and-spoke design. Although all the studies have highlighted the digital components being used to coordinate care, the bottlenecks, Which were overcome during the implementation of the interventions and the impact on cancer outcomes, need to be rigorously analysed.

AI-Assisted Screening of Oral Potentially Malignant Disorders Using Smartphone-Based Photographic Images

The prevalence of oral potentially malignant disorders (OPMDs) and oral cancer is surging in low- and middle-income countries. A lack of resources for population screening in remote locations delays the detection of these lesions in the early stages and contributes to higher mortality and a poor quality of life. Digital imaging and artificial intelligence (AI) are promising tools for cancer screening. This study aimed to evaluate the utility of AI-based techniques for detecting OPMDs in the Indian population using photographic images of oral cavities captured using a smartphone. A dataset comprising 1120 suspicious and 1058 non-suspicious oral cavity photographic images taken by trained front-line healthcare workers (FHWs) was used for evaluating the performance of different deep learning models based on convolution (DenseNets) and Transformer (Swin) architectures. The best-performing model was also tested on an additional independent test set comprising 440 photographic images taken by untrained FHWs (set I). DenseNet201 and Swin Transformer (base) models show high classification performance with an F1-score of 0.84 (CI 0.79-0.89) and 0.83 (CI 0.78-0.88) on the internal test set, respectively. However, the performance of models decreases on test set I, which has considerable variation in the image quality, with the best F1-score of 0.73 (CI 0.67-0.78) obtained using DenseNet201. The proposed AI model has the potential to identify suspicious and non-suspicious oral lesions using photographic images. This simplified image-based AI solution can assist in screening, early detection, and prompt referral for OPMDs.

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.

Machine learning for detection and classification of oral potentially malignant disorders: A conceptual review

Oral potentially malignant disorders represent precursor lesions that may undergo malignant transformation to oral cancer. There are many known risk factors associated with the development of oral potentially malignant disorders, and contribute to the risk of malignant transformation. Although many advances have been reported to understand the biological behavior of oral potentially malignant disorders, their clinical features that indicate the characteristics of malignant transformation are not well established. Early diagnosis of malignancy is the most important factor to improve patients' prognosis. The integration of machine learning into routine diagnosis has recently emerged as an adjunct to aid clinical examination. Increased performances of artificial intelligence AI-assisted medical devices are claimed to exceed the human capability in the clinical detection of early cancer. Therefore, the aim of this narrative review is to introduce artificial intelligence terminology, concepts, and models currently used in oncology to familiarize oral medicine scientists with the language skills, best research practices, and knowledge for developing machine learning models applied to the clinical detection of oral potentially malignant disorders.

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.

Status and Determinants of Early Detection of Oral Premalignant and Malignant Lesions in India

It has been over four decades since the launch of the National Cancer Control Programme in India, yet the cancer screening rates for oral cancer remain unremarkable. Moreover, India is bracing a large burden of oral cancer with poor survival rates. An effective public health programme implementation relies on a multitude of factors related to cost-effective evidence-based interventions, the healthcare delivery system, public health human resource management, community behaviour, partnership with stakeholders, identifying opportunities and political commitment. In this context, we discuss the various challenges in the early detection of oral premalignant and malignant lesions and potential solutions.