Deep Transfer Learning Driven Oral Cancer Detection and Classification Model

Early detection dramatically increases the survival rate of oral cancer (OC). Artificial intelligence (AI) technology has garnered more attention in the field of diagnostic medicine in present periods. This study set out to assess the available data regarding AI's efficacy in OC diagnosis critically. Artificial intelligence diagnostic accuracy and capacity to detect early phases of OC were highlighted. In this project, performance indicators will be measured and oral cancer will be divided and classified using intelligent computing techniques. The role of oral cancer classification and detection to achieve a high recognition rate while leveraging the best theoretical components of oral cancer images, a newly established region-based Convolutional Neural Network (RCNN-COA) and the Chimp Optimization Algorithm were used to improve a Deep Learning Method. Then, using the recommended Chimp Optimization Algorithm (COA), a region-based convolutional neural network (R-CNN) classifier was trained using the acquired theoretical properties and the innovative image. A comparison of many deep learning and machine learning models' performances has been reported in a study. The findings imply that the deep learning model is capable of managing the problematic task of early oral malignant tumor detection.

Oral cancer is a malignant tumor that usually occurs within the tissues of the mouth. This type of cancer mainly includes tumors in the lining of the mouth, tongue, lips, buccal mucosa and gums. Oral cancer is on the rise globally, especially in some specific risk groups. The early stage of oral cancer is usually asymptomatic, while the late stage may present with ulcers, lumps, bleeding, etc. The objective of this paper is to propose an effective and accurate method for the identification and classification of oral cancer. We applied two deep learning methods, CNN and Transformers. First, we propose a new CANet classification model for oral cancer, which uses attention mechanisms combined with neglected location information to explore the complex combination of attention mechanisms and deep networks, and fully tap the potential of attention mechanisms. Secondly, we design a classification model based on Swim transform. The image is segmented into a series of two-dimensional image blocks, which are then processed by multiple layers of conversion blocks. The proposed classification model was trained and predicted on Kaggle Oral Cancer Images Dataset, and satisfactory results were obtained. The average accuracy, sensitivity, specificity and F1-Socre of Swin transformer architecture are 94.95%, 95.37%, 95.52% and 94.66%, respectively. The average accuracy, sensitivity, specificity and F1-Score of CANet model were 97.00%, 97.82%, 97.82% and 96.61%, respectively. We studied different deep learning algorithms for oral cancer classification, including convolutional neural networks, converters, etc. Our Attention module in CANet leverages the benefits of channel attention to model the relationships between channels while encoding precise location information that captures the long-term dependencies of the network. The model achieves a high classification effect with an accuracy of 97.00%, which can be used in the automatic recognition and classification of oral cancer.

Oral cancer is a significant global health concern that affects people of various age groups worldwide. According to Globo Can, reports from 2022 show that approximately 377,713 new cases and 177,757 deaths are reported each year worldwide. Smartphones and Artificial intelligence (AI) are increasing in healthcare for diagnosis and treatment planning. This systematic review aims to appraise the existing evidence on the effectiveness of various artificial intelligence algorithms in the detection of oral cancer based on smartphone-based oral photographs from previously published articles. A systematic electronic search was carried out through various databases that emphasize current studies on the detection or diagnosis of oral cancer using different artificial intelligence algorithms. A modified Newcastle Ottawa scale was used to evaluate the quality of the included research and the PROBAST (Prediction model Risk of Bias Assessment tool) was used to assess the risk of bias. Among 13 articles, 8 show good quality and 5 fair qualities, mostly at low bias risk. Machine learning (support vector machines) sensitivity and specificity range from 89% to 92% and 75% to 82%; deep learning (MobileNet v2, ResNet) ranges from 85.12% to 90.23% and 87.64% to 90%. The diagnostic effectiveness of artificial intelligence models differs among machine learning and deep learning techniques. According to these results, machine learning has demonstrated encouraging outcomes in identifying oral cancer. The findings demonstrate the effectiveness of smartphone photographic images in detecting oral cancer.

Abstract—Bone cancer is a serious health condition that often leads to high mortality rates. Early detection plays a crucial role in limiting the spread of cancerous cells and improving patient outcomes. However, manual detection is a time-consuming and labor-intensive process, necessitating th6+e development of an automated system to efficiently classify and identify cancerous and healthy bone tissues. This paper introduces the Owl Search Algorithm with Deep Learning-Driven Bone Cancer Detection and Classification (OSADL-BCDC) model, which combines transfer learning and hyperparameter optimization for effective bone cancer detection. The OSADL-BCDC approach utilizes the Inception v3 model as a pretrained feature extractor, eliminating the need for manual image segmentation. The Owl Search Algorithm (OSA) is employed as a hyperparameter optimizer to enhance the performance of Inception v3. Additionally, Long Short-Term Memory (LSTM) networks are leveraged to detect the presence of bone cancer. The proposed OSADL-BCDC method reduces diagnosis time and achieves faster convergence, demonstrating superior performance in experimental evaluations compared to existing algorithms. The results of the comparison emphasize the effectiveness and improved accuracy of the OSADL-BCDC model for bone cancer detection. Keywords—Bone cancer, Owl search, hyperparameter tuning, Inception v3

Simple SummaryEarly detection of oral cancer is important to increase the survival rate and reduce morbidity. For the past few years, the early detection of oral cancer using artificial intelligence (AI) technology based on autofluorescence imaging, photographic imaging, and optical coherence tomography imaging has been an important research area. In this study, diagnostic values including sensitivity and specificity data were comprehensively confirmed in various studies that performed AI analysis of images. The diagnostic sensitivity of AI-assisted screening was 0.92. In subgroup analysis, there was no statistically significant difference in the diagnostic rate according to each image tool. AI shows good diagnostic performance with high sensitivity for oral cancer. Image analysis using AI is expected to be used as a clinical tool for early detection and evaluation of treatment efficacy for oral cancer.The accuracy of artificial intelligence (AI)-assisted discrimination of oral cancerous lesions from normal mucosa based on mucosal images was evaluated. Two authors independently reviewed the database until June 2022. Oral mucosal disorder, as recorded by photographic images, autofluorescence, and optical coherence tomography (OCT), was compared with the reference results by histology findings. True-positive, true-negative, false-positive, and false-negative data were extracted. Seven studies were included for discriminating oral cancerous lesions from normal mucosa. The diagnostic odds ratio (DOR) of AI-assisted screening was 121.66 (95% confidence interval [CI], 29.60; 500.05). Twelve studies were included for discriminating all oral precancerous lesions from normal mucosa. The DOR of screening was 63.02 (95% CI, 40.32; 98.49). Subgroup analysis showed that OCT was more diagnostically accurate (324.33 vs. 66.81 and 27.63) and more negatively predictive (0.94 vs. 0.93 and 0.84) than photographic images and autofluorescence on the screening for all oral precancerous lesions from normal mucosa. Automated detection of oral cancerous lesions by AI would be a rapid, non-invasive diagnostic tool that could provide immediate results on the diagnostic work-up of oral cancer. This method has the potential to be used as a clinical tool for the early diagnosis of pathological lesions.

Prostate cancer (PCa) is one of the most common and deadliest cancers that kill men worldwide with high mortality and prevalence especially in developed countries. PCa is regarded as one of the most prevalent cancers and is one of the main causes of deaths worldwide. Early detection of PCa diseases helps in making decisions about the progressions that should have occurred in high-risk patients decrease their risks. The recent developments in technology and methods have given rise to computer aided diagnosis (CAD). Early cancer detection can greatly increase the chance of survival through the administration of the proper treatment. Due to the emerging trends and available datasets in state-of-art machine learning (ML) and deep learning (DL) techniques, there has been significant growth in recent disease prediction and classification publications. This paper presents a unique support vector machine-based model for PCa detection and classification. This analysis aims to classify the PCa using ML algorithm and to determine the risk factors. Support vector machines (SVM) is used to identify and classify the PCa. Accuracy, sensitivity, specificity, precision, and F1-score are the measurements used to evaluate the performance of the presented method. This model will achieve accuracy, sensitivity, specificity, precision, and F1-score than earlier models.

Improved heart disease detection from ECG signal using deep learning based ensemble model

BackgroundHead and neck cancer (HNC) is one of the most prevalent malignant tumors, with higher incidence and mortality rates in men than in women, particularly for lip and oral cavity, nasopharyngeal, laryngeal, and other pharyngeal cancers. This study investigates global trends in the occurrence of these cancers in men from 1990 to 2021 and analyzes their changing trends to guide healthcare policymakers in resource allocation.MethodsUsing data from the 2021 Global Burden of Disease Study (GBD 2021), this study assesses the global prevalence, incidence, mortality, and disability-adjusted life years (DALYs) for male head and neck cancers. It also evaluates the relationship between cancer burden and economic development using the Socio-Demographic Index (SDI) and analyzes the risk factors for male head and neck cancer mortality and DALYs.ResultsFrom 1990 to 2021, the impact of male head and neck cancers increased at varying rates. In 2021, there were 968,573 prevalent cases of lip and oral cavity cancer, 272,917 incident cases, 136,890 deaths, and 3,969,812 DALYs globally. The burden of nasopharyngeal, laryngeal, and other pharyngeal cancers was lower, with 385,913, 939,924, and 258,723 prevalent cases, respectively. The age-standardized incidence rates for all four cancers were positively correlated with the SDI. Key risk factors for male head and neck cancers include smoking and alcohol consumption. Additional risk factors include chewing tobacco for lip and oral cavity cancer deaths, formaldehyde exposure for nasopharyngeal cancer, and occupational exposure to sulfuric acid and asbestos for laryngeal cancer.ConclusionsLip and oral cavity cancer remains the most burdensome, while nasopharyngeal cancer is increasing in East and Southeast Asia. Laryngeal cancer has declined in high-SDI regions, while other pharyngeal cancers are rising. Gender and lifestyle are key risk factors, underscoring the need for early prevention, particularly in resource-limited areas. As the global population ages, targeted prevention and improved healthcare infrastructure are essential.

The objective of this study was to examine the effects of marital status on stage at presentation, receipt of treatment, and survival in patients with head and neck cancer (HNC). The Surveillance, Epidemiology, and End Results database was used to analyze 51,272 patients who were diagnosed with HNC from 2007 to 2010. The impact of marital status on cancer stage at presentation, receipt of definitive treatment, and HNC-specific mortality (HNCSM) was determined using multivariable logistic and Fine and Gray competing-risks regression models, as appropriate. Marriage had a protective effect against metastatic presentation of oral and laryngeal cancers (oral cancer: adjusted odds ratio [AOR], 0.72; 95% confidence interval [CI], 0.60-0.87; P < .001; laryngeal cancer: AOR, 0.53; 95% CI, 0.42-0.67; P < .001) but not against oropharyngeal, hypopharyngeal, or nasopharyngeal cancers. Among patients with nonmetastatic disease, married patients were more likely to receive definitive treatment (overall AOR, 1.77; 95% CI, 1.60-1.95; P < .001) and had a lower risk of HNCSM (overall adjusted hazard ratio, 0.72; 95% CI, 0.68-0.77; P < .001); these associations remained significant across all HNC sites. Among patients with oral and laryngeal cancers, those who are married are less likely to present with metastatic disease. In addition, married patients are more likely to receive definitive treatment and less likely to die from HNC across all HNC sites. This suggests that spousal support may have a role in the surveillance of visual and symptomatic HNC types and leads to higher rates of treatment and better survival across all HNC sites.

Head and neck squamous cell carcinoma (HNSCC) is responsible for a large number of deaths each year. Oral cancer is the most frequent subtype of HNSCC. Historically, oral cancer has been associated with an increase in the consumption of tobacco and alcohol products, seen especially in the Asian subcontinent. It has also been associated with infection by the human papilloma virus (HPV), particularly strain HPV16. Treatment usually involves a multidisciplinary approach of surgery combined with chemotherapy and radiation. The advent of immunotherapy has broadened the scope for treatment. A better immune response to the tumour can also elicit the action of other therapeutic approaches. A heightened immune response, on the other hand, can lead to resistant tumour formation through the process of immunoediting. Molecular profiling of the tumour microenvironment (TME) can provide us with better insight into the mechanism and progression of the disease, ultimately opening up new therapeutic options. High-throughput molecular profiling techniques over the past decade have enabled us to appreciate the heterogeneity of the TME. In this review, we will be describing the clinicopathological role of the immune and genomic landscape in oral cancer. This study will update readers on the several immunological and genetic factors that can play an important function as predictive and prognostic biomarkers in various forms of head and neck cancer, with a special emphasis on oral carcinoma.

Among head and neck cancers, oral cancer (OC) is one of the most common forms. OC is diagnosed at an advanced locoregional stage, it has increased individuals of deaths, making it the sixth common cancer recorded globally. Although the greater part of OC was discovered in the final stage, about 45% probability of living two more years, early detection and prompt treatment provide the best results for patients. Poor OC outcomes are mostly caused by insufficient or nonexistent detection and monitoring in the regional primary centre, which holds up the patient transfer to specialists, for the further management. Artificial intelligence (AI) was developed quickly in the area of cancer, with noteworthy advancements recently documented. Through this review, the current work seeks to expand the body of evidence supporting the early adoption of AI in OC screening. AI may play a key role in properly predicting the onset of OC, but certain technical issues must be addressed simultaneously with the growth of AI approaches to allow for their general transfer to individuals predicated detection protocols.

10027 Background: Some studies reported the presence of somatic mutation of EGFR in head and neck cancer. Human papillomavirus (HPV) was associated with some types of head and neck cancer. We performed this study to determine clinical significance of EGFR mutation and its association with HPV infection in patients with tongue and tonsil cancer. Methods: We sequenced exons 18–21 of EGFR TK domain and HPV typing was performed using the HPV DNA chip in tissues of patients with tongue and tonsil cancer. Univariate and multivariate analysis was performed. Results: Eighty-one patients were included. We detected EGFR mutation in 10 (12%) patients. Mutation was significantly frequent in never-smoker (21% versus 5%; P = 0.031). The mutation frequency did not differ between tongue and tonsil cancer (12% vs. 13%, respectively; P = 0.978). There was no difference between female and male (12% vs. 14%, respectively; P = 0.754). Eleven of 81 (14%) patients were HPV positive. HPV positivity was more common in young (&lt;60 years) than older (≥60 years) patients (20% vs. 3%, respectively; P = 0.039). Patients with tonsil cancer showed more frequent HPV positivity than tongue cancer (42% vs. 2%, respectively; P &lt; 0.001). There was no association between HPV positivity and EGFR mutation. In terms of disease-free survival, patients with EGFR mutation had better survival independently of stage and primary site (hazard ratio, 0.246; 95% CI, 0.075 to 0.802). Conclusions: We did not find association between EGFR mutation and HPV positivity. Patients with EGFR mutation showed better outcome in tongue and tonsil cancer. These results suggest that EGFR mutation may be a prognostic factor in patients with head and neck cancer. No significant financial relationships to disclose.

Oral cancer has become a major debilitating incidence in both genders alike. Oral cancer, a part of head and neck cancer, is a combination of two types of cancer: oral cavity cancer and oropharyngeal cancer. The most common type of oral cancer is the squamous cell carcinoma which represents more than 90% of oral cancer cases. There are in existence common types of oral cancer as well, in addition to precancerous or benign lesions and tumors. These lesions and tumors may lead to cancer if left untreated. There is an increased need to combat oral cancer and its benign or malignant precursors. There is no better way of starting this battle than prevention. Prevention against oral cancer is divided into three stages, namely, primary, secondary, and tertiary prevention. Primary prevention has its manifestations in the control and/or elimination of risk factors for cancer such as tobacco smoking, excessive alcohol consumption, chewing betel quid, prolonged sunlight exposure, and improper nutrition, among others. Secondary prevention encompasses screening tests and early diagnosis and treatment of diseases that may potentially cross over into malignancy. Tertiary prevention is indicated when a person has previously had cancer or oral cancer, also when a person is immunosuppressed or has GVHD due to stem cell transplant. This stage also includes gene mutation assessment, an estimate of personal cancer risk and seeking of personalized genetic recommendations. Current research also focuses on emerging gene therapy through employing adenoviruses. This chapter will address and focus on the aforementioned prevention strategies, elaborating and expanding on risk factors and how to decrease chances of developing oral cancer. Additionally we will look at barriers against prevention developing an intricate and complete picture of the links between methods of prevention and factors that hinder prevention. In exploring the details within the chapter, one can conclude that oral cancer is a disease that is preventable and controllable but habitually has been given little significance due to many factors. Oral cancer is typically discovered late in its development, most often when it has already metastasized to the lymph nodes, at which point prognosis becomes very poor. Therefore, we firmly believe that it is no longer viable that prevention be considered a person’s own responsibility but rather a matter of a group of health professionals. Oral cancer should be prevented through creating awareness, behavioral change, routine dental checkups, and policies that eradicate exposure to risk factors.

Introduction:Human papillomavirus (HPV) causes the most common sexually transmitted infection (STI) in the world. It affects people regardless of gender and age, causing genital warts and cancer. Objective:To evaluate university students’ knowledge of HPV and its relationship with head and neck and oral cancers. Methods: This is a cross-sectional study using an online questionnaire administered to undergraduate students at a public university (n=335). Results:In total, 69.3% of the participants were unaware of the relationship between HPV and head and neck cancers and 34.6% claimed that HPV may not cause oral cancer. The chances of knowing about the relationship of HPV with head and neck cancers were significant for participants who knew that HPV could be asymptomatic (OR = 9.9; p = 0.029), that might cause genital warts in men (OR = 4.0; p = 0.015), and those aged 24 years or older (OR = 1.9; p = 0.021). However, undergraduate students in the field of health and medicine (OR = 0.419; p = 0.002), who had sex at least twice a week (OR = 0.471; p = 0.017), and were unaware of the target public for the HPV vaccine (OR: 0.222, p<0.001) were less likely to know about the relationship. Students who knew of the relationship between HPV and female (OR = 3.6; p = 0.010) and male genital warts (OR = 3.0; p = 0.005) or were immunized (OR = 1.8; p = 0.020) were more likely to understand the viral interaction with oral cancer. Those who were unaware of the population eligible for HPV vaccine (OR = 0.493; p = 0.017) also showed gaps in their knowledge of this relationship. Conclusion: Our findings showed that there were limitations in the knowledge about HPV, its vaccine, and its relationship with head and neck and oral cancers.

Oral cancer as well as other Head and Neck cancer (HNC) patients face adverse effects because of the range of treatment and the possibility of treatment-related toxicity. This includes complications like skin desquamation, depression, mucositis, nausea and vomiting. It negatively impacts the Quality of life (QoL) of HNC patients post-treatment. The goal of this study was to conduct a literature review on the occurrence of various difficulties, such as nutrition, functional status, psychological well-being and decreased QoL in post-chemoradiotherapy in head and neck cancer survivors, specifically oral cancer survivors. Databases like Google Search, Google Scholar, PubMed, Scopus, Web of Science and ScienceDirect were searched with keywords such as ‘Chemoradiotherapy’, ‘Chemotherapy’, ‘Radiotherapy’, ‘Oral cancer’ ‘Head and Neck Cancer’ and ‘QoL’ ‘Quality of life’. 30 research papers fulfilled the criteria of focusing on Oral cancer and HNC patients. The head and neck carcinomas are close to various bodily structures involved in vital physiological and social activities components. Thereupon the collateral damage commonly associated with disease treatment affects essential bodily functions and can have adverse consequences on the QoL of the patients. Patients receiving concurrent chemoradiotherapy experience such substantial side effects that it hampers their ability to finish their treatment cycle without pauses or dose modifications. Therefore, it is essential to monitor and prevent such effects from CRT. Psychological interventions, palliative care and other such efforts can help improve the QoL of Oral cancer patients.