Search

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.

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.

SignificanceConvolutional 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.AimDevelop 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.ApproachWe 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.ResultsThe 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.ConclusionsWe demonstrate the effectiveness of our approach for more interpretable and reliable oral potentially malignant lesion and malignant lesion classification.

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

SignificanceEarly 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.AimTo reduce the class bias caused by data imbalance.ApproachWe 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.ResultsBy 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.ConclusionsExperimental 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.

SignificanceOral 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.AimTo develop a mobile-based dual-mode image classification method and customized Android application for point-of-care oral cancer detection.ApproachThe 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.ResultsWe 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.ConclusionsOur study demonstrates the effectiveness of a mobile-based approach for oral cancer screening in low-resource settings.

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.

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.

Byline: Praveen. Birur, Sanjana. Patrick, Saman. Warnakulasuriya, Keerthi. Gurushanth, Shubhasini. Raghavan, Goura. Rath, Pankaj. Chaturvedi, Vijay. Chandru, Babu. Mathew, Kumar. Prabhash, Shubha. Gurudath, Nirza. Mukhia, Sumsum. Sunny, Ravi. Mehrotra, V. [...]

Objectives Materials and Methods Results Conclusions The incidence of oral cancer is significantly high in South Asia and Southeast Asia. Organized screening is an effective approach to early detection. The aim of this systematic review and meta‐analysis was to evaluate the reliability, diagnostic accuracy, and effectiveness of visual oral screening by community health workers (CHWs) in identifying oral cancer/oral potentially malignant disorders (OPMDs) in this region.We conducted a bibliographic search in PubMed, Scopus, the gray literature of Google Scholar, ProQuest dissertations, and additional manual searches. Twelve articles were included for qualitative synthesis and six for meta‐analysis. Pooled sensitivity, specificity, diagnostic odds ratio (DOR), and forest plot analysis were performed.Meta‐analysis showed CHWs identified 8% (n = 6365) as suspicious and 92% (n = 74,140) as normal. The diagnostic accuracy of visual oral screening by CHWs showed a sensitivity of 75% (CI: 74–76) and specificity of 97% (CI: 97–97) in the detection of OPMDs/oral cancer. Forest plots were obtained using a random effects model (DOR: 24.52 (CI: 22.65–26.55)) and SAUC: 0.96 (SE = 0.05).Oral visual examination by trained CHWs can be utilized for community screenings to detect oral cancer early. This approach can be used in primary healthcare to triage patients for further referral and management. [ABSTRACT FROM AUTHOR]

Objectives: Position of inferior alveolar canal with respect to an impacted third molar reveals certain radiographic signs, but three-dimensional relationship to the canal can be provided with cone-beam computed tomography (CBCT). The purpose of this study was to determine which radiographic signs on panoramic radiography indicate a true relationship on CBCT. Materials and Methods: Forty samples with signs or symptoms of impacted mandibular third molar and panoramic radiograph showing signs of a close relationship with the mandibular canal as described by Félez-Gutiérrez et al. were included in the study and subjected to CBCT. Radiographic signs on panoramic radiography were compared with the relationship on CBCT. Statistical analysis was done using Chi-square test. Results: Twenty-one samples (52.5%) showed darkening of the apex, which was the most frequent type of radiographic sign of a close relationship on panoramic radiography. Twenty-three samples (57.5%) revealed a true relationship on CBCT. Darkening of the apex and narrowing of the canal were the signs most frequently associated with a true relationship. On CBCT, coronal and axial sections better predicted a true relationship. Conclusion: This study showed that the presence of any of the radiographic signs cannot definitely predict a true relationship; however, the presence of a close sign on panoramic radiography is often associated with a true relationship to the canal.

Byline: N. Birur, Keerthi. Gurushanth, Sanjana. Patrick, Sumsum. Sunny, Shubhasini. Raghavan, Shubha. Gurudath, Usha. Hegde, Vidya. Tiwari, Vipin. Jain, Mohammed. Imran, Pratima. Rao, Moni. Kuriakose Background: The global incidence of [...]

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 < 0.001) in gray values for all the hyperdense structures in CBCT when compared to HU values of MSCT scans.Conclusion: The gray value for hypodense structures in large volume CBCT scan was more reliable and analogous to HU value in MSCT. The determination of grey values in CBCT may not be as accurate as HU value in CT for hyperdense structures. [ABSTRACT FROM AUTHOR]

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 < 0.001) in gray values for all the hyperdense structures in CBCT when compared to HU values of MSCT scans., Conclusion: The gray value for hypodense structures in large volume CBCT scan was more reliable and analogous to HU value in MSCT. The determination of grey values in CBCT may not be as accurate as HU value in CT for hyperdense structures.