Papers by Shubha Gurudath
Journal of maxillofacial and oral surgery/Journal of Maxillofacial & Oral Surgery, May 18, 2024
Indian Journal of Cancer, 2014
Oral submucous fibrosis (OSMF) a condition first described in the 1950s in the modern literature ... more Oral submucous fibrosis (OSMF) a condition first described in the 1950s in the modern literature still remains elusive of a cure. For many years this condition had been confined to countries like India, Pakistan, Bangladesh, etc., but now this condition is being reported from Western countries as well. Inspite of intensive research over the years into the etiologic factors of OSMF, a single etiologic factor cannot be pointed out with certainty rather several causative factors have been proposed. Patients suffering with OSMF initially present with a blanched or marble-like pale mucosa, vesiculations, and also intolerance to hot and spicy food. Gradually, the patient may develop fibrous bands in the buccal and labial mucosa which causes a restriction in opening the mouth. The evidence for the various treatment modalities for OSMF is weak hence better documentation of the studies performed with standardized criteria is required. The current review aims to refresh our knowledge regarding OSMF from an Indian perspective and make a few suggestions to fill the lacunae in this field.
PLOS ONE
The high prevalence of oral potentially-malignant disorders exhibits diverse severity and risk of... more The high prevalence of oral potentially-malignant disorders exhibits diverse severity and risk of malignant transformation, which mandates a Point-of-Care diagnostic tool. Low patient compliance for biopsies underscores the need for minimally-invasive diagnosis. Oral cytology, an apt method, is not clinically applicable due to a lack of definitive diagnostic criteria and subjective interpretation. The primary objective of this study was to identify and evaluate the efficacy of biomarkers for cytology-based delineation of high-risk oral lesions. A comprehensive systematic review and meta-analysis of biomarkers recognized a panel of markers (n: 10) delineating dysplastic oral lesions. In this observational cross sectional study, immunohistochemical validation (n: 131) identified a four-marker panel, CD44, Cyclin D1, SNA-1, and MAA, with the best sensitivity (>75%; AUC>0.75) in delineating benign, hyperplasia, and mild-dysplasia (Low Risk Lesions; LRL) from moderate-severe dyspla...
Cancers, Feb 23, 2023
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Indian Journal of Cancer
Oral cancer is usually preceded by oral potentially malignant disorders (OPMDs) and early detecti... more 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.
Oral Cancer is one of the most common causes of morbidity and mortality. Screening and mobile Hea... more 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...
Journal of Biomedical Optics
Significance: Oral cancer is one of the most prevalent cancers, especially in middle-and low-inco... more Significance: Oral cancer is one of the most prevalent cancers, especially in middle-and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output. Aim: We aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions. Approach: This work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists. Results: The proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings. Conclusions: Our study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model's prediction can be improved.
Lecture Notes in Networks and Systems, 2021
Rapid urbanization and a consumption centric economy have created an enormous pressure on the env... more Rapid urbanization and a consumption centric economy have created an enormous pressure on the environment. Air, water and soil pollution are a global problem. The affects of pollution are more apparent in developing countries such as China and India, because of various economic and demographic factors. In major cities, such as New Delhi, Beijing, the air pollution reaches hazardous levels, especially during winters. Air quality measurement is the first step toward mitigating the effects of air pollution; hence, there has been an effort to set up air quality measurement stations all over the world. However, the availability of these measurement stations is sparser in developing countries, where the air quality is lower. Hence, there is a need for low-cost air quality measurement devices. The following work presents a brief overview of various low-cost approaches to measuring air quality.
Journal of Orofacial Sciences, 2012
Present study was undertaken to estimate and compare erythrocyte superoxide dismutase (E-SOD) and... more Present study was undertaken to estimate and compare erythrocyte superoxide dismutase (E-SOD) and Glutathione peroxidase (GPx) levels in oral submucous fibrosis, oral leukoplakia and oral cancer patients and age/sex matched healthy subjects, 25 in each group. Statistically significant (P 0.05). Oral cancer group had the lowest levels amongst the study groups. Imbalance in antioxidant enzyme status may be considered as one of the factors responsible for the pathogenesis of cancer and may serve as a potential biomarker and therapeutic target to reduce the malignant transformation in oral premalignant lesions/conditions.
Journal of Medicine, Radiology, Pathology and Surgery, 2018
Background and Objectives: Oral submucous fibrosis (OSMF) is a potentially malignant lesion of th... more Background and Objectives: Oral submucous fibrosis (OSMF) is a potentially malignant lesion of the oral cavity and successful management remains a challenge. Our study aims to compare the efficacy of three commonly used modalities of treatment, namely (i) non-invasive therapy like physiotherapy only, (ii) physiotherapy in combination with antioxidants, and (iii) invasive therapy like intralesional therapy. It aimed to ascertain the most effective treatment modality among the three which one of them helped improve the maximum mouth opening (MMO) and reduce oral sensitivity to spicy food as measured on numeric analog scale (NAS). Materials and Methods: This randomized multilabel study was conducted on 49 patients visiting the outpatient Department of Oral Medicine and Radiology, over a 2-year period. A detailed history of burning sensation in the mouth and the severity was recorded using NAS. A Vernier caliper was used for the measurement of MMO. The symptom of burning sensation and MMO was evaluated on the 15 th , 30 th , 45 th , and 90 th days. Results: Findings from the study showed that physiotherapy alone was not effective in alleviating neither burning sensation nor did it significantly improve the MMO. The percentage decrease in burning sensation was highest in the interventional group receiving an intralesional injection (87.4% at 45 days and 100% at 90 days). Physiotherapy with antioxidant group showed almost similar percentage decrease in burning sensation as the interventional group (80.8% at 45 days and 96.8% at 90 days. For MMO, physiotherapy with antioxidant group showed better MMO at 90 days (34.2% vs. 26.8%). Conclusion: A non-invasive treatment modality of physiotherapy with antioxidant treatment modality is as effective as an invasive intralesional injection, in the management of patients with OSMF. The findings suggest that non-invasive modality of physiotherapy with antioxidant treatment can be considered as standard care for the management of OSMF.
Indian Journal of Cancer, 2014
Frontiers in Optics / Laser Science, 2020
We will report a mobile-based dual-mode image classification method for oral cancer detection in ... more We will report a mobile-based dual-mode image classification method for oral cancer detection in low-resource settings.
Journal of Biomedical Optics, 2022
Significance: Convolutional neural networks (CNNs) show the potential for automated classificatio... more 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.
International Journal of Forensic Odontology, 2017
Context: In fire accidents and cremation, fires may reach temperatures as high as 1150°C. In such... more Context: In fire accidents and cremation, fires may reach temperatures as high as 1150°C. In such circumstances, teeth and bones are the only remains which can help in personal identification, as teeth and restorations are unique to an individual. Aims: This study was conducted to assess morphological and radiographic appearances of teeth at various high temperatures. Settings and Design: This was an in vitro observational study; 160 extracted teeth were included in the study. The teeth were randomly classified into four groups of 40 teeth each. Teeth in Group 1 were retained without any restorations. A total of 60 teeth were endodontically sealed with zinc oxide eugenol sealer and restored with gutta-percha; coronal restorations were made with amalgam, light cure composite, or restorative glass ionomer cement. Radiographs of all teeth were obtained. Subjects and Methods: A burnout furnace was used for heating the teeth. Forty teeth each were heated to 200°C, 400°C, 600°C, and 800°C. The teeth and restorations were physically examined, and radiographs of all teeth were again obtained and correlated with the preincineration radiographs. Results: Teeth showed progressive discoloration from black to white, with the development of cracks and crowns shattered by 800°C. Restoration lost their marginal adaptation. On radiographs, initially, crowns developed fissures, followed by the roots. Conclusion: This study documented morphological and radiographic changes occuring in teeth when exposed to high temperatures.
Cancers, 2021
Non-invasive strategies that can identify oral malignant and dysplastic oral potentially-malignan... more 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-OPM...
Frontiers in Optics / Laser Science, 2020
Standard deep learning algorithms for clinical image classification are unable to understand thei... more 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.
Journal of Biomedical Optics, 2021
Significance: Oral cancer is among the most common cancers globally, especially in low-and middle... more 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.
Frontiers in Optics / Laser Science, 2020
Journal of Biomedical Optics, 2021
Significance: Early detection of oral cancer is vital for high-risk patients, and machine learnin... more Significance: Early detection of oral cancer is vital for high-risk patients, and machine learningbased 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.
Journal of Indian Academy of Oral Medicine and Radiology, 2017
Objectives: Position of inferior alveolar canal with respect to an impacted third molar reveals c... more 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.
Uploads
Papers by Shubha Gurudath