Thermal Imaging of the Tongue Surface as a Predictive Method in the Diagnosis of Type 2 Diabetes Mellitus.

Over the past 20 years, the high prevalence of diabetes has become a global public health problem. BACKGROUND: The objective of this study was to develop a non-invasive screening method for diabetes which will enable the detection of the disease at an early stage. METHODS: This study included 63 adult patients of both sexes: 30 patients with type 2 diabetes (t2DM) and 33 healthy volunteers. The temperature distribution on the tongue's dorsum and apex surface was studied in patients after a mouth-cooling procedure had been introduced. The study used an FLIR T540 thermal imaging camera. An analysis of the correlation between the ∆T values of the tongue dorsum and apex and the glycated hemoglobin (HbA1c) level was performed. RESULTS: The median of the average dorsum temperature measured 10 min after mouth rinsing was almost 0.8 [°C] lower than for healthy individuals. Also, studies showed a positive average correlation with a Pearson coefficient of r = 0.46 between the HbA1c level and the ∆T of the tongue dorsum. CONCLUSIONS: Tongue temperature measured using the IRT showed a correlation with standard biochemical parameters; it may also differentiate patients and constitute a specific screening method for patients with t2DM.

Whole-body fasciculation detection in amyotrophic lateral sclerosis using motor unit MRI.

OBJECTIVE: Compare fasciculation rates between amyotrophic lateral sclerosis (ALS) patients and healthy controls in body regions relevant for diagnosing ALS using motor unit MRI (MUMRI) at baseline and 6 months follow-up, and relate this to single-channel surface EMG (SEMG). METHODS: Tongue, biceps brachii, paraspinals and lower legs were assessed with MUMRI and biceps brachii and soleus with SEMG in 10 healthy controls and 10 patients (9 typical ALS, 1 primary lateral sclerosis [PLS]). RESULTS: MUMRI-detected fasciculation rates in typical ALS patients were higher compared to healthy controls for biceps brachii (2.40 ± 1.90 cm-3min-1vs. 0.04 ± 0.10 cm-3min-1, p = 0.004), paraspinals (1.14 ± 1.61 cm-3min-1vs. 0.02 ± 0.02 cm-3min-1, p = 0.016) and lower legs (1.42 ± 1.27 cm-3min-1vs. 0.13 ± 0.10 cm-3min-1, p = 0.004), but not tongue (1.41 ± 1.94 cm-3min-1vs. 0.18 ± 0.18 cm-3min-1, p = 0.556). The PLS patient showed no fasciculation. At baseline, 6/9 ALS patients had increased fasciculation rates compared to healthy controls in at least 2 body regions. At follow-up every patient had increased fasciculation rates in at least 2 body regions. The MUMRI-detected fasciculation rate correlated with SEMG-detected fasciculation rates (τ = 0.475, p = 0.006). CONCLUSION: MUMRI can non-invasively image fasciculation in multiple body regions and appears sensitive to disease progression in individual patients. SIGNIFICANCE: MUMRI has potential as diagnostic tool for ALS.

Artificial intelligence in tongue diagnosis: classification of tongue lesions and normal tongue images using deep convolutional neural network.

OBJECTIVE: This study aims to classify tongue lesion types using tongue images utilizing Deep Convolutional Neural Networks (DCNNs). METHODS: A dataset consisting of five classes, four tongue lesion classes (coated, geographical, fissured tongue, and median rhomboid glossitis), and one healthy/normal tongue class, was constructed using tongue images of 623 patients who were admitted to our clinic. Classification performance was evaluated on VGG19, ResNet50, ResNet101, and GoogLeNet networks using fusion based majority voting (FBMV) approach for the first time in the literature. RESULTS: In the binary classification problem (normal vs. tongue lesion), the highest classification accuracy performance of 93,53% was achieved utilizing ResNet101, and this rate was increased to 95,15% with the application of the FBMV approach. In the five-class classification problem of tongue lesion types, the VGG19 network yielded the best accuracy rate of 83.93%, and the fusion approach improved this rate to 88.76%. CONCLUSION: The obtained test results showed that tongue lesions could be identified with a high accuracy by applying DCNNs. Further improvement of these results has the potential for the use of the proposed method in clinic applications.

Wurster Technology-Assisted Step-by-Step Engineering of Multi-layered Pellets (Sprinkles): Microscopy, Micro-CT, and e-Tongue-Based Analysis.

The advancement in the formulation and characterization techniques have paved the path for development of new as well as modification of existing dosage forms. The present work explores the role of micro-computed tomography (micro-CT) as advanced characterization technique for multi-layered-coated pellets to ascertain the quality of coated pellets. The work further explored in-house e-tongue technique for understanding palatability of formulation in early stages of development thus by reducing clinical taste evaluation time. The developed multi-layered-coated pellets were characterized using microscopy (optical and electron microscopy). The obtained results demonstrated formation of spherical-shaped pellets with uniform coating. The uniform coating was further confirmed by results obtained from scanning electron microscopy (SEM) and cross-sectional SEM analysis, which showed visible difference in pellet surface before and after multi-layered coating. The micro-CT results confirmed the visible demarcation of layers (drug and polymer, i.e., hydroxypropyl methylcellulose (HPMC) and eudragit (EPO)) along with uniform thickness of various layering. The dissolution study of developed pellets suggested the role of layering EPO on drug release from pellets. The e-tongue analysis proved to be an excellent tool for early prediction of taste masking of drug via multi-layered pellets and can serve as potential platform for taste masking with high specificity. The overall results suggest the suitability of developed multi-layered platform as efficient dosage form (sprinkle) in pediatric/geriatric product development.

Tongue position in Mandarin Chinese voiceless stops.

The current study explores whether Mandarin initial and medial voiceless unaspirated and voiceless aspirated stops differ in their tongue positions and post-vocalic voicing during closure. Ultrasound tongue imaging and acoustic data from five Mandarin speakers revealed (1) no consistent pattern for tongue positions among speakers, and (2) no difference in degree of voicing during closure between the two stop series. These findings suggest that tongue position is not a reliable articulatory correlate for Mandarin laryngeal contrasts. This further suggests that aspiration is not correlated with tongue position differences, unlike the reported correlation between voicing and tongue root advancement.

Deep Upscale U-Net for automatic tongue segmentation.

In a treatment or diagnosis related to oral health conditions such as oral cancer and oropharyngeal cancer, an investigation of tongue's movements is a major part. In an automatic measurement of such movement, it must first start with a task of tongue segmentation. This paper proposes a solution of tongue segmentation based on a decoder-encoder CNN-based structure i.e., U-Net. However, it could suffer from a problem of feature loss in deep layers. This paper proposes a Deep Upscale U-Net (DU-UNET). An additional up-sampling of the feature map from a contracting path is concatenated to an upper layer of an expansive path, based on an original U-Net structure. The segmentation model is constructed by training DU-UNET on the two publicly available datasets, and transferred to the self-collected dataset of tongue images with five tongue postures which were recorded at a far distance from a camera under a real-world scenario. The proposed DU-UNET outperforms the other existing methods in our literature reviews, with accuracy of 99.2%, mean IoU of 97.8%, Dice score of 96.8%, and Jaccard score of 96.8%.

Superior laryngeal artery originating from the lingual artery.

In most cases, the superior laryngeal artery (SLA) branches from the superior thyroid artery, which, in turn, leaves the external carotid artery. Few dissection studies found previously that the SLA could originate from the lingual artery. We report here probably the first evidence of such a rare anatomical variation found unilaterally in a retrospectively evaluated by computed tomography angiography adult male case. The left SLA left a suprahyoid coil of the lingual artery and continued over the greater hyoid horn to enter the larynx through the thyrohyoid membrane. On both sides, thyroid foramina were found, but only the right one used for the entry of the right SLA. Therefore, the rare SLA origin from the lingual artery can be documented on computed tomography angiograms, which could help during preoperative evaluations and prevent unwanted surgical complications.

Prospective Observational Study for the Comparison of Screening Methods Including Tongue Pressure and Repetitive Saliva Swallowing With Detailed Videofluoroscopic Swallowing Study Findings in Patients With Acute Stroke.

BACKGROUND: Simple, noninvasive, and repeatable screening methods are essential for assessing swallowing disorders. We focused on patients with acute stroke and aimed to assess the characteristics of swallowing screening tests, including the modified Mann Assessment of Swallowing Ability score, tongue pressure, and repetitive saliva swallowing test (RSST), compared with detailed videofluoroscopic swallowing study (VFSS) findings to contribute as a helpful resource for their comprehensive and complementary use. METHODS AND RESULTS: We enrolled first-ever patients with acute stroke conducting simultaneous assessments, including VFSS, modified Mann Assessment of Swallowing Ability score, tongue pressure measurement, and RSST. VFSS assessed aspiration, laryngeal penetration, oral cavity residue, vallecular residue, pharyngeal residue, and swallowing reflex delay. Screening tests were compared with VFSS findings, and multiple logistic analysis determined variable importance. Cutoff values for each abnormal VFSS finding were assessed using receiver operating characteristic analyses. We evaluated 346 patients (70.5±12.6 years of age, 143 women). The modified Mann Assessment of Swallowing Ability score was significantly associated with all findings except aspiration. Tongue pressure was significantly associated with oral cavity and pharyngeal residue. The RSST was significantly associated with all findings except oral cavity residue. Receiver operating characteristic analyses revealed that the minimum cutoff value for all VFSS abnormal findings was RSST ≤2. CONCLUSIONS: The modified Mann Assessment of Swallowing Ability is useful for broadly detecting swallowing disorders but may miss mild issues and aspiration. The RSST, with a score of ≤2, is valuable for indicating abnormal VFSS findings. Tongue pressure, especially in oral and pharyngeal residues, is useful. Combining these tests might enhance accuracy of the swallowing evaluation.

The role of the tongue in post-stroke dysphagia and obstructive sleep apnea: Correlation with sonography measurement.

OBJECTIVE: Obstructive sleep apnea (OSA) is a common risk factor for stroke, and dysphagia and pneumonia are both well-known complications of stroke. The development of these conditions is related to the oropharyngeal structures. We investigated whether specific structural features of the tongue may lead to the development of these complications. METHODS: Patients with ischemic stroke who required admission and community-dwelling elderly controls were enrolled. The participants underwent tongue measurements by received hand-held ultrasound, and received questionnaires to evaluate sleep quality and daytime sleepiness. The patient group also underwent objective sleep measurement by actigraphy and the 3-Step Swallowing Test (3-SSS). Sleep parameters and outcomes were analyzed. RESULTS: Patient with ischemic stroke had significantly thicker tongue than controls (6.53 cm v. 6.05 cm, p = 0.002). Multiple logistic regression analysis revealed that the anatomical parameters of the tongue in patients with stroke were significantly correlated with parameters of OSA, and the thickness of the tongue was positively correlated with the development of OSA (p = 0.024) and pneumonia (p = 0.048). CONCLUSIONS: A thicker-than average tongue may be a risk factor for OSA and pneumonia in patient with stroke. Hand-held ultrasound can be used to identify these anatomical features. Further studies are warranted to clarify the role of the tongue in these post-stroke complications.

Predicting primate tongue morphology based on geometrical skull matching. A first step towards an application on fossil hominins.

As part of a long-term research project aiming at generating a biomechanical model of a fossil human tongue from a carefully designed 3D Finite Element mesh of a living human tongue, we present a computer-based method that optimally registers 3D CT images of the head and neck of the living human into similar images of another primate. We quantitatively evaluate the method on a baboon. The method generates a geometric deformation field which is used to build up a 3D Finite Element mesh of the baboon tongue. In order to assess the method's ability to generate a realistic tongue from bony structure information alone, as would be the case for fossil humans, its performance is evaluated and compared under two conditions in which different anatomical information is available: (1) combined information from soft-tissue and bony structures; (2) information from bony structures alone. An Uncertainty Quantification method is used to evaluate the sensitivity of the transformation to two crucial parameters, namely the resolution of the transformation grid and the weight of a smoothness constraint applied to the transformation, and to determine the best possible meshes. In both conditions the baboon tongue morphology is realistically predicted, evidencing that bony structures alone provide enough relevant information to generate soft tissue.

Changes in the swallowing pattern and tongue posture during the transition from deciduous to mixed dentition-a longitudinal ultrasonography study.

BACKGROUND: Given the importance that swallowing pattern and tongue posture might have in the aetiology of malocclusion, it appears important to be aware of the physiological changes of tongue function and its posture. OBJECTIVES: The study aimed to assess changes of the swallowing pattern and tongue posture during the transition from the deciduous to mixed dentition and the association between them. MATERIALS AND METHODS: The study included 57 subjects aged 5.87 ±â€…0.5 with normal occlusion, orofacial functions, no history of trauma, or orthodontic treatment. Ultrasonography was used for the assessment of tongue posture and swallowing pattern, where the spontaneous act of swallowing was recorded. To evaluate the possible effect of incisors' eruption, the swallowing pattern and tongue posture ultrasonograms were compared at the deciduous (DD), early mixed (EMD), and intermediate mixed (IMD) timepoints. RESULTS: A significant association between the swallowing pattern and tongue posture at the DD and IMD timepoint was found. Moreover, the visceral swallowing pattern decreases with age (odds ratio [OR] = 0.777), as well as with a prolonged phase IIa (OR = 0.071), while it increases when the tongue is postured on the mouth floor (OR = 5.020). LIMITATIONS: The young age of the investigated subjects, direct contact of the probe, and the determination of the rest phase of the tongue were considered limitations. CONCLUSIONS: No statistically significant changes in swallowing pattern and tongue posture occurred during the transition period; however, a significant association between the swallowing pattern and tongue posture among subjects with normal occlusion, regardless of the dentition phase was detected.

In vivo confocal microscopy findings of cornea and tongue mucosa in patients with Sjögren's syndrome.

INTRODUCTION AND OBJECTIVES: We aimed to investigate whether Sjögren's syndrome (SS) had distinctive findings in tongue confocal microscopy in a non-invasive manner. MATERIALS AND METHODS: This retrospective case-control study evaluated corneal and tongue confocal microscopy findings of the right eyes of 25 patients with aqueous deficient dry eye and 12 healthy volunteers without dry eye findings. There were a total of 14 patients diagnosed with SS-associated dry eye (SSDE), while 11 cases were evaluated as non-Sjögren dry eye (NSDE). RESULTS: A significant difference was observed in the dendritic cell count at the corneal subbasal nerve level between the SSDE and NSDE groups (P=.018). In SSDE group, the confocal microscopy images of dendritiform hyperreflective inflammatory cells in the tongue mucosa were in favor of inflammation. However, these findings were not found in patients with NSDE or in controls. CONCLUSIONS: This study showed that confocal microscopy provided a non-invasive evaluation of the inflammatory cells in the tongue of SS patients.

Fluoroscopic-Assisted Tongue Suspension: Advancement and Innovation in the Management of Complex Pediatric Obstructive Sleep Apnea.

OBJECTIVES: The primary aim of this study is to describe a novel surgical technique developed for tongue base suspension (TBS). The second aim of this study is to assess the efficacy of the developed procedure by quantifying preoperative and postoperative polysomnographic outcomes for pediatric patients undergoing fluoroscopic-assisted tongue suspension (FATS) with the Encore System. Our hypothesis is that our FATS technique will provide at least a 50% reduction in the Apnea/Hypopnea Index (AHI), including in the medically complex pediatric population. STUDY DESIGN: Retrospective case series. METHODS: An electronic medical record review was conducted of patients who underwent FATS by a single surgeon at a tertiary care medical center between December 2019 and June 2022. Inclusion criteria included all patients <18 years old with evidence of OSA or sleep-disordered breathing and who had glossoptosis on sleep endoscopy. Data extracted from the medical record included age, gender, medical comorbidity history, reason for referral, history of airway surgeries, length of hospital stay, surgical complications data, and preoperative and postoperative polysomnographic data. Surgical success was defined by at least a 50% reduction in AHI. RESULTS: Thirty patients (53.3% male) with a mean age of 6.3 (±5.3, 0.16-17) years underwent FATS over the study period. Most patients (93%) had an underlying comorbidity: cerebral palsy (37%), chromosomal abnormalities (23%), Down syndrome (13%), Pierre-Robin sequence (10%), and obesity (10%). The majority of patients (77%) were explicitly referred for tracheostomy placement secondary to failed management of OSA. 21 patients completed both preoperative and postoperative polysomnograms. The mean preoperative AHI, obstructive AHI (oAHI), and respiratory disturbance index (RDI) were 28.8 (±19.8), 30.8 (±19.6), and 30.5 (±19.3), respectively. The mean postoperative AHI, oAHI, and RDI were 7.3 (±9.2), 7.5 (±9.1), and 7.9 (±9.3), respectively. The mean change in AHI was -21.5 (±21.4) events/h (p < 0.01, 95% CI -29.0 to -11.4 events/h). The mean percentage decrease in AHI was 74.7%. The mean change in oAHI and RDI were -23.3 (±21.9) events/h (p < 0.01 95% CI- 39.9 to -21.4 events/h) and -22.5 (±21.5) events/h (p < 0.01, 95% CI- 31.5 to -12.4 events/h), respectively. The mean percentage decrease in oAHI and RDI was 75.6% and 73.8%, respectively. Surgical success occurred in 16 of the 21 (76%) patients. Of the 23 patients referred explicitly for tracheostomy placement, 21 (91%) were able to avoid tracheostomy placement secondary to improvements in OSA. CONCLUSIONS: Patients undergoing fluoroscopic-assisted TBS revealed statistically significant improvements in AHI, oAHI, and RDI, with an overall surgical success rate of 76%. Complication rates were minimal, despite the complex nature of the study population. FATS should be considered a viable surgical approach in pediatric patients with an identified base of tongue obstruction and OSA. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:S1-S9, 2024.

An Automatic Method for Sublingual Image Segmentation and Color Analysis.

Automatic segmentation of sublingual images and color quantification of sublingual vein are of great significance to disease diagnosis in traditional Chinese medicine. With the development of computer vision, automatic sublingual image processing provides a noninvasive way to observe patients' tongue and is convenient for both doctors and patients. However, current sublingual image segmentation methods are not accurate enough. Besides, the differences in subjective judgments by different doctors bring more difficulties in color analysis of sublingual veins. In this paper, we propose a method of sublingual image segmentation based on a modified UNet++ network to improve the segmentation accuracy, a color classification approach based on triplet network, and a color quantization method of sublingual vein based on linear discriminant analysis to provide intuitive one-dimensional results. Our methods achieve 88.2% mean intersection over union (mIoU) and 94.1% pixel accuracy on tongue dorsum segmentation, and achieves 69.8% mIoU and 82.7% pixel accuracy on sublingual vein segmentation. Compared with the state-of-art methods, the segmentation mIoUs are improved by 5.8% and 5.3% respectively. Our sublingual vein color classification method has the highest overall accuracy of 81.2% and the highest recall for the minority class of 77.5%, and the accuracy of color quantization is 90.5%.Clinical Relevance- The methods provide accurate and quantified information of the sublingual image, which can assist doctors in diagnosis.

Machine learning and topological data analysis identify unique features of human papillae in 3D scans.

The tongue surface houses a range of papillae that are integral to the mechanics and chemistry of taste and textural sensation. Although gustatory function of papillae is well investigated, the uniqueness of papillae within and across individuals remains elusive. Here, we present the first machine learning framework on 3D microscopic scans of human papillae ([Formula: see text]), uncovering the uniqueness of geometric and topological features of papillae. The finer differences in shapes of papillae are investigated computationally based on a number of features derived from discrete differential geometry and computational topology. Interpretable machine learning techniques show that persistent homology features of the papillae shape are the most effective in predicting the biological variables. Models trained on these features with small volumes of data samples predict the type of papillae with an accuracy of 85%. The papillae type classification models can map the spatial arrangement of filiform and fungiform papillae on a surface. Remarkably, the papillae are found to be distinctive across individuals and an individual can be identified with an accuracy of 48% among the 15 participants from a single papillae. Collectively, this is the first evidence demonstrating that tongue papillae can serve as a unique identifier, and inspires a new research direction for food preferences and oral diagnostics.

A Case of Phlebolith in the Tip of Tongue.

The differential diagnosis of a tongue mass containing calcified bodies includes a phlebolith associated with vascular lesions, such as hemangioma and vascular malformation, and diseases such as neoplasm, osseous choristoma and hypercalcemic states, including hyperparathyroidism. The appearance of the calcified bodies on plain radiographs may help to differentiate these entities. Computed tomography, magnetic resonance imaging, and ultrasonography are also useful for differentiating these soft tissue lesions. We report a 40-year-old man with a small mass containing a calcified body in the tip of tongue. The mass was surgically resected and histologically evaluated, confirming the diagnosis of phlebolith. Our case was a rare phlebolith that did not involve a vascular lesion.

A quantitative study of airway ultrasound in predicting difficult laryngoscopy: A prospective study.

PURPOSE: As common clinical screening tests cannot effectively predict a difficult airway, and unanticipated difficult laryngoscopy remains a challenge for physicians. We herein used ultrasound to develop some point-of-care predictors for difficult laryngoscopy. METHODS: This prospective observational study included 502 patients who underwent laryngoscopy and a detailed sonographic assessment. Patients under 18 years old, or with maxillofacial deformities or fractures, limited mouth opening, limited neck movement or history of neck surgery were excluded from the study. Laryngoscopic views of all patients were scored and grouping using the modified Cormack-Lehane (CL) scoring system. The measurements acquired comprised tongue width, the longitudinal cross-sectional area of the tongue, tongue volume, the mandible-hyoid bone distance, the hyoid bone-glottis distance, the mandible-hyoid bone-glottis angle, the skin-thyrohyoid membrane distance, the glottis-superior edge of the thyroid cartilage distance (DGTC), the skin-hyoid bone distance, and the epiglottis midway-skin distance. ANOVA and Chi-square were used to compare differences between groups. Logistic regression was used to identify risk factors for difficult laryngoscopy and it was visualized by receiver operating characteristic curves and nomogram. R version 3.6.3 and SPSS version 26.0 were used for statistical analyses. RESULTS: Difficult laryngoscopy was indicated in 49 patients (CL grade Ⅲ - Ⅳ) and easy laryngoscopy in 453 patients (CL grade Ⅰ - Ⅱ). The ultrasound-measured mandible-hyoid bone-glottis angle and DGTC significantly differed between the 2 groups (p < 0.001). Difficult laryngoscopy was predicted by an area under the curve (AUC) of 0.930 with a threshold mandible-hyoid bone-glottis angle of 125.5° and by an AUC of 0.722 with a threshold DGTC of 1.22 cm. The longitudinal cross-sectional area of the tongue, tongue width, tongue volume, the mandible-hyoid distance, and the hyoid-glottis distance did not significantly differ between the groups. CONCLUSION: Difficult laryngoscopy may be anticipated in patients in whom the mandible-hyoid bone-glottis angle is smaller than 125.5° or DGTC is larger than 1.22 cm.

Facilitating the removal of a foreign body in the tongue by intraoperative ultrasound guidance: A case report.

The presence of soft tissue foreign bodies (FBs) presents a substantial concern due to their potential to induce both acute and chronic pain as well as tissue irritation. This case report documents the admission of a 25-year-old female with a history of bur fractures during endodontic treatment, accompanied by signs of infection. The clinical examination and radiographic assessment revealed an embedded foreign body within her tongue. The surgical procedure was informed by repeated ultrasound scans through the incision, facilitating precise targeting. Intraoperative ultrasound enables the accurate detection of submucosal foreign bodies in dynamic tissues like the tongue and facilitates focused and image-guided dissection, thereby decreasing surgical trauma to the delicate soft tissues.

Novel tongue-positioning device to reduce tongue motions during radiation therapy for head and neck cancer: Geometric and dosimetric evaluation.

This study aimed to assess the performance of a tongue-positioning device in interfractional tongue position reproducibility by cone-beam computed tomography (CBCT). Fifty-two patients treated with radiation therapy (RT) while using a tongue positioning device were included in the study. All patients were treated with 28 or 30 fractions using the volumetric modulated arc therapy technique. CBCT images were acquired at the 1st, 7th, 11th, 15th, 19th, 23th, and 27th fractions. Tongues on planning computed tomography (pCT) and CBCT images were contoured in the treatment planning system. Geometric differences in the tongue between pCT and CBCT were assessed by the Dice similarity coefficient (DSC) and averaged Hausdorff distance (AHD). Two-dimensional in vivo measurements using radiochromic films were performed in 13 patients once a week during sessions. The planned dose distributions were compared with the measured dose distributions using gamma analysis with criteria of 3%/3 mm. In all patients, the mean DSC at the 1st fraction (pCT versus 1st CBCT) was 0.80 while the mean DSC at the 27th fraction (pCT versus 27th CBCT) was 0.77 with statistical significance (p-value = 0.015). There was no statistically significant difference in DSC between the 1st fraction and any other fraction, except for the 27th fraction. There was statistically significant difference in AHD between the 1st fraction and the 19th, 23th, and 27th fractions (p-value < 0.05). In vivo measurements showed an average gamma passing rate of 90.54%. There was no significant difference between measurements at the 1st week and those at other weeks. The tongue geometry during RT was compared between pCT and CBCT. In conclusion, the novel tongue-positioning device was found to minimize interfractional variations in position and shape of the tongue.

ODQN-Net: Optimized Deep Q Neural Networks for Disease Prediction Through Tongue Image Analysis Using Remora Optimization Algorithm.

Tongue analysis plays the major role in disease type prediction and classification according to Indian ayurvedic medicine. Traditionally, there is a manual inspection of tongue image by the expert ayurvedic doctor to identify or predict the disease. However, this is time-consuming and even imprecise. Due to the advancements in recent machine learning models, several researchers addressed the disease prediction from tongue image analysis. However, they have failed to provide enough accuracy. In addition, multiclass disease classification with enhanced accuracy is still a challenging task. Therefore, this article focuses on the development of optimized deep q-neural network (DQNN) for disease identification and classification from tongue images, hereafter referred as ODQN-Net. Initially, the multiscale retinex approach is introduced for enhancing the quality of tongue images, which also acts as a noise removal technique. In addition, a local ternary pattern is used to extract the disease-specific and disease-dependent features based on color analysis. Then, the best features are extracted from the available features set using the natural inspired Remora optimization algorithm with reduced computational time. Finally, the DQNN model is used to classify the type of diseases from these pretrained features. The obtained simulation performance on tongue imaging data set proved that the proposed ODQN-Net resulted in superior performance compared with state-of-the-art approaches with 99.17% of accuracy and 99.75% and 99.84% of F1-score and Mathew's correlation coefficient, respectively.