Computerised assessment-a novel approach for calculation of percentage of hypomineralized lesion on incisors and its correlation with aesthetic concern.

Introduction: Molar-incisor hypomineralization (MIH) is a localized, qualitative, demarcated enamel defect that affects first permanent molars (FPMs) and/or permanent incisors. The aim of present study was to introduce a novel computerised assessment process to detect and quantify the percentage opacity associated with MIH affected maxillary central incisors. Methodology: Children (8-16 years) enrolled in the primary study having mild (white/cream or yellow/brown) MIH lesion on fully erupted maxillary permanent central incisor. 50 standardised images of MIH lesions were captured in an artificially lit room with fixed parameters and were anonymized and securely stored. Images were analysed by AI-driven computerised software and generates output classifications via a sophisticated algorithm crafted using a meticulously annotated image dataset as reference through supervised machine learning (SML). For the validation of computerised assessment of MIH lesions, the percentage of demarked opacity was calculated using ADOBE PHOTOSHOP CS7. Results: The percentage of MIH lesion was calculated through histogram plotting with the maxima ranging from 7.29 % to 71.21 % with the mean value of 34.51 %. The validation score ranged from 10.29 % to 67.27 % with the mean value of 35.32 %. The difference between the two was statistically not significant. Out of 50 patients; 11 patients had 1-30 % of surface affected with MIH and 2 had aesthetic concern; 24 had 30-60 % of surface affected and 13 had aesthetic concern; 15 had >60 % of surface affected and 12 had aesthetic concerns. Conclusions: The proposed approach exhibit sufficient quality to be integrated into a dental software addressing practical challenges encountered in daily clinical settings.

Vein segmentation and visualization of upper and lower extremities using convolution neural network.

OBJECTIVES: The study focused on developing a reliable real-time venous localization, identification, and visualization framework based upon deep learning (DL) self-parametrized Convolution Neural Network (CNN) algorithm for segmentation of the venous map for both lower and upper limb dataset acquired under unconstrained conditions using near-infrared (NIR) imaging setup, specifically to assist vascular surgeons during venipuncture, vascular surgeries, or Chronic Venous Disease (CVD) treatments. METHODS: A portable image acquisition setup has been designed to collect venous data (upper and lower extremities) from 72 subjects. A manually annotated image dataset was used to train and compare the performance of existing well-known CNN-based architectures such as ResNet and VGGNet with self-parameterized U-Net, improving automated vein segmentation and visualization. RESULTS: Experimental results indicated that self-parameterized U-Net performs better at segmenting the unconstrained dataset in comparison with conventional CNN feature-based learning models, with a Dice score of 0.58 and displaying 96.7 % accuracy for real-time vein visualization, making it appropriate to locate veins in real-time under unconstrained conditions. CONCLUSIONS: Self-parameterized U-Net for vein segmentation and visualization has the potential to reduce risks associated with traditional venipuncture or CVD treatments by outperforming conventional CNN architectures, providing vascular assistance, and improving patient care and treatment outcomes.

Automated methods for sella turcica segmentation on cephalometric radiographic data using deep learning (CNN) techniques.

OBJECTIVE: The objective of this work is to present a novel technique using convolutional neural network (CNN) architectures for automatic segmentation of sella turcica (ST) on cephalometric radiographic image dataset. The proposed work suggests possible deep learning approaches to distinguish ST on complex cephalometric radiographs using deep learning techniques. MATERIALS AND METHODS: The dataset of 525 lateral cephalometric images was employed and randomly split into different training and testing subset ratios. The ground truth (annotated images) represents pixel-wise annotation of the ST using an online annotation platform by dental specialists. This study compared convolutional neural network architectures based on fine-tuned versions of the VGG19, ResNet34, InceptionV3, and ResNext50 architectures to select an appropriate model for autonomous segmentation of the nonlinear structure of ST. RESULTS: The study compared training and prediction results of the selected models: VGG19, ResNet34, InceptionV3, and ResNext50. The mean IoU scores for VGG19, ResNet34, InceptionV3 and ResNext50 are 0.7651, 0.7241, 0.4717, 0.4287, dice coefficients are 0.7794, 0.7487, 0.4714, 0.4363 and loss scores are 0.0973, 0.1299, 0.2049 and 0.2251, respectively. CONCLUSION: The obtained findings suggest that the VGG19 and Resnet34 architectures (mean IoU and dice coefficient > 75%) comparatively outperformed the InceptionV3 and ResNext50 architectures (mean IoU and dice coefficients is around 45%) for considered cephalometric radiographic dataset. The study findings can be used as a reference model for future investigation of non-linear ST morphological characteristics and related biological anomalies.