Evaluating Ensemble Learning Methods for Multi-Modal Emotion Recognition Using Sensor Data Fusion

Multi-model deep learning approach for segmentation of teeth and periapical lesions on pantomographs

INTRODUCTION

The fields of medicine and dentistry are beginning to integrate artificial intelligence (AI) in diagnostics. This may reduce subjectivity and improve the accuracy of diagnoses and treatment planning. Current evidence on pathosis detection on pantomographs (PGs) indicates the presence or absence of disease in the entire radiographic image, with little evidence of the relation of periapical pathosis to the causative tooth.

OBJECTIVE

To develop a deep learning (DL) AI model for the segmentation of periapical pathosis and its relation to teeth on PGs.

METHOD

250 PGs were manually annotated by subject experts to lay down the ground truth for training AI algorithms on the segmentation of periapical pathosis. Two approaches were used for lesion detection: Multi-models 1 and 2, using U-net and Mask RCNN algorithms, respectively. The resulting segmented lesions generated on the testing data set were superimposed with results of teeth segmentation and numbering algorithms trained separately to relate lesions to causative teeth. Hence, both multi-model approaches related periapical pathosis to the causative teeth on PGs.

RESULTS

The performance metrics of lesion segmentation carried out by U-net are as follows: Accuracy = 98.1%, precision = 84.5%, re-call = 80.3%, F-1 score = 82.2%, dice index = 75.2%, and Intersection over Union = 67.6%. Mask RCNN carried out lesion segmentation with an accuracy of 46.7%, precision of 80.6%, recall of 55%, and F-1 score of 63.1%.

CONCLUSION

In this study, the multi-model approach successfully related periapical pathosis to the causative tooth on PGs. However, U-net outperformed Mask RCNN in the tasks performed, suggesting that U-net will remain the standard for medical image segmentation tasks. Further training of the models on other findings and an increased number of images will lead to the automation of the detection of common radiographic findings in the dental diagnostic workflow.

Spectrum Evaluation in CR-Based Smart Healthcare Systems Using Optimizable Tree Machine Learning Approach

The rapid technological advancements in the current modern world bring the attention of researchers to fast and real-time healthcare and monitoring systems. Smart healthcare is one of the best choices for this purpose, in which different on-body and off-body sensors and devices monitor and share patient data with healthcare personnel and hospitals for quick and real-time decisions about patients' health. Cognitive radio (CR) can be very useful for effective and smart healthcare systems to send and receive patient's health data by exploiting the primary user's (PU) spectrum. In this paper, tree-based algorithms (TBAs) of machine learning (ML) are investigated to evaluate spectrum sensing in CR-based smart healthcare systems. The required data sets for TBAs are created based on the probability of detection (Pd) and probability of false alarm (Pf). These data sets are used to train and test the system by using fine tree, coarse tree, ensemble boosted tree, medium tree, ensemble bagged tree, ensemble RUSBoosted tree, and optimizable tree. Training and testing accuracies of all TBAs are calculated for both simulated and theoretical data sets. The comparison of training and testing accuracies of all classifiers is presented for the different numbers of received signal samples. Results depict that optimizable tree gives the best accuracy results to evaluate the spectrum sensing with minimum classification error (MCE).