An Explainable Deep Learning Model to Prediction Dental Caries Using Panoramic Radiograph Images.

Dental caries is the most frequent dental health issue in the general population. Dental caries can result in extreme pain or infections, lowering people's quality of life. Applying machine learning models to automatically identify dental caries can lead to earlier treatment. However, physicians frequently find the model results unsatisfactory due to a lack of explainability. Our study attempts to address this issue with an explainable deep learning model for detecting dental caries. We tested three prominent pre-trained models, EfficientNet-B0, DenseNet-121, and ResNet-50, to determine which is best for the caries detection task. These models take panoramic images as the input, producing a caries-non-caries classification result and a heat map, which visualizes areas of interest on the tooth. The model performance was evaluated using whole panoramic images of 562 subjects. All three models produced remarkably similar results. However, the ResNet-50 model exhibited a slightly better performance when compared to EfficientNet-B0 and DenseNet-121. This model obtained an accuracy of 92.00%, a sensitivity of 87.33%, and an F1-score of 91.61%. Visual inspection showed us that the heat maps were also located in the areas with caries. The proposed explainable deep learning model diagnosed dental caries with high accuracy and reliability. The heat maps help to explain the classification results by indicating a region of suspected caries on the teeth. Dentists could use these heat maps to validate the classification results and reduce misclassification.

Review of Deep Learning-Based Atrial Fibrillation Detection Studies.

Atrial fibrillation (AF) is a common arrhythmia that can lead to stroke, heart failure, and premature death. Manual screening of AF on electrocardiography (ECG) is time-consuming and prone to errors. To overcome these limitations, computer-aided diagnosis systems are developed using artificial intelligence techniques for automated detection of AF. Various machine learning and deep learning (DL) techniques have been developed for the automated detection of AF. In this review, we focused on the automated AF detection models developed using DL techniques. Twenty-four relevant articles published in international journals were reviewed. DL models based on deep neural network, convolutional neural network (CNN), recurrent neural network, long short-term memory, and hybrid structures were discussed. Our analysis showed that the majority of the studies used CNN models, which yielded the highest detection performance using ECG and heart rate variability signals. Details of the ECG databases used in the studies, performance metrics of the various models deployed, associated advantages and limitations, as well as proposed future work were summarized and discussed. This review paper serves as a useful resource for the researchers interested in developing innovative computer-assisted ECG-based DL approaches for AF detection.

Real-time deep learning-based image recognition for applications in automated positioning and injection of biological cells.

Biological cell injection is an effective method in which a foreign material is directly introduced into a biological cell. Since human involvement reduces the success rate of the biological microinjection procedure, an extensive research effort has been made towards its automation. The accurate positioning of a randomly placed biological cell in the microscope's field of view is a prerequisite for any automated injection procedure. Vision is the primary source for visual servoing in microinjection applications. For this reason, a visual sensing system is required to recognise, calculate, and manipulate the cell to the desired position. In this study, eight different pretrained neural networks were analysed and used as a backbone for the YOLOv2 object detection method, and the optimal network was evaluated based on mean Intersection over Union (IoU) accuracy, average precision (AP) at different thresholds, and frame rate (fps) in our dataset. YOLOv2 with Resnet-50 model demonstrated superior performance with 89% mean IoU accuracy and 100% detection accuracy at an average of 33 fps. Ten different sets of experiments were conducted to examine the algorithm by verifying the zebrafish embryo gradual presence within the field of view to bring the zebrafish embryo to the predefined position. Experimental results demonstrated that the developed solution performed real-time with high accuracy and illustrates auto-positioning with a 100% success rate regardless of the initial position of the biological cell within the Petri dish. Later, the generalization of the proposed solution was verified in a different dataset from the real microinjection setup.

Vision-Based Sensor for Three-Dimensional Vibrational Motion Detection in Biological Cell Injection.

Intracytoplasmic sperm injection (ICSI) is an infertility treatment where a single sperm is immobilised and injected into the egg using a glass injection pipette. Minimising vibration in three orthogonal axes is essential to have precise injector motion and full control during the egg injection procedure. Vibration displacement sensing using physical sensors in ICSI operation is challenging since the sensor interfacing is not practically feasible. This study proposes a non-invasive technique to measure the three-dimensional vibrational motion of the injection pipette by a single microscope camera during egg injection. The contrast-limited adaptive histogram equalization (CHALE) method and blob analyses technique were employed to measure the vibration displacement in axial and lateral axes, while the actual dimension of the focal axis was directly measured using the Brenner gradient algorithm as a focus measurement algorithm. The proposed algorithm operates between the magnifications range of 4× to 40× with a resolution of half a pixel. Experiments using the proposed vision-based algorithm were conducted to measure and verify the vibration displacement in axial and lateral axes at various magnifications. The results were compared against manual procedures and the differences in measurements were up to 2% among all magnifications. Additionally, the effect of injection speed on lateral vibration displacement was measured experimentally and was used to determine the values for egg deformation, force fluctuation, and penetration force. It was shown that increases in injection speed significantly increases the lateral vibration displacement of the injection pipette by as much as 54%. It has been demonstrated successfully that visual sensing has played a key role in identifying the limitation of the egg injection speed created by lateral vibration displacement of the injection pipette tip.

Effect of Injection Speed on Oocyte Deformation in ICSI.

Oocyte deformation during injection is a major cause of potential cell damage which can lead to failure in the Intracytoplasmic Sperm Injection (ICSI) operation used as an infertility treatment. Injection speed plays an important role in the deformation creation. In this paper the effect of different speeds on deformation of zebrafish embryos is studied using a specially designed experimental set-up. An analytical model is developed in order to link injection force, deformation, and injection speed. A finite element (FE) model is also developed to analyse the effect of injection speed, allowing the production of additional information that is difficult to obtain experimentally, e.g., deformation and stress fields on the oocyte. The numerical model is validated against experimental results. Experimental results indicate that by increasing the injection speed, the deformation decreases. However, higher speeds cause higher levels of injection force and force fluctuation, leading to a higher vibration during injection. For this reason, an optimum injection speed range is determined. Finally, the FE model was validated against experimental results. The FE model is able to predict the force-deformation variation during injection for different speeds. This proves to be useful for future studies investigating different injection conditions.