Publication Search

Computed Radiography (CR) is a radiographic system that can convert analog signals into digital signals so that they are easily processed by image processing , to deal with the inconsistency of image quality from errors in lighting . One of the problems in CR is that the radiograph results are less than the maximum and can inhibit or reduce the ability to diagnose. This study aims to determine how the quality control of CR. This type of research is carried out in literature ( library study) that is by reading literature that has to do with the research conducted, as well as from other sources relating to Quality Control Computed Radiography (CR)  and draw conclusions based on existing data. Based on the available literature, it can be concluded that the quality control on Computed Radiography (CR) is different but it does not reduce in terms of improving the quality of Computed Radiography (CR) in producing quality radiographs and can establish diagnoses.

Convolutional neural network (CNN) is a deep learning (DL) model that has significantly contributed to medical systems because it is very useful in digital image processing. However, CNN has several limitations, such as being prone to overfitting, not being properly trained if there is data duplication, and can cause unwanted results if there is an imbalance in the amount of data in each class. Data augmentation techniques are used to overcome overfitting, eliminate data duplication, and random under sampling methods to balance the amount of data in each class, to overcome these problems. In addition, if the CNN model is not designed properly, the computation is less efficient. Research has proved that data augmentation can prevent or overcome overfitting, eliminating duplicate data can make the model more stable, and balancing the amount of data makes the model unbiased and easy to learn new data as evidenced through model evaluation and testing. The results also show that the custom convolutional neural network model is the best model compared to ResNet50 and VGG19 in terms of accuracy, precision, recall, F1-score, loss performance, and computation time efficiency