Analyzing Lung Disease Using Highly Effective Deep Learning Techniques

Abstract

Image processing technologies and computer-aided diagnosis are medical technologies used to support decision-making processes of radiologists and medical professionals who provide treatment for lung disease. These methods involve using chest X-ray images to diagnose and detect lung lesions, but sometimes there are abnormal cases that take some time to occur. This experiment used 5810 images for training and validation with the MobileNet, Densenet-121 and Resnet-50 models, which are popular networks used to classify the accuracy of images, and utilized a rotational technique to adjust the lung disease dataset to support learning with these convolutional neural network models. The results of the convolutional neural network model evaluation showed that Densenet-121, with a state-of-the-art Mish activation function and Nadam-optimized performance. All the rates for accuracy, recall, precision and F1 measures totaled 98.88%. We then used this model to test 10% of the total images from the non-dataset training and validation. The accuracy rate was 98.97% for the result which provided significant components for the development of a computer-aided diagnosis system to yield the best performance for the detection of lung lesions.

CIABNet: Category imbalance attention block network for the classification of multi‐differentiated types of esophageal cancer

“…In this section, we present the four datasets used in this study in Section 3.1, the experimental implementation details in Section 3.2, and the qualitative, quantitative, and visualization results for each of the comparative experiments of CIABNet in Section 3.3. In this study, three different image enhancement techniques (rotation, translation, and flip) were used to expand the histopathological image dataset of esophageal and liver cancer 15,35 ; specific details of the dataset are shown in Table 4 (the column of number of data after enhancement). The rotation operation for image enhancement is done by rotating the image clockwise and counterclockwise by 45 • , 60 • , 90 • , 210 • , and 240 • , respectively, and image flip is flipping the image horizontally and vertically.…”

COVID-19 Diagnosis with Deep Learning

“…The loss function layer is used to calculate the expected results predicted by the vital features (Sriporn et al, 2020) (Figure 8). According to the results of the ROC curve (Figure 9), we obtained the best result from the CNN model with 95%, the second best result from the ZFNet model with 86,8%, and the lowest result with the DenseNet121 model (83,5%).…”

Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools: A review

“…Other limitations such as image quality dependence, laboratory infrastructure requirement, local regulatory organization permissions, or the necessity to create a standardized protocol for the final diagnosis should be addressed. Nevertheless, several studies are improving predictive models, pre-processing techniques, microscope automation, and faster detections ( Sriporn et al, 2020 ; Masud et al, 2020 ). Artificial intelligence improvements and better predictive algorithms due to computing power evolution could be an advance in terms of automatic image diagnosis with optimized predictive results in the following years.…”