Search

This paper presents an ensemble of pre-trained models for the accurate classification of endoscopic images associated with Gastrointestinal (GI) diseases and illnesses. In this paper, we propose a weighted average ensemble model called GIT-NET to classify GI-tract diseases. We evaluated the model on a KVASIR v2 dataset with eight classes. When individual models are used for classification, they are often prone to misclassification since they may not be able to learn the characteristics of all the classes adequately. This is due to the fact that each model may learn the characteristics of specific classes more efficiently than the other classes. We propose an ensemble model that leverages the predictions of three pre-trained models, DenseNet201, InceptionV3, and ResNet50 with accuracies of 94.54%, 88.38%, and 90.58%, respectively. The predictions of the base learners are combined using two methods: model averaging and weighted averaging. The performances of the models are evaluated, and the model averaging ensemble has an accuracy of 92.96% whereas the weighted average ensemble has an accuracy of 95.00%. The weighted average ensemble outperforms the model average ensemble and all individual models. The results from the evaluation demonstrate that utilizing an ensemble of base learners can successfully classify features that were incorrectly learned by individual base learners. [ABSTRACT FROM AUTHOR]

Background: Breast cancer is arguably one of the leading causes of death among women around the world. The automation of the early detection process and classification of breast masses has been a prominent focus for researchers in the past decade. The utilization of ultrasound imaging is prevalent in the diagnostic evaluation of breast cancer, with its predictive accuracy being dependent on the expertise of the specialist. Therefore, there is an urgent need to create fast and reliable ultrasound image detection algorithms to address this issue. Methods: This paper aims to compare the efficiency of six state-of-the-art, fine-tuned deep learning models that can classify breast tissue from ultrasound images into three classes: benign, malignant, and normal, using transfer learning. Additionally, the architecture of a custom model is introduced and trained from the ground up on a public dataset containing 780 images, which was further augmented to 3900 and 7800 images, respectively. What is more, the custom model is further validated on another private dataset containing 163 ultrasound images divided into two classes: benign and malignant. The pre-trained architectures used in this work are ResNet-50, Inception-V3, Inception-ResNet-V2, MobileNet-V2, VGG-16, and DenseNet-121. The performance evaluation metrics that are used in this study are as follows: Precision, Recall, F1-Score and Specificity. Results: The experimental results show that the models trained on the augmented dataset with 7800 images obtained the best performance on the test set, having 94.95 ± 0.64%, 97.69 ± 0.52%, 97.69 ± 0.13%, 97.77 ± 0.29%, 95.07 ± 0.41%, 98.11 ± 0.10%, and 96.75 ± 0.26% accuracy for the ResNet-50, MobileNet-V2, InceptionResNet-V2, VGG-16, Inception-V3, DenseNet-121, and our model, respectively. Conclusion: Our proposed model obtains competitive results, outperforming some state-of-the-art models in terms of accuracy and training time. [ABSTRACT FROM AUTHOR]

Feature fusion techniques have been proposed and tested for many medical applications to improve diagnostic and classification problems. Specifically, cervical cancer classification can be improved by using such techniques. Feature fusion combines information from different datasets into a single dataset. This dataset contains superior discriminant power that can improve classification accuracy. In this paper, we conduct comparisons among six selected feature fusion techniques to provide the best possible classification accuracy of cervical cancer. The considered techniques are canonical correlation analysis, discriminant correlation analysis, least absolute shrinkage and selection operator, independent component analysis, principal component analysis, and concatenation. We generate ten feature datasets that come from the transfer learning of the most popular pre-trained deep learning models: Alex net, Resnet 18, Resnet 50, Resnet 10, Mobilenet, Shufflenet, Xception, Nasnet, Darknet 19, and VGG Net 16. The main contribution of this paper is to combine these models and then apply them to the six feature fusion techniques to discriminate various classes of cervical cancer. The obtained results are then fed into a support vector machine model to classify four cervical cancer classes (i.e., Negative, HISL, LSIL, and SCC). It has been found that the considered six techniques demand relatively comparable computational complexity when they are run on the same machine. However, the canonical correlation analysis has provided the best performance in classification accuracy among the six considered techniques, at 99.7%. The second-best methods were the independent component analysis, least absolute shrinkage and the selection operator, which were found to have a 98.3% accuracy. On the other hand, the worst-performing technique was the principal component analysis technique, which offered 90% accuracy. Our developed approach of analysis can be applied to other medical diagnosis classification problems, which may demand the reduction of feature dimensions as well as a further enhancement of classification performance. [ABSTRACT FROM AUTHOR]

Genitourinary syndrome of menopause (GSM) is a group of syndromes, including atrophy of the reproductive tract and urinary tract, and sexual dysfunction, caused by decreased levels of hormones, such as estrogen, in women during the transition to, or late stage of, menopause. GSM symptoms can gradually become severe with age and menopausal time, seriously affecting the safety, and physical and mental health, of patients. Optical coherence tomography (OCT) systems can obtain images similar to "optical slices" in a non-destructive manner. This paper presents a neural network, called RVM-GSM, to implement automatic classification tasks for different types of GSM-OCT images. The RVM-GSM module uses a convolutional neural network (CNN) and a vision transformer (ViT) to capture local and global features of the GSM-OCT images, respectively, and, then, fuses the two features in a multi-layer perception module to classify the image. In accordance with the practical needs of clinical work, lightweight post-processing is added to the final surface of the RVM-GSM module to compress the module. Experimental results showed that the accuracy rate of RVM-GSM in the GSM-OCT image classification task was 98.2%. This result is better than those of the CNN and Vit models, demonstrating the promise and potential of the application of RVM-GSM in the physical health and hygiene fields for women. [ABSTRACT FROM AUTHOR]

The coronavirus disease 2019 (COVID-19) rapidly spread around the world, and resulted in a global pandemic. Applying artificial intelligence to COVID-19 research can produce very exciting results. However, most research has focused on applying AI techniques in the study of COVID-19, but has ignored the security and reliability of AI systems. In this paper, we explore adversarial attacks on a deep learning system based on COVID-19 CT images with the aim of helping to address this problem. Firstly, we built a deep learning system that could identify COVID-19 CT images and non-COVID-19 CT images with an average accuracy of 76.27%. Secondly, we attacked the pretrained model with an adversarial attack algorithm, i.e., FGSM, to cause the COVID-19 deep learning system to misclassify the CT images, and the classification accuracy of non-COVID-19 CT images dropped from 80% to 0%. Finally, in response to this attack, we proposed how a more secure and reliable deep learning model based on COVID-19 medical images could be built. This research is based on a COVID-19 CT image recognition system, which studies the security of a COVID-19 CT image-based deep learning system. We hope to draw more researchers' attention to the security and reliability of medical deep learning systems. [ABSTRACT FROM AUTHOR]

Diagnostic results can be radically influenced by the quality of 2D ovarian-tumor ultrasound images. However, clinically processed 2D ovarian-tumor ultrasound images contain many artificially recognized symbols, such as fingers, crosses, dashed lines, and letters which assist artificial intelligence (AI) in image recognition. These symbols are widely distributed within the lesion's boundary, which can also affect the useful feature-extraction-utilizing networks and thus decrease the accuracy of lesion classification and segmentation. Image inpainting techniques are used for noise and object elimination from images. To solve this problem, we observed the MMOTU dataset and built a 2D ovarian-tumor ultrasound image inpainting dataset by finely annotating the various symbols in the images. A novel framework called mask-guided generative adversarial network (MGGAN) is presented in this paper for 2D ovarian-tumor ultrasound images to remove various symbols from the images. The MGGAN performs to a high standard in corrupted regions by using an attention mechanism in the generator to pay more attention to valid information and ignore symbol information, making lesion boundaries more realistic. Moreover, fast Fourier convolutions (FFCs) and residual networks are used to increase the global field of perception; thus, our model can be applied to high-resolution ultrasound images. The greatest benefit of this algorithm is that it achieves pixel-level inpainting of distorted regions without clean images. Compared with other models, our model achieveed better results with only one stage in terms of objective and subjective evaluations. Our model obtained the best results for 256 × 256 and 512 × 512 resolutions. At a resolution of 256 × 256, our model achieved 0.9246 for SSIM, 22.66 for FID, and 0.07806 for LPIPS. At a resolution of 512 × 512, our model achieved 0.9208 for SSIM, 25.52 for FID, and 0.08300 for LPIPS. Our method can considerably improve the accuracy of computerized ovarian tumor diagnosis. The segmentation accuracy was improved from 71.51 % to 76.06 % for the Unet model and from 61.13 % to 66.65 % for the PSPnet model in clean images. [ABSTRACT FROM AUTHOR]