Wyniki wyszukiwania - BazTech

1

TL-med: A Two-stage transfer learning recognition model for medical images of COVID-19

Meng Jiana, Tan Zhiyong, Yu Yuhai, Wang Pengjie, Liu Shuang

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

842--855

EN

The recognition of medical images with deep learning techniques can assist physicians in clinical diagnosis, but the effectiveness of recognition models relies on massive amounts of labeled data. With the rampant development of the novel coronavirus (COVID-19) worldwide, rapid COVID-19 diagnosis has become an effective measure to combat the outbreak. However, labeled COVID-19 data are scarce. Therefore, we propose a two-stage transfer learning recognition model for medical images of COVID-19 (TL-Med) based on the concept of ‘‘generic domain-target-related domain-target domain”. First, we use the Vision Transformer (ViT) pretraining model to obtain generic features from massive heterogeneous data and then learn medical features from large-scale homogeneous data. Two-stage transfer learning uses the learned primary features and the underlying information for COVID-19 image recognition to solve the problem by which data insufficiency leads to the inability of the model to learn underlying target dataset information. The experimental results obtained on a COVID-19 dataset using the TL-Med model produce a recognition accuracy of 93.24%, which shows that the proposed method is more effective in detecting COVID-19 images than other approaches and may greatly alleviate the problem of data scarcity in this field.

2

Automated diagnosis of COVID stages from lung CT images using statistical features in 2-dimensional flexible analytic wavelet transform

Patel Rajneesh Kumar, Kashyap Manish

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

829--841

EN

TheCOVID-19 epidemic has been causing a global problem since December 2019.COVID-19 is highly contagious and spreads rapidly throughout the world. Thus, early detection is essential. The progression of COVID-19 lung illness has been demonstrated to be aided by chest imaging. The respiratory system is the most vulnerable component of the human body to the COVID virus. COVID can be diagnosed promptly and accurately using images from a chest X-ray and a computed tomography scan. CT scans are preferred over X-rays to rule out other pulmonary illnesses, assist venous entry, and pinpoint any new heart problems. The traditional and trending tools are physical, time-inefficient, and not more accurate. Many techniques for detecting COVID utilizing CT scan images have recently been developed, yet none of them can efficiently detect COVID at an early stage. We proposed a two-dimensional Flexible analytical wavelet transform (FAWT) based on a novel technique in this work. This method is decomposed pre-processed images into sub-bands. Then statistical-based relevant features are extracted, and principal component analysis (PCA) is used to identify robust features. After that, robust features are ranked with the help of the Student’s t-value algorithm. Finally, features are applied to Least Square-SVM (RBF) for classification. According to the experimental outcomes, our model beat state-of-the-art approaches for COVID classification. This model attained better classification accuracy of 93.47%, specificity 93.34%, sensitivity 93.6% and F1-score 0.93 using tenfold cross-validation.

3

WOANet: Whale optimized deep neural network for the classification of COVID-19 from radiography images

Murugan R., Goel Tripti, Mirjalili Seyedali, Chakrabartty Deba Kumar

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 4

1702--1718

EN

Coronavirus Diseases (COVID-19) is a new disease that will be declared a global pandemic in 2020. It is characterized by a constellation of traits like fever, dry cough, dyspnea, fatigue, chest pain, etc. Clinical findings have shown that the human chest Computed Tomography (CT) images can diagnose lung infection in most COVID-19 patients. Visual changes in CT scan due to COVID-19 is subjective and evaluated by radiologists for diagnosis purpose. Deep Learning (DL) can provide an automatic diagnosis tool to relieve radiologists’ burden for quantitative analysis of CT scan images in patients. However, DL techniques face different training problems like mode collapse and instability. Deciding on training hyper-parameters to adjust the weight and biases of DL by a given CT image dataset is crucial for achieving the best accuracy. This paper combines the backpropagation algorithm and Whale Optimization Algorithm (WOA) to optimize such DL networks. Experimental results for the diagnosis of COVID-19 patients from a comprehensive COVID-CT scan dataset show the best performance compared to other recent methods. The proposed network architecture results were validated with the existing pre-trained network to prove the efficiency of the network.

4

FractalCovNet architecture for COVID-19 Chest X-ray image Classification and CT-scan image Segmentation

Munusamy Hemalatha, Karthikeyan Jadarajan Muthukumar, Shriram Gnanaprakasam, Thanga Revathi Shanmugakani, Aravindkumar Sekar

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

1025--1038

EN

Precise and fast diagnosis of COVID-19 cases play a vital role in early stage of medical treatment and prevention. Automatic detection of COVID-19 cases using the chest X-ray images and chest CT-scan images will be helpful to reduce the impact of this pandemic on the human society. We have developed a novel FractalCovNet architecture using Fractal blocks and U-Net for segmentation of chest CT-scan images to localize the lesion region. The same FractalCovNet architecture is also used for classification of chest X-ray images using transfer learning. We have compared the segmentation results using various model such as UNet, DenseUNet, Segnet, ResnetUNet, and FCN. We have also compared the classification results with various models like ResNet5-, Xception, InceptionResNetV2, VGG-16 and DenseNet architectures. The proposed FractalCovNet model is able to predict the COVID-19 lesion with high F-measure and precision values compared to the other state-of-the-art methods. Thus the proposed model can accurately predict the COVID-19 cases and discover lesion regions in chest CT without the manual annotations of lesions for every suspected individual. An easily-trained and high-performance deep learning model provides a fast way to identify COVID-19 patients, which is beneficial to control the outbreak of SARS-IICOV.

5

AutoCovNet: Unsupervised feature learning using autoencoder and feature merging for detection of COVID-19 from chest X-ray images

Rashid Nayeeb, Hossain Md Adnan Faisal, Ali Mohammad, Islam Sukanya Mumtahina, Mahmud Tanvir, Fattah Shaikh Anowarul

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 4

1685--1701

EN

With the onset of the COVID-19 pandemic, the automated diagnosis has become one of the most trending topics of research for faster mass screening. Deep learning-based approaches have been established as the most promising methods in this regard. However, the limitation of the labeled data is the main bottleneck of the data-hungry deep learning methods. In this paper, a two-stage deep CNN based scheme is proposed to detect COVID-19 from chest X-ray images for achieving optimum performance with limited training images. In the first stage, an encoder-decoder based autoencoder network is proposed, trained on chest X-ray images in an unsupervised manner, and the network learns to reconstruct the X-ray images. An encoder-merging network is proposed for the second stage that consists of different layers of the encoder model followed by a merging network. Here the encoder model is initialized with the weights learned on the first stage and the outputs from different layers of the encoder model are used effectively by being connected to a proposed merging network. An intelligent feature merging scheme is introduced in the proposed merging network. Finally, the encoder-merging network is trained for feature extraction of the X-ray images in a supervised manner and resulting features are used in the classification layers of the proposed architecture. Considering the final classification task, an EfficientNet-B4 network is utilized in both stages. An end to end training is performed for datasets containing classes: COVID-19, Normal, Bacterial Pneumonia, Viral Pneumonia. The proposed method offers very satisfactory performances compared to the state of the art methods and achieves an accuracy of 90:13% on the 4-class, 96:45% on a 3-class, and 99:39% on 2-class classification.