scholarly journals A weakly supervised learning method based on attention fusion for Covid-19 segmentation in CT images

2021 ◽  
pp. 1-12
Author(s):  
Hongyu Chen ◽  
Shengsheng Wang
Keyword(s):  
Image Segmentation ◽  
Supervised Learning ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Great Success ◽  
Segmentation Method ◽  
Rt Pcr ◽  
Weakly Supervised Learning ◽  
Polymerase Chain ◽  
Weakly Supervised

Since the end of 2019, the COVID-19, which has swept across the world, has caused serious impacts on public health and economy. Although Reverse Transcription-Polymerase Chain Reaction (RT-PCR) is the gold standard for clinical diagnosis, it is very time-consuming and labor-intensive. At the same time, more and more people have doubted the sensitivity of RT-PCR. Therefore, Computed Tomography (CT) images are used as a substitute for RT-PCR. Powered by the research of the field of artificial intelligence, deep learning, which is a branch of machine learning, has made a great success on medical image segmentation. However, general full supervision methods require pixel-level point-by-point annotations, which is very costly. In this paper, we put forward an image segmentation method based on weakly supervised learning for CT images of COVID-19, which can effectively segment the lung infection area and doesn’t require pixel-level labels. Our method is contrasted with another four weakly supervised learning methods in recent years, and the results have been significantly improved.

scholarly journals ResBCDU-Net: A Deep Learning Framework for Lung CT Image Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 268
Author(s):  
Yeganeh Jalali ◽  
Mansoor Fateh ◽  
Mohsen Rezvani ◽  
Vahid Abolghasemi ◽  
Mohammad Hossein Anisi
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Great Success ◽  
Morphological Operations ◽  
Ct Image ◽  
Feature Maps ◽  
Learning Framework ◽  
Lung Ct

Lung CT image segmentation is a key process in many applications such as lung cancer detection. It is considered a challenging problem due to existing similar image densities in the pulmonary structures, different types of scanners, and scanning protocols. Most of the current semi-automatic segmentation methods rely on human factors therefore it might suffer from lack of accuracy. Another shortcoming of these methods is their high false-positive rate. In recent years, several approaches, based on a deep learning framework, have been effectively applied in medical image segmentation. Among existing deep neural networks, the U-Net has provided great success in this field. In this paper, we propose a deep neural network architecture to perform an automatic lung CT image segmentation process. In the proposed method, several extensive preprocessing techniques are applied to raw CT images. Then, ground truths corresponding to these images are extracted via some morphological operations and manual reforms. Finally, all the prepared images with the corresponding ground truth are fed into a modified U-Net in which the encoder is replaced with a pre-trained ResNet-34 network (referred to as Res BCDU-Net). In the architecture, we employ BConvLSTM (Bidirectional Convolutional Long Short-term Memory)as an advanced integrator module instead of simple traditional concatenators. This is to merge the extracted feature maps of the corresponding contracting path into the previous expansion of the up-convolutional layer. Finally, a densely connected convolutional layer is utilized for the contracting path. The results of our extensive experiments on lung CT images (LIDC-IDRI database) confirm the effectiveness of the proposed method where a dice coefficient index of 97.31% is achieved.

Weakly supervised learning of point-level annotation for coral image segmentation

2019 ◽  
Author(s):  
Xi Yu ◽  
Bing Ouyang ◽  
Jose C. Principe ◽  
Stephanie Farrington ◽  
John Reed ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Supervised Learning ◽  
Weakly Supervised Learning ◽  
Weakly Supervised ◽  
Point Level

scholarly journals Semi-supervised learning for an improved diagnosis of COVID-19 in CT images

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249450
Author(s):  
Chang Hee Han ◽  
Misuk Kim ◽  
Jin Tae Kwak
Keyword(s):  
Diagnostic Accuracy ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Ct Images ◽  
Diagnostic Tools ◽  
Rt Pcr ◽  
The Public ◽  
Feature Representations ◽  
Polymerase Chain ◽  
And Training

Coronavirus disease 2019 (COVID-19) has been spread out all over the world. Although a real-time reverse-transcription polymerase chain reaction (RT-PCR) test has been used as a primary diagnostic tool for COVID-19, the utility of CT based diagnostic tools have been suggested to improve the diagnostic accuracy and reliability. Herein we propose a semi-supervised deep neural network for an improved detection of COVID-19. The proposed method utilizes CT images in a supervised and unsupervised manner to improve the accuracy and robustness of COVID-19 diagnosis. Both labeled and unlabeled CT images are employed. Labeled CT images are used for supervised leaning. Unlabeled CT images are utilized for unsupervised learning in a way that the feature representations are invariant to perturbations in CT images. To systematically evaluate the proposed method, two COVID-19 CT datasets and three public CT datasets with no COVID-19 CT images are employed. In distinguishing COVID-19 from non-COVID-19 CT images, the proposed method achieves an overall accuracy of 99.83%, sensitivity of 0.9286, specificity of 0.9832, and positive predictive value (PPV) of 0.9192. The results are consistent between the COVID-19 challenge dataset and the public CT datasets. For discriminating between COVID-19 and common pneumonia CT images, the proposed method obtains 97.32% accuracy, 0.9971 sensitivity, 0.9598 specificity, and 0.9326 PPV. Moreover, the comparative experiments with respect to supervised learning and training strategies demonstrate that the proposed method is able to improve the diagnostic accuracy and robustness without exhaustive labeling. The proposed semi-supervised method, exploiting both supervised and unsupervised learning, facilitates an accurate and reliable diagnosis for COVID-19, leading to an improved patient care and management.

scholarly journals Robust weakly supervised learning for COVID-19 recognition using multi-center CT images

2021 ◽  
pp. 108291
Author(s):  
Qinghao Ye ◽  
Yuan Gao ◽  
Weiping Ding ◽  
Zhangming Niu ◽  
Chengjia Wang ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Ct Images ◽  
Weakly Supervised Learning ◽  
Weakly Supervised

Multiresolution Bio-Medical Image Segmentation using Fuzzy C-Means Clustering

2019 ◽  
Vol 8 (4) ◽  
pp. 9548-9551
Keyword(s):  
Image Segmentation ◽  
Medical Image Segmentation ◽  
Experimental Result ◽  
Segmentation Method ◽  
Fuzzy C Means ◽  
Fuzzy C Means Clustering ◽  
Robust Image ◽  
Multiple Clusters ◽  
Single Pixel ◽  
Popular Image

Fuzzy c-means clustering is a popular image segmentation technique, in which a single pixel belongs to multiple clusters, with varying degree of membership. The main drawback of this method is it sensitive to noise. This method can be improved by incorporating multiresolution stationary wavelet analysis. In this paper we develop a robust image segmentation method using Fuzzy c-means clustering and wavelet transform. The experimental result shows that the proposed method is more accurate than the Fuzzy c-means clustering.

Sign in / Sign up

Export Citation Format

Share Document