scholarly journals Multi-label classification of fundus images based on graph convolutional network

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Yinlin Cheng ◽  
Mengnan Ma ◽  
Xingyu Li ◽  
Yi Zhou
Keyword(s):  
Large Scale ◽  
Fundus Images ◽  
Convolutional Network ◽  
Hard Exudates ◽  
Proposed Model ◽  
Diabetic Population ◽  
Color Fundus Images ◽  
Aided Diagnosis ◽  
Large Scale Screening

Abstract Background Diabetic Retinopathy (DR) is the most common and serious microvascular complication in the diabetic population. Using computer-aided diagnosis from the fundus images has become a method of detecting retinal diseases, but the detection of multiple lesions is still a difficult point in current research. Methods This study proposed a multi-label classification method based on the graph convolutional network (GCN), so as to detect 8 types of fundus lesions in color fundus images. We collected 7459 fundus images (1887 left eyes, 1966 right eyes) from 2282 patients (1283 women, 999 men), and labeled 8 types of lesions, laser scars, drusen, cup disc ratio ($$C/D>0.6$$ C / D > 0.6 ), hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates. We constructed a specialized corpus of the related fundus lesions. A multi-label classification algorithm for fundus images was proposed based on the corpus, and the collected data were trained. Results The average overall F1 Score (OF1) and the average per-class F1 Score (CF1) of the model were 0.808 and 0.792 respectively. The area under the ROC curve (AUC) of our proposed model reached 0.986, 0.954, 0.946, 0.957, 0.952, 0.889, 0.937 and 0.926 for detecting laser scars, drusen, cup disc ratio, hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates, respectively. Conclusions Our results demonstrated that our proposed model can detect a variety of lesions in the color images of the fundus, which lays a foundation for assisting doctors in diagnosis and makes it possible to carry out rapid and efficient large-scale screening of fundus lesions.

scholarly journals Segmentation and Classification of Breast Cancer Tumour

2018 ◽  
Vol 2 (1) ◽  
pp. 14-18
Author(s):  
Gokalp Cinarer ◽  
Bulent Gursel Emiroglu ◽  
Ahmet Hasim Yurttakal
Keyword(s):  
Breast Cancer ◽  
Texture Features ◽  
Computer Aided Diagnosis ◽  
Wavelet Approximation ◽  
Proposed Model ◽  
Svm Algorithm ◽  
Computer Aided ◽  
Magnetic Resonance Imaging Mri ◽  
Aided Diagnosis

Breast cancer is cancer that forms in the cells of the breasts. Breast cancer is the most common cancer diagnosed in women in the world. Breast cancer can occur in both men and women, but it's far more common in women. Early detection of breast cancer tumours is crucial in the treatment. In this study, we presented a computer aided diagnosis expectation maximization segmentation and co-occurrence texture features from wavelet approximation tumour image of each slice and evaluated the performance of SVM Algorithm. We tested the model on 50 patients, among them, 25 are benign and 25 malign. The 80% of the images are allocated for training and 20% of images reserved for testing. The proposed model classified 2 patients correctly with success rate of 80% in case of 5 Fold Cross-Validation  Keywords: Breast Cancer, Computer-Aided Diagnosis (CAD), Magnetic Resonance Imaging (MRI);

scholarly journals Sentence Compression Using BERT and Graph Convolutional Networks

2021 ◽  
Vol 11 (21) ◽  
pp. 9910
Author(s):  
Yo-Han Park ◽  
Gyong-Ho Lee ◽  
Yong-Seok Choi ◽  
Kong-Joo Lee
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Compression Model ◽  
Sentence Compression ◽  
Dependency Tree ◽  
Proposed Model ◽  
Syntactic Information ◽  
Input Sentence

Sentence compression is a natural language-processing task that produces a short paraphrase of an input sentence by deleting words from the input sentence while ensuring grammatical correctness and preserving meaningful core information. This study introduces a graph convolutional network (GCN) into a sentence compression task to encode syntactic information, such as dependency trees. As we upgrade the GCN to activate a directed edge, the compression model with the GCN layers can distinguish between parent and child nodes in a dependency tree when aggregating adjacent nodes. Furthermore, by increasing the number of GCN layers, the model can gradually collect high-order information of a dependency tree when propagating node information through the layers. We implement a sentence compression model for Korean and English, respectively. This model consists of three components: pre-trained BERT model, GCN layers, and a scoring layer. The scoring layer can determine whether a word should remain in a compressed sentence by relying on the word vector containing contextual and syntactic information encoded by BERT and GCN layers. To train and evaluate the proposed model, we used the Google sentence compression dataset for English and a Korean sentence compression corpus containing about 140,000 sentence pairs for Korean. The experimental results demonstrate that the proposed model achieves state-of-the-art performance for English. To the best of our knowledge, this sentence compression model based on the deep learning model trained with a large-scale corpus is the first attempt for Korean.

An ensemble classification of exudates in color fundus images using an evolutionary algorithm based optimal features selection

2019 ◽  
Vol 82 (4) ◽  
pp. 361-372 ◽  
Author(s):  
Hidayat Ullah ◽  
Tanzila Saba ◽  
Naveed Islam ◽  
Naveed Abbas ◽  
Amjad Rehman ◽  
...  
Keyword(s):  
Evolutionary Algorithm ◽  
Ensemble Classification ◽  
Features Selection ◽  
Fundus Images ◽  
Color Fundus Images
Sign in / Sign up

Export Citation Format

Share Document