scholarly journals MulTiNet: Multimodal Neural Networks for Glaucoma Based on Transfer Learning

2021 ◽  
Author(s):  
Yi Li ◽  
YuJie Han ◽  
XueSi Zhao ◽  
ZiHan Li ◽  
ZhiFen Guo
Keyword(s):  
Transfer Learning ◽  
Medical Images ◽  
Open Angle Glaucoma ◽  
Three Dimensional ◽  
Classification Model ◽  
Angle Closure ◽  
Data Sets ◽  
Data Set ◽  
Primary Angle Closure ◽  
Glaucoma Diagnosis

Abstract Background: Being one of the most serious causes of irreversible blindness, glaucoma has many subtypes and complex symptoms. In clinic, doctors usually need to use a variety of medical images for diagnosis. Optical Coherence Tomography (OCT), Visual Field (VF) , Fundus Photosexams (FP) and Ultrasonic BioMicroscope (UBM) are widely-used and complementary techniques for diagnosing glaucoma.Methods: At present, the field of intelligent diagnosis of glaucoma is limited by two major problems. One is the small number of data sets, and the other is the low diagnostic accuracy of Single-Modal Modal. In order to solve the above two problems, we have done the following work. First, we construct DualSY glaucoma multimodal data set. The four most important subtypes of glaucoma are discussed in this article which are Primary Open Angle Glaucoma (POAG), Primary Angle Closure Glaucoma (PACG), Primary Angle Closure Suspect (PACS) and Primary Angle Closure (PAC). Each patient in the DualSY data set contains more than five medical images, as shown in the figure 4.And DualSY are labeled with image-level multi-labels. Second, We propose a new Multi-Modal classification network for glaucoma, which is a multiclass classification model with various medical images of glaucoma patients and text information as input. The network structure consists of three main branches to deal with patient metadata, domain-based glaucoma features and medical images. Transfer learning method is introduced into this paper due to the small number of medical image data sets. The flowchart is shown in Figure 5.Result: Our method on glaucoma diagnosis outperforms state-of-the-art methods. A promising average result of overall accuracy (ACC) of 94.7% is obtained. Our data set outperformed most data sets in glaucoma diagnosis with an accuracy of 87.8%.Conclusions: The results suggest that medical images such as Heidelberg OCT and three-dimensional fundus photos used in this paper can better express the high-level information of glaucoma and our modal greatly improve the accuracy of glaucoma diagnosis. At the same time, this data set has great potential, and we continue to study this data.

scholarly journals Classification of jujube defects in small data sets based on transfer learning

2021 ◽  
Author(s):  
Jianping Ju ◽  
Hong Zheng ◽  
Xiaohang Xu ◽  
Zhongyuan Guo ◽  
Zhaohui Zheng ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Loss Function ◽  
Training Model ◽  
Parameter Distribution ◽  
Test Accuracy ◽  
Small Data ◽  
Data Sets ◽  
Data Set ◽  
Small Data Sets

AbstractAlthough convolutional neural networks have achieved success in the field of image classification, there are still challenges in the field of agricultural product quality sorting such as machine vision-based jujube defects detection. The performance of jujube defect detection mainly depends on the feature extraction and the classifier used. Due to the diversity of the jujube materials and the variability of the testing environment, the traditional method of manually extracting the features often fails to meet the requirements of practical application. In this paper, a jujube sorting model in small data sets based on convolutional neural network and transfer learning is proposed to meet the actual demand of jujube defects detection. Firstly, the original images collected from the actual jujube sorting production line were pre-processed, and the data were augmented to establish a data set of five categories of jujube defects. The original CNN model is then improved by embedding the SE module and using the triplet loss function and the center loss function to replace the softmax loss function. Finally, the depth pre-training model on the ImageNet image data set was used to conduct training on the jujube defects data set, so that the parameters of the pre-training model could fit the parameter distribution of the jujube defects image, and the parameter distribution was transferred to the jujube defects data set to complete the transfer of the model and realize the detection and classification of the jujube defects. The classification results are visualized by heatmap through the analysis of classification accuracy and confusion matrix compared with the comparison models. The experimental results show that the SE-ResNet50-CL model optimizes the fine-grained classification problem of jujube defect recognition, and the test accuracy reaches 94.15%. The model has good stability and high recognition accuracy in complex environments.

Auto-sharing parameters for transfer learning based on multi-objective optimization

2021 ◽  
pp. 1-13
Author(s):  
Hailin Liu ◽  
Fangqing Gu ◽  
Zixian Lin
Keyword(s):  
Transfer Learning ◽  
Optimization Problem ◽  
Data Sets ◽  
Multi Objective Optimization ◽  
Particle Swarm Optimizer ◽  
Real World Data ◽  
Data Set ◽  
Target Task ◽  
Main Research ◽  
Multi Objective

Transfer learning methods exploit similarities between different datasets to improve the performance of the target task by transferring knowledge from source tasks to the target task. “What to transfer” is a main research issue in transfer learning. The existing transfer learning method generally needs to acquire the shared parameters by integrating human knowledge. However, in many real applications, an understanding of which parameters can be shared is unknown beforehand. Transfer learning model is essentially a special multi-objective optimization problem. Consequently, this paper proposes a novel auto-sharing parameter technique for transfer learning based on multi-objective optimization and solves the optimization problem by using a multi-swarm particle swarm optimizer. Each task objective is simultaneously optimized by a sub-swarm. The current best particle from the sub-swarm of the target task is used to guide the search of particles of the source tasks and vice versa. The target task and source task are jointly solved by sharing the information of the best particle, which works as an inductive bias. Experiments are carried out to evaluate the proposed algorithm on several synthetic data sets and two real-world data sets of a school data set and a landmine data set, which show that the proposed algorithm is effective.

Bayesian Classifier for Sparsity-Promoting Feature Selection

2015 ◽  
Vol 29 (06) ◽  
pp. 1550022 ◽  
Author(s):  
Danlei Xu ◽  
Lan Du ◽  
Hongwei Liu ◽  
Penghui Wang
Keyword(s):  
Feature Selection ◽  
Synthetic Data ◽  
Original Data ◽  
Radar Data ◽  
Bayesian Classifier ◽  
Classification Model ◽  
Data Sets ◽  
Data Set ◽  
Classification Boundary ◽  
Nonlinear Mappings

A Bayesian classifier for sparsity-promoting feature selection is developed in this paper, where a set of nonlinear mappings for the original data is performed as a pre-processing step. The linear classification model with such mappings from the original input space to a nonlinear transformation space can not only construct the nonlinear classification boundary, but also realize the feature selection for the original data. A zero-mean Gaussian prior with Gamma precision and a finite approximation of Beta process prior are used to promote sparsity in the utilization of features and nonlinear mappings in our model, respectively. We derive the Variational Bayesian (VB) inference algorithm for the proposed linear classifier. Experimental results based on the synthetic data set, measured radar data set, high-dimensional gene expression data set, and several benchmark data sets demonstrate the aggressive and robust feature selection capability and comparable classification accuracy of our method comparing with some other existing classifiers.

scholarly journals Managing Primary Angle Closure Glaucoma – The Role of Lens Extraction in this Era

2016 ◽  
Vol 10 (1) ◽  
pp. 86-93 ◽  
Author(s):  
Nafees Baig ◽  
Ka-Wai Kam ◽  
Clement C.Y. Tham
Keyword(s):  
Gold Standard ◽  
Open Angle Glaucoma ◽  
Angle Closure Glaucoma ◽  
Angle Closure ◽  
Predisposing Factor ◽  
Lens Extraction ◽  
Primary Angle Closure ◽  
Primary Angle Closure Glaucoma ◽  
Anterior Position

Trabeculectomy has been the gold standard in reducing intraocular pressure (IOP) in glaucoma patients, no matter it is angle closure or open angle glaucoma. However in primary angle closure glaucoma, no matter the lens is cataractous or not, it is likely to be pathological, this thicker than usual lens, with or without a more anterior position, is often regarded as a strong contributing factor to angle closure. Lens extraction, no matter it is cataractous or clear, can theoretically eliminate this anatomical predisposing factor of angle closure, and thus IOP can be reduced. Based on recent results of a number of clinical trials, lens extraction alone or in combination with other IOP-lowering surgeries, may therefore play a more important role in the treating primary angle closure glaucoma. In cases when greater IOP-lowering effect is needed or if drug dependency has to be minimized, combined procedures, such as phacotrabeculectomy, can be considered, but the surgical risk can be higher than lens extraction alone.

scholarly journals Ambulatory and Laboratory Stress Detection Based on Raw Electrocardiogram Signals Using a Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4408 ◽  
Author(s):  
Hyun-Myung Cho ◽  
Heesu Park ◽  
Suh-Yeon Dong ◽  
Inchan Youn
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Mental Arithmetic ◽  
Small Data ◽  
Data Sets ◽  
Learning Method ◽  
Data Set ◽  
Electrocardiogram Signals ◽  
Proposed Model ◽  
Small Data Set

The goals of this study are the suggestion of a better classification method for detecting stressed states based on raw electrocardiogram (ECG) data and a method for training a deep neural network (DNN) with a smaller data set. We suggest an end-to-end architecture to detect stress using raw ECGs. The architecture consists of successive stages that contain convolutional layers. In this study, two kinds of data sets are used to train and validate the model: A driving data set and a mental arithmetic data set, which smaller than the driving data set. We apply a transfer learning method to train a model with a small data set. The proposed model shows better performance, based on receiver operating curves, than conventional methods. Compared with other DNN methods using raw ECGs, the proposed model improves the accuracy from 87.39% to 90.19%. The transfer learning method improves accuracy by 12.01% and 10.06% when 10 s and 60 s of ECG signals, respectively, are used in the model. In conclusion, our model outperforms previous models using raw ECGs from a small data set and, so, we believe that our model can significantly contribute to mobile healthcare for stress management in daily life.

Sign in / Sign up

Export Citation Format

Share Document