CSF images fast recognition model based on improved convolu-tional Neural Network

Huang, Wenming; Leng, Jinqiang; Deng, Zhenrong

doi:10.2991/amcce-15.2015.97

Cited by 74 publications

(112 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate our proposed method, we employ two strong baseline methods: ResNet-18 [21] and EfficientNet-b0 [22], both of which have high performance in image recognition and medical applications. In addition, we compare them with the performances of the MVCTNet, using two baseline methods as the feature extractors, on our dataset.…”

Section: B Comparisons With Baseline Methodsmentioning

confidence: 99%

“…For this, we extract representations g a = G a (x a ) and g b = G b (x b ), which are the outputs of the global average pooling (GAP) layer of the features extractors, which are the inputs of the task layers and our dissimilarity loss. We employ ResNet-18[21] and EfficientNet-b0[22] pre-trained on ImageNet dataset as the feature extractors (G a , G b ) and the two task layers (F a , F b ) in our experiments.For the task layers, which consist of one MLP layer, we train two of them (F a , F b ) using g a and g b , respectively,…”

mentioning

confidence: 99%

See 1 more Smart Citation

Multi-View Computed Tomography Network for Osteoporosis Classification

Hwang¹,

Kim³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Osteoporosis is a skeletal disease that is difficult to identify in advance of symptoms. Existing skeletal disease screening methods, such as dual-energy X-ray absorptiometry, are only used for specific purpose due to cost and safety reasons once symptoms develop. Early detection of osteopenia and osteoporosis using other modalities for relatively frequent examinations is helpful in terms of early treatment and cost. Recently, many studies have proposed deep learning-based osteoporosis diagnosis methods for various modalities and achieved outstanding results. However, these studies have limitations in clinical use because they require tedious processes, such as manually cropping a region of interest or diagnosing osteoporosis rather than osteopenia. In this study, we present a classification task for diagnosing osteopenia and osteoporosis using computed tomography (CT). Additionally, we propose a multi-view CT network (MVCTNet) that automatically classifies osteopenia and osteoporosis using two images from the original CT image. Unlike previous methods that use a single CT image as input, the MVCTNet captures various features from the images generated by our multi-view settings. The MVCTNet comprises two feature extractors and three task layers. Two feature extractors use the images as separate inputs and learn different features through dissimilarity loss. The target layers learn the target task through the features of the two feature extractors and then aggregate them. For the experiments, we use a dataset containing 2,883 patients' CT images labeled as normal, osteopenia, and osteoporosis. Additionally, we observe that the proposed method improves the performance of all experiments based on the quantitative and qualitative evaluations.

show abstract

Section: B Comparisons With Baseline Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Multi-View Computed Tomography Network for Osteoporosis Classification

Hwang¹,

Kim³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Although not the focus of this paper, it is also noticeable that folded ResNets with learned weights achieve higher accuracy than previously reported in both datasets, especially with deeper configurations. , MobileNetV2 [89], NasNet [90], EfficientNet [91].…”

Section: ) Imagenetmentioning

confidence: 99%

“…HFN is both the most parameter-efficient and the tiniest. (b) also compares with popular efficient models: DenseNet[88], MobileNetV2[89], NasNet[90], EfficientNet[91].…”

mentioning

confidence: 99%

Recurrent Residual Networks Contain Stronger Lottery Tickets

et al. 2023

View full text Add to dashboard Cite

Accurate neural networks can be found just by pruning a randomly initialized overparameterized model, leaving out the need for any weight optimization. The resulting subnetworks are small, sparse, and ternary, making excellent candidates for efficient hardware implementation. However, finding optimal connectivity patterns is an open challenge. Based on the evidence that residual networks may be approximating unrolled shallow recurrent neural networks, we conjecture that they contain better candidate subnetworks at inference time when explicitly transformed into recurrent architectures. This hypothesis is put to the test on image classification tasks, where we find subnetworks within the recurrent models that are more accurate and parameter-efficient than both the ones found within feedforward models and than the full models with learned weights. Furthermore, random recurrent subnetworks are tiny: under a simple compression scheme, ResNet-50 is compressed without a drastic loss in performance to 48.55× less memory size, fitting in under 2 megabytes. Code available at: https://github.com/Lopez-Angel/hidden-fold-networks.

show abstract

“…Gao [7] used whitening pretreatment and stochastic pooling based on traditional CNN; it improved the network generalization ability for military image classification by this method. Zhang et al [8] constructed a deep convolutional neural network (DCNN) with seven layers for the vehicle type identification; the recognition rate reached 96.8% based on comparative experiment with different model parameters. Guo [9] constructed a DCNN used on hand-printed character recognition; the experimental results show that the receptive field size has a significant influence on the number of model parameters but has little effect on the recognition rate and the running time is in a reverse trend.…”

Section: Introductionmentioning

confidence: 99%

Computer-Aided Diagnosis Research of a Lung Tumor Based on a Deep Convolutional Neural Network and Global Features

2021

BioMed Research International

View full text Add to dashboard Cite

Based on the better generalization ability and the feature learning ability of the deep convolutional neural network, it is very significant to use the DCNN on the computer-aided diagnosis of a lung tumor. Firstly, a deep convolutional neural network was constructed according to the fuzzy characteristics and the complexity of lung CT images. Secondly, the relation between model parameters (iterations, different resolution) and recognition rate is discussed. Thirdly, the effects of different model structures for the identification of a lung tumor were analyzed by changing convolution kernel size, feature dimension, and depth of the network. Fourthly, the different optimization methods on how to influence the DCNN performance were discussed from three aspects containing pooling methods (maximum pooling and mean pooling), activation function (sigmoid and ReLU), and training algorithm (batch gradient descent and gradient descent with momentum). Finally, the experimental results verified the feasibility of DCNN used on computer-aided diagnosis of lung tumors, and it can achieve a good recognition rate when selecting the appropriate model parameters and model structure and using the method of gradient descent with momentum.

show abstract

CSF images fast recognition model based on improved convolu-tional Neural Network

Cited by 74 publications

References 8 publications

Multi-View Computed Tomography Network for Osteoporosis Classification

Multi-View Computed Tomography Network for Osteoporosis Classification

Recurrent Residual Networks Contain Stronger Lottery Tickets

Computer-Aided Diagnosis Research of a Lung Tumor Based on a Deep Convolutional Neural Network and Global Features

Contact Info

Product

Resources

About