Diagnosis of osteoporosis disease from bone X-ray images with stacked sparse autoencoder and SVM classifier

The novel Coronavirus 2019 (COVID-19) has spread rapidly and has become a pandemic around the world. So far, about 44 million cases have been registered, causing more than one million deaths worldwide. COVID-19 has had a devastating impact on every nation, particularly the economic sector. To identify the infected human being and prevent the virus from spreading further, easy, and precise screening is required. COVID-19 can be potentially detected by using Chest X-ray and computed tomography (CT) images, as these images contain essential information of lung infection. This radiology image is usually examined by the expert to detect the presence of COVID-19 symptom. In this study, the improved stacked sparse autoencoder is used to examine the radiology images. According to the result, the proposed deep learning model was able to achieve a classification accuracy of 96.6% and 83.0% for chest X-ray and chest CT-scan images, respectively.

Download Full-text

Remaining Useful Life Prediction Based on Stacked Sparse Autoencoder and Echo State Network

2020 39th Chinese Control Conference (CCC) ◽

10.23919/ccc50068.2020.9188550 ◽

2020 ◽

Author(s):

Yinghua Yang ◽

Dandan Yao ◽

Xiaozhi Liu

Keyword(s):

Life Prediction ◽

Remaining Useful Life ◽

Echo State Network ◽

Useful Life ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

Download Full-text

Ability of radiofrequency echographic multispectrometry to identify osteoporosis status in elderly women with type 2 diabetes

Aging Clinical and Experimental Research ◽

10.1007/s40520-021-01889-w ◽

2021 ◽

Author(s):

Carla Caffarelli ◽

Maria Dea Tomai Pitinca ◽

Antonella Al Refaie ◽

Elena Ceccarelli ◽

Stefano Gonnelli

Keyword(s):

Type 2 Diabetes ◽

Lumbar Spine ◽

Elderly Women ◽

Fragility Fractures ◽

Dual Energy ◽

Healthy Controls ◽

Diagnosis Of Osteoporosis ◽

X Ray ◽

The Difference

Abstract Background Patients with type 2 diabetes (T2DM) have an increased or normal BMD; however fragility fractures represent one of the most important complications of T2DM. Aims This study aimed to evaluate whether the use of the Radiofrequency Echographic multi spectrometry (REMS) technique may improve the identification of osteoporosis in T2DM patients. Methods In a cohort of 90 consecutive postmenopausal elderly (70.5 ± 7.6 years) women with T2DM and in 90 healthy controls we measured BMD at the lumbar spine (LS-BMD), at femoral neck (FN-BMD) and total hip (TH-BMD) using a dual-energy X-ray absorptiometry device; moreover, REMS scans were also carried out at the same axial sites. Results DXA measurements were all higher in T2DM than in non-T2DM women; instead, all REMS measurements were lower in T2DM than in non T2DM women. Moreover, the percentage of T2DM women classified as “osteoporotic”, on the basis of BMD by REMS was markedly higher with respect to those classified by DXA (47.0% vs 28.0%, respectively). On the contrary, the percentage of T2DM women classified as osteopenic or normal by DXA was higher with respect to that by REMS (48.8% and 23.2% vs 38.6% and 14.5%, respectively). T2DM women with fragility fractures presented lower values of both BMD-LS by DXA and BMD-LS by REMS with respect to those without fractures; however, the difference was significant only for BMD-LS by REMS (p < 0.05). Conclusions Our data suggest that REMS technology may represent a useful approach to enhance the diagnosis of osteoporosis in patients with T2DM.

Download Full-text

Breath analysis based early gastric cancer classification from deep stacked sparse autoencoder neural network

Scientific Reports ◽

10.1038/s41598-021-83184-2 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Muhammad Aqeel Aslam ◽

Cuili Xue ◽

Yunsheng Chen ◽

Amin Zhang ◽

Manhua Liu ◽

...

Keyword(s):

Neural Network ◽

Gastric Cancer ◽

Feature Extraction ◽

Early Gastric Cancer ◽

Breath Analysis ◽

Cancer Classification ◽

Unlabeled Data ◽

Softmax Classifier ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

AbstractDeep learning is an emerging tool, which is regularly used for disease diagnosis in the medical field. A new research direction has been developed for the detection of early-stage gastric cancer. The computer-aided diagnosis (CAD) systems reduce the mortality rate due to their effectiveness. In this study, we proposed a new method for feature extraction using a stacked sparse autoencoder to extract the discriminative features from the unlabeled data of breath samples. A Softmax classifier was then integrated to the proposed method of feature extraction, to classify gastric cancer from the breath samples. Precisely, we identified fifty peaks in each spectrum to distinguish the EGC, AGC, and healthy persons. This CAD system reduces the distance between the input and output by learning the features and preserve the structure of the input data set of breath samples. The features were extracted from the unlabeled data of the breath samples. After the completion of unsupervised training, autoencoders with Softmax classifier were cascaded to develop a deep stacked sparse autoencoder neural network. In last, fine-tuning of the developed neural network was carried out with labeled training data to make the model more reliable and repeatable. The proposed deep stacked sparse autoencoder neural network architecture exhibits excellent results, with an overall accuracy of 98.7% for advanced gastric cancer classification and 97.3% for early gastric cancer detection using breath analysis. Moreover, the developed model produces an excellent result for recall, precision, and f score value, making it suitable for clinical application.

Download Full-text

Reliable Fault Diagnosis of Rotary Machine Bearings Using a Stacked Sparse Autoencoder-Based Deep Neural Network

Shock and Vibration ◽

10.1155/2018/2919637 ◽

2018 ◽

Vol 2018 ◽

pp. 1-11 ◽

Cited By ~ 14

Author(s):

Muhammad Sohaib ◽

Jong-Myon Kim

Keyword(s):

Fault Diagnosis ◽

Language Processing ◽

Classification Performance ◽

Fault Classification ◽

Shaft Speed ◽

Complex Envelope ◽

The Past ◽

Feature Extraction And Selection ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder

Due to enhanced safety, cost-effectiveness, and reliability requirements, fault diagnosis of bearings using vibration acceleration signals has been a key area of research over the past several decades. Many fault diagnosis algorithms have been developed that can efficiently classify faults under constant speed conditions. However, the performances of these traditional algorithms deteriorate with fluctuations of the shaft speed. In the past couple of years, deep learning algorithms have not only improved the classification performance in various disciplines (e.g., in image processing and natural language processing), but also reduced the complexity of feature extraction and selection processes. In this study, using complex envelope spectra and stacked sparse autoencoder- (SSAE-) based deep neural networks (DNNs), a fault diagnosis scheme is developed that can overcome fluctuations of the shaft speed. The complex envelope spectrum made the frequency components associated with each fault type vibrant, hence helping the autoencoders to learn the characteristic features from the given input signals more readily. Moreover, the implementation of SSAE-DNN for bearing fault diagnosis has avoided the need of handcrafted features that are used in traditional fault diagnosis schemes. The experimental results demonstrate that the proposed scheme outperforms conventional fault diagnosis algorithms in terms of fault classification accuracy when tested with variable shaft speed data.

Download Full-text

DSSAE: Deep Stacked Sparse Autoencoder Analytical Model for COVID-19 Diagnosis by Fractional Fourier Entropy

ACM Transactions on Management Information Systems ◽

10.1145/3451357 ◽

2022 ◽

Vol 13 (1) ◽

pp. 1-20

Author(s):

Shui-Hua Wang ◽

Xin Zhang ◽

Yu-Dong Zhang

Keyword(s):

Data Augmentation ◽

State Of The Art ◽

Community Acquired Pneumonia ◽

Chest Ct ◽

Two Dimensional ◽

The World ◽

Healthy Control ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder ◽

Fractional Fourier Entropy

( Aim ) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. ( Methods ) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom deep stacked sparse autoencoder (DSSAE) model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. ( Results ) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). ( Conclusion ) Our method outperforms 10 state-of-the-art approaches.

Download Full-text

Intelligent Fault Diagnosis of Planetary Wheel Bearing Using Constrained Independent Component Analysis and Stacked Sparse Autoencoder

Volume 12: Wind Energy ◽

10.1115/gt2020-15311 ◽

2020 ◽

Author(s):

Hongkun Li ◽

Gangjin Huang ◽

Jiayu Ou ◽

Yuanliang Zhang

Keyword(s):

Independent Component Analysis ◽

Time Domain ◽

Component Analysis ◽

Independent Component ◽

Mechanical Equipment ◽

Training Samples ◽

Sparse Autoencoder ◽

Stacked Sparse Autoencoder ◽

Constrained Independent Component Analysis ◽

Wheel Bearing

Abstract Industrial machinery is developing in the direction of large-scale, automation, and high precision, which brings novel troubles to mechanical equipment management and maintenance. Intelligent diagnosis of mechanical running state based on vibration signals is becoming increasingly important, and it is still a great challenge at pattern recognition. As one of the indispensable components in mechanical equipment, planetary gearboxes are widely used in wind power, aerospace, and heavy industry. However, the problem of automatically maximizing the accuracy of planetary gearbox under different working conditions has not been solved. Therefore, an intelligent diagnosis method for planetary wheel bearing based on constrained independent component analysis (CICA) and stacked sparse autoencoder (SSAE) is presented in this research. Firstly, the fault signal with obvious time-domain characteristics is extracted by constrained independent component analysis (CICA), and the fault signals and noise is separated. Then, calculating the correlation kurtosis value of the time domain signals at different iteration periods as the eigenvalue to obtain the training samples and the test samples. The parameters of the network layer, the number of hidden nodes and learning rate are determined to build the model of SSAE. In the end, the training samples are input into the model for training and the whole network is fine-tuned. The advantages and disadvantages of the model are verified by the test samples. The intelligent classification and diagnosis of the mechanical running state are completed. Experiments analysis with real datasets of planetary wheel bearing show that the proposed method can achieve higher accuracy and robustness for fault classification compared with other data-driven methods. The application of this method in other major machinery industry also has bright prospects.

Download Full-text