scholarly journals Study on the early detection of gastric cancer based on discrete wavelet transformation feature extraction of FT-IR spectra combined with probability neural network

2011 ◽  
Vol 26 (3) ◽  
pp. 155-165 ◽  
Author(s):  
Tao Hu ◽  
Yu-Hui Lu ◽  
Cun-Gui Cheng ◽  
Xiao-Chen Sun
Keyword(s):  
Neural Network ◽  
Gastric Cancer ◽  
Feature Extraction ◽  
Ir Spectra ◽  
Wavelet Transformation ◽  
Gastric Cancer Tissue ◽  
Discrete Wavelet ◽  
Cancer Tissue ◽  
Discrete Wavelet Transformation ◽  
Ft Ir

This paper introduces a new method for the early detection of gastric cancer using a combination of feature extraction based on discrete wavelet transformation (DWT) for horizontal attenuated total reflectance–Fourier transform infrared spectroscopy (HATR–FT-IR) and classification using probability neural network (PNN). 344 FT-IR spectra were collected from 172 pairs of fresh normal and abnormal stomach tissue᾽s samples. After preprocessing, 5 features were extracted with DWT analysis. Based on the PNN classification, all FT-IR spectra were classified into three categories. The accuracy of identifying normal gastric tissue, early gastric cancer tissue and gastric cancer tissue samples were 100.00, 97.56 and 100.00%, respectively. This result indicated that FT-IR with DWT and PNN could effectively and easily diagnose gastric cancer in its early stages.

scholarly journals Recognition of FT-IR Data Cuscutae Semen, Japanese Dodder, and Sinapis Semen Using Discrete Wavelet Transformation and RBF Networks

2013 ◽  
Vol 2013 ◽  
pp. 1-8
Author(s):  
Tao Hu ◽  
Xuexiang Weng ◽  
Lishan Xu ◽  
Cungui Cheng ◽  
Peng Yu
Keyword(s):  
Neural Networks ◽  
Wavelet Transformation ◽  
Feature Vector ◽  
Recognition Rate ◽  
Discrete Wavelet ◽  
Discrete Wavelet Transformation ◽  
Rbf Neural Networks ◽  
Feature Extracting ◽  
Ir Studies ◽  
Ft Ir

Horizontal attenuation total reflection Fourier transformation infrared spectroscopy (HATR-FT-IR) studies on cuscutae semen and its confusable varieties Japanese dodder and sinapis semen combined with discrete wavelet transformation (DWT) and radial basis function (RBF) neural networks have been conducted in order to classify them. DWT is used to decompose the FT-IRs of cuscutae semen, Japanese dodder, and sinapis semen. Two main scales are selected as the feature extracting space in the DWT domain. According to the distribution of cuscutae semen, Japanese dodder, and sinapis semen’s FT-IRs, three feature regions are determined at detail 3, and two feature regions are determined at detail 4 by selecting two scales in the DWT domain. Thus five feature parameters form the feature vector. The feature vector is input to the RBF neural networks to train so as to accurately classify the cuscutae semen, Japanese dodder, and sinapis semen. 120 sets of FT-IR data are used to train and test the proposed method, where 60 sets of data are used to train samples, and another 60 sets of FT-IR data are used to test samples. Experimental results show that the accurate recognition rate of cuscutae semen, Japanese dodder, and sinapis semen is average of 100.00%, 98.33%, and 100.00%, respectively, following the proposed method.

scholarly journals Ekstrasi Fitur Citra MRI Otak Menggunakan Data Wavelet Transform (DWT) untuk Klasifikasi Penyakit Tumor Otak

2019 ◽  
Vol 10 (2) ◽  
Author(s):  
Lastri Widya Astuti
Keyword(s):  
Magnetic Resonance Imaging ◽  
Feature Extraction ◽  
Magnetic Resonance ◽  
Wavelet Transformation ◽  
Discrete Wavelet ◽  
Discrete Wavelet Transformation ◽  
Resonance Imaging ◽  
Magnetic Resonance Imaging Mri ◽  
Adaptive Neighborhood ◽  
The Brain

<p class="SammaryHeader" align="center"><strong>ABSTRACT</strong></p><p><em>The brain is formed from two types of cells: glia and neurons. Glia functions to support and protect neurons, while neurons carry information in the form of electrical pulses known as potential action. The brain regulates and coordinates most of the body's movements, behavior, and homeostasis functions such as heart rate, blood pressure, body fluid balance and body temperature. A brain tumor is a mass of abnormally growing brain cells. Most brain tumors can spread through brain tissue, but rarely spread to other areas of the body. But in the case of benign brain tumors, as they grow they can destroy and suppress other normal brain tissue, which can result in paralysis. Several methods are used to detect disorders of the brain nerve tissue, including: Magnetic Resonance Imaging (MRI). This research is intended to build a classification system for brain image data using Magnetic Resonance Imaging (MRI) with the category, normal, Glioma, metastatic bronchogenic carcinoma or Alzheimer's using Magnetic Resonance Imaging (MRI) so that it can assist in decision making for medical experts. While the method used in this research is Discrete Wavelet Transformation (DWT) for the feature extraction process so that the unique characteristics of an object can be recognized, as well as the classification process using the adaptive neighborhood neural network method. This research is able to integrate the two methods with the acquisition of significant accuracy.</em></p><p><strong><em>Keywords</em></strong><strong><em> </em></strong><strong><em>: </em></strong><em>feature extraction, classification, MRI, Brain</em></p><p class="SammaryHeader" align="center"><strong>ABSTRAK</strong></p><p><em>Otak terbentuk dari dua jenis sel: glia dan neuron. Glia berfungsi untuk menunjang dan melindungi neuron, sedangkan neuron membawa informasi dalam bentuk pulsa listrik yang di kenal sebagai</em><em> potensi aksi</em><em>.</em><em> </em><em>Otak mengatur dan mengkordinir sebagian besar,</em><em>gerakan</em><em>, </em><em>perilaku</em><em> dan fungsi tubuh homeostasis seperti detak jantung, tekanan darah, keseimbangan cairan tubuh dan suhu tubuh</em><em>.</em><em> Tumor otak adalah sekumpulan massa sel-sel otak yang tumbuh abnormal. Sebagian besar tumor otak dapat menyebar melalui jaringan otak, tetapi jarang sekali menyebar ke area lain dari tubuh. Namun pada kasus tumor otak yang jinak, saat mereka tumbuh dapat menghancurkan dan menekan jaringan otak normal lainnya, yang dapat berakibat pada kelumpuhan. Beberapa metode dipergunakan untuk mendeteksi gangguan pada jaringan syaraf otak, diantaranya: </em><em>Magnetic</em><em> </em><em>Resonance Imaging</em><em> (MRI)</em><em>.</em><em> </em><em>Penelitian </em><em>ini dimaksudkan untuk m</em><em>embangun sistem klasifikasi </em><em>untuk data citra otak menggunakan Magnetic Resonance Imaging (MRI) dengan kategori, normal, Glioma, metastatic bronchogenic carcinoma atau Alzheimer menggunakan Magnetic Resonance Imaging (MRI) sehingga dapat membantu  dalam pengambilan keputusan bagi tenaga ahli dibidang kedokteran. Sedangkan metode yang digunakan dalam penelitian adalah Discrete Wavelet Transformation (DWT) untuk proses ekstrasi fitur (feature extraction) </em><em>agar</em><em> karakteristik unik dari suatu objek</em><em> dapat dikenali</em><em>, serta proses k</em><em>lasifikasi</em><em> meng</em><em>gunakan metode adaptive neighborhood neural network. Penelitian ini mampu mengintegrasikan kedua metoda dengan perolehan hasil akurasi yang signifikan.</em></p><strong><em>Kata kunci : </em></strong><em>ekstrasi fitur, klasifikasi, MRI, Otak</em>

scholarly journals Recognition of MIR Data of Semen Armeniacae Amarum and Semen Persicae Using Discrete Wavelet Transformation and BP-Artificial Neural Network

2012 ◽  
Vol 27 ◽  
pp. 253-264 ◽  
Author(s):  
Cun-Gui Cheng ◽  
Peng Yu ◽  
Chang-Shun Wu ◽  
Jia-Ni Shou
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wavelet Transformation ◽  
Feature Vector ◽  
Recognition Rate ◽  
Back Propagation ◽  
Discrete Wavelet ◽  
Discrete Wavelet Transformation ◽  
Artificial Neural ◽  
The Difference

Horizontal attenuation total reflection-Fourier transformation infrared spectroscopy (HATR-FT-IR) is used to measure the Mid-IR (MIR) of semen armeniacae amarum and its confusable varieties semen persicae. In order to extrude the difference between semen armeniacae amarum and semen persicae, discrete wavelet transformation (DWT) is used to decompose the MIR of semen armeniacae amarum and semen persicae. Two main scales are selected as the feature extracting space in the DWT domain. According to the distribution of semen armeniacae amarum and semen persicae’s MIR, five feature regions are determined at every spectra band by selecting two scales in the DWT domain. Thus, ten feature parameters form the feature vector. The feature vector is input to the back-propagation artificial neural network (BP-ANN) to train so as to accurately classify the semen armeniacae amarum and semen persicae. 100 couples of MIR are used to train and test the proposed method, where 50 couples of data are used to train samples and other 50 couples of data are used to test samples. Experimental results show that the accurate recognition rate between semen armeniacae amarum and semen persicae is averaged 99% following the proposed method.

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

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.

Sign in / Sign up

Export Citation Format

Share Document