Feature Extraction and Classification on Esophageal X-Ray Images of Xinjiang Kazak Nationality

Abstract

Esophageal cancer is one of the fastest rising types of cancers in China. The Kazak nationality is the highest-risk group in Xinjiang. In this work, an effective computer-aided diagnostic system is developed to assist physicians in interpreting digital X-ray image features and improving the quality of diagnosis. The modules of the proposed system include image preprocessing, feature extraction, feature selection, image classification, and performance evaluation. 300 original esophageal X-ray images were resized to a region of interest and then enhanced by the median filter and histogram equalization method. 37 features from textural, frequency, and complexity domains were extracted. Both sequential forward selection and principal component analysis methods were employed to select the discriminative features for classification. Then, support vector machine and K-nearest neighbors were applied to classify the esophageal cancer images with respect to their specific types. The classification performance was evaluated in terms of the area under the receiver operating characteristic curve, accuracy, precision, and recall, respectively. Experimental results show that the classification performance of the proposed system outperforms the conventional visual inspection approaches in terms of diagnostic quality and processing time. Therefore, the proposed computer-aided diagnostic system is promising for the diagnostics of esophageal cancer.

Efficient intelligent system for diagnosis pneumonia (SARS-COVID19) in X-Ray images empowered with initial clustering

“…HOG is an efficient image descriptor that converts a 2D image into a vector of features [12,17,18]. Technically, it extracts features from an image based on the oriented gradient of colors in localized portions of an image.…”

“…COVID-19 is a world epidemic disease of respiratory infections due to the wide propagation among people. X-ray examination is widely used in medical test to determine respiratory infections [2,3,12]. Designing an application that identifies cases infected with respiratory infections based only on X-ray would significantly reduce the momentum on hospitals and helps patients to know their health state remotely.…”

“…This will negatively affect the performance of machine learning algorithms Yang et.al. [12] have proposed a new model to classify x-ray images of oesophagal cancer. They extracted features in four-level discrete wavelet decomposition (DWT).…”

Deep Learning-Based Earlier Detection of Esophageal Cancer Using Improved Empirical Wavelet Transform From Endoscopic Image

“…The prognosis of the intraepithelial or normal mucosal patients that are screened with carcinomas is outstanding at 5-year of 85-100 survival rates [8]. In some of these cases, mucosal resections have been undertaken endoscopically and can expect to contribute to regular, high-lifestyles [9,10].…”

Computational Model for Creating Neural Network Dataset of Extracted Features From Images Captured by Multimedia Security Devices

“…One of the commonly used methods for extracting texture features is the Gray-level co-occurrence matrix (GLCM) which describes patterns of gray-level repetition. This method was introduced by Haralick et al [17]. The co-occurrence matrix contains information about the orientation and distance between the pixels.…”