A statistical interpretation of the chest radiograph for the detection of pulmonary tuberculosis

Noor, Norliza Mohd; Rijal, Omar Mohd; Ashari, Yunus; Mahayiddin, Aziah Ahmad; Peng, Gan Chew; Abu-Bakar, S. A. R.

doi:10.1109/iecbes.2010.5742197

Cited by 11 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tan et al [81] proposed a tuberculosis index (TI) based on the segmented pulmonary regional texture features and classified the normal and abnormal CXR using a decision tree, and obtained an accuracy rate of 94.9%. Noor et al [82] proposed a statistical interpretation technique to detect tuberculosis in CXR images. They first applied the wavelet transform to the CXR image, calculated 12 texture measures from the wavelet coefficients, reduced the dimensions with PCA, and estimated the probability of misclassification using the probability ellipsoid and discriminant functions.…”

Section: Specific Disease Detectionmentioning

confidence: 99%

Computer-aided detection in chest radiography based on artificial intelligence: a survey

et al. 2018

View full text Add to dashboard Cite

As the most common examination tool in medical practice, chest radiography has important clinical value in the diagnosis of disease. Thus, the automatic detection of chest disease based on chest radiography has become one of the hot topics in medical imaging research. Based on the clinical applications, the study conducts a comprehensive survey on computer-aided detection (CAD) systems, and especially focuses on the artificial intelligence technology applied in chest radiography. The paper presents several common chest X-ray datasets and briefly introduces general image preprocessing procedures, such as contrast enhancement and segmentation, and bone suppression techniques that are applied to chest radiography. Then, the CAD system in the detection of specific disease (pulmonary nodules, tuberculosis, and interstitial lung diseases) and multiple diseases is described, focusing on the basic principles of the algorithm, the data used in the study, the evaluation measures, and the results. Finally, the paper summarizes the CAD system in chest radiography based on artificial intelligence and discusses the existing problems and trends.

show abstract

Section: Specific Disease Detectionmentioning

confidence: 99%

Computer-aided detection in chest radiography based on artificial intelligence: a survey

et al. 2018

View full text Add to dashboard Cite

show abstract

“…One of those characteristics is, for example, the number and size of the data sets used for experimentation, which is typically restricted to one data set consisting of roughly hundred images (e.g., [6]- [8]). In this regard, the closest study to ours is perhaps the one by Jaeger et al [3], who experimented with two data sets composed of 138 and 615 CXRs, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…For instance, Noor et al [6] analyzed CXRs with the Daubechies wavelet and processed the resulting features with a modified principal component analysis algorithm and discriminant functions. Rijal et al [7] proposed a method based on phase congruency to measure the transition between pixels representing normal and infected tissue.…”

Section: Introductionmentioning

confidence: 99%

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

Melendez

Ginneken

Maduskar

et al. 2015

IEEE Trans. Med. Imaging

113

View full text Add to dashboard Cite

To reach performance levels comparable to human experts, computer-aided detection (CAD) systems are typically optimized following a supervised learning approach that relies on large training databases comprising manually annotated lesions. However, manually outlining those lesions constitutes a difficult and time-consuming process that renders detailedly annotated data difficult to obtain. In this paper, we investigate an alternative approach, namely multiple-instance learning (MIL), that does not require detailed information for optimization. We have applied MIL to a CAD system for tuberculosis detection. Only the case condition (normal or abnormal) was required during training. Based upon the well-known miSVM technique, we propose an improved algorithm that overcomes miSVM's drawbacks related to positive instance underestimation and costly iteration. To show the advantages of our MIL-based approach as compared with a traditional supervised one, experiments with three X-ray databases were conducted. The area under the receiver operating characteristic curve was utilized as a performance measure. With the first database, for which training lesion annotations were available, our MIL-based method was comparable to the supervised system ( 0.86 versus 0.88 ). When evaluating the remaining databases, given their large difference with the previous image set, the most appealing strategy was to retrain the CAD systems. However, since only the case condition was available, only the MIL-based system could be retrained. This scenario, which is common in real-world applications, demonstrates the better adaptation capabilities of the proposed approach. After retraining, our MIL-based system significantly outperformed the supervised one ( 0.86 versus 0.79 and 0.91 versus 0.85 , and p=0.0002 , respectively).

show abstract

“…The initial Feature Vector (FV) was formed with eight basic texture features of the ROI. These eight texture features are: average gray level, average contrast, measure of smoothness, third moment, measure of uniformity, entropy, energy, and maximum column sum energy [5][6][7].…”

Section: Generation Of the Feature Vectormentioning

confidence: 99%

“…Hence, even today, most of the clustered cellular level deterioration is heuristically estimated using the human expertise, as generally done by a radiologist. Several approaches have been proposed for achieving CAD of diseases through radiological images [4][5][6][7][8][9][10][11][12], but they were developed and tested under mutually different conditions. It is not possible to compare the effectiveness of these approaches as they are evaluated over varying data sets in different conditions.…”

Section: Introductionmentioning

confidence: 99%

Studies of Suspicious Lesions through Local Texture Analysis in Spine Radiographs

Sharma¹,

Nair²

2016

IJCA

View full text Add to dashboard Cite

This paper presents a method to assess and classify the textural abnormalities created by the cellular changes made available through digital radiographs. In this process, digital X-ray images of the spine were subjected to investigations. A study has been made to choose the optimum set of features selectively to train the classifier. In most common applications, the feature vector is extracted from the image data using pixel intensity and magnitude of the frequency displayed as an image. In this case, the introduction of the phase angle of the frequency involved in generating the hue of the suspicious lesions considerably enhanced the success rate of the detection (approximately by 25%). Our experimental study based on 32 subjects indicates that the proposed system is successfully classifying the abnormal regions with 94.37% mean Correct Classification Ratio (CCR). Here, CCR is defined as correctly classified samples versus all the samples.

show abstract

A statistical interpretation of the chest radiograph for the detection of pulmonary tuberculosis

Cited by 11 publications

References 10 publications

Computer-aided detection in chest radiography based on artificial intelligence: a survey

Computer-aided detection in chest radiography based on artificial intelligence: a survey

A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays

Studies of Suspicious Lesions through Local Texture Analysis in Spine Radiographs

Contact Info

Product

Resources

About