Small lung nodules detection based on local variance analysis and probabilistic neural network
Introduction
Lung cancer is most curable when detected at an early stage. Unfortunately, the majority of individuals discover the presence of the lung cancer at an advanced stage, when the prognosis is very poor. The major goal of any screening program is a reduction in the number of disease specific deaths in the screened population.
The principle of the x-ray methods require radiation source, which generates the waves with length ranging from 10 pm to 10 nm, and detector. Radiation with these properties penetrate our body. Different tissues have different absorption capacity, when x-ray burst of radiation passes through the body and strikes a detector. Body parts with higher density are presented as structures (i.e. bones). In contrasts, tissues with lower density such as lungs have darker reflection in the image. As a result, bones appear white, soft tissues show up in shades of gray and air appears black. The dose of radiation used in x-ray is about 0.02 [mSv] for a front view and 0.08 [mSv] for a side view. Modern x-ray systems have well-controlled x-ray beams and doses minimized to stray (scatter) radiation. In Fig. 1 are shown some samples of chest x-ray with diagnosed nodules in lungs.
Chest x-ray screening for lung carcinoma (radiography performed to detect pre symptomatic disease) is the most important tool for the prevention. Unfortunately, the early detection and interpretation of lung carcinoma using chest X-ray is achieved in ≈ 30% of cases. A very important fact is that, in 90% of peripheral neoplasms and in 65–70% of central neoplasms, there was radiographic evidence many months before the malignancies actually were diagnosed.
The most frequent cause of detection failure is the radiologist’s difficulty in interpreting the presence of lungs carcinoma in chest x-ray. In fact is very hard evaluate unclear zones that are very opaque and may have scarcely defined margins or may be hidden totally by superimposition of other structures, particularly bones.
Due to the high prevalence of lung cancer among total cancer cases and the high mortality rate of the disease post-diagnosis, the prevailing thought is to identify visible nodules before they metastasize in order to dramatically reduce the death toll.
The in-depth interpretation of the chest x-ray requires a subtlety that may not be immediately obvious in many circumstances. In such circumstances, an automated approach could be highly advantageous as it provides important help in medical diagnosis.
In this paper we propose a new classification method of the lung carcinomas, based on a simple segmentation method and on a probabilistic neural network in order to obtain a more accurate classification of the presence or absence of lung carcinomas in chest x-ray image. The proposed method presents good performances obtaining an overall correct classification rate of 92%.
The analysis of the consequences from the untreated symptoms that may lead to cancer were presented in [1], [2]. In these papers are reported the recent advances in automated detection of abnormalities in lungs were reported. An approach based on radiomic features provided by Support Vector Machine was presented in [3], while in [4] a model of pulmonary nodules detection based on the analysis of significant features in x-ray images was presented. In [5] the possible nodules were extracted by using a polygon approximation. A comparative analysis of various approaches are discussed in [6]. The neural networks play an important role in classification of lung tissues abnormalities. In [7] was presented a fusion of deep learning approach used for evaluation of nodules from texture and shape analysis. While in [8], Zhang et al. [9] are used a Convolutional Neural Network and an Extreme Learning Machine, respectively, for classification of lung nodules. Furthermore, adaptive models of neural networks have been developed [10], [11], [12]. A comparative analysis on a wide range of similar approaches was presented in [13].
Section snippets
Methods
By analyzing the available x-ray images it is possible to note that the presence of lung carcinoma in the image is characterized by a different local variance of its gray levels. Then in order to localize and extract the lung nodules we calculate for each pixel of the original image the local variance as illustrated in Fig. 2. So the output image (variance image) is an image with the same size as the original image. Each entry of the variance image is the local variance of the corresponding
Results
The performance of the proposed method can be evaluate, also, by using the confusion matrix and benchmark metrics such as Accuracy (Γ), Sensitivity (χ) and Specificity (ζ) , which are defined as follows: where TP, FP, TN and FN represent true positive, false positive, true negative and false negative lung nodules, respectively.
The Sensitivity measures the efficiency in recognition of the lung nodules (correct recognition of patients with health problems),
Discussion
The chest x-ray is a very useful examination, but it has limitations. The problem with this kind of examination is related to the nature of this method. There is a variety of pathological changes, which may give a similar projection on the image. Therefore, in the past years, various approaches to improve the x-ray examinations and to provide an automated support for the x-ray diagnose have been presented. Some of these are discussed in [41].
Lung cancer most commonly manifests itself with the
Conclusions
The proposed method is relatively simple, but at the same time provides good results. In Table 1 we present a summary of similar approaches for lungs nodules detection. In comparison to other methods the main advantages of the proposed method are: a better correct classification rate (92%) and the fact that is capable to detect low-contrast nodules and lung cancers of minor or equal to 20 mm of diameter.
Ethical standard
On this matter we would like to point out that our experiments, concerning data analysis and classification, most images have not directly been performed on human beings, but were concerning the off-line analysis of the signals obtained by a public database (http://radiologykey.com/solitary-and-multiple-pulmonary-nodules) in order to grant more transparency and to use a safe data source also in terms of ethical approval. The remaining images come from Zagłȩbiowskie Oncology Centre, Poland. For
References (49)
- et al.
Fusing texture, shape and deep model-learned information at decision level for automated classification of lung nodules on chest ct
Inf. Fusion
(2018) - et al.
Hybrid-feature-guided lung nodule type classification on ct images
Comput. Graphics
(2018) - et al.
Multi-kernel extreme learning machine for eeg classification in brain-computer interfaces
Expert Syst. Appl.
(2018) - et al.
Application of probabilistic neural network in bacterial identification by biochemical profiles
J. Microbiol. Methods
(2013) Probabilistic neural networks
Neural Netw.
(1990)- et al.
Automatic detection of pleural effusion in chest radiographs
Med. Image Anal.
(2016) - et al.
Feature selection using ant colony optimization with tandem-run recruitment to diagnose bronchitis from ct scan images
Comput. Methods Programs Biomed.
(2017) - et al.
Rough set based rule induction in decision making using credible classification and preference from medical application perspective
Comput. Methods Programs Biomed.
(2016) - et al.
A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in lung nodule cad
Comput. Methods Programs Biomed.
(2017) - et al.
Edge enhancement algorithm for low-dose x-ray fluoroscopic imaging
Comput. Methods Programs Biomed.
(2017)
Incidental perifissural nodules on routine chest computed tomography: lung cancer or not?
Eur. Radiol.
Controversies on lung cancers manifesting as part-solid nodules
Eur. Radiol.
Radiomic features analysis in computed tomography images of lung nodule classification
PLoS ONE
Significant features to detect pulmonary nodules from ct lung images
Biomed. Eng
Lung nodule detection using polygon approximation and hybrid features from ct images
Curr. Med. Imaging Rev.
Content-based image retrieval for lung nodule classification using texture features and learned distance metric
J. Med. Syst.
An adaptive neural network approach for operator functional state prediction using psychophysiological data
Integr. Comput. Aided Eng.
A novel multilayer correlation maximization model for improving cca-based frequency recognition in ssvep brain–computer interface
Int. J. Neural Syst.
Discriminative feature extraction via multivariate linear regression for ssvep-based bci
IEEE Trans. Neural Syst. Rehabil. Eng.
An appraisal of nodules detection techniques for lung cancer in ct images
Biomed. Signal Process. Control
Local directional mask maximum edge patterns for image retrieval and face recognition
IET Comput. Vision
Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm
IEEE Trans. Med. Imaging
Automatic heart activity diagnosis based on gram polynomials and probabilistic neural networks
Biomed. Eng. Lett.
Cited by (82)
Advancements in traditional machine learning techniques for detection and diagnosis of fatal cancer types: Comprehensive review of biomedical imaging datasets
2024, Measurement: Journal of the International Measurement ConfederationA new leak recognition method for natural gas pipelines in the urban underground space based on probabilistic neural network
2023, Journal of Loss Prevention in the Process IndustriesAnalysis based on machine and deep learning techniques for the accurate detection of lung nodules from CT images
2023, Biomedical Signal Processing and ControlAutomatic algorithm for determining bone and soft-tissue factors in dual-energy subtraction chest radiography
2023, Biomedical Signal Processing and ControlCitation Excerpt :For this reason, the early stage of lung cancer detection is still a challenge. In lung diagnosis, nodules sometimes overlap with ribs and tissues on lung chest radiographic images [2–4]; hence, it is difficult for doctors and radiologists to have an exact diagnosis. Dual-energy subtraction (DES) is a suitable solution to solve that issue [5,6].
Content-based medical image retrieval by spatial matching of visual words
2022, Journal of King Saud University - Computer and Information Sciences