Application of the homology method for quantification of low-attenuation lung region inpatients with and without COPD

Long non-coding RNA SNHG4 aggravates cigarette smoke-induced COPD by regulating miR-144-3p/EZH2 axis

OBJECTIVE

The purpose of this study was to explore the expression level of SNHG4 in patients with COPD and its diagnostic value in COPD, to probe the biological function of SNHG4 in COPD at the cellular level, and to reveal the interaction between SNHG4 and miR-144-3p/EZH2 axis.

METHODS

The serum levels of SNHG4, miR-144-3p and EZH2 in healthy people and patients with COPD were detected by RT-qPCR. The diagnostic value of SNHG4 in COPD was evaluated by ROC curve. Pearson method was chosen to estimate the correlation between SNHG4 and clinical indicators in patients with COPD. Cigarette smoke extract (CSE) was obtained, and Beas-2B cells were exposed with 2% CSE to establish an inflammatory cell model of COPD in vitro. MTT assay was used to detect cell viability, flow cytometry was used to evaluate cell apoptosis, and ELISA was performed to detect inflammatory cytokines. Dual-luciferase reporting assay was carried out to verify the targeting of lncRNA-miRNA or miRNA-mRNA.

RESULTS

(1) The expression of SNHG4 is decreased in patients with COPD, and the expression level in acute exacerbation COPD was lower than that in stable COPD. SNHG4 demonstrated high diagnostic accuracy in distinguishing between stable and acute exacerbation COPD. (2) The expression of SNHG4 was decreased in CSE-induced Beas-2B cells, and overexpression of SNHG4 was beneficial to alleviate CSE-induced apoptosis and inflammation. (3) The expression of miR-144-3p is up-regulated in patients with COPD and CSE-induced Beas-2B cells. MiR-144-3p has a targeting relationship with SNHG4, which is negatively regulated by SNHG4. Overexpression of miR-144-3p could counteract the beneficial effects of increased SNHG4 on CSE-induced cells. (4) The expression of EZH2 is reduced in patients with COPD and CSE-induced Beas-2B cells. Bioinformatics analysis and luciferase reporter gene confirmed that EZH2 is the downstream target gene of miR-144-3p and is negatively regulated by miR-144-3p.

CONCLUSION

The expression of SNHG4 decreased in patients with COPD, and it may promote the progression of COPD by inhibiting the viability, promoting apoptosis and inflammatory response of bronchial epithelial cells via regulating the miR-144-3p/EZH2 axis.

Homology-Based Image Processing for Automatic Classification of Histopathological Images of Lung Tissue

Simple Summary

The purpose of this study was to develop a computer-aided diagnosis (CAD) system for automatic classification of histopathological images of lung tissues. Homology-based image processing (HI) was proposed for CAD. For developing and validating CAD with HI, two datasets of histopathological images of lung tissues were used. The private dataset consists of 94 histopathological images that were obtained for the following five categories: normal, emphysema, atypical adenomatous hyperplasia, lepidic pattern of adenocarcinoma, and invasive adenocarcinoma. The public dataset consists of 15,000 histopathological images that were obtained for the following three categories: lung adenocarcinoma, lung squamous cell carcinoma, and benign lung tissue. For the two datasets, our results show that HI was more useful than conventional texture analysis for the CAD system.

Abstract

The purpose of this study was to develop a computer-aided diagnosis (CAD) system for automatic classification of histopathological images of lung tissues. Two datasets (private and public datasets) were obtained and used for developing and validating CAD. The private dataset consists of 94 histopathological images that were obtained for the following five categories: normal, emphysema, atypical adenomatous hyperplasia, lepidic pattern of adenocarcinoma, and invasive adenocarcinoma. The public dataset consists of 15,000 histopathological images that were obtained for the following three categories: lung adenocarcinoma, lung squamous cell carcinoma, and benign lung tissue. These images were automatically classified using machine learning and two types of image feature extraction: conventional texture analysis (TA) and homology-based image processing (HI). Multiscale analysis was used in the image feature extraction, after which automatic classification was performed using the image features and eight machine learning algorithms. The multicategory accuracy of our CAD system was evaluated in the two datasets. In both the public and private datasets, the CAD system with HI was better than that with TA. It was possible to build an accurate CAD system for lung tissues. HI was more useful for the CAD systems than TA.

Homology-based radiomic features for prediction of the prognosis of lung cancer based on CT-based radiomics

PURPOSE

Radiomics is a new technique that enables noninvasive prognostic prediction by extracting features from medical images. Homology is a concept used in many branches of algebra and topology that can quantify the contact degree. In the present study, we developed homology-based radiomic features to predict the prognosis of non-small-cell lung cancer (NSCLC) patients and then evaluated the accuracy of this prediction method.

METHODS

Four datasets were used: two to provide training and test data and two for the selection of robust radiomic features. All the datasets were downloaded from The Cancer Imaging Archive (TCIA). In two-dimensional cases, the Betti numbers consist of two values: b₀ (zero-dimensional Betti number), which is the number of isolated components, and b₁ (one-dimensional Betti number), which is the number of one-dimensional or "circular" holes. For homology-based evaluation, computed tomography (CT) images must be converted to binarized images in which each pixel has two possible values: 0 or 1. All CT slices of the gross tumor volume were used for calculating the homology histogram. First, by changing the threshold of the CT value (range: -150 to 300 HU) for all its slices, we developed homology-based histograms for b₀ , b₁ , and b₁ /b₀ using binarized images. All histograms were then summed, and the summed histogram was normalized by the number of slices. 144 homology-based radiomic features were defined from the histogram. To compare the standard radiomic features, 107 radiomic features were calculated using the standard radiomics technique. To clarify the prognostic power, the relationship between the values of the homology-based radiomic features and overall survival was evaluated using LASSO Cox regression model and the Kaplan-Meier method. The retained features with nonzero coefficients calculated by the LASSO Cox regression model were used for fitting the regression model. Moreover, these features were then integrated into a radiomics signature. An individualized rad score was calculated from a linear combination of the selected features, which were weighted by their respective coefficients.

RESULTS

When the patients in the training and test datasets were stratified into high-risk and low-risk groups according to the rad scores, the overall survival of the groups was significantly different. The C-index values for the homology-based features (rad score), standard features (rad score), and tumor size were 0.625, 0.603, and 0.607, respectively, for the training datasets and 0.689, 0.668, and 0.667 for the test datasets. This result showed that homology-based radiomic features had slightly higher prediction power than the standard radiomic features.

CONCLUSIONS

Prediction performance using homology-based radiomic features had a comparable or slightly higher prediction power than standard radiomic features. These findings suggest that homology-based radiomic features may have great potential for improving the prognostic prediction accuracy of CT-based radiomics. In this result, it is noteworthy that there are some limitations.

Estimation of lung cancer risk using homology-based emphysema quantification in patients with lung nodules

The purpose of this study was to assess whether homology-based emphysema quantification (HEQ) is significantly associated with lung cancer risk. This retrospective study was approved by our institutional review board. We included 576 patients with lung nodules (317 men and 259 women; age, 66.8 ± 12.3 years), who were selected from a database previously generated for computer-aided diagnosis. Of these, 283 were diagnosed with lung cancer, whereas the remaining 293 showed benign lung nodules. HEQ was performed and percentage of low-attenuation lung area (LAA%) was calculated on the basis of computed tomography scans. Statistical models were constructed to estimate lung cancer risk using logistic regression; sex, age, smoking history (Brinkman index), LAA%, and HEQ were considered independent variables. The following three models were evaluated: the base model (sex, age, and smoking history); the LAA% model (the base model + LAA%); and the HEQ model (the base model + HEQ). Model performance was assessed using receiver operating characteristic analysis and the associated area under the curve (AUC). Differences in AUCs among the models were evaluated using Delong’s test. AUCs of the base, LAA%, and HEQ models were 0.585, 0.593, and 0.622, respectively. HEQ coefficient was statistically significant in the HEQ model (P = 0.00487), but LAA% coefficient was not significant in the LAA% model (P = 0.199). Delong’s test revealed significant difference in AUCs between the LAA% and HEQ models (P = 0.0455). In conclusion, after adjusting for age, sex, and smoking history (Brinkman index), HEQ was significantly associated with lung cancer risk.

Convolutional auto-encoder for image denoising of ultra-low-dose CT

OBJECTIVES

The purpose of this study was to validate a patch-based image denoising method for ultra-low-dose CT images. Neural network with convolutional auto-encoder and pairs of standard-dose CT and ultra-low-dose CT image patches were used for image denoising. The performance of the proposed method was measured by using a chest phantom.

MATERIALS AND METHODS

Standard-dose and ultra-low-dose CT images of the chest phantom were acquired. The tube currents for standard-dose and ultra-low-dose CT were 300 and 10 mA, respectively. Ultra-low-dose CT images were denoised with our proposed method using neural network, large-scale nonlocal mean, and block-matching and 3D filtering. Five radiologists and three technologists assessed the denoised ultra-low-dose CT images visually and recorded their subjective impressions of streak artifacts, noise other than streak artifacts, visualization of pulmonary vessels, and overall image quality.

RESULTS

For the streak artifacts, noise other than streak artifacts, and visualization of pulmonary vessels, the results of our proposed method were statistically better than those of block-matching and 3D filtering (p-values < 0.05). On the other hand, the difference in the overall image quality between our proposed method and block-matching and 3D filtering was not statistically significant (p-value = 0.07272). The p-values obtained between our proposed method and large-scale nonlocal mean were all less than 0.05.

CONCLUSION

Neural network with convolutional auto-encoder could be trained using pairs of standard-dose and ultra-low-dose CT image patches. According to the visual assessment by radiologists and technologists, the performance of our proposed method was superior to that of large-scale nonlocal mean and block-matching and 3D filtering.

Automated prediction of emphysema visual score using homology-based quantification of low-attenuation lung region

Objective

The purpose of this study was to investigate the relationship between visual score of emphysema and homology-based emphysema quantification (HEQ) and evaluate whether visual score was accurately predicted by machine learning and HEQ.

Materials and methods

A total of 115 anonymized computed tomography images from 39 patients were obtained from a public database. Emphysema quantification of these images was performed by measuring the percentage of low-attenuation lung area (LAA%). The following values related to HEQ were obtained: nb₀ and nb₁. LAA% and HEQ were calculated at various threshold levels ranging from −1000 HU to −700 HU. Spearman’s correlation coefficients between emphysema quantification and visual score were calculated at the various threshold levels. Visual score was predicted by machine learning and emphysema quantification (LAA% or HEQ). Random Forest was used as a machine learning algorithm, and accuracy of prediction was evaluated by leave-one-patient-out cross validation. The difference in the accuracy was assessed using McNemar’s test.

Results

The correlation coefficients between emphysema quantification and visual score were as follows: LAA% (−950 HU), 0.567; LAA% (−910 HU), 0.654; LAA% (−875 HU), 0.704; nb₀ (−950 HU), 0.552; nb₀ (−910 HU), 0.629; nb₀ (−875 HU), 0.473; nb₁ (−950 HU), 0.149; nb₁ (−910 HU), 0.519; and nb₁ (−875 HU), 0.716. The accuracy of prediction was as follows: LAA%, 55.7% and HEQ, 66.1%. The difference in accuracy was statistically significant (p = 0.0290).

Conclusion

LAA% and HEQ at −875 HU showed a stronger correlation with visual score than those at −910 or −950 HU. HEQ was more useful than LAA% for predicting visual score.

Homology analysis detects topological changes of Iba1 localization accompanied by microglial activation

The state of microglial activation provides important information about the central nervous system. However, a reliable index of microglial activation in histological samples has yet to be established. Here, we show that microglial activation induces topological changes of Iba1 localization that can be detected by analysis based on homology theory. Analysis of homology was applied to images of Iba1-stained tissue sections, and the 0-dimentional Betti number (b0: the number of solid components) and the 1-dimentional Betti number (b1: the number of windows surrounded by solid components) were obtained. We defined b1/b0 as the Homology Value (HV), and investigated its validity as an index of microglial activation using cerebral ischemia model mice. Microglial activation was accompanied by changes to Iba1 localization and morphology of microglial processes. In single microglial cells, the change of Iba1 localization increased b1. Conversely, thickening or retraction of microglial processes decreased b0. Consequently, microglial activation increased the HV. The HV of a tissue area increased with proximity to the ischemic core and showed a high degree of concordance with the number of microglia expressing activation makers. Furthermore, the HV of human metastatic brain tumor tissue also increased with proximity to the tumor. These results suggest that our index, based on homology theory, can be used to correctly evaluate microglial activation in various tissue images.