A Novel Morphological Analysis of DXA-DICOM Images by Artificial Neural Networks for Estimating Bone Mineral Density in Health and Disease.

One of the best methods for diagnosing bone disease in humans is site-specific and total bone mineral density (BMD) measurements by Dual-energy X-ray Absorptiometry (DXA) machines. The basic disadvantage of this technology is inconsistent BMD measurements among different DXA machines from different manufacturers due to different image analysis algorithms. The objective of the present study was to apply artificial neural networks (ANNs) to estimate total BMD for diagnosing a population of Egyptians with and without pathology, using extracted features from DXA-DICOM images based on the Histogram and Binary algorithms as compared to reference BMD measurements by DXA machine. The sample size comprised 3000 male and female participants with an age range 22-49 years, who were referred to us for diagnosis and/or treatment and for DXA total body scans in the period from January 2016 till December 2017. We constructed an entry computer data-logging visible unit, where we applied morphological operations to get a specific bone image, and used their extracted feature vectors as inputs to ANNs with cascade training, gathering, and testing for DXA-DICOM image processing. The multilayer feed-forward ANN set up its initial weights, carried out training and initiated the recall mode, and finally observed its decision and interaction based on estimated BMD. The ANN construction was carried out using a 3-layer architecture, with one hidden layer of 85 neurons. The input layer has neuron numbers equal to 256 for the Histogram and 77,365 for Binary algorithms, respectively. Total BMD estimation performance based on the Binary algorithm was capable of identifying all DXA-DICOM images with an accuracy of 100% for the training, cross-validation, and testing of the ANN phases. We believe this strategy will represent the means for standardizing bone measurements of all DXA machines, regardless of the manufacturer.

Volatile organic compounds of biofluids for detecting lung cancer by an electronic nose based on artificial neural network.

Lung cancer (LC) incidence represents 11.5% of all new cancers, resulting in 1.72 million deaths worldwide in 2015. With the aim to investigate the capability of the electronic nose (e-nose) technology for detecting and differentiating complex mixtures of volatile organic compounds in biofluids ex-vivo, we enrolled 50 patients with suspected LC and 50 matching controls. Tissue biopsy was taken from suspicious lung mass for histopathological evaluation and blood, exhaled breath, and urine samples were collected from all participants and qualitatively processed using e-nose. Odor-print patterns were further analysed using the principal component analysis (PCA) and artificial neural network (ANN) analysis. Adenocarcinoma, non-small cell LC and squamous cell carcinoma were the predominant pathological types among LC patients. PCA cluster-plots showed a clear distinction between LC patients and controls for all biological samples; where the overall success ratios of classification for principal components #1 and #2 were: 95.46, 82.01, and 91.66% for blood, breath and urine samples, respectively. Moreover, ANN showed a better discrimination between LC patients and controls with success ratios of 95.74, 91.67 and 100% for blood, breath and urine samples, respectively. The e-nose is an easy noninvasive tool, capable of identifying LC patients from controls with great precision.

Underexpression of miR-486-5p but not Overexpression of miR-155 is Associated with Lung Cancer Stages.

BACKGROUND: Evidence is increasing that microRNAs (miR) are particularly important in lung homeostasis and development and have been shown to be involved in many pulmonary diseases such as asthma, chronic obstructive pulmonary disease, sarcoidosis, Lung Cancer (LC) and other smoking-related diseases. OBJECTIVE: The objective of this study was to investigate the expression of miR-155 and miR-486-5p in tissues from LC patients and healthy endobronchial mucosa as prognostic biomarkers for diagnosing LC. METHODS: Bronchoscopic and thoracoscopic tissue biopsies were taken from 50 LC patients and other 50 control subjects without lung mass, who were planned for a clinical bronchoscopy. The expressions of miR-155 and miR-486-5p in both tumor tissue and healthy mucosa were detected by quantitative real-time polymerase chain reaction. RESULTS: Histopathology showed that 72% of LC patients were in advanced stages III and IV, with non-small cell lung carcinoma and adenocarcinoma being the most common diagnosis. miR-155 was significantly overexpressed while, miR-486-5p was underexpressed, in LC patients as compared to controls. Area under receiver operating characteristic curves of miR-155 (<-0.9) and miR-486 (>-0.62) had sensitivity of 92 and 96% and specificity of 80 and 84%, respectively, in discriminating LC patients from controls with benign solitary pulmonary nodules. CONCLUSION: miR-155 was highly overexpressed, yet it did not correlate with stages, while miR-486- 5p was extremely underexpressed and significantly correlated with stages of LC. Thus, their detection represents an excellent diagnostic/prognostic tool to support more established techniques linked to LC spread locally and systemically.