Implementation of Combinational Deep Learning Algorithm for Non-alcoholic Fatty Liver Classification in Ultrasound Images.

BACKGROUND: Nowadays, fatty liver is one of the commonly occurred diseases for the liver which can be observed generally in obese patients. Final results from a variety of exams and imaging methods can help to identify and evaluate people affected by this condition. OBJECTIVE: The aim of this study is to present a combined algorithm based on neural networks for the classification of ultrasound images from fatty liver affected patients. MATERIAL AND METHODS: In experimental research can be categorized as a diagnostic study which focuses on classification of the acquired ultrasonography images for 55 patients with fatty liver. We implemented pre-trained convolutional neural networks of Inception-ResNetv2, GoogleNet, AlexNet, and ResNet101 to extract features from the images and after combining these resulted features, we provided support vector machine (SVM) algorithm to classify the liver images. Then the results are compared with the ones in implementing the algorithms independently. RESULTS: The area under the receiver operating characteristic curve (AUC) for the introduced combined network resulted in 0.9999, which is a better result compared to any of the other introduced algorithms. The resulted accuracy for the proposed network also caused 0.9864, which seems acceptable accuracy for clinical application. CONCLUSION: The proposed network can be used with high accuracy to classify ultrasound images of the liver to normal or fatty. The presented approach besides the high AUC in comparison with other methods have the independence of the method from the user or expert interference.

Physical and Dosimetric Aspect of Euromechanics Add-on Multileaf Collimator on Varian Clinac 2100 C/D.

BACKGROUND: Before treatment planning and dose delivery, quality assurance of multi-leaf collimator (MLC) has an important role in intensity-modulated radiation therapy (IMRT) due to the creation of multiple segments from optimization process. OBJECTIVE: The purpose of this study is to assess the quality control of MLC leaves using EBT3 Gafchromic films. MATERIAL AND METHODS: Leaf Position accuracy and leaf gap reproducibility were checked with Garden fence test. The garden fence test consists of 5 thin bands A) 0.2 Cm width spaced at 2 Cm intervals and B) 1 Cm width spaced at 1 Cm intervals. Each leaf accuracy was analyzed with measuring the full-width half-maximum (FWHM). Maximum and average leaf transmission were measured with gafchromic EBT3 films from Ashland for both 6 MV and 18 MV beams. RESULTS: Leaf positions were found to be in a range between 1.78 - 2.53 mm, instead of nominal 2 mm for the test A and between 9.09 - 10.36 mm, instead of nominal 10 mm for the test B. The Average radiation transmission of the MLC was noted 1.79% and 1.98% of the open 10x10 Cm2 field at isocenter for 6 MV and 18 MV beams, respectively. Maximum radiation transmission was noted 4.1% and 4.4% for 6 MV and 18 MV beams, respectively. CONCLUSION: In this study, application of gafchromic EBT3 films for the quality assurance of Euromechanics multileaf collimator was studied. Our results showed that the average leaf leakage and positional accuracy of this type of MLC were in the acceptance level based on the Protocols.

Use of Artificial Neural Networks and PCA to Predict Results of Infertility Treatment in the ICSI Method.

BACKGROUND: Intracytoplasmic sperm injection (ICSI) or microinjection is one of the most commonly used assisted reproductive technologies (ART) in the treatment of patients with infertility problems. At each stage of this treatment cycle, many dependent and independent variables may affect the results, according to which, estimating the accuracy of fertility rate for physicians will be difficult. OBJECTIVE: This study aims to evaluate the efficiency of artificial neural networks (ANN) and principal component analysis (PCA) to predict results of infertility treatment in the ICSI method. MATERIAL AND METHODS: In the present research that is an analytical study, multilayer perceptron (MLP) artificial neural networks were designed and evaluated to predict results of infertility treatment using the ICSI method. In addition, the PCA method was used before the process of training the neural network for extracting information from data and improving the efficiency of generated models. The network has 11 to 17 inputs and 2 outputs. RESULTS: The area under ROC curve (AUC) values were derived from modeling the results of the ICSI technique for the test data and the total data. The AUC for total data vary from 0.7670 to 0.9796 for two neurons, 0.9394 to 0.9990 for three neurons and 0.9540 to 0.9906 for four neurons in hidden layers. CONCLUSION: The proposed MLP neural network can model the specialist performance in predicting treatment results with a high degree of accuracy and reliability.

Automatic Prostate Cancer Segmentation Using Kinetic Analysis in Dynamic Contrast-Enhanced MRI.

BACKGROUND: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) provides functional information on the microcirculation in tissues by analyzing the enhancement kinetics which can be used as biomarkers for prostate lesions detection and characterization. OBJECTIVE: The purpose of this study is to investigate spatiotemporal patterns of tumors by extracting semi-quantitative as well as wavelet-based features, both extracted from pixel-based time-signal intensity curves to segment prostate lesions on prostate DCE-MRI. METHODS: Quantitative dynamic contrast-enhanced MRI data were acquired on 22 patients. Optimal features selected by forward selection are used for the segmentation of prostate lesions by applying fuzzy c-means (FCM) clustering. The images were reviewed by an expert radiologist and manual segmentation performed as the ground truth. RESULTS: Empirical results indicate that fuzzy c-mean classifier can achieve better results in terms of sensitivity, specificity when semi-quantitative features were considered versus wavelet kinetic features for lesion segmentation (Sensitivity of 87.58% and 75.62%, respectively) and (Specificity of 89.85% and 68.89 %, respectively). CONCLUSION: The proposed segmentation algorithm in this work can potentially be implemented for automatic prostate lesion detection in a computer aided diagnosis scheme and combined with morphologic features to increase diagnostic credibility.

Configuration of gamma detectors in a neutron interrogation system for detection of explosives.

This paper investigates the use of a suitable gamma detector array to increase the detectably of explosives in a prompt-gammas neutron activation analysis (PGNAA) system. Monte Carlo simulations (MCNP-4C) were used for analyzing the system. It was found that the system's performance is enhanced by the use of four detectors: three of the are located on the same side as the neutron source and the fourth on the opposite side. Signature-based radiation-scanning, with nine signatures for each detector, is also discussed.

Development and characterization of a novel PRESAGE formulation for radiotherapy applications.

A novel water equivalent formulation of PRESAGE dosimeter more suitable for radiotherapy applications has been introduced and its radiological water equivalency has been investigated. Furthermore, its radiological properties have been compared with an existing PRESAGE formulation over an energy range from 10 to 20 MeV. Monte Carlo simulation method has been implemented to determine and compare depth dose profiles in both of the PRESAGE formulations at two different photon energies (140 KV(P) and 6 MV). The results show that our proposed PRESAGE formulation is more water equivalent than its known formulation especially for low photon energy beams.

A basic dosimetric study of PRESAGE: the effect of different amounts of fabricating components on the sensitivity and stability of the dosimeter.

Over the past few years there has been much interest in the development of three-dimensional dosimeters to determine the complex absorbed dose distribution in modern radiotherapy techniques such as IMRT and IGRT. In routine methods used for three-dimensional dosimetry, polymer gels are commonly used. Recently, a novel transparent polymer dosimeter, known as PRESAGE, has been introduced in which a radiochromic color change is observed upon radiation. PRESAGE has some advantages over usual polymer gel dosimeters. It has been noted that the sensitivity of PRESAGE can be changed when different amounts of the components are used for its fabrication. This study has focused on the assessment of dosimetric characteristics of PRESAGE for various amounts of components in its formulation. To achieve this, PRESAGE dosimeters were fabricated using various amounts of their constituting components. Then the dosimeters were irradiated to (60)Co gamma photons for a range of radiation doses from 0 to 50 Gy. Consequently, the light absorption changes of the dosimeters were measured by a spectrophotometer at different post-irradiation time periods. It was generally observed that as the concentration of the radical initiator is increased, the PRESAGE dosimeter sensitivity is increased while its stability is decreased. Furthermore, it was noted that with the high concentration of the radical initiator and leuco dye, the sensitivity of PRESAGE is decreased.