ABSTRACT
BACKGROUND AND OBJECTIVES: Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data. METHODS: We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information". RESULTS: We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches. CONCLUSION: AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.
Subject(s)
Non-alcoholic Fatty Liver Disease , Humans , Non-alcoholic Fatty Liver Disease/diagnostic imaging , Non-alcoholic Fatty Liver Disease/pathology , Artificial Intelligence , Liver Cirrhosis , Biomarkers , Ultrasonography , Liver/diagnostic imaging , BiopsyABSTRACT
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.
ABSTRACT
In this paper, a routine algorithm is presented to design a fractional order controller for tracking the reference model. Using this algorithm, a pole placement controller can be designed by assigning the desired integer and fractional order closed loop transfer functions. Considering the desired time response and using the generalized characteristic ratio assignment (CRA) method for fractional order systems and coefficient diagram method (CDM) for integer order systems, the desired closed loop system can be achieved. For various practical experiments, having the desired time responses is vital for magnetic flux in Damavand tokamak. To approach this, at first, the desired reference models are obtained based on CRA and CDM methods. After that, a fractional order pole placement controller is designed and simulated by this algorithm. At last, this controller is implemented on a digital signal processor to control the vertical magnetic flux of Damavand tokamak plant. The practical results show the satisfactory performance of the controller.
ABSTRACT
Psalmocharias alhageos is an important pest of vine in most parts of Iran, Afghanistan, Pakistan, southern areas of Russia, Turkey and Iraq. This cicada is spread in most provinces in Iran such as Esfahan, Hamedan, Qazvin, Markazi, Lorestan, Qom, Kerman, Tehran and Kordestan. In addition to vine, this insect damages some other fruit trees, such as apple, sour cherry, quince, peach, pomegranate and pear trees and some non-fruit trees, namely white poplar, ash, elm, eglantine, silk and black poplar trees. The nymphs of cicada damage the trees by feeding on root, adult insects on young bud and by oviposition under branch barks. Nourishing root by nymph leads to the weakness of the tree and hinder its growth. The high density oviposition of adult insects inside young barks causes withering of branches. The resulted damage on vine products is 40% which is one of the most important factors in product reduction in vineyard. This research was conducted in Takestan in Qazvin. It was conducted for the first time to study the behaviors of the mates of this vine cicada in order to manage it. Two systems were used to record the sound of male cicada called analog voice-recorder and digital voice recorder. To analyze the recorded sound of the male cicada we used of spectrum analyzer, digital storage oscilloscope and protens 7 computer softwares. We could call the attention of natural enemies an disturb the male insect's attracting sound by producing natural and artificial sound in the range of 1-6 kHz in two different ripeness status of the fruits and could prevent mating and oviposition of female cicadas.
