Search

Background and Objectives Prostate cancer is the most common type of malignant cancer among men and is known as one of the leading causes of cancer mortality in men. The difficulty of diagnostic procedures such as tumor biopsy has made new diagnostic methods, such as magnetic resonance imaging (MRI), to be one of the research priorities for prostate cancer in recent years. The aim of this study is to develop an automated system capable of accurately diagnosing prostate cancer from MRI images. Subjects and Methods In this applied descriptive study, a four-step method was used for diagnosing prostate cancer with MRI technique. In the first step, the effect of noise was reduced by using the discrete two-dimensional wavelet transform and histogram equalization. In the second step, the blackhole optimization algorithm was used for the segmentation of the input image based on the multilevel threshold technique. In this way, the tumor suspicious areas can be identified on the image. In the third step, the features of each target area were extracted. In the final step, a combination of three machine learning algorithms, including artificial neural network, decision tree, and support vector machine, was used to diagnose prostate cancer. The effectiveness of the proposed method was evaluated from various aspects and its performance was compared with other machine learning models. Results The proposed method had an accuracy of 99%, sensitivity of 0.98, precision and specificity of 1 in diagnosing prostate cancer with MRI method. Conclusion The proposed ensemble method using a combination of image processing, optimization, and machine learning techniques, has higher accuracy compared to other machine learning models. [ABSTRACT FROM AUTHOR]

Background and Objectives Most digital imaging systems offer a variety of image processing techniques. Due to the importance of the accuracy of these images and their widespread application, this study aims to evaluate the detection of vertical root fracture (VRF) in indirect digital images by changing their gamma values. Subjects and Methods In this study, 23 extracted teeth were prepared as samples from dental clinics in Ahvaz, Iran. The radiographs were obtained from the samples before and after VRF induction. After root canal preparation, a very thin disc was used to divide the teeth into two halves in the buccal-lingual direction to create a VRF. The two halves were re-attached to each other and mounted in in molds filled with a mixture of plaster and sawdust. After processing the images by adjusting their gamma values using low, medium and high settings, the images were viewed by two radiologists for the presence or absence of VRF. Results In all three modes of gamma adjustment, the sensitivity, specificity and overall accuracy of images were high and there was no significant difference between the three modes. Conclusion The high gamma for digital images can used to as a filter to detect VRF. The images with medium and low gamma values are less helpful for detecting VRF. [ABSTRACT FROM AUTHOR]

Background and Objectives The digital radiography offers a variety of image processing techniques. Due to the importance of the accuracy of this method and its widespread applications, in this study we aim to investigate the diagnose of vertical root fracture (VRF) by conventional digital radiography with and without unsharp masking (UM) filter. Subjects and Methods Radiographs were taken from 24 extracted anterior teeth before and after VRF induction. The root canal was prepared with passive step-back technique, and then the teeth were divided into two halves buccolingually with a very thin disk. The two halves were re-attached to each other and mounted in a mixture of gypsum and sawdust. After processing by the UM filter, the radiographs were evaluated by two observers to detect the presence or absence of VRF. Results For the first observer, the sensitivity of both methods was the same, while the specificity of the UM filtering mode was higher. For the second observer, the sensitivity of the unfiltered mode was higher, while the specificity of the two methods was the same. Conclusion There is no significant difference between digital radiography with and without the UM filter in diagnosing VRF. Due to the high sensitivity and specifity of the UM filtering method, the specialist can use this filter based on personal preferences. [ABSTRACT FROM AUTHOR]