Automated hemangioma detection using Otsu based binarized Kaze features
- PDF / 3,273,512 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 62 Downloads / 203 Views
Automated hemangioma detection using Otsu based binarized Kaze features Uğurhan Kutbay 1 Received: 3 September 2019 / Revised: 25 May 2020 / Accepted: 4 June 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
This study aims to detect liver hemangioma on CT images by using hybrid image processing methods as well as binarized histogram of gradients based Kaze feature extraction. Using hybrid strategies, automatic hemangioma detector design is the state of art of this study. Our study helps doctors to detect the solid liver masses. Proposed algorithm includes detection of hemangioma using Otsu auto-threshold based Histogram of Gradients (HOG) and Kaze feature extraction implementation. 48 liver CT images, 28 of which are hemangiomas and 20 of which are healthy liver images, are used as the dataset. CT images are obtained by the Department of the Radiology at Fırat University. Presented work was implemented to 48-CT images and 91,66% accuracy was achieved for different shaped and sized hemangiomas. These results show that the developed algorithm could ease the process of detecting liver masses for radiologist and doctors could evaluate their findings easily. Keywords Hemangioma . CT . Otsu . Histogram of gradients . Kaze features . Diagnosis system . Biomedical image processing
1 Introduction Being the largest internal organ, liver is also a vital organ since it performs the production of bile and provides clearing of toxins, processing proteins and fats. According to the American Cancer Society, hemangioma is the fifth most common type of tumor among women and the 8th most common in men [27]. Hemangiomas are the most common benign mesenchymal tumors of the liver, with a prevalence range of 3–20% [4]. US [7, 14], MRI [18, 33], CT [15, 23, 29] etc. are generally used for liver lesion detection in radiological imaging. The most common symptoms of hemangioma are pain in the right upper quadrant, nausea, vomiting and feeling of early saturation [11]. In addition to these symptoms; infarction,
* Uğurhan Kutbay [email protected]
1
Department of Electrical and Electronic Engineering, Gazi University, Ankara, Turkey
Multimedia Tools and Applications
hemorrhage, torsion can be observed secondary [30]. Although hemangioma is a benign tumor, it is important to determine the risk of the rupture and Kasabach-Merritt [19] syndrome. Because of these medical risks, computer-aided systems are important in the decisionmaking mechanism. Computer-aided diagnosis (CAD) systems make it easier for doctors to decide on the diagnosis. From this point of view, this study was designed to provide radiologists for the determination of liver hemangioma. There have been numerous studies about CAD systems in recent years [2, 16, 31]. Although histopathological evaluation is the gold standard, it is an invasive and risky process [25]. Radiological based imaging provides noninvasive and non-ionizing diagnosis. Artifacts that consisted of the imaging system, is a challenge for radiologists. Overcoming this pro
Data Loading...
