International Conference

Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/177

Browse

Now showing 1 - 3 of 3

A METHOD FOR REMOVING PET IMAGING ARTIFACT USING COMBINATION OF STANDARD DEVIATION AND COMPUTATIONAL GEOMETRY TECHNIQUE
(Elsevier – Science Direct, 2019) Sindhu A; Radha V
Positron emission tomography/Computed tomography is a non-intrusive imaging methodology, which is clinically utilized for both finding and getting to treatment reaction in oncology, cardiology, as well as neurology. Many different artifacts can occur during Positron emission tomography (PET) imaging, these artifacts are expected essentially to metallic inserts, respiratory movement, utilization of contrast media also image truncation. Artifacts are relatively common in PET/CT imaging and may potentially degrade image quality and interfere with accurate radiological reporting and diagnosis. Improving the recognition of PET/CT artifacts may assist imaging practitioners to avoid or limit their effect on image quality and interpretation. This paper proposed a statistical method of standard deviation to figure the global threshold for binarizing image and computational geometry to reach the output. This combination would produce good results for removing the artifacts from pancreatic PET/CT images.
A NOVEL HISTOGRAM EQUALIZATION BASED ADAPTIVE CENTER WEIGHTED MEDIAN FILTER FOR DE-NOISING POSITRON EMISSION TOMOGRAPHY(PET) SCAN IMAGES
(IEEE, 2019-05-30) Sindhu A; Radha V
Medical images are most of the time influenced by noise because of errors happened in the way toward decoding signals from analog to- digital, the noisy sensor as well as occurred during the communication process. This corrupted pixel certainly modifies intensity values of remaining noiseless pixels in an input image. In order to eliminate noise and enhance the image quality, this paper proposed a novel technique for pancreatic cancer PET scan image using Histogram Equalization (HE) based Adaptive Center Weighted Median filter (ACWM). The technique is checked against medical image noise and compared with existing methods. Results are compared using Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and Mean Square Error (MSE) for assessing the quality of denoised images. It is observed that the HE/ACWM is a magnificent method for preserving detail smoothly that can suppress image noise without destroying fine details.
PANCREATIC TUMOR SEGMENTATION IN RECENT MEDICAL IMAGING – AN OVERVIEW
(“Advances in Intelligent Systems and computing” 2194-5357 @ Springer Nature Switzerland AG 2020 S. pp.514 -522, 2020-01-07) Sindhu A; Radha V
Pancreatic tumor is one of the deadliest diseases, which is the fourth leading cause of cancer death worldwide. Detecting pancreatic cancer at an early stage may increase the life of the patients. Pancreatic tumor segmentation is one of the difficult challenges in medical field. Accurate and Efficient segmentation in medical images are emerging as a challenging task during radiotherapy planning. Various medical modalities like MRI, CT and PET are widely used for diagnosing the abnormalities present in the medical images. Image segmentation plays an important part for the exact detection of the tumor in diagnosing, detecting, treatment and planning. In this review paper, various algorithms are used for segmenting the pancreatic tumor in medical images were discussed.