Comparison of lung tumor segmentation methods on PET images

Eset, Kubra; İçer, Semra; Karaçavuş, Seyhan; Yılmaz, Bülent; Kayaalti, Omer; Ayyildiz, Oguzhan; Kaya, Eser

doi:10.1109/tiptekno.2015.7374569

Cited by 4 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most important feature of PET images and their main difference from radiological methods is that they are oriented to show functional and metabolic activity and do not show anatomical details. CT is used in the same imaging device to give anatomical information to PET images and is called PET/CT [5]. Especially in oncology, it is the most advanced medical imaging technique used for tumor detection, staging, evaluation of response to treatment, restaging in the case of metastasis, radiotherapy planning, and in some cases, whether the mass present is benign or malignant.…”

Section: Data Used and Data Preparationmentioning

confidence: 99%

“…Segmentation approaches have been applied after selecting a common/general region of interest (ROI) for all PET image sections transferred to the Matlab program. As a result of each approach, three-dimensional volume information and images were obtained in different patients and sections [5]. In the study of M. Sasikala et al, the region of interest detection algorithms for the www.iiste.org detection of tumors in brain images are presented and compared.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Processing PET/CT Medicine Images and Determining the Object

2021

JSTR

View full text Add to dashboard Cite

Today, as a result of the developments in medical imaging systems, combined Positron Emission Tomography and Computed Tomography (PET/CT) images are used as effective imaging tools in cancer diagnosis and treatment. The study aims to display the tumor in 3D using PET/CT images and to determine the change in tumor size over time. For rapid detection of tumor tissues from numerous PET/CT images is developed software (in Phyton). With the software, tomography images taken at 3 different times 30.05.2017, 23.10.2017 and 08.02.2019 of a patient with hypopharynx cancer are evaluated. The image and real object coordinates of the cancerous region with a radioactive substance in the images are calculated. For 3 different times, variables related to changes in the tumor size of the patient are evaluated in Matlab software and 3D imaging and volume calculations are made. Thus, the temporal variation of the shape, location, and dimensions of the tumor is determined, and whether the patient's response to treatment is positive is observed with image processing and evaluation techniques.

show abstract

Section: Data Used and Data Preparationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Processing PET/CT Medicine Images and Determining the Object

2021

JSTR

View full text Add to dashboard Cite

show abstract

“…In the segmentation, a popular approach called random walk [18] was used to automatically distinguish the tumor from the background. Different segmentation methods like Otsu's, k-means, and active-contour approaches were also tested [19], and the best results were obtained using the random walk approach based on the comparison of the segmentation results and the manual drawings of the nuclear medicine expert in our team. The binning process corresponds to linear mapping of intensity values on the pixels of the segmented tumor region to be between 1 and 64.…”

Section: Image Processing and Texture Analysismentioning

confidence: 99%

Lung cancer subtype differentiation from positron emission tomography images

Ayyildiz¹,

Aydın²,

Yılmaz³

et al. 2020

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

Lung cancer is one of the deadly cancer types, and almost 85% of lung cancers are nonsmall cell lung cancer (NSCLC). In the present study we investigated classification and feature selection methods for the differentiation of two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The major advances in understanding the effects of therapy agents suggest that future targeted therapies will be increasingly subtype specific.We obtained positron emission tomography (PET) images of 93 patients with NSCLC, 39 of which had ADC while the rest had SqCC. Random walk segmentation was applied to delineate three-dimensional tumor volume, and 39 texture features were extracted to grade the tumor subtypes. We examined 11 classifiers with two different feature selection methods and the effect of normalization on accuracy. The classifiers we used were the k-nearest-neighbor, logistic regression, support vector machine, Bayesian network, decision tree, radial basis function network, random forest, AdaBoostM1, and three stacking methods. To evaluate the prediction accuracy we performed a leave-one-out cross-validation experiment on the dataset. We also considered optimizing certain hyperparameters of these models by performing 10-fold cross-validation separately on each training set. We found that the stacking ensemble classifier, which combines a decision tree, AdaBoostM1, and logistic regression methods by a metalearner, was the most accurate method for detecting subtypes of NSCLC, and normalization of feature sets improved the accuracy of the classification method.

show abstract

“…FCM was first proposed by Dunn in 1973. Performs clustering using fuzzy logic [19]. In classical clustering methods, each data must belong to a set and the data must be expressed as data "0" or " 1".…”

Section: E Fuzzy C-meanssmentioning

confidence: 99%

Comparing of K-Means, K-Medodis and Fuzzy C Means Cluster Method for Analog Modulation Recognition

Kaya¹,

Avcı

Gedikpınar

2019

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

A modulation process is required to transmit analog signals with higher quality. Modulation is the process of transporting the signal by another carrier signal. This study aims to process analog signals. Using 200 samples of each of the six types of analog modulation modules. Nowadays these are Amplitude Modulation (AM), Double Side Band (DSB), Upper Side Band (USB), Lower Side Band (LSB), Frequency Modulation (FM) and Phase Modulation(PM) respectively. In the study an intelligent clustering method has been developed. The 5th level Discrete Wavelet Transform (DWT), Norm Entropy and Energy properties of AM, DSB, USB, LSB, FM and PM analog modulated signals have been removed during feature extraction phase. The results have been compared using K-Means, K-medoid and Fuzzy Cmeans (FCM) algorithms using a feature vector of 6x2x1200 obtained at the feature extraction stage and carrying out smart intelligent clustering for recognition. The most successful result has been obtained with FCM of 85.75%.

show abstract

Comparison of lung tumor segmentation methods on PET images

Cited by 4 publications

References 5 publications

Processing PET/CT Medicine Images and Determining the Object

Processing PET/CT Medicine Images and Determining the Object

Lung cancer subtype differentiation from positron emission tomography images

Comparing of K-Means, K-Medodis and Fuzzy C Means Cluster Method for Analog Modulation Recognition

Contact Info

Product

Resources

About