Cancer lungs detection on CT scan image using artificial neural network backpropagation based gray level coocurrence matrices feature

Anifah, Lilik; Haryanto, Haryanto; Harimurti, Rina; Permatasari, Zaimah; Rusimamto, Puput Wanarti; Muhamad, Adam Ridiantho

doi:10.1109/icacsis.2017.8355054

Cited by 22 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penelitian yang dilakukan adalah deteksi kangker paru berdasarkan sampel jaringan atau biopsi paru yang di ekstraksi dengan pendekatan GLCM dan mendapatkan nilai akurasi data uji sebesar 81,25% [8]. Pendeteksian kangker paru berdasarkan citra Computed tomography (CT) dengan nilai akurasi 80% [9]. Deteksi penyakit Tuberculosis (TB) berdasarkan chest X-Ray dengan menggunakan 34 data latih dan 30 data uji.…”

Section: Abstrakunclassified

Identifikasi Penderita COVID-19 Berdasarkan Chest X-Ray Menggunakan Algoritma Jaringan Syaraf Tiruan Backpropagation

Putra

Yuhandri

2021

JSisfotek

View full text Add to dashboard Cite

Corona Virus Disease 2019 (COVID-19) is an infectious respiratory disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV2). This disease first appeared in Wuhan, China and spread throughout the world. COVID-19 has had a major impact on public health around the world. On March 9, 2020, the World Health Organization (WHO) declared COVID-19 a pandemic. Early identification of people with COVID-19 can help limit the wider spread. One of the factors behind the rapid spread of the disease is the long clinical trial time. Rapid clinical testing is a challenge facing the spread of COVID-19. Most countries, including Indonesia, face the problem of lack of detection equipment and experts in diagnosing this disease. Chest X-Ray is one of the medical imaging techniques and also an alternative to identify the symptoms of pneumonia caused by COVID-19. This study aims to identify pneumonia caused by COVID-19 and other diseases based on Chest X-Ray. 107 Chest X-Ray images used as material for this study were obtained from the General Hospital of Ibnu Sina Padang Indonesia, which consisted of 27 images of pneumonia caused by COVID-19, 51 images with other diseases and 29 images of normal lungs. Then pre-processing is carried out as an initial stage and then feature extraction is carried out. Furthermore, the learning and identification process is carried out using the Backpropagation Artificial Neural Network (ANN) algorithm. In this study, 92 images were used as training data, and 15 images were used as test data. The results of calculations carried out using a network with a pattern of 16-100-100-100-2 obtained an accuracy value of 73%. The results of the identification prediction can be used as consideration in establishing a diagnosis of COVID-19 sufferers, but cannot be used as an absolute reference.

show abstract

Section: Abstrakunclassified

Identifikasi Penderita COVID-19 Berdasarkan Chest X-Ray Menggunakan Algoritma Jaringan Syaraf Tiruan Backpropagation

Putra

Yuhandri

2021

JSisfotek

View full text Add to dashboard Cite

show abstract

“…Linlin [22] propose 3D indoor localization by implementing BPNN. Lilik [23] and Dimililer [24] used it to detect the lung cancer on CT scan images. Comparison of workload prediction model for cloud computing by Kumar et al [6], privacypreserving using modified BPNN for cloud computing by Yuan et al [25], and a system in order to detect the sub-pixel land change for remotely sensed images by Wu et al [26] proposed using BPNN.…”

Section: Hidden Neuron Usage In the Literaturementioning

confidence: 99%

Review and analysis of hidden neuron number effect of shallow backpropagation neural networks

Şekeroğlu¹,

Dimililer²

2020

NNW

View full text Add to dashboard Cite

Shallow neural network implementations are still popular for real-life classification problems that require rapid achievements with limited data. Parameters selection such as hidden neuron number, learning rate and momentum factor of neural networks are the main challenges that causes time loss during these implementations. In these parameters, the determination of hidden neuron numbers is the main drawback that affects both training and generalization phases of any neural system for learning efficiency and system accuracy. In this study, several experiments are performed in order to observe the effect of hidden neuron number of 3-layered backpropagation neural network on the generalization rate of classification problems using both numerical datasets and image databases. Experiments are performed by considering the increasing number of total processing elements, and various numbers of hidden neurons are used during the training. The results of each hidden neuron number are analyzed according to the accuracy rates and iteration numbers during the convergence. Results show that the effect of the hidden neuron numbers mainly depends on the number of training patterns. Also obtained results suggest intervals of hidden neuron numbers for different number of total processing elements and training patterns.

show abstract

“…In yet another work [6] the focusis to extract the lung region and the desired features using grey level co-occurrence matrix (GLCM). The drawback of this work is that a classifier has not been employed to classify the given images.In another related work [7] a model is developed using ANN algorithm with back propagation for training the developed model. This work employs several processing steps to enhance the image.…”

Section: Previous Workmentioning

confidence: 99%

Lung cancer detection with prediction employing machine learning algorithms

2020

IJATCSE

View full text Add to dashboard Cite

Lung cancer-related deaths are increasing globally every year. The prediction of the onset of cancer in patients can help doctors in the process of decision making regarding their medications and treatments. This paper proposed a novel system which is capable of detecting and predicting the presence of cancerous nodules in the patient's lungs. The proposed system employs machine learning algorithms like support vector machine (SVM) and deep learning algorithm like convolutional neural network (CNN), to perform the classification, using an extensive lung cancer repository database namely, the UCI repository. In the first stage of cleaning of images, they are pre-processed and further post-processed. The pre-processing step includes RGB to grey scale conversion and further removal of noise is achieved by using Non-Local Means (NLM) filter. In the second stage of development image segmentation has been realized using Otsu's algorithm and feature extraction has been realized with the help of Grey Level Co-occurrence Matrix (GLCM). Finally, lung cancerous images are classified using the two classifiers and the accuracy of their classifications are being compared and tabulated. .

show abstract

Cancer lungs detection on CT scan image using artificial neural network backpropagation based gray level coocurrence matrices feature

Cited by 22 publications

References 3 publications

Identifikasi Penderita COVID-19 Berdasarkan Chest X-Ray Menggunakan Algoritma Jaringan Syaraf Tiruan Backpropagation

Identifikasi Penderita COVID-19 Berdasarkan Chest X-Ray Menggunakan Algoritma Jaringan Syaraf Tiruan Backpropagation

Review and analysis of hidden neuron number effect of shallow backpropagation neural networks

Lung cancer detection with prediction employing machine learning algorithms

Contact Info

Product

Resources

About