scholarly journals Image processing based detection of lung cancer on CT scan images

2017 ◽  
Vol 893 ◽  
pp. 012063 ◽  
Author(s):  
Bariqi Abdillah ◽  
Alhadi Bustamam ◽  
Devvi Sarwinda
Keyword(s):  
Author(s):  
Mohd Firdaus Abdullah ◽  
Siti Noraini Sulaiman ◽  
Muhammad Khusairi Osman ◽  
Noor Khairiah A. Karim ◽  
Ibrahim Lutfi Shuaib ◽  
...  

2019 ◽  
Vol 8 (2S11) ◽  
pp. 2695-2699

According to the American Cancer Society, lung cancer is the second most widespread cancer and the leading cause of cancer deaths in both men and women. The death rate of lung cancer every year is greater than that of colon, breast, and prostate cancers combined. CT scan is a non-invasive method for diagnosis of any ailment, and can be used to detect lung cancer as well. The proposed project involves cell detection using image processing techniques. Because the time is a very important factor in cancer treatment, especially in cancers such as the lung, imaging techniques are used to accelerate diagnosis. The image processing paired with data analysis techniques helps us diagnose the particular type of cancer by comparing the output of the CT scan to an available database of images. This improves accuracy and reduces the time required for the diagnosis. Features of the image under test are extracted and analysed, and the decision regarding the morphological characteristics of the image are made. This helps us arrive at a decision regarding the nature of the image.


Author(s):  
Hamdalla Fadil Kareem ◽  
Muayed S AL-Huseiny ◽  
Furat Y. Mohsen ◽  
Enam A. Khalil ◽  
Zainab S. Hassan

<p>This paper concerns the development/analysis of the IQ-OTH/NCCD lung cancer dataset. This CT-scan dataset includes more than 1100 images of diagnosed healthy and tumorous chest scans collected in two Iraqi hospitals. A computer system is proposed for detecting lung cancer in the dataset by using image-processing/computer-vision techniques. This includes three preprocessing stages: image enhancement, image segmentation, and feature extraction techniques. Then, support vector machine (SVM) is used at the final stage as a classification technique for identifying the cases on the slides as one of three classes: normal, benign, or malignant. Different SVM kernels and feature extraction techniques are evaluated. The best accuracy achieved by applying this procedure on the new dataset was 89.8876%.</p>


Sign in / Sign up

Export Citation Format

Share Document