| Summary: | This paper presents a comparative study between 3 segmentation techniques compared against 'the ground truth' obtained from manual segmentation from the oncologist applied for lung cancer detection. Lung cancer is the common cause of death among people throughout the world. Lung cancer detection can be done in several ways, such as Radiography, Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). These methods use a lot of resources in terms of time and money. However, CT has good detection of classification, offers a lower cost, short imaging time and widespread availability. Early diagnosis of lung cancer can help doctors to treat patients in order to reduce number of mortalities. Therefore, the primary aim of this research is to establish an image processing method to segment CT scan images of lung cancer using image segmentation algorithms. The proposed method comprises the following steps which involves using image processing technique: data collection, image segmentation and region growing. Lastly, the performance evaluation was calculated by referring to accuracy, precision, recall and F-score test. Data were collected from the Advance Medical and Dental Institute (AMDI), Universiti Sains Malaysia, Penang. Image segmentation algorithms such as k-means clustering, Otsu's thresholding and watershed segmentation were applied to segment the lung image. Then, region growing was applied to detect the lung area. The segmentation algorithm performance was evaluated by using the above mentioned performance analysis. Based on the analysis, the watershed segmentation had produced better image segmentation performance which was 99.8553% for accuracy, 99.9886% for precision, 98.3919% for recall and F-score test was 99.1499%. © 2019 IEEE.
|
|---|