2021/01/04 by Niloofar Akhavan Javan, Javan, Niloofar Akhavan, Ali Jebreili +7
Computer Science · Medicine · #Radiomics and Machine Learning in Medical Imaging #cs.CV
paper · pdf · doi:10.48550/arxiv.2101.00948
arxiv created 2022/04/05 · arxiv updated 2022/04/06
Given that lung cancer is one of the deadliest illnesses, early identification and diagnosis are critical to preserving a patient's life. However, lung illness diagnosis is time-intensive and requires the expertise of a pulmonary disease specialist, subject to a significant rate of inaccuracy. Our objective is to design a system capable of accurately detecting and classifying lung lesions and segmenting them in CT-scan images. The suggested technique extracts features automatically from the CT-scan image and then classifies them using Ensemble Gradient Boosting methods. Finally, if a lesion is detected in the CT-scan image, it is segmented using a hybrid approach based on Fuzzy Clustering and Level Set. To train and test our models we gathered a dataset that included CT images of patients residing in Mashhad, Iran. Finally, the results indicate 96% accuracy within this dataset. This approach may assist clinicians in diagnosing lung abnormalities and avoiding potential errors.