PET-CT image Co-segmentation of lung tumor using joint level set model. (January 2023)

• Record Type: Journal Article
• Authors: Chen, Zhe; Qiu, Nan; Feng, Hui; Dai, Dongfang
• Is Part Of: Computers & electrical engineering. Volume 105(2023)
• Publication Date: 2023-01
• Subjects: Lung tumor segmentation -- Image co-segmentation -- Joint level set -- Positron emission tomography (PET) -- Computed tomography (CT); Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108545
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Accurate lung tumor segmentation plays an important role in radiotherapy and targeted therapy. Positron emission tomography (PET) and computed tomography (CT) scanner imaging provide complementary evidence for lung tumor segmentation. In specific, PET can recognize the tumor tissues, while the tissue boundaries are blurred in such a modality. By contrast, CT has a better resolution but a lower contrast between tumor and normal tissues. It is well known that jointly exploiting the evidence from PET and CT images significantly benefits lung tumor delineation. A novel joint level set model is proposed in this paper to integrate PET and CT evidence in a unified energy form, providing co-segmentation results. The convergence result of our co-segmentation model can find the optimal tradeoff between PET and CT modalities. Different characteristics of these two modalities are comprehensively considered in the adaptive convergence process which starts mostly with the PET evidence to locate tumor tissues and stops mostly with the CT evidence to delineate tissue boundaries. The novelty of our joint level set model lies in its adaptability which stepwise moderates joint weights during the model convergence process. The performance of our proposed model is validated on 20 PET-CT images of the nonsmall cell lung tumor. The excellent performance of our proposed model for PET-CT image co-segmentation of the lung tumor is demonstrated by comparing it to the state-of-art models.