A novel level set model initialized with guided filter for automated PET-CT image segmentation
Positron emission tomography (PET) and computed tomography (CT) scanner image analysis plays an important role in clinical radiotherapy treatment. PET and CT images provide complementary cues for identifying tumor tissues. In specific, PET images can clearly denote the tumor tissue, whereas this sou...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2022-01-01
|
| Series: | Cognitive Robotics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667241322000180 |
| _version_ | 1828067369688236032 |
|---|---|
| author | Shuhua Bai Xiaojian Qiu Rongqun Hu Yunqiang Wu |
| author_facet | Shuhua Bai Xiaojian Qiu Rongqun Hu Yunqiang Wu |
| author_sort | Shuhua Bai |
| collection | DOAJ |
| description | Positron emission tomography (PET) and computed tomography (CT) scanner image analysis plays an important role in clinical radiotherapy treatment. PET and CT images provide complementary cues for identifying tumor tissues. In specific, PET images can clearly denote the tumor tissue, whereas this source suffers from the problem of low spatial resolution. On the contrary, CT images have a high resolution, but they can not recognize the tumor from normal tissues. In this work, we firstly fuse PET and CT images by using the guided filter. Then, a region and edge-based level set model is proposed to segment PET-CT fusion images. At last, a normalization term is designed by combining length, distance and H1 terms with the aim to improve segmentation accuracy. The proposed method was validated in the robust delineation of lung tumor tissues on 20 PET-CT samples. Both qualitative and quantitative results demonstrate significant improvement compared to both the data-independent and deep learning based segmentation methods. |
| first_indexed | 2024-04-10T23:45:41Z |
| format | Article |
| id | doaj.art-3e3ed4b0a4d54e3ab49509f48f051a5b |
| institution | Directory Open Access Journal |
| issn | 2667-2413 |
| language | English |
| last_indexed | 2024-04-10T23:45:41Z |
| publishDate | 2022-01-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Cognitive Robotics |
| spelling | doaj.art-3e3ed4b0a4d54e3ab49509f48f051a5b2023-01-11T04:30:33ZengKeAi Communications Co. Ltd.Cognitive Robotics2667-24132022-01-012193201A novel level set model initialized with guided filter for automated PET-CT image segmentationShuhua Bai0Xiaojian Qiu1Rongqun Hu2Yunqiang Wu3School of Electronics and Information, Nanchang Institute of Technology, Nanchang 330044, China; Center for International Education, Philippine Christian University, Manila 907, Philippine; Corresponding author.Nanchang Hangtian Guangxin Technology Co., LTD, Nanchang 330044, ChinaSchool of Electronics and Information, Nanchang Institute of Technology, Nanchang 330044, ChinaSchool of Electronics and Information, Nanchang Institute of Technology, Nanchang 330044, ChinaPositron emission tomography (PET) and computed tomography (CT) scanner image analysis plays an important role in clinical radiotherapy treatment. PET and CT images provide complementary cues for identifying tumor tissues. In specific, PET images can clearly denote the tumor tissue, whereas this source suffers from the problem of low spatial resolution. On the contrary, CT images have a high resolution, but they can not recognize the tumor from normal tissues. In this work, we firstly fuse PET and CT images by using the guided filter. Then, a region and edge-based level set model is proposed to segment PET-CT fusion images. At last, a normalization term is designed by combining length, distance and H1 terms with the aim to improve segmentation accuracy. The proposed method was validated in the robust delineation of lung tumor tissues on 20 PET-CT samples. Both qualitative and quantitative results demonstrate significant improvement compared to both the data-independent and deep learning based segmentation methods.http://www.sciencedirect.com/science/article/pii/S2667241322000180PET-CT imageLevel setGuided filterImage segmentation |
| spellingShingle | Shuhua Bai Xiaojian Qiu Rongqun Hu Yunqiang Wu A novel level set model initialized with guided filter for automated PET-CT image segmentation Cognitive Robotics PET-CT image Level set Guided filter Image segmentation |
| title | A novel level set model initialized with guided filter for automated PET-CT image segmentation |
| title_full | A novel level set model initialized with guided filter for automated PET-CT image segmentation |
| title_fullStr | A novel level set model initialized with guided filter for automated PET-CT image segmentation |
| title_full_unstemmed | A novel level set model initialized with guided filter for automated PET-CT image segmentation |
| title_short | A novel level set model initialized with guided filter for automated PET-CT image segmentation |
| title_sort | novel level set model initialized with guided filter for automated pet ct image segmentation |
| topic | PET-CT image Level set Guided filter Image segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2667241322000180 |
| work_keys_str_mv | AT shuhuabai anovellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT xiaojianqiu anovellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT rongqunhu anovellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT yunqiangwu anovellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT shuhuabai novellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT xiaojianqiu novellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT rongqunhu novellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation AT yunqiangwu novellevelsetmodelinitializedwithguidedfilterforautomatedpetctimagesegmentation |