A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning
The segmentation of pulmonary lobes is important in clinical assessment, lesion location, and surgical planning. Automatic lobe segmentation is challenging, mainly due to the incomplete fissures or the morphological variation resulting from lung disease. In this work, we propose a learning-based app...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/21/8560 |
| _version_ | 1797466431414075392 |
|---|---|
| author | Mengfan Xue Lu Han Yiran Song Fan Rao Dongliang Peng |
| author_facet | Mengfan Xue Lu Han Yiran Song Fan Rao Dongliang Peng |
| author_sort | Mengfan Xue |
| collection | DOAJ |
| description | The segmentation of pulmonary lobes is important in clinical assessment, lesion location, and surgical planning. Automatic lobe segmentation is challenging, mainly due to the incomplete fissures or the morphological variation resulting from lung disease. In this work, we propose a learning-based approach that incorporates information from the local fissures, the whole lung, and priori pulmonary anatomy knowledge to separate the lobes robustly and accurately. The prior pulmonary atlas is registered to the test CT images with the aid of the detected fissures. The result of the lobe segmentation is obtained by mapping the deformation function on the lobes-annotated atlas. The proposed method is evaluated in a custom dataset with COPD. Twenty-four CT scans randomly selected from the custom dataset were segmented manually and are available to the public. The experiments showed that the average dice coefficients were 0.95, 0.90, 0.97, 0.97, and 0.97, respectively, for the right upper, right middle, right lower, left upper, and left lower lobes. Moreover, the comparison of the performance with a former learning-based segmentation approach suggests that the presented method could achieve comparable segmentation accuracy and behave more robustly in cases with morphological specificity. |
| first_indexed | 2024-03-09T18:38:48Z |
| format | Article |
| id | doaj.art-121ce186d8f1431e94820c550a60e4fe |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:38:48Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-121ce186d8f1431e94820c550a60e4fe2023-11-24T06:49:59ZengMDPI AGSensors1424-82202022-11-012221856010.3390/s22218560A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep LearningMengfan Xue0Lu Han1Yiran Song2Fan Rao3Dongliang Peng4School of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaPhilips Healthcare, Shanghai 200072, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaResearch Center for Healthcare Data Science, Zhejiang Lab, Hangzhou 311121, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaThe segmentation of pulmonary lobes is important in clinical assessment, lesion location, and surgical planning. Automatic lobe segmentation is challenging, mainly due to the incomplete fissures or the morphological variation resulting from lung disease. In this work, we propose a learning-based approach that incorporates information from the local fissures, the whole lung, and priori pulmonary anatomy knowledge to separate the lobes robustly and accurately. The prior pulmonary atlas is registered to the test CT images with the aid of the detected fissures. The result of the lobe segmentation is obtained by mapping the deformation function on the lobes-annotated atlas. The proposed method is evaluated in a custom dataset with COPD. Twenty-four CT scans randomly selected from the custom dataset were segmented manually and are available to the public. The experiments showed that the average dice coefficients were 0.95, 0.90, 0.97, 0.97, and 0.97, respectively, for the right upper, right middle, right lower, left upper, and left lower lobes. Moreover, the comparison of the performance with a former learning-based segmentation approach suggests that the presented method could achieve comparable segmentation accuracy and behave more robustly in cases with morphological specificity.https://www.mdpi.com/1424-8220/22/21/8560medical imagingimage processingsegmentation |
| spellingShingle | Mengfan Xue Lu Han Yiran Song Fan Rao Dongliang Peng A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning Sensors medical imaging image processing segmentation |
| title | A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning |
| title_full | A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning |
| title_fullStr | A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning |
| title_full_unstemmed | A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning |
| title_short | A Fissure-Aided Registration Approach for Automatic Pulmonary Lobe Segmentation Using Deep Learning |
| title_sort | fissure aided registration approach for automatic pulmonary lobe segmentation using deep learning |
| topic | medical imaging image processing segmentation |
| url | https://www.mdpi.com/1424-8220/22/21/8560 |
| work_keys_str_mv | AT mengfanxue afissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT luhan afissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT yiransong afissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT fanrao afissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT dongliangpeng afissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT mengfanxue fissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT luhan fissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT yiransong fissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT fanrao fissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning AT dongliangpeng fissureaidedregistrationapproachforautomaticpulmonarylobesegmentationusingdeeplearning |