Liver tumor segmentation in CT volumes using an adversarial densely connected network
Abstract Background Malignant liver tumor is one of the main causes of human death. In order to help physician better diagnose and make personalized treatment schemes, in clinical practice, it is often necessary to segment and visualize the liver tumor from abdominal computed tomography images. Due...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-019-3069-x |
| _version_ | 1818384735212142592 |
|---|---|
| author | Lei Chen Hong Song Chi Wang Yutao Cui Jian Yang Xiaohua Hu Le Zhang |
| author_facet | Lei Chen Hong Song Chi Wang Yutao Cui Jian Yang Xiaohua Hu Le Zhang |
| author_sort | Lei Chen |
| collection | DOAJ |
| description | Abstract Background Malignant liver tumor is one of the main causes of human death. In order to help physician better diagnose and make personalized treatment schemes, in clinical practice, it is often necessary to segment and visualize the liver tumor from abdominal computed tomography images. Due to the large number of slices in computed tomography sequence, developing an automatic and reliable segmentation method is very favored by physicians. However, because of the noise existed in the scan sequence and the similar pixel intensity of liver tumors with their surrounding tissues, besides, the size, position and shape of tumors also vary from one patient to another, automatic liver tumor segmentation is still a difficult task. Results We perform the proposed algorithm to the Liver Tumor Segmentation Challenge dataset and evaluate the segmentation results. Experimental results reveal that the proposed method achieved an average Dice score of 68.4% for tumor segmentation by using the designed network, and ASD, MSD, VOE and RVD improved from 27.8 to 21, 147 to 124, 0.52 to 0.46 and 0.69 to 0.73, respectively after performing adversarial training strategy, which proved the effectiveness of the proposed method. Conclusions The testing results show that the proposed method achieves improved performance, which corroborated the adversarial training based strategy can achieve more accurate and robustness results on liver tumor segmentation task. |
| first_indexed | 2024-12-14T03:26:59Z |
| format | Article |
| id | doaj.art-72cd1958e630452ca5b131a13a6f97bc |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-14T03:26:59Z |
| publishDate | 2019-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-72cd1958e630452ca5b131a13a6f97bc2022-12-21T23:18:51ZengBMCBMC Bioinformatics1471-21052019-12-0120S1611310.1186/s12859-019-3069-xLiver tumor segmentation in CT volumes using an adversarial densely connected networkLei Chen0Hong Song1Chi Wang2Yutao Cui3Jian Yang4Xiaohua Hu5Le Zhang6School of Computer Science & Technology, Beijing Institute of TechnologySchool of Computer Science & Technology, Beijing Institute of TechnologySchool of Computer Science & Technology, Beijing Institute of TechnologySchool of Computer Science & Technology, Beijing Institute of TechnologySchool of Optics and Electronics & Technology, Beijing Institute of TechnologyCollege of Computing & Informatics, Drexel UniversityCollege of Computer Science, Sichuan UniversityAbstract Background Malignant liver tumor is one of the main causes of human death. In order to help physician better diagnose and make personalized treatment schemes, in clinical practice, it is often necessary to segment and visualize the liver tumor from abdominal computed tomography images. Due to the large number of slices in computed tomography sequence, developing an automatic and reliable segmentation method is very favored by physicians. However, because of the noise existed in the scan sequence and the similar pixel intensity of liver tumors with their surrounding tissues, besides, the size, position and shape of tumors also vary from one patient to another, automatic liver tumor segmentation is still a difficult task. Results We perform the proposed algorithm to the Liver Tumor Segmentation Challenge dataset and evaluate the segmentation results. Experimental results reveal that the proposed method achieved an average Dice score of 68.4% for tumor segmentation by using the designed network, and ASD, MSD, VOE and RVD improved from 27.8 to 21, 147 to 124, 0.52 to 0.46 and 0.69 to 0.73, respectively after performing adversarial training strategy, which proved the effectiveness of the proposed method. Conclusions The testing results show that the proposed method achieves improved performance, which corroborated the adversarial training based strategy can achieve more accurate and robustness results on liver tumor segmentation task.https://doi.org/10.1186/s12859-019-3069-xFully convolutional neural networkCTLiver segmentationLiver tumor segmentation |
| spellingShingle | Lei Chen Hong Song Chi Wang Yutao Cui Jian Yang Xiaohua Hu Le Zhang Liver tumor segmentation in CT volumes using an adversarial densely connected network BMC Bioinformatics Fully convolutional neural network CT Liver segmentation Liver tumor segmentation |
| title | Liver tumor segmentation in CT volumes using an adversarial densely connected network |
| title_full | Liver tumor segmentation in CT volumes using an adversarial densely connected network |
| title_fullStr | Liver tumor segmentation in CT volumes using an adversarial densely connected network |
| title_full_unstemmed | Liver tumor segmentation in CT volumes using an adversarial densely connected network |
| title_short | Liver tumor segmentation in CT volumes using an adversarial densely connected network |
| title_sort | liver tumor segmentation in ct volumes using an adversarial densely connected network |
| topic | Fully convolutional neural network CT Liver segmentation Liver tumor segmentation |
| url | https://doi.org/10.1186/s12859-019-3069-x |
| work_keys_str_mv | AT leichen livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork AT hongsong livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork AT chiwang livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork AT yutaocui livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork AT jianyang livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork AT xiaohuahu livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork AT lezhang livertumorsegmentationinctvolumesusinganadversarialdenselyconnectednetwork |