Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study
PurposeAccurate segmentation of gross target volume (GTV) from computed tomography (CT) images is a prerequisite in radiotherapy for nasopharyngeal carcinoma (NPC). However, this task is very challenging due to the low contrast at the boundary of the tumor and the great variety of sizes and morpholo...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.827991/full |
| _version_ | 1811335207681261568 |
|---|---|
| author | Geng Yang Geng Yang Geng Yang Zhenhui Dai Yiwen Zhang Yiwen Zhang Lin Zhu Junwen Tan Zefeiyun Chen Zefeiyun Chen Bailin Zhang Chunya Cai Qiang He Fei Li Xuetao Wang Wei Yang Wei Yang |
| author_facet | Geng Yang Geng Yang Geng Yang Zhenhui Dai Yiwen Zhang Yiwen Zhang Lin Zhu Junwen Tan Zefeiyun Chen Zefeiyun Chen Bailin Zhang Chunya Cai Qiang He Fei Li Xuetao Wang Wei Yang Wei Yang |
| author_sort | Geng Yang |
| collection | DOAJ |
| description | PurposeAccurate segmentation of gross target volume (GTV) from computed tomography (CT) images is a prerequisite in radiotherapy for nasopharyngeal carcinoma (NPC). However, this task is very challenging due to the low contrast at the boundary of the tumor and the great variety of sizes and morphologies of tumors between different stages. Meanwhile, the data source also seriously affect the results of segmentation. In this paper, we propose a novel three-dimensional (3D) automatic segmentation algorithm that adopts cascaded multiscale local enhancement of convolutional neural networks (CNNs) and conduct experiments on multi-institutional datasets to address the above problems.Materials and MethodsIn this study, we retrospectively collected CT images of 257 NPC patients to test the performance of the proposed automatic segmentation model, and conducted experiments on two additional multi-institutional datasets. Our novel segmentation framework consists of three parts. First, the segmentation framework is based on a 3D Res-UNet backbone model that has excellent segmentation performance. Then, we adopt a multiscale dilated convolution block to enhance the receptive field and focus on the target area and boundary for segmentation improvement. Finally, a central localization cascade model for local enhancement is designed to concentrate on the GTV region for fine segmentation to improve the robustness. The Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average symmetric surface distance (ASSD) and 95% Hausdorff distance (HD95) are utilized as qualitative evaluation criteria to estimate the performance of our automated segmentation algorithm.ResultsThe experimental results show that compared with other state-of-the-art methods, our modified version 3D Res-UNet backbone has excellent performance and achieves the best results in terms of the quantitative metrics DSC, PPR, ASSD and HD95, which reached 74.49 ± 7.81%, 79.97 ± 13.90%, 1.49 ± 0.65 mm and 5.06 ± 3.30 mm, respectively. It should be noted that the receptive field enhancement mechanism and cascade architecture can have a great impact on the stable output of automatic segmentation results with high accuracy, which is critical for an algorithm. The final DSC, SEN, ASSD and HD95 values can be increased to 76.23 ± 6.45%, 79.14 ± 12.48%, 1.39 ± 5.44mm, 4.72 ± 3.04mm. In addition, the outcomes of multi-institution experiments demonstrate that our model is robust and generalizable and can achieve good performance through transfer learning.ConclusionsThe proposed algorithm could accurately segment NPC in CT images from multi-institutional datasets and thereby may improve and facilitate clinical applications. |
| first_indexed | 2024-04-13T17:20:43Z |
| format | Article |
| id | doaj.art-bb5e0a45c5734ef18e29aecda801e401 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-13T17:20:43Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-bb5e0a45c5734ef18e29aecda801e4012022-12-22T02:37:59ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-03-011210.3389/fonc.2022.827991827991Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset StudyGeng Yang0Geng Yang1Geng Yang2Zhenhui Dai3Yiwen Zhang4Yiwen Zhang5Lin Zhu6Junwen Tan7Zefeiyun Chen8Zefeiyun Chen9Bailin Zhang10Chunya Cai11Qiang He12Fei Li13Xuetao Wang14Wei Yang15Wei Yang16School of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaDepartment of Oncology, The Fourth Affiliated Hospital of Guangxi Medical University, Liuzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaDepartment of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaPurposeAccurate segmentation of gross target volume (GTV) from computed tomography (CT) images is a prerequisite in radiotherapy for nasopharyngeal carcinoma (NPC). However, this task is very challenging due to the low contrast at the boundary of the tumor and the great variety of sizes and morphologies of tumors between different stages. Meanwhile, the data source also seriously affect the results of segmentation. In this paper, we propose a novel three-dimensional (3D) automatic segmentation algorithm that adopts cascaded multiscale local enhancement of convolutional neural networks (CNNs) and conduct experiments on multi-institutional datasets to address the above problems.Materials and MethodsIn this study, we retrospectively collected CT images of 257 NPC patients to test the performance of the proposed automatic segmentation model, and conducted experiments on two additional multi-institutional datasets. Our novel segmentation framework consists of three parts. First, the segmentation framework is based on a 3D Res-UNet backbone model that has excellent segmentation performance. Then, we adopt a multiscale dilated convolution block to enhance the receptive field and focus on the target area and boundary for segmentation improvement. Finally, a central localization cascade model for local enhancement is designed to concentrate on the GTV region for fine segmentation to improve the robustness. The Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average symmetric surface distance (ASSD) and 95% Hausdorff distance (HD95) are utilized as qualitative evaluation criteria to estimate the performance of our automated segmentation algorithm.ResultsThe experimental results show that compared with other state-of-the-art methods, our modified version 3D Res-UNet backbone has excellent performance and achieves the best results in terms of the quantitative metrics DSC, PPR, ASSD and HD95, which reached 74.49 ± 7.81%, 79.97 ± 13.90%, 1.49 ± 0.65 mm and 5.06 ± 3.30 mm, respectively. It should be noted that the receptive field enhancement mechanism and cascade architecture can have a great impact on the stable output of automatic segmentation results with high accuracy, which is critical for an algorithm. The final DSC, SEN, ASSD and HD95 values can be increased to 76.23 ± 6.45%, 79.14 ± 12.48%, 1.39 ± 5.44mm, 4.72 ± 3.04mm. In addition, the outcomes of multi-institution experiments demonstrate that our model is robust and generalizable and can achieve good performance through transfer learning.ConclusionsThe proposed algorithm could accurately segment NPC in CT images from multi-institutional datasets and thereby may improve and facilitate clinical applications.https://www.frontiersin.org/articles/10.3389/fonc.2022.827991/fullnasopharyngeal carcinomasegmentationdeep learningradiotherapyCT images |
| spellingShingle | Geng Yang Geng Yang Geng Yang Zhenhui Dai Yiwen Zhang Yiwen Zhang Lin Zhu Junwen Tan Zefeiyun Chen Zefeiyun Chen Bailin Zhang Chunya Cai Qiang He Fei Li Xuetao Wang Wei Yang Wei Yang Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study Frontiers in Oncology nasopharyngeal carcinoma segmentation deep learning radiotherapy CT images |
| title | Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study |
| title_full | Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study |
| title_fullStr | Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study |
| title_full_unstemmed | Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study |
| title_short | Multiscale Local Enhancement Deep Convolutional Networks for the Automated 3D Segmentation of Gross Tumor Volumes in Nasopharyngeal Carcinoma: A Multi-Institutional Dataset Study |
| title_sort | multiscale local enhancement deep convolutional networks for the automated 3d segmentation of gross tumor volumes in nasopharyngeal carcinoma a multi institutional dataset study |
| topic | nasopharyngeal carcinoma segmentation deep learning radiotherapy CT images |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.827991/full |
| work_keys_str_mv | AT gengyang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT gengyang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT gengyang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT zhenhuidai multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT yiwenzhang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT yiwenzhang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT linzhu multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT junwentan multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT zefeiyunchen multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT zefeiyunchen multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT bailinzhang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT chunyacai multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT qianghe multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT feili multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT xuetaowang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT weiyang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy AT weiyang multiscalelocalenhancementdeepconvolutionalnetworksfortheautomated3dsegmentationofgrosstumorvolumesinnasopharyngealcarcinomaamultiinstitutionaldatasetstudy |