Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network
Objective:Precise segmentation of human organs and anatomic structures (especially organs at risk, OARs) is the basis and prerequisite for the treatment planning of radiation therapy. In order to ensure rapid and accurate design of radiotherapy treatment planning, an automatic organ segmentation tec...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2022.813135/full |
| _version_ | 1828413679606956032 |
|---|---|
| author | Guosheng Shen Guosheng Shen Guosheng Shen Guosheng Shen Xiaodong Jin Xiaodong Jin Xiaodong Jin Xiaodong Jin Chao Sun Chao Sun Chao Sun Chao Sun Qiang Li Qiang Li Qiang Li Qiang Li |
| author_facet | Guosheng Shen Guosheng Shen Guosheng Shen Guosheng Shen Xiaodong Jin Xiaodong Jin Xiaodong Jin Xiaodong Jin Chao Sun Chao Sun Chao Sun Chao Sun Qiang Li Qiang Li Qiang Li Qiang Li |
| author_sort | Guosheng Shen |
| collection | DOAJ |
| description | Objective:Precise segmentation of human organs and anatomic structures (especially organs at risk, OARs) is the basis and prerequisite for the treatment planning of radiation therapy. In order to ensure rapid and accurate design of radiotherapy treatment planning, an automatic organ segmentation technique was investigated based on deep learning convolutional neural network.MethodA deep learning convolutional neural network (CNN) algorithm called BCDU-Net has been modified and developed further by us. Twenty two thousand CT images and the corresponding organ contours of 17 types delineated manually by experienced physicians from 329 patients were used to train and validate the algorithm. The CT images randomly selected were employed to test the modified BCDU-Net algorithm. The weight parameters of the algorithm model were acquired from the training of the convolutional neural network.ResultThe average Dice similarity coefficient (DSC) of the automatic segmentation and manual segmentation of the human organs of 17 types reached 0.8376, and the best coefficient reached up to 0.9676. It took 1.5–2 s and about 1 h to automatically segment the contours of an organ in an image of the CT dataset for a patient and the 17 organs for the CT dataset with the method developed by us, respectively.ConclusionThe modified deep neural network algorithm could be used to automatically segment human organs of 17 types quickly and accurately. The accuracy and speed of the method meet the requirements of its application in radiotherapy. |
| first_indexed | 2024-12-10T13:13:26Z |
| format | Article |
| id | doaj.art-9fb74a869fb44cda9665aa28828301e0 |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-12-10T13:13:26Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-9fb74a869fb44cda9665aa28828301e02022-12-22T01:47:37ZengFrontiers Media S.A.Frontiers in Public Health2296-25652022-04-011010.3389/fpubh.2022.813135813135Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural NetworkGuosheng Shen0Guosheng Shen1Guosheng Shen2Guosheng Shen3Xiaodong Jin4Xiaodong Jin5Xiaodong Jin6Xiaodong Jin7Chao Sun8Chao Sun9Chao Sun10Chao Sun11Qiang Li12Qiang Li13Qiang Li14Qiang Li15Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, ChinaKey Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Lanzhou, ChinaKey Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaInstitute of Modern Physics, Chinese Academy of Sciences, Lanzhou, ChinaKey Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Lanzhou, ChinaKey Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaInstitute of Modern Physics, Chinese Academy of Sciences, Lanzhou, ChinaKey Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Lanzhou, ChinaKey Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaInstitute of Modern Physics, Chinese Academy of Sciences, Lanzhou, ChinaKey Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Lanzhou, ChinaKey Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaObjective:Precise segmentation of human organs and anatomic structures (especially organs at risk, OARs) is the basis and prerequisite for the treatment planning of radiation therapy. In order to ensure rapid and accurate design of radiotherapy treatment planning, an automatic organ segmentation technique was investigated based on deep learning convolutional neural network.MethodA deep learning convolutional neural network (CNN) algorithm called BCDU-Net has been modified and developed further by us. Twenty two thousand CT images and the corresponding organ contours of 17 types delineated manually by experienced physicians from 329 patients were used to train and validate the algorithm. The CT images randomly selected were employed to test the modified BCDU-Net algorithm. The weight parameters of the algorithm model were acquired from the training of the convolutional neural network.ResultThe average Dice similarity coefficient (DSC) of the automatic segmentation and manual segmentation of the human organs of 17 types reached 0.8376, and the best coefficient reached up to 0.9676. It took 1.5–2 s and about 1 h to automatically segment the contours of an organ in an image of the CT dataset for a patient and the 17 organs for the CT dataset with the method developed by us, respectively.ConclusionThe modified deep neural network algorithm could be used to automatically segment human organs of 17 types quickly and accurately. The accuracy and speed of the method meet the requirements of its application in radiotherapy.https://www.frontiersin.org/articles/10.3389/fpubh.2022.813135/fullconvolutional neural network (CNN)human organsCT imagesautomatic segmentationDice similarity coefficient (DSC) |
| spellingShingle | Guosheng Shen Guosheng Shen Guosheng Shen Guosheng Shen Xiaodong Jin Xiaodong Jin Xiaodong Jin Xiaodong Jin Chao Sun Chao Sun Chao Sun Chao Sun Qiang Li Qiang Li Qiang Li Qiang Li Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network Frontiers in Public Health convolutional neural network (CNN) human organs CT images automatic segmentation Dice similarity coefficient (DSC) |
| title | Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network |
| title_full | Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network |
| title_fullStr | Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network |
| title_full_unstemmed | Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network |
| title_short | Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network |
| title_sort | artificial intelligence radiotherapy planning automatic segmentation of human organs in ct images based on a modified convolutional neural network |
| topic | convolutional neural network (CNN) human organs CT images automatic segmentation Dice similarity coefficient (DSC) |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2022.813135/full |
| work_keys_str_mv | AT guoshengshen artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT guoshengshen artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT guoshengshen artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT guoshengshen artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT xiaodongjin artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT xiaodongjin artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT xiaodongjin artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT xiaodongjin artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT chaosun artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT chaosun artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT chaosun artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT chaosun artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT qiangli artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT qiangli artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT qiangli artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork AT qiangli artificialintelligenceradiotherapyplanningautomaticsegmentationofhumanorgansinctimagesbasedonamodifiedconvolutionalneuralnetwork |