{"title":"基于深度学习的宫颈癌术后近距离放疗CT图像间质针自动重建。","authors":"Hongling Xie, Jiahao Wang, Yuanyuan Chen, Yeqiang Tu, Yukai Chen, Yadong Zhao, Pengfei Zhou, Shichun Wang, Zhixin Bai, Qiu Tang","doi":"10.5114/jcb.2023.126514","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to investigate the precision of deep learning (DL)-based auto-reconstruction in localizing interstitial needles in post-operative cervical cancer brachytherapy (BT) using three-dimensional (3D) computed tomography (CT) images.</p><p><strong>Material and methods: </strong>A convolutional neural network (CNN) was developed and presented for automatic reconstruction of interstitial needles. Data of 70 post-operative cervical cancer patients who received CT-based BT were used to train and test this DL model. All patients were treated with three metallic needles. Dice similarity coefficient (DSC), 95% Hausdorff distance (95% HD), and Jaccard coefficient (JC) were applied to evaluate the geometric accuracy of auto-reconstruction for each needle. Dose-volume indexes (DVI) between manual and automatic methods were used to analyze the dosimetric difference. Correlation between geometric metrics and dosimetric difference was evaluated using Spearman correlation analysis.</p><p><strong>Results: </strong>The mean DSC values of DL-based model were 0.88, 0.89, and 0.90 for three metallic needles. Wilcoxon signed-rank test indicated no significant dosimetric differences in all BT planning structures between manual and automatic reconstruction methods (<i>p</i> > 0.05). Spearman correlation analysis demonstrated weak link between geometric metrics and dosimetry differences.</p><p><strong>Conclusions: </strong>DL-based reconstruction method can be used to precisely localize the interstitial needles in 3D-CT images. The proposed automatic approach could improve the consistency of treatment planning for post-operative cervical cancer brachytherapy.</p>","PeriodicalId":51305,"journal":{"name":"Journal of Contemporary Brachytherapy","volume":"15 2","pages":"134-140"},"PeriodicalIF":1.1000,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ac/2c/JCB-15-50520.PMC10196730.pdf","citationCount":"0","resultStr":"{\"title\":\"Automatic reconstruction of interstitial needles using CT images in post-operative cervical cancer brachytherapy based on deep learning.\",\"authors\":\"Hongling Xie, Jiahao Wang, Yuanyuan Chen, Yeqiang Tu, Yukai Chen, Yadong Zhao, Pengfei Zhou, Shichun Wang, Zhixin Bai, Qiu Tang\",\"doi\":\"10.5114/jcb.2023.126514\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>The purpose of this study was to investigate the precision of deep learning (DL)-based auto-reconstruction in localizing interstitial needles in post-operative cervical cancer brachytherapy (BT) using three-dimensional (3D) computed tomography (CT) images.</p><p><strong>Material and methods: </strong>A convolutional neural network (CNN) was developed and presented for automatic reconstruction of interstitial needles. Data of 70 post-operative cervical cancer patients who received CT-based BT were used to train and test this DL model. All patients were treated with three metallic needles. Dice similarity coefficient (DSC), 95% Hausdorff distance (95% HD), and Jaccard coefficient (JC) were applied to evaluate the geometric accuracy of auto-reconstruction for each needle. Dose-volume indexes (DVI) between manual and automatic methods were used to analyze the dosimetric difference. Correlation between geometric metrics and dosimetric difference was evaluated using Spearman correlation analysis.</p><p><strong>Results: </strong>The mean DSC values of DL-based model were 0.88, 0.89, and 0.90 for three metallic needles. Wilcoxon signed-rank test indicated no significant dosimetric differences in all BT planning structures between manual and automatic reconstruction methods (<i>p</i> > 0.05). Spearman correlation analysis demonstrated weak link between geometric metrics and dosimetry differences.</p><p><strong>Conclusions: </strong>DL-based reconstruction method can be used to precisely localize the interstitial needles in 3D-CT images. The proposed automatic approach could improve the consistency of treatment planning for post-operative cervical cancer brachytherapy.</p>\",\"PeriodicalId\":51305,\"journal\":{\"name\":\"Journal of Contemporary Brachytherapy\",\"volume\":\"15 2\",\"pages\":\"134-140\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2023-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ac/2c/JCB-15-50520.PMC10196730.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Contemporary Brachytherapy\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.5114/jcb.2023.126514\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Contemporary Brachytherapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.5114/jcb.2023.126514","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ONCOLOGY","Score":null,"Total":0}
Automatic reconstruction of interstitial needles using CT images in post-operative cervical cancer brachytherapy based on deep learning.
Purpose: The purpose of this study was to investigate the precision of deep learning (DL)-based auto-reconstruction in localizing interstitial needles in post-operative cervical cancer brachytherapy (BT) using three-dimensional (3D) computed tomography (CT) images.
Material and methods: A convolutional neural network (CNN) was developed and presented for automatic reconstruction of interstitial needles. Data of 70 post-operative cervical cancer patients who received CT-based BT were used to train and test this DL model. All patients were treated with three metallic needles. Dice similarity coefficient (DSC), 95% Hausdorff distance (95% HD), and Jaccard coefficient (JC) were applied to evaluate the geometric accuracy of auto-reconstruction for each needle. Dose-volume indexes (DVI) between manual and automatic methods were used to analyze the dosimetric difference. Correlation between geometric metrics and dosimetric difference was evaluated using Spearman correlation analysis.
Results: The mean DSC values of DL-based model were 0.88, 0.89, and 0.90 for three metallic needles. Wilcoxon signed-rank test indicated no significant dosimetric differences in all BT planning structures between manual and automatic reconstruction methods (p > 0.05). Spearman correlation analysis demonstrated weak link between geometric metrics and dosimetry differences.
Conclusions: DL-based reconstruction method can be used to precisely localize the interstitial needles in 3D-CT images. The proposed automatic approach could improve the consistency of treatment planning for post-operative cervical cancer brachytherapy.
期刊介绍:
The “Journal of Contemporary Brachytherapy” is an international and multidisciplinary journal that will publish papers of original research as well as reviews of articles. Main subjects of the journal include: clinical brachytherapy, combined modality treatment, advances in radiobiology, hyperthermia and tumour biology, as well as physical aspects relevant to brachytherapy, particularly in the field of imaging, dosimetry and radiation therapy planning. Original contributions will include experimental studies of combined modality treatment, tumor sensitization and normal tissue protection, molecular radiation biology, and clinical investigations of cancer treatment in brachytherapy. Another field of interest will be the educational part of the journal.