
浏览全部资源
扫码关注微信
1.重庆国家应用数学中心,重庆
2.山西省肿瘤医院胸外科,山西太原
3.重庆师范大学计算机与信息科学学院,重庆;陆军军医大学(第三军医大学):4.生物医学工程与影像医学系数字医学教研室
4.第一附属医院心外科,重庆
5.Department of Cardiovascular Surgery, First Affiliated Hospital, Army Medical University (Third Military Medical University), Chongqing, China
张方红,E-mail:fanghong.zhang@cqnu.edu.cn
吴 毅,E-mail:wuy1979@tmmu.edu.cn
收稿日期:2024-12-13,
修回日期:2025-03-07,
纸质出版日期:2025-05-30
移动端阅览
熊铃焰,王润媛,张方红,等.基于DAEUnet和ConvNeXt网络的食管癌智能分割与分期诊断模型构建[J].陆军军医大学学报,2025,47(10):1135-1144.
XIONG Lingyan,WANG Runyuan,ZHANG Fanghong,et al.Intelligent segmentation and staging system for esophageal cancer based on DAEUnet and ConvNeXt networks[J].J Army Med Univ,2025,47(10):1135-1144.
熊铃焰,王润媛,张方红,等.基于DAEUnet和ConvNeXt网络的食管癌智能分割与分期诊断模型构建[J].陆军军医大学学报,2025,47(10):1135-1144. DOI:10.16016/j.2097-0927.202412075.
XIONG Lingyan,WANG Runyuan,ZHANG Fanghong,et al.Intelligent segmentation and staging system for esophageal cancer based on DAEUnet and ConvNeXt networks[J].J Army Med Univ,2025,47(10):1135-1144. DOI:10.16016/j.2097-0927.202412075.
目的
2
基于DAEUnet和ConvNeXt网络,通过迁移学习策略构建食管癌智能分割和T分期诊断模型。
方法
2
收集2018年1月至2022年4月共126例确诊为食管癌患者Dicom原始数据,其中100例来源于陆军军医大学第一附属医院胸外科,26例来自山西省肿瘤医院胸外科,数据增强后共计60 275张,搭建DAEUnet食管癌智能分割网络,并在此基础上构建ConvNeXt、Swin Transfoemr以及ResNet 3个分类网络进行食管癌T分期诊断。
结果
2
基于DAEUnet网络食管癌智能分割Dice相似系数(Dice similarity coefficient,DSC)为0.82,食管癌、主动脉、正常食管、纵隔淋巴结、心脏各个部位DSC分别为72.4%、87.5%、79.3%、60.5%、96.8%;在3个食管癌T分期诊断模型中,ConvNeXt模型效果最好,T1~T4期的精确度分别为0.65、0.727、0.889、0.92,曲线下面积(AUC)=0.892,优于ResNet和Swin Transformer网络。
结论
2
基于DAEUnet和ConvNeXt网络的食管癌智能分割与T分期诊断模型,能够提高食管癌T分期的准确性与治疗效率。
Objective To construct an intelligent segmentation and T-stage diagnostic model for esophageal cancer based on the DAEUnet and ConvNeXt networks using transfer learning. Methods Dicom raw data from 126 patients diagnosed with esophageal cancer between January 2018 and April 2022 were collected
including 100 cases from Department of Thoracic Surgery at the First Affiliated Hospital of Army Medical University and 26 cases from the Department of Thoracic Surgery at Shanxi Cancer Hospital. After data augmentation
a total of 60 275 images were obtained. The DAEUnet esophageal cancer intelligent segmentation network was built
and on this basis
3 classification networks
ConvNeXt
Swin Transformer
and ResNet were constructed for T-stage diagnosis of esophageal cancer. Results The Dice similarity coefficient (DSC) for esophageal cancer intelligent segmentation using the DAEUnet network was 0.82
and the DSC value of the esophagus
aorta
normal esophagus
mediastinal lymph nodes
and heart was 72.4%
87.5%
79.3%
60.5% and 96.8%
respectively. Among the 3 T-stage diagnosis models for esophageal cancer
the ConvNeXt model performed the best
with a precision value for T1~T4 stages of 0.65
0.727
0.889 and 0.92
respectively
and an AUC value of 0.892
which were superior to the ResNet and Swin Transformer networks. Conclusion The proposed DAEUnet and ConvNeXt-based intelligent segmentation and T-stage diagnosis model for esophageal cancer improves T-stage accuracy and treatment efficiency.
MA D , ZHOU T L , CHEN J , et al . Radiomics diagnostic performance for predicting lymph node metastasis in esophageal cancer: a systematic review and meta-analysis [J]. BMC Med Imaging , 2024 , 24 ( 1 ): 144 . DOI: 10.1186/s12880-024-01278-5 http://dx.doi.org/10.1186/s12880-024-01278-5 .
王润媛 . 基于深度学习的食管癌智能分割与分期诊断 [D]. 太原 : 山西医科大学 , 2023 . DOI: 10.27288/d.cnki.gsxyu.2023.001615 http://dx.doi.org/10.27288/d.cnki.gsxyu.2023.001615 .
WANG R Y . Intelligent segmentation and staging diagnosis of esophageal cancer based on deep learning [D]. Taiyuan : Shanxi Medical University , 2023 . DOI: 10.27288/d.cnki.gsxyu.2023.001615 http://dx.doi.org/10.27288/d.cnki.gsxyu.2023.001615 .
TALUKDAR F R , DI PIETRO M , SECRIER M , et al . Molecular landscape of esophageal cancer: implications for early detection and personalized therapy [J]. Ann N Y Acad Sci , 2018 , 1434 ( 1 ): 342 - 359 . DOI: 10.1111/nyas.13876 http://dx.doi.org/10.1111/nyas.13876 .
CAI Z J , LIU Q . Understanding the global cancer statistics 2018: implications for cancer control [J]. Sci China Life Sci , 2021 , 64 ( 6 ): 1017 - 1020 . DOI: 10.1007/s11427-019-9816-1 http://dx.doi.org/10.1007/s11427-019-9816-1 .
SAEKI H , SOHDA M , SAKAI M , et al . Role of surgery in multidisciplinary treatment strategies for locally advanced esophageal squamous cell carcinoma [J]. Annals Gastroent Surgery , 2020 , 4 ( 5 ): 490 - 497 . DOI: 10.1002/ags3.12364 http://dx.doi.org/10.1002/ags3.12364 .
薛龙梅 , 赵学武 , 贾霞 , 等 . MSCT对食管癌术前TNM分期的诊断及临床指导价值分析 [J]. 中国CT和MRI杂志 , 2022 , 20 ( 9 ): 102 - 103, 123 . DOI: 10.3969/j.issn.1672-5131.2022.09.038 http://dx.doi.org/10.3969/j.issn.1672-5131.2022.09.038 .
XUE L M , ZHAO X W , JIA X , et al . Analysis on value of MSCT in the diagnosis and clinical guidance of preoperative TNM staging of esophageal cancer [J]. Chin J CT MRI , 2022 , 20 ( 9 ): 102 - 103, 123 . DOI: 10.3969/j.issn.1672-5131.2022.09.038 http://dx.doi.org/10.3969/j.issn.1672-5131.2022.09.038 .
YANG M W , HU P P , LI M L , et al . Computed tomography-based radiomics in predicting T stage and length of esophageal squamous cell carcinoma [J]. Front Oncol , 2021 , 11 : 722961 . DOI: 10.3389/fonc.2021.722961 http://dx.doi.org/10.3389/fonc.2021.722961 .
WU A J , BOSCH W R , CHANG D T , et al . Expert consensus contouring guidelines for intensity modulated radiation therapy in esophageal and gastroesophageal junction cancer [J]. Int J Radiat Oncol Biol Phys , 2015 , 92 ( 4 ): 911 - 920 . DOI: 10.1016/j.ijrobp.2015.03.030 http://dx.doi.org/10.1016/j.ijrobp.2015.03.030 .
OLD O J , ISABELLE M , BARR H . Staging early esophageal cancer [J]. Adv Exp Med Biol , 2016 , 908 : 161 - 181 . DOI: 10.1007/978-3-319-41388-4_9 http://dx.doi.org/10.1007/978-3-319-41388-4_9 .
王润媛 , 陈星材 , 吴蔚 , 等 . 基于增强CT图像和Swin Transformer网络的食管癌T分期智能诊断模型的构建与评估 [J]. 陆军军医大学学报 , 2023 , 45 ( 16 ): 1770 - 1778 . DOI: 10.16016/j.2097-0927.202302021 http://dx.doi.org/10.16016/j.2097-0927.202302021 .
WANG R Y , CHEN X C , WU W , et al . Construction and evaluation of an intelligent diagnostic model based on enhanced CT images and Swin Transformer network for T staging of esophageal cancer [J]. J Army Med Univ , 2023 , 45 ( 16 ): 1770 - 1778 . DOI: 10.16016/j.2097-0927.202302021 http://dx.doi.org/10.16016/j.2097-0927.202302021 .
LIU G S , HUA J , WU Z , et al . Automatic classification of esophageal lesions in endoscopic images using a convolutional neural network [J]. Ann Transl Med , 2020 , 8 ( 7 ): 486 . DOI: 10.21037/atm.2020.03.24 http://dx.doi.org/10.21037/atm.2020.03.24 .
EBIGBO A , MENDEL R , PROBST A , et al . Computer-aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma [J]. Gut , 2019 , 68 ( 7 ): 1143 - 1145 . DOI: 10.1136/gutjnl-2018-317573 http://dx.doi.org/10.1136/gutjnl-2018-317573 .
RAMDHAN ABDALLA W A . Classifying esophageal cancer using a hybrid quantum-classical neural network [C]// 2023 IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA) . IEEE , 2023 : 229 - 234 . DOI: 10.1109/MI-STA57575.2023.10169293 http://dx.doi.org/10.1109/MI-STA57575.2023.10169293 .
GUO L J , XIAO X , WU C C , et al . Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos) [J]. Gastrointest Endosc , 2020 , 91 ( 1 ): 41 - 51 . DOI: 10.1016/j.gie.2019.08.018 http://dx.doi.org/10.1016/j.gie.2019.08.018 .
WAN J , ZENG Y K . Prediction of hepatic metastasis in esophageal cancer based on machine learning [J]. Sci Rep , 2024 , 14 ( 1 ): 14507 . DOI: 10.1038/s41598-024-63213-6 http://dx.doi.org/10.1038/s41598-024-63213-6 .
LIU Z , MAO H Z , WU C Y , et al . A ConvNet for the 2020s [C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE , 2022 : 11966 - 11976 . DOI: 10.1109/CVPR52688.2022.01167 http://dx.doi.org/10.1109/CVPR52688.2022.01167 .
LI M , WANG J P , CHEN Y , et al . Low-dose CT image synthesis for domain adaptation imaging using a generative adversarial network with noise encoding transfer learning [J]. IEEE Trans Med Imag , 2023 , 42 ( 9 ): 2616 - 2630 . DOI: 10.1109/TMI.2023.3261822 http://dx.doi.org/10.1109/TMI.2023.3261822 .
CHEN Y , LIN H P , ZHANG W , et al . ICycle-GAN: Improved cycle generative adversarial networks for liver medical image generation [J]. Biomed Signal Process Contr , 2024 , 92 : 106100 . DOI: 10.1016/j.bspc.2024.106100 http://dx.doi.org/10.1016/j.bspc.2024.106100 .
AKTER S . Generative AI: a Pix2pix-GAN-based machine learning approach for robust and efficient lung segmentation [EB/OL]. 2024: 2412 . 10826 . https://arxiv.org/abs/2412. 10826v1 https://arxiv.org/abs/2412.10826v1 .
马岽奡 , 唐娉 , 赵理君 , 等 . 深度学习图像数据增广方法研究综述 [J]. 中国图象图形学报 , 2021 , 26 ( 3 ): 487 - 502 .
MA D A , TANG P , ZHAO L J , et al . Review of data augmentation for image in deep learning [J]. J Image Graph , 2021 , 26 ( 3 ): 487 - 502 .
LIU W F , WANG S F , YE Z H , et al . Prediction of lung metastases in thyroid cancer using machine learning based on SEER database [J]. Cancer Med , 2022 , 11 ( 12 ): 2503 - 2515 . DOI: 10.1002/cam4.4617 http://dx.doi.org/10.1002/cam4.4617 .
GRANADOS SÁNCHEZ A M , OREJUELA ZAPATA J F . Diagnosis of mesial temporal sclerosis: sensitivity, specificity and predictive values of the quantitative analysis of magnetic resonance imaging [J]. Neuroradiol J , 2018 , 31 ( 1 ): 50 - 59 . DOI: 10.1177/1971400917731301 http://dx.doi.org/10.1177/1971400917731301 .
KIM S C , CHO Y S . Predictive system implementation to improve the accuracy of urine self-diagnosis with smartphones: application of a confusion matrix-based learning model through RGB semiquantitative analysis [J]. Sensors , 2022 , 22 ( 14 ): 5445 . DOI: 10.3390/s22145445 http://dx.doi.org/10.3390/s22145445 .
CHENG Y , LI X C , DAI Y B , et al . Identification of an immune-related risk signature and nomogram predicting the overall survival in patients with endometrial cancer [J]. J Gynecol Oncol , 2021 , 32 ( 3 ): e30 . DOI: 10.3802/jgo.2021.32.e30 http://dx.doi.org/10.3802/jgo.2021.32.e30 .
ZHANG T M , CHEN Z , WANG Z Z , et al . Esophago-gastroscopy for predicting endoscopic ultrasonography T-stage by utilizing deep learning methods in esophageal cancer [J]. Appl Intell , 2024 , 54 ( 19 ): 9286 - 9294 . DOI: 10.1007/s10489-024-05640-6 http://dx.doi.org/10.1007/s10489-024-05640-6 .
GHATWARY N , YE X J , ZOLGHARNI M . Esophageal abnormality detection using DenseNet based faster R-CNN with Gabor features [J]. IEEE Access , 2019 , 7 : 84374 - 84385 . DOI: 10.1109/ACCESS.2019.2925585 http://dx.doi.org/10.1109/ACCESS.2019.2925585 .
DU K P , LI L X , WANG Q , et al . Development and application of a dynamic prediction model for esophageal cancer [J]. Ann Transl Med , 2021 , 9 ( 20 ): 1546 . DOI: 10.21037/atm-21-4964 http://dx.doi.org/10.21037/atm-21-4964 .
ZHAO X J , CHEN K X , WU G , et al . Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema [J]. Eur Radiol , 2021 , 31 ( 7 ): 5012 - 5020 . DOI: 10.1007/s00330-020-07558-2 http://dx.doi.org/10.1007/s00330-020-07558-2 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621