收藏切换
Intelligent segmentation and staging system for esophageal cancer based on DAEUnet and ConvNeXt networks
收藏切换
Lingyan XIONG1, Runyuan WANG2, Fanghong ZHANG1, 3, You YANG1, 3, Yi WU4, Wei WU5, Shulei WU3
Journal of Army Medical University | 2025, 47(10) : 1135 - 1144
Less
收藏切换
Journal of Army Medical University | 2025, 47(10): 1135-1144
• Biomedical Engineering •
Intelligent segmentation and staging system for esophageal cancer based on DAEUnet and ConvNeXt networks
Full
Lingyan XIONG1, Runyuan WANG2, Fanghong ZHANG1, 3, You YANG1, 3, Yi WU4, Wei WU5, Shulei WU3
Affiliations
  • 1Chongqing National Center for Applied Mathematics,Chongqing
  • 2Department of Thoracic Surgery,Shanxi Cancer Hospital,Taiyuan,Shanxi
  • 3School of Computer and Information Science,Chongqing Normal University,Chongqing
  • 4Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine
  • 5Department of Cardiovascular Surgery,First Affiliated Hospital,Army Medical University (Third Military Medical University),Chongqing,China
Published: 2025-05-30 doi: 10.16016/j.2097-0927.202412075
Outline
收藏切换
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.

esophageal cancer  /  enhanced CT  /  intelligent segmentation  /  ConvNeXt  /  T-stage diagnosis
熊铃焰, 王润媛, 张方红, 杨有, 吴毅, 吴蔚, 武书磊. 基于DAEUnet和ConvNeXt网络的食管癌智能分割与分期诊断模型构建. 陆军军医大学学报, 2025 , 47 (10) : 1135 -1144 . DOI: 10.16016/j.2097-0927.202412075
Lingyan XIONG, Runyuan WANG, Fanghong ZHANG, You YANG, Yi WU, Wei WU, Shulei WU. Intelligent segmentation and staging system for esophageal cancer based on DAEUnet and ConvNeXt networks[J]. Journal of Army Medical University, 2025 , 47 (10) : 1135 -1144 . DOI: 10.16016/j.2097-0927.202412075
Year 2025 volume 47 Issue 10
18
7
Cite this Article
BibTeX
Article Info
doi: 10.16016/j.2097-0927.202412075
  • Receive Date:2024-12-13
  • Online Date:2026-10-28
  • Published:2025-05-30
Article Data
Affiliations
History
  • Received:2024-12-13
  • Revised:2025-03-07
Affiliations
    1Chongqing National Center for Applied Mathematics,Chongqing
    2Department of Thoracic Surgery,Shanxi Cancer Hospital,Taiyuan,Shanxi
    3School of Computer and Information Science,Chongqing Normal University,Chongqing
    4Department of Digital Medicine,Faculty of Biomedical Engineering and Imaging Medicine
    5Department of Cardiovascular Surgery,First Affiliated Hospital,Army Medical University (Third Military Medical University),Chongqing,China
References
Share
https://castjournals.cast.org.cn/joweb/ljjydxxb/EN/10.16016/j.2097-0927.202412075
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT