Skip to content
DraconiticResearch
Search Sources API
194,226 studies31 sourcesUpdated 1 min ago
Peer-reviewedCC BY 4.0PLOS Digital Health

Artificial intelligence for evaluation of magnetic resonance imaging-detected extramural vascular invasion in rectal cancer

  • Haitao Huang1
  • Lili Feng2
  • Min-Er Zhong3
  • Huifen Ye4
  • Zhenhui Li5
  • Su Yao6
  • Yunrui Ye7
  • Yulin Liu8
  • Minning Zhao9
  • Weixiong Xu10
  • Lifen Yan11
  • ChuanMiao Xie12
6 more authors
  • Changhong Liang13
  • Zaiyi Liu14
  • Tong Tong15
  • Yanfen Cui16
  • Xin-Juan Fan17
  • Ke Zhao18
18 affiliations
  1. 1Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
  2. 2School of Medicine, South China University of Technology, Guangzhou, China
  3. 3Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
  4. 4State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China
  5. 5Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, China
  6. 6Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
  7. 7Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China
  8. 8Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
  9. 9Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming, China
  10. 10Department of Pathology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
  11. 11Department of Pathology, Heyuan People’s Hospital, Heyuan, China
  12. 12Heyuan Key Laboratory of Molecular Diagnosis and Disease Prevention and Treatment, Heyuan People’s Hospital, Heyuan, China
  13. 13Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
  14. 14Department of Radiology, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
  15. 15Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
  16. 16Department of Radiology, Shanxi Cancer Hospital, Shanxi Medical University, Taiyuan, China
  17. 17Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
  18. 18Henan Provincial Key Laboratory of Radiation Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Read full textPDFDOICite

Abstract

MRI-detected extramural vascular invasion (mrEMVI) is an important prognostic biomarker in rectal cancer, reflecting tumor invasiveness and metastatic potential. To address the subjectivity and inter-observer variability inherent in manual mrEMVI assessment, this study trained and validated an nnUNet-based segmentation model for automated voxel-level localization and visualization of mrEMVI. This multi-center retrospective study included a total of 2,501 rectal cancer patients, comprising 1,830 in the training cohort (with 5-fold cross-validation) and 671 in two independent external test cohorts. The Dice similarity coefficient was used to evaluate segmentation performance; the inter-reader agreement for mrEMVI identification was assessed using Cohen’s kappa (κ). The prognostic value of mrEMVI status identified by the artificial intelligence (AI) model was evaluated using Kaplan-Meier survival analysis and multivariable Cox regression. In internal five-fold cross-validation, the model yielded Dice scores of 0.850, 0.442, and 0.335 for tumor, intravascular tumor signal, and dilated vessel segmentation, respectively. The model demonstrated strong classification performance, with accuracies of 81.5% (95% CI: 76.7%–85.8%) and 84.7% (95% CI: 80.7%–88.2%) in the two external test cohorts, and achieved substantial agreement with senior radiologists (κ = 0.713–0.736). Patients identified as AI-mrEMVI+ had significantly lower 3-year disease-free survival (DFS) and 5-year overall survival (OS) rates than AI-mrEMVI− patients (DFS: 62.3% vs. 84.9%, HR = 2.67, 95% CI: 1.95–3.66; OS: 68.7% vs. 87.1%, HR = 2.64, 95% CI: 1.75–3.97; both p < 0.001). This work establishes a scalable, objective framework for mrEMVI assessment based on voxel-level segmentation, inter-observer agreement analysis, and comprehensive prognostic validation, with direct implications for risk stratification and treatment individualization in rectal cancer. Author summary: In this study, we aimed to make the evaluation of MRI-detected extramural vascular invasion (mrEMVI) in rectal cancer more objective and reliable. Traditionally, radiologists assess this feature manually on MRI scans, but such evaluations can vary between readers. To address this challenge, we trained a deep learning model based on the nnUNet framework that can automatically identify and outline mrEMVI regions in rectal cancer images. Using MRI data from multiple medical centers, our model learned to recognize these features with high accuracy and achieved substantial agreement with experienced radiologists in mrEMVI identification. We also found that patients identified by the model as AI-mrEMVI+ had a significantly higher risk of cancer recurrence and shorter survival times, indicating that our model can provide valuable prognostic information in addition to achieving substantial agreement with experienced radiologists. By offering a consistent and visually interpretable approach to mrEMVI assessment, our work may help doctors make better treatment decisions and move toward more personalized care for people with rectal cancer.

Related

  1. Artificial Intelligence-Enhanced Cardiac Magnetic Resonance in Hypertrophic Cardiomyopathy: Diagnosis, Phenotypic Characterization, and Risk Prediction
    Yu-Jie Xiang, Yu-Cong Zheng, Ju Han +3
    Diagnostics (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Multicentre medicoeconomic evaluation of cardiac magnetic resonance imaging for predicting coronary artery disease in left ventricular dysfunction: The CAMAREC study design
    Louis-Marie Desroche, Damien Mandry, Gregory Ducrocq +14
    Archives of cardiovascular diseasesPeer-reviewedLicence not stated3 citedGeneral biologyCardiovascular medicineHAL
  3. Evaluation of rupture risk of pediatric intracranial aneurysm using high-resolution magnetic resonance imaging techniques: a case report.
    Xin Feng, Lele Dai, Wenxin Chen +7
    BMC neurologyPeer-reviewedCC BYFull textNeurologyEurope PMCPMC
  4. OP–249 A comparative evaluation of artificial intelligence models for adolescent-centered scoliosis questions
    Esra Rabia Taşpolat, Ebru Kübra Taşpolat, Tuba Sarıkaya +2
    BMJ Paediatrics OpenPeer-reviewedCC BYObstetrics, gynaecology & paediatricsDOAJ
  5. Evaluation of Tooth Shade Selection With Conventional Methods and Artificial Intelligence-Integrated Methods: A Comparative Study
    Rahul Das, Sheenam Markan, Mukesh Kumar +3
    CureusPeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{huang2026artificial,
  title = {{Artificial intelligence for evaluation of magnetic resonance imaging-detected extramural vascular invasion in rectal cancer}},
  author = {Haitao Huang and Lili Feng and Min-Er Zhong and Huifen Ye and Zhenhui Li and Su Yao and Yunrui Ye and Yulin Liu and Minning Zhao and Weixiong Xu and Lifen Yan and ChuanMiao Xie and Changhong Liang and Zaiyi Liu and Tong Tong and Yanfen Cui and Xin-Juan Fan and Ke Zhao},
  journal = {PLOS Digital Health},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pdig.0001763},
  url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001763},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Artificial intelligence for evaluation of magnetic resonance imaging-detected extramural vascular invasion in rectal cancer
AU  - Haitao Huang
AU  - Lili Feng
AU  - Min-Er Zhong
AU  - Huifen Ye
AU  - Zhenhui Li
AU  - Su Yao
AU  - Yunrui Ye
AU  - Yulin Liu
AU  - Minning Zhao
AU  - Weixiong Xu
AU  - Lifen Yan
AU  - ChuanMiao Xie
AU  - Changhong Liang
AU  - Zaiyi Liu
AU  - Tong Tong
AU  - Yanfen Cui
AU  - Xin-Juan Fan
AU  - Ke Zhao
PY  - 2026
DA  - 2026/10/01
JO  - PLOS Digital Health
DO  - 10.1371/journal.pdig.0001763
UR  - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001763
AB  - MRI-detected extramural vascular invasion (mrEMVI) is an important prognostic biomarker in rectal cancer, reflecting tumor invasiveness and metastatic potential. To address the subjectivity and inter-observer variability inherent in manual mrEMVI assessment, this study trained and validated an nnUNet-based segmentation model for automated voxel-level localization and visualization of mrEMVI. This multi-center retrospective study included a total of 2,501 rectal cancer patients, comprising 1,830 in the training cohort (with 5-fold cross-validation) and 671 in two independent external test cohorts. The Dice similarity coefficient was used to evaluate segmentation performance; the inter-reader agreement for mrEMVI identification was assessed using Cohen’s kappa (κ). The prognostic value of mrEMVI status identified by the artificial intelligence (AI) model was evaluated using Kaplan-Meier survival analysis and multivariable Cox regression. In internal five-fold cross-validation, the model yielded Dice scores of 0.850, 0.442, and 0.335 for tumor, intravascular tumor signal, and dilated vessel segmentation, respectively. The model demonstrated strong classification performance, with accuracies of 81.5% (95% CI: 76.7%–85.8%) and 84.7% (95% CI: 80.7%–88.2%) in the two external test cohorts, and achieved substantial agreement with senior radiologists (κ = 0.713–0.736). Patients identified as AI-mrEMVI+ had significantly lower 3-year disease-free survival (DFS) and 5-year overall survival (OS) rates than AI-mrEMVI− patients (DFS: 62.3% vs. 84.9%, HR = 2.67, 95% CI: 1.95–3.66; OS: 68.7% vs. 87.1%, HR = 2.64, 95% CI: 1.75–3.97; both p < 0.001). This work establishes a scalable, objective framework for mrEMVI assessment based on voxel-level segmentation, inter-observer agreement analysis, and comprehensive prognostic validation, with direct implications for risk stratification and treatment individualization in rectal cancer. Author summary: In this study, we aimed to make the evaluation of MRI-detected extramural vascular invasion (mrEMVI) in rectal cancer more objective and reliable. Traditionally, radiologists assess this feature manually on MRI scans, but such evaluations can vary between readers. To address this challenge, we trained a deep learning model based on the nnUNet framework that can automatically identify and outline mrEMVI regions in rectal cancer images. Using MRI data from multiple medical centers, our model learned to recognize these features with high accuracy and achieved substantial agreement with experienced radiologists in mrEMVI identification. We also found that patients identified by the model as AI-mrEMVI+ had a significantly higher risk of cancer recurrence and shorter survival times, indicating that our model can provide valuable prognostic information in addition to achieving substantial agreement with experienced radiologists. By offering a consistent and visually interpretable approach to mrEMVI assessment, our work may help doctors make better treatment decisions and move toward more personalized care for people with rectal cancer.
SN  - 2767-3170
ER  -