Share：
Share this content in WeChat
X
[Chinese] [PDF] 11 1
• Review •
Research progress and current status of artificial intelligence based on MR diffusion imaging technology in evaluating cervical cancer
SUN Shihua  ZHANG Jing  MOU Yanan  PANG Yaxuan  LI Xinyuan  YIN Liang 

DOI:10.12015/issn.1674-8034.2025.12.032.


[Abstract] Cervical cancer (CC) is the most common malignant tumor in the female reproductive system in China. Artificial intelligence (AI) based on magnetic resonance diffusion imaging technology can achieve accurate characterization of CC, which is currently a research hotspot in the diagnosis and evaluation of CC imaging. However, the existing reviews are mostly limited to the research and application of AI with different MRI technologies, and lack of horizontal comparison of AI models with different modal imaging technologies. This review makes up for this deficiency, analyzes its clinical application value, advantages and disadvantages, discusses improvement strategies, and looks forward to the future development directions. By fusing multi-sequence images and clinical features, AI based on MR diffusion imaging technology can effectively improve the accuracy of CC in pathological classification, staging, metastasis prediction and prognosis evaluation, thereby providing reference for clinical treatment decision-making and transformation.
[Keywords] uterine cervical neoplasms；magnetic resonance imaging；diffusion weighted imaging；artificial intelligence；radiomics；deep learning

SUN Shihua1   ZHANG Jing1   MOU Yanan1   PANG Yaxuan1   LI Xinyuan1   YIN Liang2*  

1 The First Clinical Medical College of Lanzhou University, Lanzhou 730000, China

2 Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730000, China

Corresponding author: YIN L, E-mail: yinliang_ldyy@163.com

Conflicts of interest   None.

Received  2025-08-08
Accepted  2025-12-06
DOI: 10.12015/issn.1674-8034.2025.12.032
DOI:10.12015/issn.1674-8034.2025.12.032.

[1]
JIANG D M, NIU Z Y, TAN X J, et al. The mortalities of female-specific cancers in China and other countries with distinct socioeconomic statuses: a longitudinal study[J]. J Adv Res, 2023, 49: 127-139. DOI: 10.1016/j.jare.2022.09.002.
[2]
ZHENG N, TANG J, REN X M. Common malignant tumors in the reproductive system of Chinese women: disease burden during 1990-2019 and prediction of future trend[J]. Zhongguo Yi Xue Ke Xue Yuan Xue Bao Acta Acad Med Sin, 2024, 46(1): 25-32. DOI: 10.3881/j.issn.1000-503X.15801.
[3]
SHAKUR A, LEE J Y J, FREEMAN S. An update on the role of MRI in treatment stratification of patients with cervical cancer[J/OL]. Cancers (Basel), 2023, 15(20): 5105 [2025-08-07]. https://doi.org/10.3390/cancers15205105.. DOI: 10.3390/cancers15205105.
[4]
AHANGARI S, LITTRUP ANDERSEN F, HANSEN N LIV, et al. Multi-parametric PET/MRI for enhanced tumor characterization of patients with cervical cancer[J/OL]. Eur J Hybrid Imaging, 2022, 6(1): 7 [2025-08-07]. https://doi.org/10.1186/s41824-022-00129-2. DOI: 10.1186/s41824-022-00129-2.
[5]
WANG J Z, WANG K, YU Y F, et al. Self-improving generative foundation model for synthetic medical image generation and clinical applications[J]. Nat Med, 2025, 31(2): 609-617. DOI: 10.1038/s41591-024-03359-y.
[6]
ZHONG J Y, XING Y, HU Y F, et al. Assessment of robustness of MRI radiomic features in the abdomen: impact of deep learning reconstruction and accelerated acquisition[J/OL]. J Imag Inform Med, 2025 [2025-08-07]. https://doi.org/10.1007/s10278-025-01503-9. DOI: 10.1007/s10278-025-01503-9.
[7]
SCAPICCHIO C, GABELLONI M, BARUCCI A, et al. A deep look into radiomics[J]. Radiol Med, 2021, 126(10): 1296-1311. DOI: 10.1007/s11547-021-01389-x.
[8]
CHEN C, CHEN J, XIA L M. Artificial intelligence promotes the clinical application and research of medical imaging[J]. Radiol Pract, 2024, 39(1): 12-16. DOI: 10.13609/j.cnki.1000-0313.2024.01.003.
[9]
CHEN Z, YE N, JIANG N, et al. Deep learning model for intracranial hemangiopericytoma and meningioma classification[J/OL]. Front Oncol, 2022, 12: 839567 [2025-08-07]. https://doi.org/10.3389/fonc.2022.839567. DOI: 10.3389/fonc.2022.839567.
[10]
CHEN J W, XUE Y P, REN L H, et al. Predicting meningioma grades and pathologic marker expression via deep learning[J]. Eur Radiol, 2024, 34(5): 2997-3008. DOI: 10.1007/s00330-023-10258-2.
[11]
YU Z C, WANG K, WAN Z B, et al. Popular deep learning algorithms for disease prediction: a review[J]. Cluster Comput, 2023, 26(2): 1231-1251. DOI: 10.1007/s10586-022-03707-y.
[12]
HUANG Y H, ZHU T, ZHANG X L, et al. Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: a multicenter, retrospective study[J/OL]. EClinicalMedicine, 2023, 58: 101899 [2025-08-07]. https://doi.org/10.1016/j.eclinm.2023.101899. DOI: 10.1016/j.eclinm.2023.101899.
[13]
QAMAR T, BAWANY N Z. Understanding the black-box: towards interpretable and reliable deep learning models[J/OL]. PeerJ Comput Sci, 2023, 9: e1629 [2025-08-07]. https://doi.org/10.7717/peerj-cs.1629. DOI: 10.7717/peerj-cs.1629.
[14]
WANG W, JIAO Y N, ZHANG L C, et al. Multiparametric MRI-based radiomics analysis: differentiation of subtypes of cervical cancer in the early stage[J]. Acta Radiol, 2022, 63(6): 847-856. DOI: 10.1177/02841851211014188.
[15]
FANG Y H, WANG K Y, XIAO M L, et al. Multiparametric MRI-based radiomics nomogram for identifying cervix-corpus junction cervical adenocarcinoma from endometrioid adenocarcinoma[J]. Abdom Radiol (NY), 2024, 49(5): 1557-1568. DOI: 10.1007/s00261-024-04214-x.
[16]
WU F, ZHANG R, LI F, et al. Radiomics analysis based on multiparametric magnetic resonance imaging for differentiating early stage of cervical cancer[J/OL]. Front Med (Lausanne), 2024, 11: 1336640 [2025-08-07]. https://doi.org/10.3389/fmed.2024.1336640. DOI: 10.3389/fmed.2024.1336640.
[17]
HUANG Q H, DENG B D, WANG Y C, et al. Reduced field-of-view DWI-derived clinical-radiomics model for the prediction of stage in cervical cancer[J/OL]. Insights Imaging, 2023, 14(1): 18 [2025-08-07]. https://doi.org/10.1186/s13244-022-01346-w. DOI: 10.1186/s13244-022-01346-w.
[18]
HUANG G, CUI Y Q, WANG P, et al. Multi-parametric magnetic resonance imaging-based radiomics analysis of cervical cancer for preoperative prediction of lymphovascular space invasion[J/OL]. Front Oncol, 2022, 11: 663370 [2025-08-07]. https://doi.org/10.3389/fonc.2021.663370. DOI: 10.3389/fonc.2021.663370.
[19]
DONG L X, LIU J J, ZHANG Y J, et al. Prediction of lymphovascular space invasion in locally advanced cervical cancer patients after neoadjuvant chemotherapy based on pre-treatment multi-parameter MRI radiomics features[J]. Chin J Magn Reson Imag, 2024, 15(8): 25-30, 45. DOI: 10.12015/issn.1674-8034.2024.08.004.
[20]
MA N N, WANG T, LV Y N, et al. An MRI radiomics-based model for the prediction of invasion of the lymphovascular space in patients with cervical cancer[J/OL]. Front Oncol, 2024, 14: 1394427 [2025-08-07]. https://doi.org/10.3389/fonc.2024.1394427. DOI: 10.3389/fonc.2024.1394427.
[21]
ZHAO X J, LEI J Q, GAO Y L, et al. Evaluation of lymph nodes metastasis and lymphovascular space invasion in cervical cancer based on radiomics[J]. J China Clin Med Imag, 2022, 33(3): 216-220. DOI: 10.12117/jccmi.2022.03.015.
[22]
LIU J J, DONG L X, ZHANG X X, et al. Radiomics analysis for prediction of lymph node metastasis after neoadjuvant chemotherapy based on pretreatment MRI in patients with locally advanced cervical cancer[J/OL]. Front Oncol, 2024, 14: 1376640 [2025-08-07]. https://doi.org/10.3389/fonc.2024.1376640. DOI: 10.3389/fonc.2024.1376640.
[23]
SHI Z J, LU L L. Magnetic resonance imaging radiomics-based model for prediction of lymph node metastasis in cervical cancer[J]. Int J Gen Med, 2025, 18: 1371-1381. DOI: 10.2147/IJGM.S491986.
[24]
XIAO M L, WEI Y, ZHANG J, et al. MRI texture analysis for preoperative prediction of lymph node metastasis in patients with nonsquamous cell cervical carcinoma[J]. Acad Radiol, 2022, 29(11): 1661-1671. DOI: 10.1016/j.acra.2022.01.005.
[25]
LIU J J, DONG L X, YANG Z H, et al. Radiomics analysis for prediction of lymph node metastasis after neoadjuvant chemotherapy based on pretreatment MRI in locally advanced cervical squamous cell carcinoma[J]. Chin J Magn Reson Imag, 2024, 15(8): 17-24. DOI: 10.12015/issn.1674-8034.2024.08.003.
[26]
WANG T, LI Y Y, MA N N, et al. A MRI radiomics-based model for prediction of pelvic lymph node metastasis in cervical cancer[J/OL]. World J Surg Oncol, 2024, 22(1): 55 [2025-08-07]. https://doi.org/10.1186/s12957-024-03333-5. DOI: 10.1186/s12957-024-03333-5.
[27]
QIAN W L, CHEN Q. Radiomics based on super-resolution diffusion weighted imaging for prediction of normal-sized lymph node metastasis in cervical cancer patients[J]. Radiol Pract, 2025, 40(7): 889-895. DOI: 10.13609/j.cnki.1000-0313.2025.07.009.
[28]
ZHANG Z H, WAN X J, LEI X Y, et al. Intra- and peri-tumoral MRI radiomics features for preoperative lymph node metastasis prediction in early-stage cervical cancer[J/OL]. Insights Imaging, 2023, 14(1): 65 [2025-08-07]. https://doi.org/10.1186/s13244-023-01405-w. DOI: 10.1186/s13244-023-01405-w.
[29]
ZHONG S X, AI C H, DING Y Y, et al. Combining multimodal diffusion-weighted imaging and morphological parameters for detecting lymph node metastasis in cervical cancer[J]. Abdom Radiol (NY), 2024, 49(12): 4574-4583. DOI: 10.1007/s00261-024-04494-3.
[30]
WAGNER-LARSEN K S, HODNELAND E, FASMER K E, et al. MRI-based radiomic signatures for pretreatment prognostication in cervical cancer[J]. Cancer Med, 2023, 12(20): 20251-20265. DOI: 10.1002/cam4.6526.
[31]
ZHENG R R, CAI M T, LAN L, et al. An MRI-based radiomics signature and clinical characteristics for survival prediction in early-stage cervical cancer[J/OL]. Br J Radiol, 2022, 95(1129): 20210838 [2025-08-07]. https://doi.org/10.1259/bjr.20210838. DOI: 10.1259/bjr.20210838.
[32]
CAI M T, YAO F, DING J, et al. MRI radiomic features: a potential biomarker for progression-free survival prediction of patients with locally advanced cervical cancer undergoing surgery[J/OL]. Front Oncol, 2021, 11: 749114 [2025-08-07]. https://doi.org/10.3389/fonc.2021.749114. DOI: 10.3389/fonc.2021.749114.
[33]
LI J, ZHOU H, LU X F, et al. Preoperative prediction of cervical cancer survival using a high-resolution MRI-based radiomics nomogram[J/OL]. BMC Med Imaging, 2023, 23(1): 153 [2025-08-07]. https://doi.org/10.1186/s12880-023-01111-5. DOI: 10.1186/s12880-023-01111-5.
[34]
ZHOU Y, GU H L, ZHANG X L, et al. Multiparametric magnetic resonance imaging-derived radiomics for the prediction of disease-free survival in early-stage squamous cervical cancer[J]. Eur Radiol, 2022, 32(4): 2540-2551. DOI: 10.1007/s00330-021-08326-6.
[35]
ZHANG Q, OUYANG H, YE F, et al. Feasibility of intravoxel incoherent motion diffusion-weighted imaging in distinguishing adenocarcinoma originated from uterine corpus or cervix[J]. Abdom Radiol (NY), 2021, 46(2): 732-744. DOI: 10.1007/s00261-020-02586-4.
[36]
ZHANG Y, ZHANG K Y, JIA H D, et al. Feasibility of predicting pelvic lymph node metastasis based on IVIM-DWI and texture parameters of the primary lesion and lymph nodes in patients with cervical cancer[J]. Acad Radiol, 2022, 29(7): 1048-1057. DOI: 10.1016/j.acra.2021.08.026.
[37]
ZHANG Y, QIN Z H, LI L R, et al. Machine learning-based models for assessing postoperative risk factors in patients with cervical cancer[J]. Acad Radiol, 2024, 31(4): 1410-1418. DOI: 10.1016/j.acra.2023.09.031.
[38]
ZHANG Y, ZOU J, LI L R, et al. Comprehensive assessment of postoperative recurrence and survival in patients with cervical cancer[J/OL]. Eur J Surg Oncol, 2024, 50(10): 108583 [2025-08-07]. https://doi.org/10.1016/j.ejso.2024.108583. DOI: 10.1016/j.ejso.2024.108583.
[39]
ZHANG Y, LIU L, ZHANG K Y, et al. Nomograms combining clinical and imaging parameters to predict recurrence and disease-free survival after concurrent chemoradiotherapy in patients with locally advanced cervical cancer[J]. Acad Radiol, 2023, 30(3): 499-508. DOI: 10.1016/j.acra.2022.08.002.
[40]
ZHANG Y, ZHANG K Y, JIA H D, et al. IVIM-DWI and MRI-based radiomics in cervical cancer: Prediction of concurrent chemoradiotherapy sensitivity in combination with clinical prognostic factors[J]. Magn Reson Imaging, 2022, 91: 37-44. DOI: 10.1016/j.mri.2022.05.005.
[41]
WANG M D, PERUCHO J A U, VARDHANABHUTI V, et al. Radiomic features of T2-weighted imaging and diffusion kurtosis imaging in differentiating clinicopathological characteristics of cervical carcinoma[J]. Acad Radiol, 2022, 29(8): 1133-1140. DOI: 10.1016/j.acra.2021.08.018.
[42]
ZHANG Q, YU X D, OUYANG H, et al. Whole-tumor texture model based on diffusion kurtosis imaging for assessing cervical cancer: a preliminary study[J]. Eur Radiol, 2021, 31(8): 5576-5585. DOI: 10.1007/s00330-020-07612-z.
[43]
XIAO M L, FU L, QIAN T, et al. The deep learning radiomics nomogram helps to evaluate the lymph node status in cervical adenocarcinoma/adenosquamous carcinoma[J/OL]. Front Oncol, 2024, 14: 1414609 [2025-08-07]. https://doi.org/10.3389/fonc.2024.1414609. DOI: 10.3389/fonc.2024.1414609.
[44]
QIAN W L, LI Z S, CHEN W D, et al. RESOLVE-DWI-based deep learning nomogram for prediction of normal-sized lymph node metastasis in cervical cancer: a preliminary study[J/OL]. BMC Med Imaging, 2022, 22(1): 221 [2025-08-07]. https://doi.org/10.1186/s12880-022-00948-6. DOI: 10.1186/s12880-022-00948-6.
[45]
AOUADI S, TORFEH T, BOUHALI O, et al. Prediction of cervix cancer stage and grade from diffusion weighted imaging using EfficientNet[J/OL]. Biomed Phys Eng Express, 2024, 10(4) [2025-08-07]. https://doi.org/10.1088/2057-1976/ad5207.. DOI: 10.1088/2057-1976/ad5207.
[46]
XIAO M L, QIAN T, FU L, et al. Deep learning nomogram for the identification of deep stromal invasion in patients with early-stage cervical adenocarcinoma and adenosquamous carcinoma: a multicenter study[J]. J Magn Reson Imaging, 2024, 59(4): 1394-1406. DOI: 10.1002/jmri.28882.
[47]
ZHANG Y J, WU C, XIAO Z B, et al. A deep learning radiomics nomogram to predict response to neoadjuvant chemotherapy for locally advanced cervical cancer: a two-center study[J/OL]. Diagnostics (Basel), 2023, 13(6): 1073 [2025-08-07]. https://doi.org/10.3390/diagnostics13061073. DOI: 10.3390/diagnostics13061073.
[48]
ZHANG Y J, WU C, DU J L, et al. Prediction of recurrence risk factors in patients with early-stage cervical cancers by nomogram based on MRI handcrafted radiomics features and deep learning features: a dual-center study[J]. Abdom Radiol (NY), 2024, 49(1): 258-270. DOI: 10.1007/s00261-023-04125-3.
[49]
KOÇAK B, PONSIGLIONE A, STANZIONE A, et al. Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects[J]. Diagn Interv Radiol, 2025, 31(2): 75-88. DOI: 10.4274/dir.2024.242854.
[50]
LEE T, LEE J H, YOON S H, et al. Availability and transparency of artificial intelligence models in radiology: a meta-research study[J]. Eur Radiol, 2025, 35(9): 5287-5298. DOI: 10.1007/s00330-025-11492-6.

PREV Advances in predicting HER-2 expression status in breast cancer using magnetic resonance imaging
NEXT Recent advances in brown adipose tissue imaging using magnetic resonance techniques and their emerging clinical applications
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn