Share：
Share this content in WeChat
X
[Chinese] [PDF] 60 1
• Review •
Research progress on preoperative prediction of endometrial carcinoma molecular subtypes based on MRI radiomics and deep learning
ZHANG Xuxia  TANG Zhongfeng  DENG Lin  ZHAI Xiaojing  SUN Bixia  CAO Shan  ZHU Dalin  ZHANG Shipeng  QIAN Jifang 

DOI:10.12015/issn.1674-8034.2026.07.027.


[Abstract] The incidence of endometrial carcinoma (EC) continues to rise with a younger onset trend. Molecular typing serves as the core basis for precise diagnosis, individualized treatment and prognostic evaluation of EC and has been included in authoritative clinical guidelines. Conventional invasive biopsy is constrained by limited sampling coverage and clinical contraindications, making it incapable of achieving comprehensive and non-invasive evaluation of the integral molecular characteristics of tumors. As the essential preoperative imaging modality for EC, magnetic resonance imaging (MRI), in combination with radiomics and deep learning technologies, can excavate high-order subtle imaging features that are unrecognizable to the naked eye and establish non-invasive associations between imaging phenotypes and tumor molecular pathologies, thereby providing a novel pathway for preoperative molecular typing. This article systematically reviews recent frontier studies worldwide, summarizes the application progress of MRI-based artificial intelligence technologies in the preoperative prediction of four molecular subtypes of EC, compares the diagnostic performance and application advantages of traditional radiomics, deep learning and multimodal fusion models, and analyzes the underlying imaging-pathological correlation mechanisms of different subtypes. Nevertheless, current research still has prominent deficiencies. Most existing studies are single-center and retrospective, with a lack of unified standardized protocols, resulting in insufficient repeatability and generalizability of predictive models. Moreover, the poor interpretability of artificial intelligence models greatly impedes clinical transformation and practical application. By overviewing existing research findings and unresolved limitations, this review prospects future research directions involving multicenter prospective studies, explainable artificial intelligence and multidimensional model fusion, aiming to provide a reference for the clinical translation of non-invasive preoperative molecular typing and precision diagnosis and treatment of EC.
[Keywords] endometrial carcinoma；microsatellite instability；p53 abnormal；magnetic resonance imaging；radiomics；deep learning

ZHANG Xuxia1   TANG Zhongfeng2   DENG Lin2   ZHAI Xiaojing1   SUN Bixia1   CAO Shan1   ZHU Dalin1   ZHANG Shipeng1   QIAN Jifang1*  

1 Medical Imaging Center of Gansu Provincial Central Hospital (Gansu Provincial Maternity and Child-care Hospital), Lanzhou 730000, China

2 Prenatal Diagnosis Center of Gansu Provincial Central Hospital (Gansu Provincial Maternity and Child-care Hospital), Lanzhou 730000, China

Corresponding author: QIAN J F, E-mail: 495248996@qq.com

Conflicts of interest   None.

Received  2026-01-26
Accepted  2026-06-22
DOI: 10.12015/issn.1674-8034.2026.07.027
DOI:10.12015/issn.1674-8034.2026.07.027.

[1]
LI J Y, ZHAO X Y, LI X M, et al. Analysis of the disease burden of malignancies in the female reproductive system in China from 1990 to 2019: an age-period-cohort study and joinpoint analysis[J/OL]. BMJ Open, 2025, 15(4): e081511[2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12049911/. DOI: 10.1136/bmjopen-2023-081511.
[2]
YAN Y, WANG Y M, WANG Y D, et al. Incidence and mortality of endometrial cancer in China, data from China Cancer Registry Annual Report, 2004-2017[J]. Natl Med J China, 2024, 104(10): 721-728. DOI: 10.3760/cma.j.cn112137-20231017-00784.
[3]
WANG M H, HUI P. A timely update of immunohistochemistry and molecular classification in the diagnosis and risk assessment of endometrial carcinomas[J]. Arch Pathol Lab Med, 2021, 145(11): 1367-1378. DOI: 10.5858/arpa.2021-0098-RA.
[4]
KUMARI A, KUMAR H, HARVEY S E, et al. Molecular classification of endometrial carcinomas: Review and recent updates[J/OL]. Cancers, 2025, 18(1): 51 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12785015/. DOI: 10.3390/cancers18010051.
[5]
CONCIN N, MATIAS-GUIU X, CIBULA D, et al. ESGO-ESTRO-ESP guidelines for the management of patients with endometrial carcinoma: update 2025[J/OL]. Lancet Oncol, 2025, 26(8): e423-e435 [2026-05-04]. https://www.sciencedirect.com/science/article/abs/pii/S1470204525001676. DOI: 10.1016/S1470-2045(25)00167-6.
[6]
KOSKAS M, CROSBIE E J, FOKDAL L, et al. Cancer of the corpus uteri: A 2025 update[J]. Int J Gynecol Obstet, 2025, 171(S1): 60-77. DOI: 10.1002/ijgo.70326.
[7]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[8]
GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: Images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[9]
ZHANG Z Y, KELES E, DURAK G, et al. Large-scale multi-center CT and MRI segmentation of pancreas with deep learning[J/OL]. Med Image Anal, 2025, 99: 103382 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11698238/. DOI: 10.1016/j.media.2024.103382.
[10]
SHIA W C. Deep learning-based classification of benign and malignant breast microcalcifications in mammography[J/OL]. Sci Rep, 2025, 15(1): 42768 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12663291/. DOI: 10.1038/s41598-025-27149-9.
[11]
WANG Y L, LOMBARDO E, HUANG L L, et al. Comparison of deep learning networks for fully automated head and neck tumor delineation on multi-centric PET/CT images[J/OL]. Radiat Oncol, 2024, 19(1): 3 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10773015/. DOI: 10.1186/s13014-023-02388-0.
[12]
XIA T Y, ZHOU Z H, MENG X P, et al. Predicting microvascular invasion in hepatocellular carcinoma using CT-based radiomics model[J/OL]. Radiology, 2023, 307(4): e222729[2026-05-04]. https://pubs.rsna.org/doi/abs/10.1148/radiol.222729. DOI: 10.1148/radiol.222729.
[13]
PAN Y J, WU S J, ZENG Y, et al. Intra- and peri-tumoral radiomics based on dynamic contrast enhanced-MRI to identify lymph node metastasis and prognosis in intrahepatic cholangiocarcinoma[J]. Magnetic Resonance Imaging, 2024, 60(6): 2669-2680. DOI: 10.1002/jmri.29390.
[14]
SHI Z W, HUANG X M, CHENG Z L, et al. MRI-based quantification of intratumoral heterogeneity for predicting treatment response to neoadjuvant chemotherapy in breast cancer[J/OL]. Radiology, 2023, 308(1): e222830[2026-05-04]. https://pubmed.ncbi.nlm.nih.gov/37432083/. DOI: 10.1148/radiol.222830.
[15]
PEREZ-JOHNSTON R, ARAUJO-FILHO J A, CONNOLLY J G, et al. CT-based radiogenomic analysis of clinical stage I lung adenocarcinoma with histopathologic features and oncologic outcomes[J]. Radiology, 2022, 303(3): 664-672. DOI: 10.1148/radiol.211582.
[16]
GUI Y, HU W, REN J L, et al. Preoperative diagnosis of meningioma sinus invasion based on MRI radiomics and deep learning: a multicenter study[J/OL]. Cancer Imaging, 2025, 25(1): 20 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11869444/. DOI: 10.1186/s40644-025-00845-5.
[17]
REN Q P, ZHANG X, WU X W, et al. Pathology-interpretable radiomic model for predicting clinical outcome in patients with osteosarcoma: a retrospective, multicenter study[J/OL]. BMC Med, 2025, 23(1): 594 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12573972/. DOI: 10.1186/s12916-025-04424-0.
[18]
LIN Z J, GU W Y, GUO Q H, et al. Multisequence MRI-based radiomics model for predicting POLE mutation status in patients with endometrial cancer[J/OL]. Br J Radiol, 2023, 96(1151): 20221063 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10607390/. DOI: 10.1259/bjr.20221063.
[19]
ZHOU J, YU X, CUI Y Y, et al. Prediction of molecular subtypes of endometrial cancer patients on the basis of intratumoral and peritumoral radiomic features from multiparametric MR images[J/OL]. Eur J Radiol, 2025, 187: 112110 [2026-05-04]. https://pubmed.ncbi.nlm.nih.gov/40262460/. DOI: 10.1016/j.ejrad.2025.112110.
[20]
YUE W Y, HAN R X, WANG H J, et al. Development and validation of clinical-radiomics deep learning model based on MRI for endometrial cancer molecular subtypes classification[J/OL]. Insights Imaging, 2025, 16(1): 107 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12084453/. DOI: 10.1186/s13244-025-01966-y.
[21]
CONCIN N, MATIAS-GUIU X, VERGOTE I, et al. ESGO/ESTRO/ESP guidelines for the management of patients with endometrial carcinoma[J]. Int J Gynecol Cancer, 2021, 31(1): 12-39. DOI: 10.1136/ijgc-2020-002230.
[22]
CHUNG Y S, WOO H Y, LEE J Y, et al. Mismatch repair status influences response to fertility-sparing treatment of endometrial cancer[J/OL]. Am J Obstet Gynecol, 2021, 224(4): 370.e1-370.e13 [2026-05-04]. https://www.sciencedirect.com/science/article/abs/pii/S0002937820311753. DOI: 10.1016/j.ajog.2020.10.003.
[23]
RIEDINGER C J, ESNAKULA A, HAIGHT P J, et al. Characterization of mismatch-repair/microsatellite instability-discordant endometrial cancers[J]. Cancer, 2024, 130(3): 385-399. DOI: 10.1002/cncr.35030.
[24]
PETERS I, MARCHETTI C, SCAMBIA G, et al. New windows of surgical opportunity for gynecological cancers in the era of targeted therapies[J]. Int J Gynecol Cancer, 2024, 34(3): 352-362. DOI: 10.1136/ijgc-2023-004580.
[25]
ZHAO J, YANG F, REN J P, et al. Value of diffusion-weighted imaging radiomics model in the prediction of microsatellite instability in endometrial cancer: A comparative study with ADC[J]. Radiol Pract, 2024, 39(8): 1067-1071. DOI: 10.13609/j.cnki.1000-0313.2024.08.013.
[26]
ZHAO J F, TIAN Y, MA M M, et al. Application research of imaging genomics in preoperative prediction of microsatellite stability of endometrial cancer using mp-MRI[J]. Chin J Magn Reson Imaging, 2024, 15(11): 110-116, 122. DOI: 10.12015/issn.1674-8034.2024.11.017.
[27]
WANG J, SONG P J, ZHANG M, et al. A prediction model based on deep learning and radiomics features of DWI for the assessment of microsatellite instability in endometrial cancer[J/OL]. Cancer Med, 2024, 13(16): e70046[2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11339853/. DOI: 10.1002/cam4.70046.
[28]
WANG Z C, HU Y, CAI J, et al. Potential value of novel multiparametric MRI radiomics for preoperative prediction of microsatellite instability and Ki-67 expression in endometrial cancer[J/OL]. Sci Rep, 2025, 15: 3226 [2026-05-04]. https://pubmed.ncbi.nlm.nih.gov/39863695/. DOI: 10.1038/s41598-025-87966-w.
[29]
ZHOU L L, ZHENG L Y, HONG C C, et al. A novel model for predicting microsatellite instability in endometrial cancer: Integrating deep learning-pathomics and MRI-based radiomics[J]. Acad Radiol, 2025, 32(10): 5940-5950. DOI: 10.1016/j.acra.2025.07.050.
[30]
TIAN C H, SUN P, XIAO K Y, et al. Voxel-level radiomics and deep learning based on MRI for predicting microsatellite instability in endometrial carcinoma: A two-center study[J]. Acad Radiol, 2025, 32(12): 7281-7293. DOI: 10.1016/j.acra.2025.08.028.
[31]
XU B L, MAIMAITIJIANG A, NUERBIYAMU D, et al. The multifaceted role of p53 in cancer molecular biology: Insights for precision diagnosis and therapeutic breakthroughs[J/OL]. Biomolecules, 2025, 15(8): 1088 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12383685/. DOI: 10.3390/biom15081088.
[32]
ZHANG B H, ZHANG H Z, QIN Y R. A primer on the role of TP53 mutation and targeted therapy in endometrial cancer[J/OL]. Front Biosci (Landmark Ed), 2025, 30(1): 25447 [2026-05-04]. https://www.imrpress.com/journal/FBL/30/1/10.31083/FBL25447. DOI: 10.31083/FBL25447.
[33]
ZHU K L, SU F, YANG J R, et al. TP53 to mediate immune escape in tumor microenvironment: an overview of the research progress[J/OL]. Mol Biol Rep, 2024, 51(1): 205 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10811008/. DOI: 10.1007/s11033-023-09097-7.
[34]
THIEL K W, DEVOR E J, FILIACI V L, et al. TP53 sequencing and p53 immunohistochemistry predict outcomes when bevacizumab is added to frontline chemotherapy in endometrial cancer: An NRG oncology/gynecologic oncology group study[J]. J Clin Oncol, 2022, 40(28): 3289-3300. DOI: 10.1200/JCO.21.02506.
[35]
TRAVAGLINO A, RAFFONE A, RAIMONDO D, et al. Prognostic value of the TCGA molecular classification in uterine carcinosarcoma[J]. Int J Gynaecol Obstet, 2022, 158(1): 13-20. DOI: 10.1002/ijgo.13937.
[36]
JAMIESON A, THOMPSON E F, HUVILA J, et al. p53abn Endometrial Cancer: understanding the most aggressive endometrial cancers in the era of molecular classification[J]. Int J Gynecol Cancer, 2021, 31(6): 907-913. DOI: 10.1136/ijgc-2020-002256.
[37]
MARTIN S D, THORNTON S, CHOW C, et al. Activated immune infiltrates expand opportunities for targeted therapy in p53-abnormal endometrial carcinoma[J]. J Pathol, 2025, 266(3): 292-305. DOI: 10.1002/path.6429.
[38]
ARCIUOLO D, TRAVAGLINO A, RAFFONE A, et al. TCGA molecular prognostic groups of endometrial carcinoma: Current knowledge and future perspectives[J/OL]. Int J Mol Sci, 2022, 23(19): 11684 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9569906/. DOI: 10.3390/ijms231911684.
[39]
CUI T T, GUO J S, REN J, et al. Early dynamic enhanced MRI-based radiomics model for predicting p53abn type endometrial cancer[J]. J Clin Radiol, 2025, 44(6): 1047-1051. DOI: 10.13437/j.cnki.jcr.2025.06.009.
[40]
NING Y, LIU W, WANG H J, et al. Determination of p53abn endometrial cancer: a multitask analysis using radiological-clinical nomogram on MRI[J]. Br J Radiol, 2024, 97(1157): 954-963. DOI: 10.1093/bjr/tqae066.
[41]
ZHANG H, YANG Y Z, HE J H, et al. Prediction of p53 mutation in endometrial carcinoma based on radiomics nomogram of intratumoral and peritumoral MRI[J]. Chin J Med Imaging, 2025, 33(5): 553-559. DOI: 10.3969/j.issn.1005-5185.2025.05.018.
[42]
CHO H H, KIM H, NAM S Y, et al. Measurement of perfusion heterogeneity within tumor habitats on magnetic resonance imaging and its association with prognosis in breast cancer patients[J/OL]. Cancers, 2022, 14(8): 1858 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9025287/. DOI: 10.3390/cancers14081858.
[43]
YANG Y, HAN Y, ZHAO S J, et al. Spatial heterogeneity of edema region uncovers survival-relevant habitat of Glioblastoma[J/OL]. Eur J Radiol, 2022, 154: 110423 [2026-05-04]. https://www.ejradiology.com/article/S0720-048X(22)00273-X/abstract. DOI: 10.1016/j.ejrad.2022.110423.
[44]
BRAMAN N, PRASANNA P, WHITNEY J, et al. Association of peritumoral radiomics with tumor biology and pathologic response to preoperative targeted therapy for HER2 (ERBB2)-positive breast cancer[J/OL]. JAMA Netw Open, 2019, 2(4): e192561[2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC6481453/. DOI: 10.1001/jamanetworkopen.2019.2561.
[45]
PENG Q H, ZHOU S M, CHEN R Z, et al. CT-based habitat radiomics combining multi-instance learning for early prediction of post-neoadjuvant lymph node metastasis in esophageal squamous cell carcinoma[J/OL]. Bioengineering (Basel), 2025, 12(8): 813 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC12383342/. DOI: 10.3390/bioengineering12080813.
[46]
MANDAIR D, REIS-FILHO J S, ASHWORTH A. Biological insights and novel biomarker discovery through deep learning approaches in breast cancer histopathology[J/OL]. NPJ Breast Cancer, 2023, 9(1): 21 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10079681/. DOI: 10.1038/s41523-023-00518-1.
[47]
CHEN Z K, WANG X C. Research progress of magnetic resonance habitat imaging in the prognosis of malignant tumors[J]. Chin J Magn Reson Imaging, 2025, 16(2): 222-228. DOI: 10.12015/issn.1674-8034.2025.02.036.
[48]
KONG L M, QIN Y J, LI H, et al. Development and validation of a PreoperativeMRIHabitat radiomics model to predict variant histology in bladder cancer[J]. Magnetic Resonance Imaging, 2025, 62(6): 1698-1710. DOI: 10.1002/jmri.70069.
[49]
JIN W T, WANG T P, CHEN X J, et al. MRI-based habitat radiomics analysis for identifying molecular subtypes of endometrial cancer: a feasible study from two institutions[J]. Fudan Univ J Med Sci, 2024, 51(6): 890-899. DOI: 10.3969/j.issn.1672-8467.2024.06.003.
[50]
SHEN L, DAI B, DOU S W, et al. Estimation of TP53 mutations for endometrial cancer based on diffusion-weighted imaging deep learning and radiomics features[J/OL]. BMC Cancer, 2025, 25(1): 45 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11715916/. DOI: 10.1186/s12885-025-13424-5.
[51]
ANCA-STANCIU M B, MANU A, OLINCA M V, et al. Comprehensive review of endometrial cancer: new molecular and FIGO classification and recent treatment changes[J/OL]. J Clin Med, 2025, 14(4): 1385 [2026-05-04]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11856752/. DOI: 10.3390/jcm14041385.

PREV Research progress on radiomics-based precise subtyping and risk stratification of intrahepatic cholangiocarcinoma
NEXT Research progress of magnetic resonance elastography in uterine tumors
  


LINK


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