Research progress of magnetic resonance imaging combined with artificial intelligence in the precision diagnosis and treatment of cervical cancer

Share this content in WeChat

[Chinese] [PDF] 5 1

• Reviews •

KONG Qiqi FENG Yuze BAN Yunqing

Cite this article as: KONG Q Q, FENG Y Z, BAN Y Q. Research progress of magnetic resonance imaging combined with artificial intelligence in the precision diagnosis and treatment of cervical cancer[J]. Chin J Magn Reson Imaging, 2026, 17(3): 201-205, 234. DOI:10.12015/issn.1674-8034.2026.03.029.

Abstract

[Abstract] Precision diagnosis and therapy for cervical cancer, a major global public health challenge, are hindered by tumor heterogeneity and the limitations of conventional assessment methods. The integration of artificial intelligence (AI) with multi-parametric MRI (mp-MRI) provides a new paradigm for non-invasively assessing tumor pathophysiology. Research in this field has established an AI-driven, hierarchical technical framework spanning from anatomical localization to molecular characterization: At the anatomical level, the introduction of novel architectures such as Transformer and state space models (SSM) has overcome the receptive field limitations of convolutional neural networks (CNN), achieving precise lesion segmentation within complex pelvic anatomical backgrounds. At the functional level, AI optimizes the parameter fitting models of intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), and dynamic contrast-enhanced MRI (DCE-MRI) via deep neural networks (DNN), significantly enhancing the robustness of quantitative parameters. Furthermore, it utilizes habitat analysis techniques to quantify intra-tumoral microscopic heterogeneity for predicting lymph node metastasis (LNM) and lymphovascular space invasion (LVSI). At the molecular level, radiomics and radiogenomics leverage machine learning to deeply mine high-dimensional imaging features, establishing non-linear mappings between imaging phenotypes and molecular characteristics such as gene mutations and the immune microenvironment. Additionally, the integration of circulating tumor DNA (ctDNA) data facilitates the formation of a multi-modal "imaging biopsy" paradigm. This AI-empowered three-stage system (segmentation–functional analysis-molecular decoding) connects the entire chain of precision diagnosis and treatment for cervical cancer. However, the clinical translation of this system is still limited by systemic challenges such as inadequate data standardization, limited model generalizability, and poor interpretability. This article systematically reviews these advancements, deeply analyzes technical principles, clinical values, and practical dilemmas, aiming to provide a forward-looking perspective for promoting this technology towards clinically-oriented individualized precision medicine.

[Keywords] cervical cancer；deep learning；molecular biomarkers；magnetic resonance imaging；radiomics；precision medicine；review

Contributor Information

KONG Qiqi¹ FENG Yuze² BAN Yunqing^1*

¹ Department of CT/MRI, The Fifth Affiliated Hospital of Xinjiang Medical University, Urumqi 830000, China

² Department of Rehabilitation Medicine, The Fifth Affiliated Hospital of Xinjiang Medical University, Urumqi 830000, China

Corresponding author: BAN Y Q, E-mail: banyq_5@163.com

Conflicts of interest None.

Publication Information

Received 2025-09-29

Accepted 2026-01-15

DOI: 10.12015/issn.1674-8034.2026.03.029

Text

References

[1]

BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.

[2]

HAN B F, ZHENG R S, ZENG H M, et al. Cancer incidence and mortality in China, 2022[J]. J Natl Cancer Cent, 2024, 4(1): 47-53. DOI: 10.1016/j.jncc.2024.01.006.

[3]

KIDO A, NAKAMOTO Y. Implications of the new FIGO staging and the role of imaging in cervical cancer[J/OL]. Br J Radiol, 2021, 94(1125): 20201342 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/33989030/. DOI: 10.1259/bjr.20201342.

[4]

RAMÓN Y CAJAL S, SESÉ M, CAPDEVILA C, et al. Clinical implications of intratumor heterogeneity: challenges and opportunities[J]. J Mol Med (Berl), 2020, 98(2): 161-177. DOI: 10.1007/s00109-020-01874-2.

[5]

LIU B, GAO H, ZHOU F, et al. Dynamic contrast-enhanced magnetic resonance imaging in cervical cancer: correlation between quantitative parameters and molecular markers hypoxia-inducible factors-1-alpha, vascular endothelial growth factor, and Ki-67[J/OL]. Clin Radiol, 2024, 79(6): e826-e833 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/38582634/. DOI: 10.1016/j.crad.2024.01.039.

[6]

HARRY V N, PERSAD S, BASSAW B, et al. Diffusion-weighted MRI to detect early response to chemoradiation in cervical cancer: a systematic review and meta-analysis[J/OL]. Gynecol Oncol Rep, 2021, 38: 100883 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/38582634/. DOI: 10.1016/j.gore.2021.100883.

[7]

HALLE M K, HODNELAND E, WAGNER-LARSEN K S, et al. Radiomic profiles improve prognostication and reveal targets for therapy in cervical cancer[J/OL]. Sci Rep, 2024, 14(1): 11339 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/38760387/. DOI: 10.1038/s41598-024-61271-4.

[8]

HORVAT N, PAPANIKOLAOU N, KOH D M. Radiomics beyond the hype: a critical evaluation toward oncologic clinical use[J/OL]. Radiol Artif Intell, 2024, 6(4): e230437 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/38717290/. DOI: 10.1148/ryai.230437.

[9]

FUSCO R, GRANATA V, GRAZZINI G, et al. Radiomics in medical imaging: pitfalls and challenges in clinical management[J]. Jpn J Radiol, 2022, 40(9): 919-929. DOI: 10.1007/s11604-022-01271-4.

[10]

LEUNG S N, CHANDRA S S, LIM K, et al. Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations[J]. Phys Eng Sci Med, 2024, 47(3): 919-928. DOI: 10.1007/s13246-024-01415-y.

[11]

MATOSKA T, PATEL M, LIU H F, et al. Review of deep learning based autosegmentation for clinical target volume: current status and future directions[J/OL]. Adv Radiat Oncol, 2024, 9(5): 101470 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/38550365/. DOI: 10.1016/j.adro.2024.101470.

[12]

KALANTAR R, CURCEAN S, WINFIELD J M, et al. Deep learning framework with multi-head dilated encoders for enhanced segmentation of cervical cancer on multiparametric magnetic resonance imaging[J/OL]. Diagnostics (Basel), 2023, 13(21): 3381 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/37958277/. DOI: 10.3390/diagnostics13213381.

[13]

CHUNG S Y, CHANG J S, KIM Y B. Comprehensive clinical evaluation of deep learning-based auto-segmentation for radiotherapy in patients with cervical cancer[J/OL]. Front Oncol, 2023, 13: 1119008 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/37188180/. DOI: 10.3389/fonc.2023.1119008.

[14]

MA C Y, ZHOU J Y, XU X T, et al. Deep learning-based auto-segmentation of clinical target volumes for radiotherapy treatment of cervical cancer[J/OL]. J Appl Clin Med Phys, 2022, 23(2): e13470 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/34807501/. DOI: 10.1002/acm2.13470.

[15]

QAMAR S, FAZIL M, AHMAD P, et al. UNet with self-adaptive Mamba-like attention and causal-resonance learning for medical image segmentation[J/OL]. Sci Rep, 2025, 16(1): 135 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/41339647/. DOI: 10.1038/s41598-025-28885-8.

[16]

RUAN J C, LI J C, XIANG S C. VM-UNet: vision mamba UNet for medical image segmentation[J/OL]. ACM Trans Multimedia Comput Commun Appl, 2025: 3767748 [2025-09-28]. https://dl.acm.org/doi/10.1145/3767748. DOI: 10.1145/3767748.

[17]

ZHU S T, LIN L, LIU Q, et al. Integrating a deep neural network and Transformer architecture for the automatic segmentation and survival prediction in cervical cancer[J]. Quant Imaging Med Surg, 2024, 14(8): 5408-5419. DOI: 10.21037/qims-24-560.

[18]

WANG B, ZHANG Y Y, WU C Y, et al. Multimodal MRI analysis of cervical cancer on the basis of artificial intelligence algorithm[J/OL]. Contrast Medium Mol Imag, 2021, 2021: 1673490 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/34858113/. DOI: 10.1155/2021/1673490.

[19]

LIN Y C, LIN Y, HUANG Y L, et al. Generalizable transfer learning of automated tumor segmentation from cervical cancers toward a universal model for uterine malignancies in diffusion-weighted MRI[J/OL]. Insights Imaging, 2023, 14(1): 14 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/36690870/. DOI: 10.1186/s13244-022-01356-8.

[20]

WANG X, SONG J, ZHOU S F, et al. A comparative study of methods for determining Intravoxel incoherent motion parameters in cervix cancer[J/OL]. Cancer Imaging, 2021, 21(1): 12 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/33446273/. DOI: 10.1186/s40644-020-00377-0.

[21]

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.

[22]

HOU M Y, SONG K, REN J P, et al. Comparative analysis of the value of amide proton transfer-weighted imaging and diffusion kurtosis imaging in evaluating the histological grade of cervical squamous carcinoma[J/OL]. BMC Cancer, 2022, 22(1): 87 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/35057777/. DOI: 10.1186/s12885-022-09205-z.

[23]

YANG C S, TAN Z Y, WANG Y J, et al. SwinUNeCCt: bidirectional hash-based agent transformer for cervical cancer MRI image multi-task learning[J/OL]. Sci Rep, 2024, 14: 24621 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/39427015/. DOI: 10.1038/s41598-024-75544-5.

[24]

XIA S J, ZHAO B, LI Y M, et al. Cer-ConvN3Unet: an end-to-end multi-parametric MRI-based pipeline for automated detection and segmentation of cervical cancer[J/OL]. Eur Radiol Exp, 2025, 9(1): 20 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/39966210/. DOI: 10.1186/s41747-025-00557-2.

[25]

WANG X, LI S J, LIN X H, et al. Evaluation of tracer kinetic parameters in cervical cancer using dynamic contrast-enhanced MRI as biomarkers in terms of biological relevance, diagnostic performance and inter-center variability[J/OL]. Front Oncol, 2022, 12: 958219 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/36324571/. DOI: 10.3389/fonc.2022.958219.

[26]

WANG W P, YANG G, LIU Y L, et al. Multimodal deep learning model for prognostic prediction in cervical cancer receiving definitive radiotherapy: a multi-center study[J/OL]. NPJ Digit Med, 2025, 8(1): 503 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/40760164/. DOI: 10.1038/s41746-025-01903-9.

[27]

LI J, LI Y T, DU L Z, et al. Amide proton transfer-weighted habitat radiomics: a superior approach for preoperative prediction of lymphovascular space invasion in cervical cancer[J/OL]. Front Oncol, 2025, 15: 1599522 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/40708939/. DOI: 10.3389/fonc.2025.1599522.

[28]

SONG Q L, TIAN S F, MA C J, et al. Amide proton transfer weighted imaging combined with dynamic contrast-enhanced MRI in predicting lymphovascular space invasion and deep stromal invasion of IB1-IIA1 cervical cancer[J/OL]. Front Oncol, 2022, 12: 916846 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/36172148/. DOI: 10.3389/fonc.2022.916846.

[29]

LUO S G, GUO Y, YE Y Q, et al. Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study[J/OL]. Sci Rep, 2025, 15(1): 29259 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/40784909/. DOI: 10.1038/s41598-025-13781-y.

[30]

LIU F H, ZHAO X R, ZHANG X L, et al. Multiparametric MRI-based radiomics nomogram for predicting lymph-vascular space invasion in cervical cancer[J/OL]. BMC Med Imaging, 2024, 24(1): 167 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/38969972/. DOI: 10.1186/s12880-024-01344-y.

[31]

GUO Y S, LI T X, GONG B X, et al. From images to genes: radiogenomics based on artificial intelligence to achieve non-invasive precision medicine in cancer patients[J/OL]. Adv Sci (Weinh), 2025, 12(2): e2408069 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/39535476/. DOI: 10.1002/advs.202408069.

[32]

HE W L, HUANG W H, ZHANG L, et al. Radiogenomics: bridging the gap between imaging and genomics for precision oncology[J/OL]. MedComm, 2024, 5(9): e722 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/39252824/. DOI: 10.1002/mco2.722.

[33]

TIAN Y, LI X, ZHANG H, et al. Comparing deep learning and handcrafted radiomics to predict chemoradiotherapy response for locally advanced cervical cancer using pretreatment MRI[J]. Sci Rep, 2024, 14: 1045 . DOI: 10.1038/s41598-024-51742-z.

[34]

LIU K H, YANG W, TIAN H P, et al. Nomogram based on clinical, pathological, and DWI quantitative parameters for predicting the programmed death-ligand 1 positive expression in cervical cancer: Comparison of different ROI options[J]. Chin J Magn Reson Imag, 2023, 14(10): 98-104, 115 . DOI: 10.12015/issn.1674-8034.2023.10.017.

[35]

ZHANG R, JIANG C F, LI F, et al. Preoperative MRI-based radiomics analysis of intra- and peritumoral regions for predicting CD3 expression in early cervical cancer[J/OL]. Sci Rep, 2025, 15(1): 26754 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/40702236/. DOI: 10.1038/s41598-025-12162-9.

[36]

GENNARINI M, CANESE R, CAPUANI S, et al. Multi-model quantitative MRI of uterine cancers in precision medicine's era: a narrative review[J/OL]. Insights Imag, 2025, 16(1): 113 [2025-09-28]. https://pubmed.ncbi.nlm.nih.gov/40437300/. DOI: 10.1186/s13244-025-01965-z.

[37]

MAYADEV J, VÁZQUEZ LIMÓN J C, RAMÍREZ GODINEZ F J, et al. Ultrasensitive detection and tracking of circulating tumor DNA to predict relapse and survival in patients with locally advanced cervical cancer: phase III CALLA trial analyses[J]. Ann Oncol, 2025, 36(9): 1047-1057 . DOI: 10.1016/j.annonc.2025.05.533.

[38]

SU Y, ZENG K J, YAN Z H, et al. Predicting the Ki-67 proliferation index in cervical cancer: a preliminary comparative study of four non-Gaussian diffusion-weighted imaging models combined with histogram analysis[J]. Quant Imaging Med Surg, 2024, 14(10): 7484-7495 . DOI: 10.21037/qims-24-576.

PREV Research progress on 4D Flow CMR in evaluating myocardial infarction

NEXT Research progress on the application of T1 mapping and T2 mapping technology in gynecological malignant tumors

LINK

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