Share：
Share this content in WeChat
X
[Chinese] [PDF] 178 8
• Review •
Research progress on multimodal MRI and radiomics for assessing tumor budding in rectal cancer
ZHANG Xiaoyan  LIU Nianjun  ZHANG Yiming  QIAO Miaomiao  GUO Shunlin 

DOI:10.12015/issn.1674-8034.2025.08.033.


[Abstract] Colorectal cancer (CRC), as one of the most prevalent malignant tumors in China, poses a serious threat to patients' health and survival. Tumor budding (TB) serves as a crucial pathological indicator for evaluating prognosis in rectal cancer patients. However, traditional pathological assessment relies on invasive biopsies and suffers from limitations including strong subjectivity and inability to obtain preoperative evaluation. Multimodal MRI technology offers potential for noninvasive TB assessment by analyzing microenvironmental characteristics through combined anatomical and functional imaging, thereby compensating for the shortcomings of pathological methods. Nevertheless, challenges remain regarding parameter stability and limited image resolution. Research demonstrates that artificial intelligence technologies can overcome imaging analysis bottlenecks. For instance, radiomics improves diagnostic objectivity through high-throughput quantitative feature extraction, while deep learning enhances model performance via cross-modal fusion and adaptive learning mechanisms. However, current studies are still constrained by insufficient technical standardization, weak model generalizability, and lack of clinical validation. To date, there has been no systematic review comprehensively addressing these aspects. This review proposes that future efforts should focus on optimizing multimodal MRI technology, developing higher-performance models, and validating TB assessment systems through prospective multicenter clinical trials to guide individualized treatment decisions, ultimately achieving substantial progress from scientific innovation to routine clinical application.
[Keywords] rectal cancer；tumor budding；radiomics；magnetic resonance imaging；deep learning

ZHANG Xiaoyan1   LIU Nianjun1, 2   ZHANG Yiming1   QIAO Miaomiao1   GUO Shunlin2*  

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: GUO S L, E-mail: guoshunlin@msn.com

Conflicts of interest   None.

Received  2025-05-02
Accepted  2025-07-07
DOI: 10.12015/issn.1674-8034.2025.08.033
DOI:10.12015/issn.1674-8034.2025.08.033.

[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]
CHEN H D, LU B, DAI M. Colorectal cancer screening in China: status, challenges, and prospects - China, 2022[J]. China CDC Wkly, 2022, 4(15): 322-328. DOI: 10.46234/ccdcw2022.077.
[3]
WANG Y X, PAN K F, LI W Q. Interpretation on the report of global cancer statistics 2022[J]. J Multidiscip Cancer Manag Electron Version, 2024, 10(3): 1-16. [2025-05-08]. http://www.jmcm2018.com/CN/10.12151/JMCM.2024.03-01.
[4]
ZHENG S S, SCHRIJVERS J J A, GREUTER M J W, et al. Effectiveness of colorectal cancer (CRC) screening on all-cause and CRC-specific mortality reduction: A systematic review and meta-analysis[J/OL]. Cancers (Basel), 2023, 15(7): 1948 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37046609/. DOI: 10.3390/cancers15071948.
[5]
KARJULA T, KEMI N, NISKAKANGAS A, et al. The prognostic role of tumor budding and tumor-stroma ratio in pulmonary metastasis of colorectal carcinoma[J]. Eur J Surg Oncol, 2023, 49(7): 1298-1306. DOI: 10.1016/j.ejso.2023.02.009.
[6]
EL AGY F, BARDAI S EL, BOUGUENOUCH L, et al. Prognostic impact of tumor budding on Moroccan colon cancer patients[J/OL]. Int J Surg Oncol, 2022, 2022: 9334570 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/35096426/. DOI: 10.1155/2022/9334570.
[7]
FRIDLAND S, CHOI J, NAM M, et al. Assessing tumor heterogeneity: integrating tissue and circulating tumor DNA (ctDNA) analysis in the era of immuno-oncology-blood TMB is not the same as tissue TMB[J/OL]. J Immunother Cancer, 2021, 9(8): e002551 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/34462324/. DOI: 10.1136/jitc-2021-002551.
[8]
LE TRAN N, WANG Y, NIE G Y. Podocalyxin in normal tissue and epithelial cancer[J/OL]. Cancers (Basel), 2021, 13(12): 2863 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/34201212/. DOI: 10.3390/cancers13122863.
[9]
YAMADERA M, SHINTO E, KAJIWARA Y, et al. Differential survival benefits of 5-fluorouracil-based adjuvant chemotherapy for patients with microsatellite-stable stage III colorectal cancer according to the tumor budding status: a retrospective analysis[J]. Dis Colon Rectum, 2019, 62(11): 1316-1325. DOI: 10.1097/DCR.0000000000001480.
[10]
WANG P P, DENG C L, WU B. Magnetic resonance imaging-based artificial intelligence model in rectal cancer[J]. World J Gastroenterol, 2021, 27(18): 2122-2130. DOI: 10.3748/wjg.v27.i18.2122.
[11]
BATES D D B, HOMSI M EL, CHANG K J, et al. MRI for rectal cancer: staging, mrCRM, EMVI, lymph node staging and post-treatment response[J]. Clin Colorectal Cancer, 2022, 21(1): 10-18. DOI: 10.1016/j.clcc.2021.10.007.
[12]
ZHANG L, JIN Z W, YANG F, et al. Added value of histogram analysis of intravoxel incoherent motion and diffusion kurtosis imaging for the evaluation of complete response to neoadjuvant therapy in locally advanced rectal cancer[J]. Eur Radiol, 2025, 35(3): 1669-1678. DOI: 10.1007/s00330-024-11081-z.
[13]
ZHOU M, CHEN M Y, LUO M F, et al. Pathological prognostic factors of rectal cancer based on diffusion-weighted imaging, intravoxel incoherent motion, and diffusion kurtosis imaging[J]. Eur Radiol, 2025, 35(2): 979-988. DOI: 10.1007/s00330-024-11025-7.
[14]
ZHU L P, ZHU Y M, DONG Y Y, et al. Application value of magnetic resonance IVIM in preoperative evaluation of tumor budding of rectal cancer[J]. Chin J CT MRI, 2025, 23(2): 175-177. DOI: 10.3969/j.issn.1672-5131.2025.02.054.
[15]
HUANG H Y, HAN L J, GUO J B, et al. Multiphase and multiparameter MRI-based radiomics for prediction of tumor response to neoadjuvant therapy in locally advanced rectal cancer[J/OL]. Radiat Oncol, 2023, 18(1): 179 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37907928/. DOI: 10.1186/s13014-023-02368-4.
[16]
LIU X R, ZHANG J, YI T, et al. Decoding tumor angiogenesis: pathways, mechanisms, and future directions in anti-cancer strategies[J/OL]. Biomark Res, 2025, 13(1): 62 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/40251641/. DOI: 10.1186/s40364-025-00779-x.
[17]
NAGY J A, CHANG S H, DVORAK A M, et al. Why are tumour blood vessels abnormal and why is it important to know?[J]. Br J Cancer, 2009, 100(6): 865-869. DOI: 10.1038/sj.bjc.6604929.
[18]
HUANG H M. Calculation of intravoxel incoherent motion parameter maps using a kernelized total difference-based method[J/OL]. NMR Biomed, 2024, 37(10): e5201 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/38863271/. DOI: 10.1002/nbm.5201.
[19]
IIMA M, HONDA M, SATAKE H, et al. Standardization and advancements efforts in breast diffusion-weighted imaging[J]. Jpn J Radiol, 2025, 43(3): 347-354. DOI: 10.1007/s11604-024-01696-z.
[20]
CHEN A L, XIE S L, WANG Y, et al. The value of quantitative parameters of diffusion kurtosis imaging in preoperative prediction of tumor budding grade of rectal cancer[J]. Chin J Magn Reson Imag, 2025, 16(2): 59-64, 99. DOI: 10.12015/issn.1674-8034.2025.02.009.
[21]
DAI E P, ZHU A T, YANG G K, et al. Frequency-dependent diffusion kurtosis imaging in the human brain using an oscillating gradient spin echo sequence and a high-performance head-only gradient[J/OL]. NeuroImage, 2023, 279: 120328 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37586445/. DOI: 10.1016/j.neuroimage.2023.120328.
[22]
CHEN R, YUE J W, LI R, et al. Research on diffusion kurtosis imaging of the brain based on deep learning[J]. IEEE Access, 2025, 13: 67769-67783. DOI: 10.1109/access.2025.3561035.
[23]
CHEN F Y, ZHANG S T, FU C X, et al. Predicting disease-free survival in locally advanced rectal cancer using a prognostic model based on pretreatment b-value threshold map and postoperative pathologic features[J]. Jpn J Radiol, 2025, 43(2): 236-246. DOI: 10.1007/s11604-024-01674-5.
[24]
SHEN F, CHEN L G, LI Z H, et al. The usefulness of b value threshold map in the evaluation of rectal adenocarcinoma[J]. Abdom Radiol (NY), 2020, 45(2): 332-341. DOI: 10.1007/s00261-019-02272-0.
[25]
ZHAO N, MA C, YE X L, et al. The feasibility of b-value maps based on threshold DWI for detection of breast cancer: A case-control STROBE compliant study[J/OL]. Medicine (Baltimore), 2019, 98(44): e17640 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/31689773/. DOI: 10.1097/MD.0000000000017640.
[26]
CHEN F Y, ZHANG S T, MA X L, et al. Prediction of tumor budding in patients with rectal adenocarcinoma using b-value threshold map[J]. Eur Radiol, 2023, 33(2): 1353-1363. DOI: 10.1007/s00330-022-09087-6.
[27]
GRIFFITH J F, VAN DER HEIJDEN R A. Bone marrow MR perfusion imaging and potential for tumor evaluation[J]. Skeletal Radiol, 2023, 52(3): 477-491. DOI: 10.1007/s00256-022-04202-6.
[28]
ZHOU Z, SHEN F, LU H D, et al. The value of dynamic contrast-enhanced magnetic resonance imaging for preoperative evaluation of the tumor budding of rectal cancer[J]. Chin Comput Med Imag, 2022, 28(4): 379-384. DOI: 10.19627/j.cnki.cn31-1700/th.2022.04.002.
[29]
BAKIR B, CHIARELLA A M, PITARRESI J R, et al. EMT, MET, plasticity, and tumor metastasis[J]. Trends Cell Biol, 2020, 30(10): 764-776. DOI: 10.1016/j.tcb.2020.07.003.
[30]
GARRUCHO L, KUSHIBAR K, REIDEL C A, et al. A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations[J/OL]. Sci Data, 2025, 12(1): 453 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/40108146/. DOI: 10.1038/s41597-025-04707-4.
[31]
ZÖLLNER F G, DASTRÙ W, IRRERA P, et al. Analysis protocol for dynamic contrast enhanced (DCE) MRI of renal perfusion and filtration[J]. Methods Mol Biol, 2021, 2216: 637-653. DOI: 10.1007/978-1-0716-0978-1_38.
[32]
XIE P Y, HUANG Q T, ZHENG L T, et al. Sub-region based histogram analysis of amide proton transfer-weighted MRI for predicting tumor budding grade in rectal adenocarcinoma: a prospective study[J]. Eur Radiol, 2025, 35(3): 1382-1393. DOI: 10.1007/s00330-024-11172-x.
[33]
ZHANG H, ZHOU J Y, PENG Y. Amide proton transfer-weighted MR imaging of pediatric central nervous system diseases[J]. Magn Reson Imaging Clin N Am, 2021, 29(4): 631-641. DOI: 10.1016/j.mric.2021.06.012.
[34]
ZHANG C X, CHEN J Y, LIU Y F, et al. Amide proton transfer-weighted MRI for assessing rectal adenocarcinoma T-staging and perineural invasion: a prospective study[J]. Eur Radiol, 2025, 35(2): 968-978. DOI: 10.1007/s00330-024-11000-2.
[35]
DU Y X, XU W X, HE Y Q, et al. Amide proton transfer weighted and diffusion-weighted imaging in evaluating rectal cancer tumor budding grade value[J]. Chin J Magn Reson Imag, 2025, 16(1): 42-47, 73. DOI: 10.12015/issn.1674-8034.2025.01.007.
[36]
ZHOU J Y, ZAISS M, KNUTSSON L, et al. Review and consensus recommendations on clinical APT-weighted imaging approaches at 3T: Application to brain tumors[J]. Magn Reson Med, 2022, 88(2): 546-574. DOI: 10.1002/mrm.29241.
[37]
WANG Y H, WANG L J, HUANG H T, et al. Amide proton transfer-weighted magnetic resonance imaging for the differentiation of parotid gland tumors[J/OL]. Front Oncol, 2023, 13: 1223598 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37664057/. DOI: 10.3389/fonc.2023.1223598.
[38]
LONG D, HUA L, CHEN S J, et al. Current status and prospects of radiomics in the diagnosis of colorectal cancer[J]. Chin J Magn Reson Imag, 2024, 15(9): 211-217, 229. DOI: 10.12015/issn.1674-8034.2024.09.037.
[39]
LI Z H, CHEN F Y, ZHANG S T, et al. The feasibility of MRI-based radiomics model in presurgical evaluation of tumor budding in locally advanced rectal cancer[J]. Abdom Radiol (NY), 2022, 47(1): 56-65. DOI: 10.1007/s00261-021-03311-5.
[40]
PENG L, WANG D Q, ZHUANG Z J, et al. Preoperative noninvasive evaluation of tumor budding in rectal cancer using multiparameter MRI radiomics[J]. Acad Radiol, 2024, 31(6): 2334-2345. DOI: 10.1016/j.acra.2023.11.023.
[41]
QU X T, ZHANG L, JI W N, et al. Preoperative prediction of tumor budding in rectal cancer using multiple machine learning algorithms based on MRI T2WI radiomics[J/OL]. Front Oncol, 2023, 13: 1267838 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37941552/. DOI: 10.3389/fonc.2023.1267838.
[42]
COBO M, FERNÁNDEZ-MIRANDA P M, BASTARRIKA G, et al. Enhancing radiomics and Deep Learning systems through the standardization of medical imaging workflows[J/OL]. Sci Data, 2023, 10(1): 732 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37865635/. DOI: 10.1038/s41597-023-02641-x.
[43]
LE T D, SHITIRI N C, JUNG S H, et al. Image synthesis in nuclear medicine imaging with deep learning: A review[J/OL]. Sensors (Basel), 2024, 24(24): 8068 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/39771804/. DOI: 10.3390/s24248068.
[44]
DAYARATHNA S, ISLAM K T, URIBE S, et al. Deep learning based synthesis of MRI, CT and PET: Review and analysis[J/OL]. Med Image Anal, 2024, 92: 103046 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/38052145/. DOI: 10.1016/j.media.2023.103046.
[45]
YANG M W, YANG M Y, YANG L L, et al. Deep learning for MRI lesion segmentation in rectal cancer[J/OL]. Front Med (Lausanne), 2024, 11: 1394262 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/38983364/. DOI: 10.3389/fmed.2024.1394262.
[46]
BEDRIKOVETSKI S, DUDI-VENKATA N N, KROON H M, et al. Artificial intelligence for pre-operative lymph node staging in colorectal cancer: a systematic review and meta-analysis[J/OL]. BMC Cancer, 2021, 21(1): 1058 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/34565338/. DOI: 10.1186/s12885-021-08773-w.
[47]
SHEN H, JIN Z, CHEN Q Y, et al. Image-based artificial intelligence for the prediction of pathological complete response to neoadjuvant chemoradiotherapy in patients with rectal cancer: a systematic review and meta-analysis[J]. Radiol Med, 2024, 129(4): 598-614. DOI: 10.1007/s11547-024-01796-w.
[48]
LIU Z Y, JIA J Y, BAI F, et al. Predicting rectal cancer tumor budding grading based on MRI and CT with multimodal deep transfer learning: A dual-center study[J/OL]. Heliyon, 2024, 10(7): e28769 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/38590908/. DOI: 10.1016/j.heliyon.2024.e28769.
[49]
ZHANG M H, XUE M H, LI S Y, et al. Fusion deep learning approach combining diffuse optical tomography and ultrasound for improving breast cancer classification[J]. Biomed Opt Express, 2023, 14(4): 1636-1646. DOI: 10.1364/BOE.486292.
[50]
TANG X, ZHUANG Z J, JIANG L, et al. A preoperative CT-based multiparameter deep learning and radiomic model with extracellular volume parameter images can predict the tumor budding grade in rectal cancer patients[J]. Acad Radiol, 2025, 32(7): 4002-4012. DOI: 10.1016/j.acra.2025.02.028.
[51]
SAFAEI S, SAJED R, SHARIFTABRIZI A, et al. Tumor matrix stiffness provides fertile soil for cancer stem cells[J/OL]. Cancer Cell Int, 2023, 23(1): 143 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/37468874/. DOI: 10.1186/s12935-023-02992-w.
[52]
HU Z T, WANG Z, JIN Y, et al. VGG-TSwinformer: Transformer-based deep learning model for early Alzheimer's disease prediction[J/OL]. Comput Meth Programs Biomed, 2023, 229: 107291 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/36516516/. DOI: 10.1016/j.cmpb.2022.107291.
[53]
JIA J Y, KANG Y, WANG J H, et al. Attention mechanism-based multi-parametric MRI ensemble model for predicting tumor budding grade in rectal cancer patients[J/OL]. Abdom Radiol (NY), 2025 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/40167646/. DOI: 10.1007/s00261-025-04886-z.
[54]
CHEN X X, WANG X M, ZHANG K, et al. Recent advances and clinical applications of deep learning in medical image analysis[J/OL]. Med Image Anal, 2022, 79: 102444 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/35472844/. DOI: 10.1016/j.media.2022.102444.
[55]
LIU Z H, YANG H, NIE L, et al. Prediction of tumor budding grading in rectal cancer using a multiparametric MRI radiomics combined with a 3D vision transformer deep learning approach[J]. Acad Radiol, 2025, 32(8): 4512-4523. DOI: 10.1016/j.acra.2025.03.046.
[56]
ZHOU C, LIU Y, AN X H, et al. Optimization of deep learning architecture based on multi-path convolutional neural network algorithm[J/OL]. Sci Rep, 2025, 15(1): 19532 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/40467835/. DOI: 10.1038/s41598-025-03765-3.
[57]
CHAI Y X, NIU Y C, CHENG R X, et al. Dynamic contrast-enhanced MRI combined with intravoxel incoherent motion in quantitative evaluation for preoperative risk stratification of resectable rectal adenocarcinoma[J/OL]. Oncol Lett, 2024, 29(2): 68 [2025-05-08]. https://pubmed.ncbi.nlm.nih.gov/39619420/. DOI: 10.3892/ol.2024.14814.

PREV Research progress of diffusion-weighted magnetic resonance imaging technology in the diagnosis and treatment of lung cancer
NEXT Clinical application progress of artificial intelligence-assisted compressed sensing technology in MRI
  


LINK


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