Share：
Share this content in WeChat
X
[Chinese] [PDF] 8 1
• Clinical Article •
Prediction of treatment response to neoadjuvant chemoradiotherapy in patients with locally advanced rectal cancer by interpretable model based on multiparametric MRI
LI Xuemeng  ZHOU Yanfei  WANG Aoyang  ZHAO Min  WANG Jing  JIANG Li  WEI Wei  GAO Fei 

DOI:10.12015/issn.1674-8034.2026.01.009.


[Abstract] Objective To establish a prediction model based on multiparametric MRI radiomics and clinical-radiology features, and evaluate its efficacy in predicting neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer. The Shapley algorithm was employed to enhance model interpretability.Materials and Methods A retrospective analysis was conducted on 172 patients who received nCRT and surgery from the First Affiliated Hospital of the University of Science and Technology of China (center 1) and the Hefei Cancer Hospital of the Chinese Academy of Sciences (center 2), and Clinical and MRI data were analyzed. According to the 8th edition AJCC tumor regression grading (TRG) criteria for rectal cancer, patients with TRG 0-1 were classified as good responders (GR), while those with TRG 2-3 were classified as poor responders (PR) based on postoperative pathological results. The GR group comprised 77 patients, and the PR group comprised 95 patients. Patients from center 1 were randomly divided into a training set (n = 92) and an internal validation set (n = 40), while the patients from center 2 were utilized as an independent external validation set (n = 40). High-resolution axial T2WI, diffusion-weighted imaging (DWI) and sagittal contrast-enhanced T1WI (CE-T1WI) sequences were selected to delineate the region of interest (ROI) along the tumor margins. PyRadiomics software was used to extract all radiomics features after image preprocessing. Spearman correlation analysis and least absolute shrinkage and selection operator (LASSO) analysis were used to retain the radiomics features strongly associated with the efficacy of nCRT. T2WI, DWI, CE-T1WI and multiparametric radiomics score (Rad-score) were obtained by eXtreme gradient boosting (XGBoost) classifier. The independent clinical-radiology predictors were screened by single-multiple logistic regression to build the clinical-radiology model, and the multiparametric model Rad-score combined with independent clinical-radiology predictors was selected to build the nomogram model. The performance of the model was evaluated using receiver operating characteristic (ROC) curves. The best-performing radiomics model was explained by the Shapley algorithm.Results Univariate and multivariate logistic regression analysis identified age, tumor longest diameter, and neoadjuvant treatment modalities as independent predictors for treatment efficacy. The clinical-radiology model demonstrated the area under the curve (AUC) of 0.80 (95% CI: 0.75 to 0.85) in the training set, 0.73 (95% CI: 0.68 to 0.78) in the internal validation set, and 0.60 (95% CI: 0.55 to 0.65) in the external validation set. Among radiomics models, the multiparametric radiomics model (T2WI + DWI + CE-T1WI) achieved optimal performance, with AUCs of 0.98 (95% CI: 0.95 to 1.00), 0.95 (95% CI: 0.91 to 0.99), 0.86 (95% CI: 0.81 to 0.91) in the training, internal validation, and external validation sets, respectively. The nomogram model achieved the best predictive performance. The AUC, accuracy, sensitivity, and specificity of the training set of nomogram model were 0.99 (95% CI: 0.97 to 1.00), 98%, 95%, and 98%, respectively. The internal validation sets were 0.98 (95% CI: 0.95 to 1.00), 98%, 98% and 98%, respectively. The external validation sets were 0.88 (95% CI: 0.83 to 0.93), 88%, 87% and 87% respectively. DeLong test indicated that the nomogram model's performance was superior to the clinical model and the radiomics models (P < 0.05). Shapley analysis revealed that wavelet-LHL_glszm_SmallAreaEmphasis in DWI sequence was the most important feature in the radiomics model.Conclusions The nomogram based on multiparametric MRI radiomics and clinical-radiology features may be used as an accurate and non-invasive method to predict the efficacy of nCRT in rectal cancer patients, and the Shapley algorithm can provide interpretability of radiomics model. This nomogram has been validated using an external validation set, suggesting its potential utility of providing important guidance for clinical diagnosis and treatment decision-making.
[Keywords] locally advanced rectal cancer；neoadjuvant chemoradiotherapy；magnetic resonance imaging；multiparametric；radiomics；nomogram；interpretability

LI Xuemeng1   ZHOU Yanfei2   WANG Aoyang3   ZHAO Min3   WANG Jing3   JIANG Li4   WEI Wei5   GAO Fei1, 5*  

1 Graduate School, Bengbu Medical University, Bengbu 233030, China

2 Department of Radiology, Hefei Cancer Hospital, Chinese Academy of Sciences, Hefei 236000, China

3 Graduate School, Wannan Medical College, Wuhu 241000, China

4 Department of Pathology, The People's Hospital of Chizhou, Chizhou 247000, China

5 Department of Radiology, the First Affiliated Hospital of USTC, Anhui Provincial Hospital, Hefei 230001, China

Corresponding author: GAO F, E-mail: 15956912758@163.com

Conflicts of interest   None.

Received  2025-07-10
Accepted  2026-01-06
DOI: 10.12015/issn.1674-8034.2026.01.009
DOI:10.12015/issn.1674-8034.2026.01.009.

[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]
LI N, LU B, LUO C Y, et al. Incidence, mortality, survival, risk factor and screening of colorectal cancer: a comparison among China, Europe, and northern America[J]. Cancer Lett, 2021, 522: 255-268. DOI: 10.1016/j.canlet.2021.09.034.
[4]
BILLER L H, SCHRAG D. Diagnosis and treatment of metastatic colorectal cancer: a review[J]. JAMA, 2021, 325(7): 669-685. DOI: 10.1001/jama.2021.0106.
[5]
QADERI S M, DICKMAN P W, DE WILT J H W, et al. Conditional survival and cure of patients with colon or rectal cancer: a population-based study[J]. J Natl Compr Canc Netw, 2020, 18(9): 1230-1237. DOI: 10.6004/jnccn.2020.7568.
[6]
BENSON A B, VENOOK A P, AL-HAWARY M M, et al. Rectal cancer, version 2.2022, NCCN clinical practice guidelines in oncology[J]. J Natl Compr Canc Netw, 2022, 20(10): 1139-1167. DOI: 10.6004/jnccn.2022.0051.
[7]
GANI C H, FOKAS E, POLAT B, et al. Organ preservation after total neoadjuvant therapy for locally advanced rectal cancer (CAO/ARO/AIO-16): an open-label, multicentre, single-arm, phase 2 trial[J]. Lancet Gastroenterol Hepatol, 2025, 10(6): 562-572. DOI: 10.1016/S2468-1253(25)00049-4.
[8]
PATIL P S, SAKLANI A, KUMAR N A N, et al. A randomized phase Ⅱ/Ⅲ trial of rosuvastatin with neoadjuvant chemo-radiation in patients with locally advanced rectal cancer[J/OL]. Front Oncol, 2025, 15: 1450602 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/40177244/. DOI: 10.3389/fonc.2025.1450602.
[9]
MIRANDA J, ANDRIEU P C, NINCEVIC J, et al. Advances in MRI-based assessment of rectal cancer post-neoadjuvant therapy: a comprehensive review[J/OL]. J Clin Med, 2023, 13(1): 172 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/38202179/. DOI: 10.3390/jcm13010172.
[10]
WANG F, CHEN G, ZHANG Z, et al. The Chinese society of clinical oncology (CSCO): clinical guidelines for the diagnosis and treatment of colorectal cancer, 2024 update[J]. Cancer Commun (Lond), 2025, 45(3): 332-379. DOI: 10.1002/cac2.12639.
[11]
HOŁDAKOWSKA A, KURKOWSKA K, PIETRZAK L, et al. Which tumour factors preclude organ preservation in patients with rectal cancer [J/OL]. Radiother Oncol, 2024, 191: 110054 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/38104780/. DOI: 10.1016/j.radonc.2023.110054.
[12]
CAI C P, HU T D, RONG Z N, et al. Prognostic prediction value of the clinical-radiomics tumour-stroma ratio in locally advanced rectal cancer[J/OL]. Eur J Radiol, 2024, 170: 111254 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/38091662/. DOI: 10.1016/j.ejrad.2023.111254.
[13]
FENG L L, LIU Z Y, LI C F, et al. Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicentre observational study[J/OL]. Lancet Digit Health, 2022, 4(1): e8-e17 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/34952679/. DOI: 10.1016/S2589-7500(21)00215-6.
[14]
MAO J W, YE W L, MA W L, et al. Prediction by a multiparametric magnetic resonance imaging-based radiomics signature model of disease-free survival in patients with rectal cancer treated by surgery[J/OL]. Front Oncol, 2024, 14: 1255438 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/38454930/. DOI: 10.3389/fonc.2024.1255438.
[15]
PENG W J, WAN L J, WANG S C, et al. A multiple-time-scale comparative study for the added value of magnetic resonance imaging-based radiomics in predicting pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer[J/OL]. Front Oncol, 2023, 13: 1234619 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/37664046/. DOI: 10.3389/fonc.2023.1234619.
[16]
ZHAO R, WAN L J, CHEN S, et al. MRI-based multiregional radiomics for pretreatment prediction of distant metastasis after neoadjuvant chemoradiotherapy in patients with locally advanced rectal cancer[J]. Acad Radiol, 2024, 31(4): 1367-1377. DOI: 10.1016/j.acra.2023.09.007.
[17]
LIU X Y, ZHANG D F, LIU Z Y, et al. Deep learning radiomics-based prediction of distant metastasis in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy: a multicentre study[J/OL]. EBioMedicine, 2021, 69: 103442 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/34157487/. DOI: 10.1016/j.ebiom.2021.103442.
[18]
TIAN X W, MA A L, JIA Z Q, et al. MRI radiomics combined with delta-radiomics model for predicting pathological complete response in locally advanced rectal cancer patients after neoadjuvant chemoradiotherapy: a multi-institutional study[J/OL]. Appl Radiat Isot, 2025, 222: 111842 [2025-07-06] . https://pubmed.ncbi.nlm.nih.gov/40273481/. DOI: 10.1016/j.apradiso.2025.111842.
[19]
WEI Q R, CHEN Z L, TANG Y H, et al. External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study[J]. Eur Radiol, 2023, 33(3): 1906-1917. DOI: 10.1007/s00330-022-09204-5.
[20]
Colorectal Cancer Diagnosis and Treatment Technology Professional Committee of Chinese Medical Doctor Association, Abdomen Group Chinese Society of Radiology Chinese Medical Association, SUN Y S, et al. Expert consensus on MR examination and structured report of rectal cancer[J]. Chin J Radiol, 2021, 55(11): 1121-1127. DOI: 10.3760/cma.j.cn112149-20210518-00490.
[21]
AMIN M B, GREENE F L, EDGE S B, et al. The eighth edition AJCC cancer staging manual: continuing to build a bridge from a population-based to a more "personalized" approach to cancer staging[J]. CA Cancer J Clin, 2017, 67(2): 93-99. DOI: 10.3322/caac.21388.
[22]
CROMBÉ A, KATAOKA M. Breast cancer molecular subtype prediction: Improving interpretability of complex machine-learning models based on multiparametric-MRI features using SHapley Additive exPlanations (SHAP) methodology[J]. Diagn Interv Imaging, 2024, 105(5): 161-162. DOI: 10.1016/j.diii.2024.01.008.
[23]
WANG J, CHEN J J, ZHOU R Z, et al. Machine learning-based multiparametric MRI radiomics for predicting poor responders after neoadjuvant chemoradiotherapy in rectal Cancer patients[J/OL]. BMC Cancer, 2022, 22(1): 420 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/35439946/. DOI: 10.1186/s12885-022-09518-z.
[24]
FIDAN M, NURAL M S, ÇAMLıDAĞ İ, et al. Evaluation of treatment response by multiparametric MR imaging in locally advanced rectal tumors following neoadjuvant chemotherapy[J]. Abdom Radiol (NY), 2024, 49(11): 3768-3779. DOI: 10.1007/s00261-024-04389-3.
[25]
SCHURINK N W, VAN KRANEN S R, VAN GRIETHUYSEN J J M, et al. Development and multicenter validation of a multiparametric imaging model to predict treatment response in rectal cancer[J]. Eur Radiol, 2023, 33(12): 8889-8898. DOI: 10.1007/s00330-023-09920-6.
[26]
ZHU W L, XU Y S, ZHU H L, et al. Multi-parametric MRI radiomics for predicting response to neoadjuvant therapy in patients with locally advanced rectal cancer[J]. Jpn J Radiol, 2024, 42(12): 1448-1457. DOI: 10.1007/s11604-024-01630-3.
[27]
XIANG Y R, LI S, WANG H Z, et al. MRI-based radiomics to predict neoadjuvant chemoradiotherapy outcomes in locally advanced rectal cancer: a multicenter study[J]. Clin Transl Radiat Oncol, 2022, 38: 175-182. DOI: 10.1016/j.ctro.2022.11.009.
[28]
ZHANG Z W, CHEN Y, WEN Z Q, et al. MRI for nodal restaging after neoadjuvant therapy in rectal cancer with histopathologic comparison[J/OL]. Cancer Imaging, 2023, 23(1): 67 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/37443085/. DOI: 10.1186/s40644-023-00589-0.
[29]
FERRI V, VICENTE E, QUIJANO Y, et al. Predicting treatment response and survival in rectal cancer: insights from 18 FDG-PET/MRI post-neoadjuvant therapy[J/OL]. Int J Colorectal Dis, 2025, 40(1): 6 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/39757340/. DOI: 10.1007/s00384-024-04803-8.
[30]
ZHOU X Z, YU Y, FENG Y R, et al. Attention mechanism based multi-sequence MRI fusion improves prediction of response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer[J/OL]. Radiat Oncol, 2023, 18(1): 175 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/37891611/. DOI: 10.1186/s13014-023-02352-y.
[31]
AO W Q, WANG N, CHEN X, et al. Multiparametric MRI-based deep learning models for preoperative prediction of tumor deposits in rectal cancer and prognostic outcome[J]. Acad Radiol, 2025, 32(3): 1451-1464. DOI: 10.1016/j.acra.2024.10.004.
[32]
LIAO H, ZHAO Y, PEI W, et al. An interpretable machine learning model assists in predicting induction chemotherapy response and survival for locoregionally advanced nasopharyngeal carcinoma using MRI: a multicenter study[J]. Eur Radiol, 2025, 35(8): 5121-5134. DOI: 10.1007/s00330-025-11396-5.
[33]
KARAHACIOGLU D, ATALAY H O, ESMER R, et al. What is the predictive value of pretreatment MRI characteristics for achieving a complete response after total neoadjuvant treatment in locally advanced rectal cancer [J/OL]. Eur J Radiol, 2025, 185: 112005 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/39970545/. DOI: 10.1016/j.ejrad.2025.112005.
[34]
CHEN X J, WANG W H, CHEN J G, et al. Predicting pathologic complete response in locally advanced rectal cancer patients after neoadjuvant therapy: a machine learning model using XGBoost[J]. Int J Colorectal Dis, 2022, 37(7): 1621-1634. DOI: 10.1007/s00384-022-04157-z.
[35]
DIEFENHARDT M, KOSMALA R, FLEISCHMANN M, et al. Chemotherapy before or after preoperative chemoradiotherapy and surgery for locally advanced rectal cancer: 5-year results of the CAO/ARO/AIO-12 trial - a general pairwise comparison[J/OL]. ESMO Open, 2025, 10(3): 104483 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/40056849/. DOI: 10.1016/j.esmoop.2025.104483.
[36]
SONG M, LI S, WANG H Z, et al. MRI radiomics independent of clinical baseline characteristics and neoadjuvant treatment modalities predicts response to neoadjuvant therapy in rectal cancer[J]. Br J Cancer, 2022, 127(2): 249-257. DOI: 10.1038/s41416-022-01786-7.
[37]
LIU X B, JI Z L, ZHANG L B, et al. Prediction of pathological complete response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer using 18F-FDG PET radiomics features of primary tumour and lymph nodes[J/OL]. BMC Cancer, 2025, 25(1): 520 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/40119358/. DOI: 10.1186/s12885-025-13905-7.
[38]
SHENG Z X, JI S Y, CHEN Y C, et al. Machine learning algorithms integrating positron emission tomography/computed tomography features to predict pathological complete response after neoadjuvant chemoimmunotherapy in lung cancer[J/OL]. Eur J Cardiothorac Surg, 2025, 67(5): ezaf132 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/40221851/. DOI: 10.1093/ejcts/ezaf132.
[39]
HU T D, GONG J, SUN Y Q, et al. Magnetic resonance imaging-based radiomics analysis for prediction of treatment response to neoadjuvant chemoradiotherapy and clinical outcome in patients with locally advanced rectal cancer: A large multicentric and validated study[J/OL]. MedComm (2020), 2024, 5(7): e609 [2025-07-06]. https://pubmed.ncbi.nlm.nih.gov/38911065/. DOI: 10.1002/mco2.609.

PREV The advantage of gadoxetate disodium-enhanced MRI in differentiating focal chronic inflammatory lesions of the liver from solitary hepatic metastases
NEXT Interpretable machine learning model based on DCE-MRI habitat imaging radiomics for predicting lymph node metastasis in rectal cancer
  


LINK


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