Share：
Share this content in WeChat
X
[Chinese] [PDF] 12 1
• Clinical Article •
Prediction of regional lymph node status in rectal cancer with radiomics features based on deep learning segmented tumor area
ZHAO Wanting  LI Wanqing  HAO Yongfei  QIAO Xiaoai  HOU Guorui  DU Shaohua  ZHANG Guangwen  ZHANG Jinsong 

Cite this article as: ZHAO W T, LI W Q, HAO Y F, et al. Prediction of regional lymph node status in rectal cancer with radiomics features based on deep learning segmented tumor area[J]. Chin J Magn Reson Imaging, 2025, 16(10): 60-67. DOI:10.12015/issn.1674-8034.2025.10.010.


[Abstract] Objective To predict regional lymph node metastasis (LNM) in rectal cancer (RC) using deep learning-based tumor auto-segmentation and radiomics.Materials and Methods This single-center research retrospectively analyzed T2WI and DWI of 282 rectal cancers from two MR scanners. The deep learning-based auto-segmentation models were constructed on T2WI and DWI with 3D U-Net, 3D V-Net, and nnU-Net v2 and assessed with the dice similarity coefficient (DSC). Radiomics features on manual-based volume of interest (MbV) and deep learning-based volume of interest (DbV, with the highest DSC) were extracted respectively. After feature normalization and selection, five machine learning algorithms were used for radiomics model building and then for LNM prediction. The optimal model was evaluated with area under the curve (AUC), accuracy, specificity, and sensitivity.Results The DSC of the nnU-Net v2 was significantly higher than that of the 3D U-Net and 3D V-Net (T2WI: 0.886 vs. 0.548 vs. 0.616, P < 0.001; DWI: 0.906 vs. 0.583 vs. 0.433, P < 0.001) in test set. The AUC of DbV based-radiomics models constructed with logistic regression algorithm were comparable to those of the corresponding MbV-based radiomics models (T2WI: 0.700 vs. 0.633, P = 0.638; DWI: 0.667 vs. 0.700, P = 0.544; T2WI + DWI: 0.800 vs. 0.833, P = 0.248) in LNM prediction in validation set.Conclusions Radiomics features of T2WI and DWI based on nnU-net v2 segmented tumor area showed a reliable performance in predicting LNM in RC.
[Keywords] rectal cancer；deep learning；radiomics；magnetic resonance imaging；lymph node metastasis

ZHAO Wanting   LI Wanqing   HAO Yongfei   QIAO Xiaoai   HOU Guorui   DU Shaohua   ZHANG Guangwen   ZHANG Jinsong*  

Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi'an 710032, China

Corresponding author: ZHANG J S, E-mail: stspine@163.com

Conflicts of interest   None.

Received  2025-07-30
Accepted  2025-10-10
DOI: 10.12015/issn.1674-8034.2025.10.010
Cite this article as: ZHAO W T, LI W Q, HAO Y F, et al. Prediction of regional lymph node status in rectal cancer with radiomics features based on deep learning segmented tumor area[J]. Chin J Magn Reson Imaging, 2025, 16(10): 60-67. DOI:10.12015/issn.1674-8034.2025.10.010.

[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]
DOSSA F, CHESNEY T R, ACUNA S A, et al. A watch-and-wait approach for locally advanced rectal cancer after a clinical complete response following neoadjuvant chemoradiation: a systematic review and meta-analysis[J]. Lancet Gastroenterol Hepatol, 2017, 2(7): 501-513. DOI: 10.1016/S2468-1253(17)30074-2.
[3]
LE VOYER T E, SIGURDSON E R, HANLON A L, et al. Colon cancer survival is associated with increasing number of lymph nodes analyzed: A secondary survey of intergroup trial INT-0089[J]. J Clin Oncol, 2003, 21(15): 2912-2919. DOI: 10.1200/JCO.2003.05.062.
[4]
ONG M L H, SCHOFIELD J B. Assessment of lymph node involvement in colorectal cancer[J]. World J Gastrointest Surg, 2016, 8(3): 179-192. DOI: 10.4240/wjgs.v8.i3.179.
[5]
ZHAO W T, ZHANG G W, GAO H, et al. Current status and challenges of deep learning in predicting lymph node status in colorectal cancer[J]. Chin J Magn Reson Imag, 2025, 16(1): 222-227. DOI: 10.12015/issn.1674-8034.2025.01.036.
[6]
BENSON A B, VENOOK A P, ADAM M, et al. NCCN guidelines® insights: rectal cancer, version 3.2024[J]. J Natl Compr Canc Netw, 2024, 22(6): 366-375. DOI: 10.6004/jnccn.2024.0041.
[7]
AO W Q, WU S K, WANG N, et al. Novel deep learning algorithm based MRI radiomics for predicting lymph node metastases in rectal cancer[J/OL]. Sci Rep, 2025, 15(1): 12089 [2025-09-22]. https://www.nature.com/articles/s41598-025-96618-y. DOI: 10.1038/s41598-025-96618-y.
[8]
BIPAT S, GLAS A S, SLORS F J M, et al. Rectal cancer: local staging and assessment of lymph node involvement with endoluminal US, CT, and MR imaging: A meta-analysis[J]. Radiology, 2004, 232(3): 773-783. DOI: 10.1148/radiol.2323031368.
[9]
NIU Y, WEN L, YANG Y H, et al. Diagnostic performance of Node Reporting and Data System (Node-RADS) for assessing mesorectal lymph node in rectal cancer by CT[J/OL]. BMC Cancer, 2024, 24(1): 716 [2025-09-22]. https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12487-0. DOI: 10.1186/s12885-024-12487-0.
[10]
GRÖNE J, LOCH F N, TAUPITZ M, et al. Accuracy of various lymph node staging criteria in rectal cancer with magnetic resonance imaging[J]. J Gastrointest Surg, 2018, 22(1): 146-153. DOI: 10.1007/s11605-017-3568-x.
[11]
KOÇAK B, DURMAZ E Ş, ATEŞ E C, et al. Radiomics with artificial intelligence: a practical guide for beginners[J]. Diagn Interv Radiol, 2019, 25(6): 485-495. DOI: 10.5152/dir.2019.19321.
[12]
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.
[13]
HAO Y F, ZHENG J Y, LI W Q, et al. Ultra-high b-value DWI in rectal cancer: image quality assessment and regional lymph node prediction based on radiomics[J]. Eur Radiol, 2025, 35(1): 49-60. DOI: 10.1007/s00330-024-10958-3.
[14]
MA C Y, FU Y, LIU L, et al. Radiation enteritis associated with temporal sequencing of total neoadjuvant therapy in locally advanced rectal cancer: a preliminary study[J/OL]. Radiat Oncol, 2025, 20(1): 118 [2025-09-22]. https://ro-journal.biomedcentral.com/articles/10.1186/s13014-025-02701-z. DOI: 10.1186/s13014-025-02701-z.
[15]
ZHONG J Y, HUANG T, JIANG R J, et al. MRI-based habitat, intra-, and peritumoral machine learning model for perineural invasion prediction in rectal cancer[J/OL]. Abdom Radiol (NY), 2025 [2025-09-22]. https://link.springer.com/article/10.1007/s00261-025-05095-4. DOI: 10.1007/s00261-025-05095-4.
[16]
YANG Y S, QIU Y J, ZHENG G H, et al. High resolution MRI-based radiomic nomogram in predicting perineural invasion in rectal cancer[J/OL]. Cancer Imaging, 2021, 21(1): 40 [2025-09-22]. https://cancerimagingjournal.biomedcentral.com/articles/10.1186/s40644-021-00408-4. DOI: 10.1186/s40644-021-00408-4.
[17]
WANG Y, ZHAO H Y, GAO H Q, et al. Research progress of CT radiomics in the diagnosis and treatment of colorectal cancer[J]. J Pract Radiol, 2025, 41(5): 870-873. DOI: 10.3969/j.issn.1002-1671.2025.05.034.
[18]
GHAFOORIAN M, KARSSEMEIJER N, HESKES T, et al. Location sensitive deep convolutional neural networks for segmentation of white matter hyperintensities[J/OL]. Sci Rep, 2017, 7(1): 5110 [2025-09-22]. https://www.nature.com/articles/s41598-017-05300-5. DOI: 10.1038/s41598-017-05300-5.
[19]
PELLICER-VALERO O J, MARENCO JIMÉNEZ J L, GONZALEZ-PEREZ V, et al. Deep learning for fully automatic detection, segmentation, and Gleason grade estimation of prostate cancer in multiparametric magnetic resonance images[J/OL]. Sci Rep, 2022, 12(1): 2975 [2025-09-22]. https://www.nature.com/articles/s41598-022-06730-6. DOI: 10.1038/s41598-022-06730-6.
[20]
WANG S Q, MAHON R, WEISS E, et al. Automated lung cancer segmentation using a PET and CT dual-modality deep learning neural network[J]. Int J Radiat Oncol Biol Phys, 2023, 115(2): 529-539. DOI: 10.1016/j.ijrobp.2022.07.2312.
[21]
SHAUKAT Z, FAROOQ Q U A, TU S S, et al. A state-of-the-art technique to perform cloud-based semantic segmentation using deep learning 3D U-Net architecture[J/OL]. BMC Bioinformatics, 2022, 23(1): 251 [2025-09-22]. https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-022-04794-9. DOI: 10.1186/s12859-022-04794-9.
[22]
MILLETARI F, NAVAB N, AHMADI S A. V-net: fully convolutional neural networks for volumetric medical image segmentation[C]//2016 Fourth International Conference on 3D Vision (3DV). October 25-28, 2016, Stanford, CA, USA. IEEE, 2016: 565-571. DOI: 10.1109/3DV.2016.79.
[23]
ISENSEE F, JAEGER P F, KOHL S A A, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nat Methods, 2021, 18(2): 203-211. DOI: 10.1038/s41592-020-01008-z.
[24]
ZHENG R C, WANG Q D, LV S Z, et al. Automatic liver tumor segmentation on dynamic contrast enhanced MRI using 4D information: deep learning model based on 3D convolution and convolutional LSTM[J]. IEEE Trans Med Imag, 2022, 41(10): 2965-2976. DOI: 10.1109/TMI.2022.3175461.
[25]
ZHANG G W, CHEN L, LIU A E, et al. Comparable performance of deep learning-based to manual-based tumor segmentation in KRAS/NRAS/BRAF mutation prediction with MR-based radiomics in rectal cancer[J/OL]. Front Oncol, 2021, 11: 696706 [2025-09-22]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.696706/full. DOI: 10.3389/fonc.2021.696706.
[26]
ZHAO E D, YANG Y F, BAI M M, et al. MRI radiomics-based interpretable model and nomogram for preoperative prediction of Ki-67 expression status in primary central nervous system lymphoma[J/OL]. Front Med (Lausanne), 2024, 11: 1345162 [2025-09-22]. https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2024.1345162/full. DOI: 10.3389/fmed.2024.1345162.
[27]
LIANG B C, PENG F F, LUO D D, et al. Automatic segmentation of 15 critical anatomical labels and measurements of cardiac axis and cardiothoracic ratio in fetal four chambers using nnU-NetV2[J/OL]. BMC Med Inform Decis Mak, 2024, 24(1): 128 [2025-09-22]. https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-024-02527-x. DOI: 10.1186/s12911-024-02527-x.
[28]
ZHANG Y, LIU J, WU C Y, et al. Preoperative prediction of microsatellite instability in rectal cancer using five machine learning algorithms based on multiparametric MRI radiomics[J/OL]. Diagnostics (Basel), 2023, 13(2): 269 [2025-09-22]. https://www.mdpi.com/2075-4418/13/2/269. DOI: 10.3390/diagnostics13020269.
[29]
SONG M Y, WANG Q, FENG H, et al. Preoperative grading of rectal cancer with multiple DWI models, DWI-derived biological markers, and machine learning classifiers[J/OL]. Bioengineering, 2023, 10(11): 1298 [2025-09-22]. https://www.mdpi.com/2306-5354/10/11/1298. DOI: 10.3390/bioengineering10111298.
[30]
FANG J J, SUN W, WU D, et al. Value of texture analysis based on dynamic contrast-enhanced magnetic resonance imaging in preoperative assessment of extramural venous invasion in rectal cancer[J/OL]. Insights Imaging, 2022, 13(1): 179 [2025-09-22]. https://insightsimaging.springeropen.com/articles/10.1186/s13244-022-01316-2. DOI: 10.1186/s13244-022-01316-2.
[31]
LEE C S, LEE A Y. Clinical applications of continual learning machine learning[J/OL]. Lancet Digit Health, 2020, 2(6): e279-e281 [2025-09-22]. https://linkinghub.elsevier.com/retrieve/pii/S2589-7500(20)30102-3. DOI: 10.1016/S2589-7500(20)30102-3.
[32]
ZHANG J H, LAI Z H, KONG H, et al. Learning the optimal discriminant SVM with feature extraction[J]. IEEE Trans Pattern Anal Mach Intell, 2025, 47(4): 2897-2911. DOI: 10.1109/TPAMI.2025.3529711.
[33]
KIREMIT B Y, ŞAHIN D Ö. Comparison of machine learning algorithms for predicting length of stay in chronic kidney disease patients[J/OL]. Comput Biol Med, 2025, 196(Pt B): 110825 [2025-09-22]. https://linkinghub.elsevier.com/retrieve/pii/S0010-4825(25)01176-X. DOI: 10.1016/j.compbiomed.2025.110825.
[34]
TABARI A, CHAN S M, OMAR O M F, et al. Role of machine learning in precision oncology: applications in gastrointestinal cancers[J/OL]. Cancers (Basel), 2022, 15(1): 63 [2025-09-22]. https://www.mdpi.com/2072-6694/15/1/63. DOI: 10.3390/cancers15010063.
[35]
NIU Y, YU X P, WEN L, et al. Comparison of preoperative CT- and MRI-based multiparametric radiomics in the prediction of lymph node metastasis in rectal cancer[J/OL]. Front Oncol, 2023, 13: 1230698 [2025-09-22]. https://linkinghub.elsevier.com/retrieve/pii/S2589-7500(20)30102-3. DOI: 10.3389/fonc.2023.1230698.
[36]
YUAN H, XU X R, TU S L, et al. The CT-based intratumoral and peritumoral machine learning radiomics analysis in predicting lymph node metastasis in rectal carcinoma[J/OL]. BMC Gastroenterol, 2022, 22(1): 463 [2025-09-22]. https://bmcgastroenterol.biomedcentral.com/articles/10.1186/s12876-022-02525-1. DOI: 10.1186/s12876-022-02525-1.
[37]
GÜRSES B, BÖGE M, ALTıNMAKAS E, et al. Multiparametric MRI in rectal cancer[J]. Diagn Interv Radiol, 2019, 25(3): 175-182. DOI: 10.5152/dir.2019.18189.
[38]
LIMKIN E J, SUN R, DERCLE L, et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology[J]. Ann Oncol, 2017, 28(6): 1191-1206. DOI: 10.1093/annonc/mdx034.
[39]
HE B, JI T, ZHANG H, et al. MRI-based radiomics signature for tumor grading of rectal carcinoma using random forest model[J]. J Cell Physiol, 2019, 234(11): 20501-20509. DOI: 10.1002/jcp.28650.

PREV A study on the correlation between quantitative parameters of DCE-MRI and the pathological grading and angiogenesis of extrahepatic cholangiocarcinoma
NEXT Habitat analysis and peritumoral radiomics for predicting castration resistance in prostate cancer patients
  


LINK


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