Share this content in WeChat
Clinical Article
Radiomics based on deep learning to predict T2 and T3 staging of rectal cancer
WU Shujian  YU Yongmei  FAN Lifang  ZHANG Hu  CHEN Guoxian  XU Jingya  YA Shengnan 

Cite this article as: WU S J, YU Y M, FAN L F, et al. Radiomics based on deep learning to predict T2 and T3 staging of rectal cancer[J]. Chin J Magn Reson Imaging, 2023, 14(11): 84-89, 102. DOI:10.12015/issn.1674-8034.2023.11.014.

[Abstract] Objective To explore the value of deep learning (DL) imageomics based on MRI axial high-resolution T2WI images in predicting T2 and T3 stages of rectal cancer before surgery.Materials and Methods Retrospective analysis of the complete data of 361 patients with T2 and T3 stage rectal cancer confirmed by postoperative pathology at the First Affiliated Hospital of Wannan Medical College (Yijishan Hospital) from January 2018 to December 2022. Among them, there were 100 cases in T2 phase and 261 cases in T3 phase. Patients were randomly divided into a training set (n=262) and a testing set (n=99) using stratified sampling at 7∶3. Univariate and multivariate logistic regression analysis was used to screen independent risk factors for clinical imaging features. The ResNet-18 model was employed as the foundational model for DL feature extraction. Subsequently, twelve machine learning models were developed by incorporating clinical imaging features, hand-crafted radiomi features, DL features, and their combined features. The support vector machine (SVM), K-nearest neighbor (KNN), and extreme gradient enhancement machine (XGBoost) algorithms were utilized for constructing these models. The diagnostic performance of each model was assessed by calculating the area under the curve (AUC) of the subject. Finally, the model with the highest performance was identified as the optimal output model.Results The results of both univariate and multivariate logistic regression analysis indicate that carbohydrate antigen (CA19-9) [95% confidence interval (CI): 1.150-1.820, P=0.002] and tumor length (LD) (95% CI: 1.159-22.584, P=0.031) were independent risk factors for predicting T2 and T3 stage rectal cancer based on clinical imaging features. Among all the models constructed, the performance of combined feature model was higher than that of individual feature model, and the training set XGBoost classifier model had the highest performance, with an AUC of 0.998 (95% CI: 0.995-1.000), and was therefore selected as the output model for this study.Conclusions The DL radiomics machine learning model based on MRI axial high-resolution T2WI images can effectively predict T2 and T3 stages of rectal cancer, with the XGBoost classifier model with combined features of the training set having the best performance.
[Keywords] magnetic resonance imaging;deep learning;radiomics;machine learning;rectal cancer

WU Shujian1   YU Yongmei1*   FAN Lifang2   ZHANG Hu3   CHEN Guoxian4   XU Jingya1   YA Shengnan2  

1 Department of Radiology, the First Affiliated Hospital of Wannan Medical College (Yijishan Hospital), Wuhu 241001, China

2 Department of Medical Imaging, Wannan Medical College, Wuhu 241002, China

3 Department of Radiology, Wuhu Second People's Hospital, Wuhu 241001, China

4 Department of Clinical Medicine, Wannan Medical College, Wuhu 241002, China

Corresponding author: YU Y M, E-mail:

Conflicts of interest   None.

ACKNOWLEDGMENTS Natural Science Foundation for Universities in Anhui Province (No. 2022AH051215).
Received  2023-04-25
Accepted  2023-10-27
DOI: 10.12015/issn.1674-8034.2023.11.014
Cite this article as: WU S J, YU Y M, FAN L F, et al. Radiomics based on deep learning to predict T2 and T3 staging of rectal cancer[J]. Chin J Magn Reson Imaging, 2023, 14(11): 84-89, 102. DOI:10.12015/issn.1674-8034.2023.11.014.

CHEN J Y, CHEN Y, ZHENG D C, et al. Pretreatment MR-based radiomics nomogram as potential imaging biomarker for individualized assessment of perineural invasion status in rectal cancer[J]. Abdom Radiol, 2021, 46(3): 847-857. DOI: 10.1007/s00261-020-02710-4.
LI M, JIN Y M, ZHANG Y C, et al. Radiomics for predicting perineural invasion status in rectal cancer[J]. World J Gastroenterol, 2021, 27(33): 5610-5621. DOI: 10.3748/wjg.v27.i33.5610.
YUAN J, GONG Z G, LIU K, et al. Correlation between diffusion kurtosis and intravoxel incoherent motion derived (IVIM) parameters and tumor tissue composition in rectal cancer: a pilot study[J]. Abdom Radiol, 2022, 47(4): 1223-1231. DOI: 10.1007/s00261-022-03426-3.
GE Y X, XU W B, WANG Z, et al. Prognostic value of CT radiomics in evaluating lymphovascular invasion in rectal cancer: diagnostic performance based on different volumes of interest[J]. J Xray Sci Technol, 2021, 29(4): 663-674. DOI: 10.3233/XST-210877.
National Health Commission of the People's Republic of China. Chinese protocol of diagnosis and treatment of colorectal cancer (2020 edition)[J]. Chin J Surg, 2020, 58(8): 561-585. DOI: 10.3760/cma.j.cn112139-20200518-00390.
TIMUDOM K, AKARAVIPUTH T, CHINSWANGWATANAKUL V, et al. Predictive significance of cancer related-inflammatory markers in locally advanced rectal cancer[J]. World J Gastrointest Surg, 2020, 12(9): 390-396. DOI: 10.4240/wjgs.v12.i9.390.
GOLLUB M J, BLAZIC I, FELDER S, et al. Value of adding dynamic contrast-enhanced MRI visual assessment to conventional MRI and clinical assessment in the diagnosis of complete tumour response to chemoradiotherapy for rectal cancer[J]. Eur Radiol, 2019, 29(3): 1104-1113. DOI: 10.1007/s00330-018-5719-1.
HORVAT N, CARLOS TAVARES ROCHA C, CLEMENTE OLIVEIRA B, et al. MRI of rectal cancer: tumor staging, imaging techniques, and management[J]. Radiographics, 2019, 39(2): 367-387. DOI: 10.1148/rg.2019180114.
DONG D, FANG M J, TANG L, et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: an international multicenter study[J]. Ann Oncol, 2020, 31(7): 912-920. DOI: 10.1016/j.annonc.2020.04.003.
CHOI Y S, BAE S, CHANG J H, et al. Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics[J]. Neuro Oncol, 2021, 23(2): 304-313. DOI: 10.1093/neuonc/noaa177.
HAMM C A, WANG C J, SAVIC L J, et al. Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI[J]. Eur Radiol, 2019, 29(7): 3338-3347. DOI: 10.1007/s00330-019-06205-9.
OKUMA T, HAMAMOTO S, MAEBAYASHI T, et al. Quantitative evaluation of COVID-19 pneumonia severity by CT pneumonia analysis algorithm using deep learning technology and blood test results[J]. Jpn J Radiol, 2021, 39(10): 956-965. DOI: 10.1007/s11604-021-01134-4.
BILAL M, RAZA S E A, AZAM A, et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study[J/OL]. Lancet Digit Health, 2021, 3(12): e763-e772 [2023-04-24]. DOI: 10.1016/S2589-7500(21)00180-1.
YU H H, HUANG T, FENG B, et al. Deep-learning model for predicting the survival of rectal adenocarcinoma patients based on a surveillance, epidemiology, and end results analysis[J/OL]. BMC Cancer, 2022, 22(1): 210 [2023-04-24]. DOI: 10.1186/s12885-022-09217-9.
YUAN Z X, XU T Y, CAI J, et al. Development and validation of an image-based deep learning algorithm for detection of synchronous peritoneal carcinomatosis in colorectal cancer[J/OL]. Ann Surg, 2022, 275(4): e645-e651 [2023-04-24]. DOI: 10.1097/SLA.0000000000004229.
HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 770-778. DOI: 10.1109/CVPR.2016.90.
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.
ZHANG B B, SUN Z Z, SONG M, et al. Ultrasound/CT combined with serum CEA/CA19.9 in the diagnosis and prognosis of rectal cancer[J]. J BUON, 2018, 23(3): 592-597.
SHAN J J, GU B X, SHI L M, et al. Prognostic value of CEA and CA19-9 in patients with local advanced rectal cancer receiving neoadjuvant chemoradiotherapy, radical surgery and postoperative chemotherapy[J]. Transl Cancer Res, 2021, 10(1): 88-98. DOI: 10.21037/tcr-20-2269.
ZHENG Z F, WANG X J, LU X R, et al. Prognostic significance of carcinoembryonic antigen combined with carbohydrate antigen 19-9 following neoadjuvant chemoradiotherapy in patients with locally advanced rectal cancer[J]. Colorectal Dis, 2021, 23(9): 2320-2330. DOI: 10.1111/codi.15694.
LIN X, ZHAO S, JIANG H J, et al. A radiomics-based nomogram for preoperative T staging prediction of rectal cancer[J]. Abdom Radiol, 2021, 46(10): 4525-4535. DOI: 10.1007/s00261-021-03137-1.
YANG Y, WEI H H, FU F F, et al. Preoperative prediction of vascular invasion in rectal cancer patients without lymph node metastasis based on multimodal MRI imaging features combined with clinical risk factors[J]. Chin J Magn Reson Imag, 2023, 14(1): 94-99, 110. DOI: 10.12015/issn.1674-8034.2023.01.017.
SAMMOUR T, BEDRIKOVETSKI S. Radiomics for diagnosing lateral pelvic lymph nodes in rectal cancer: artificial intelligence enabling precision medicine?[J]. Ann Surg Oncol, 2020, 27(11): 4082-4083. DOI: 10.1245/s10434-020-08978-6.
BIAN T T, WU Z J, LIN Q, et al. Evaluating tumor-infiltrating lymphocytes in breast cancer using preoperative MRI-based radiomics[J]. J Magn Reson Imaging, 2022, 55(3): 772-784. DOI: 10.1002/jmri.27910.
WANG T T, SHE Y L, YANG Y, et al. Radiomics for survival risk stratification of clinical and pathologic stage IA pure-solid non-small cell lung cancer[J]. Radiology, 2022, 302(2): 425-434. DOI: 10.1148/radiol.2021210109.
HU Z S, YANG Z Y, LAFATA K J, et al. A radiomics-boosted deep-learning model for COVID-19 and non-COVID-19 pneumonia classification using chest X-ray images[J]. Med Phys, 2022, 49(5): 3213-3222. DOI: 10.1002/mp.15582.
WANG H X, YANG S F, WANG T Y, et al. Preoperative MRI-based deep learning radiomics machine learning model for prediction of the histopathological grade of soft tissue sarcomas[J]. Chin J Radiol, 2022, 56(7): 792-799. DOI: 10.3760/cma.j.cn112149-20220323-00269.
JIANG L, ZHOU L L, AI Z P, et al. Prediction of the onset time of acute stroke by deep learning based on DWI and FLAIR[J]. Chin J Radiol, 2021, 55(8): 811-816. DOI: 10.3760/cma.j.cn112149-20220323-00269.
ABBASPOUR S, ABDOLLAHI H, ARABALIBEIK H, et al. Endorectal ultrasound radiomics in locally advanced rectal cancer patients: despeckling and radiotherapy response prediction using machine learning[J]. Abdom Radiol, 2022, 47(11): 3645-3659. DOI: 10.1007/s00261-022-03625-y.
KASAI S, SHIOMI A, KAGAWA H, et al. The effectiveness of machine learning in predicting lateral lymph node metastasis from lower rectal cancer: a single center development and validation study[J]. Ann Gastroenterol Surg, 2022, 6(1): 92-100. DOI: 10.1002/ags3.12504.
LIANG M, CAI Z T, ZHANG H M, et al. Machine learning-based analysis of rectal cancer MRI radiomics for prediction of metachronous liver metastasis[J]. Acad Radiol, 2019, 26(11): 1495-1504. DOI: 10.1016/j.acra.2018.12.019.
ZHAO B Q, GABRIEL R A, VAIDA F, et al. Predicting overall survival in patients with metastatic rectal cancer: a machine learning approach[J]. J Gastrointest Surg, 2020, 24(5): 1165-1172. DOI: 10.1007/s11605-019-04373-z.
HOU M, ZHOU L, SUN J H. Deep-learning-based 3D super-resolution MRI radiomics model: superior predictive performance in preoperative T-staging of rectal cancer[J]. Eur Radiol, 2023, 33(1): 1-10. DOI: 10.1007/s00330-022-08952-8.
YUAN Y, LU H D, MA X L, et al. Is rectal filling optimal for MRI-based radiomics in preoperative T staging of rectal cancer?[J]. Abdom Radiol, 2022, 47(5): 1741-1749. DOI: 10.1007/s00261-022-03477-6.
WEN D G, HU S X, LI Z L, et al. Application of automated machine learning based on radiomics features of T2WI and RS-EPI DWI to predict preoperative T staging of rectal cancer[J]. J Sichuan Univ Med Sci Ed, 2021, 52(4): 698-705. DOI: 10.12182/20210460201.
QIU Y G, ZENG J H, WANG X B, et al. Differentiation of T2 and T3 rectal cancer based on T2WI and DWI imaging features[J]. J China Clin Med Imag, 2022, 33(8): 557-560. DOI: 10.12117/jccmi.2022.08.005.
SUN B Y, JIANG Y, ZHENG X W, et al. Study on the application value of differential diagnosis of T2 and T3 rectal cancer based on ADC sequence imageology[J]. Chin J Lab Diagn, 2020, 24(12): 1993-1995. DOI: 10.3969/j.issn.1007-4287.2020.12.018.

PREV Predicting the efficacy of neoadjuvant therapy for locally advanced rectal cancer based on 3.0 T MRI and comparing the effectiveness of multiple classifiers
NEXT Application of ASL in renal function injury and staging of T2DM

Tel & Fax: +8610-67113815    E-mail: