[an error occurred while processing this directive] | [an error occurred while processing this directive]
Prediction of deep learning-based radiomic features for neoadjuvant radiochemotherapy response in locally advanced rectal cancer
Li Ning1, Sharon Qi2, Feng Lingling3, Tang Yuan1, Li Yexiong1, Ren Ye1, Fang Hui1, Tang Yu1, Chen Bo1, Lu Ningning1, Jing Hao1, Qi Shunan1, Wang Shulian1, Liu Yueping1, Song Yongwen1, Jin Jing1
1Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/ Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China; 2Department of Radiation Oncology, University of California Los Angeles Medical Center, Los Angeles 90095, USA; 3Department of Radiation Oncology,National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen 518116, China
AbstractObjective To evaluate the effectiveness of deep learning (DL)-based radiomic features extracted from pre-treatment diffusion-weighted magnetic resonance images (DWI) for predicting neoadjuvant chemoradiation treatment (nCRT) response in patients with locally advanced rectal cancer (LARC). Methods Forty-three patients receiving nCRT from 2016 to 2017 were included. All patients received DWI before nCRT and total mesorectal excision surgery 6-12 weeks after completion of nCRT. The patient-cohort was split into the responder group (n=22) and the non-responder group (n=21) based on the post-nCRT response assessed by postoperative pathology, MRI or colonoscopy. DL-based radiomic features were extracted from the apparent diffusion coefficient map of the DWI using a pre-trained convolution neural network, respectively. Least absolute shrinkage and selection operator-Logistic regression models were constructed using extracted radiomic features for predicting treatment response. The model performance was evaluated with repeated 20 times stratified 4-fold cross-validation using receiver operating characteristic (ROC) curves.Results The model established with DL-based radiomic features achieved the mean area under the ROC curve of 0.73(SE, 0.58-0.80). Conclusion DL-based radiomic features extracted from pre-treatment DWI achieve high accuracy for predicting nCRT response in patients with LARC.
Fund:National Natural Science Foundation of China (81871509, 81272510,81773241);Chinese Academy of Medical Science Innovation Fund for Medical Sciences (2017-I2M-1-006);Central Public-interest Scientific Institution Basal Research Fund of the Chinese Academy of Medical Sciences (2018RC310010)
Corresponding Authors:
Jin Jing;Email:jinjing@csco.org.cn
Cite this article:
Li Ning,Sharon Qi,Feng Lingling et al. Prediction of deep learning-based radiomic features for neoadjuvant radiochemotherapy response in locally advanced rectal cancer[J]. Chinese Journal of Radiation Oncology, 2020, 29(6): 441-445.
Li Ning,Sharon Qi,Feng Lingling et al. Prediction of deep learning-based radiomic features for neoadjuvant radiochemotherapy response in locally advanced rectal cancer[J]. Chinese Journal of Radiation Oncology, 2020, 29(6): 441-445.
[1] Chen W, Zheng R, Baade PD, et al. Cancer statistics in China, 2015[J]. CA Cancer J Clin, 2016, 66(2):115-32. DOI:10.3322/caac.21338. [2] 苗儒林,李子禹,武爱文. 中国胃肠肿瘤外科联盟数据报告(2014-2016)[J]. 中国实用外科杂志, 2018, 38(1):90-93. Miao R, Li Z, Wu A. Data report of China gastrointestinal cancer surgery union (2014-2016)[J]. Chin J Pract Surg, 2018, 38(1):90-93. [3] Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019[J]. CA Cancer J Clin, 2019, 69(1):7-34. DOI:10.3322/caac.21551. [4] NCCN. Clinical practice guidelines in rectal cancer (2019 VersionI)[2019-11-10].https://www.nccn.org/professionals/physician_gls/f_guidelines.asp. [5] Bosset JF, Calais G, Mineur L, et al. Enhanced tumorocidal effect of chemotherapy with preoperative radiotherapy for rectal cancer:preliminary results—EORTC 22921[J]. J Clin Oncol, 2005, 23(24):5620-5627. [6] Capirci C, Valentini V, Cionini L, et al. Prognostic value of pathologic complete response after neoadjuvant therapy in locally advanced rectal cancer:long-term analysis of 566 ypCR patients[J]. Int J Radiat Oncol Biol Phys, 2008, 72(1):99-107. DOI:10.1016/j.ijrobp.2007.12.019. [7] van der Valk MJM, Hilling DE, Bastiaannet E, et al. Long-term outcomes of clinical complete responders after neoadjuvant treatment for rectal cancer in the International Watch& Wait Database (IWWD):an international multicentre registry study[J]. Lancet, 2018, 391(10139):2537-2545. DOI:10.1016/S0140-6736(18)31078-X. [8] On J, Aly EH.′Watch and wait′ in rectal cancer:summary of the current evidence[J]. Int J Colorectal Dis, 2018, 33(9):1159-1168. DOI:10.1007/s00384-018-3116-5. [9] Schurink NW, Lambregts DMJ, Beets-Tan RGH. Diffusion-weighted imaging in rectal cancer:current applications and future perspectives[J]. Br J Radiol, 2019, 92(1096):20180655. DOI:10.1259/bjr.20180655. [10] Beets-Tan RGH, Lambregts DMJ, Maas M, et al. Magnetic resonance imaging for clinical management of rectal cancer:Updated recommendations from the 2016 European Society of Gastrointestinal and Abdominal Radiology (ESGAR) consensus meeting[J]. Eur Radiol, 2018, 28(4):1465-1475. DOI:10.1007/s00330-017-5026-2. [11] Kim SH,Lee JY, Lee JM, et al. Apparent diffusion coefficient for evaluating tumour response to neoadjuvant chemoradiation therapy for locally advanced rectal cancer[J]. Eur Radiol, 2011, 21(5):987-995. DOI:10.1007/s00330-010-1989-y. [12] Amodeo S, Rosman AS, Desiato V, et al. MRI-based apparent diffusion coefficient for predicting pathologic response of rectal cancer after neoadjuvant therapy:systematic review and meta-analysis[J]. Am J Roentgenol, 2018, 211(5):W205-W216. DOI:10.2214/AJR.17.19135. [13] Lambin P,Leijenaar RTH, Deist TM, et al. Radiomics:the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12):749-762. DOI:10.1038/nrclinonc.2017.141. [14] Horvat N, Veeraraghavan H, Khan M, et al. MR imaging of rectal cancer:radiomics analysis to assess treatment response after neoadjuvant therapy[J]. Radiology, 2018, 287(3):833-843. DOI:10.1148/radiol.2018172300. [15] Nie K, Shi L, Chen Q, et al. Rectal cancer:assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI[J]. Clin Cancer Res, 2016, 22(21):5256-5264. DOI:10.1158/1078-0432. CCR-15-2997. [16] Liu Z, Zhang XY, Shi YJ, et al. Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer[J]. Clin Cancer Res, 2017, 23(23):7253-7262. DOI:10.1158/1078-0432. CCR-17-1038. [17] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444. DOI:10.1038/nature14539. [18] Lao J, Chen Y, Li ZC, et al. A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme[J]. Sci Rep, 2017, 7(1):10353. DOI:10.1038/s41598-017-10649-8. [19] Li Z, Wang Y, Yu J, et al. Deep learning based radiomics (DLR) and its usage in noninvasive IDH1 prediction for low grade glioma[J]. Sci Rep, 2017, 7(1):5467. DOI:10.1038/s41598-017-05848-2. [20] Zhou L,Zhang Z, Chen YC, et al. A deep learning-based radiomics model for differentiating benign and malignant renal tumors[J]. Transl Oncol, 2019, 12(2):292-300. DOI:10.1016/j.tranon.2018.10.012. [21] Antropova N, Huynh BQ, Giger ml. A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets[J]. Med Phys, 2017, 44(10):5162-5171. DOI:10.1002/mp.12453. [22] Bouckaert RR, Frank E. Evaluating the replicability of significance tests for comparing learning algorithms[C]. Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2004:3-12. [23] Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge[J]. Int J Comput Vis, 2015, 115(3):211-252. DOI:10.1007/s11263-015-0816-y. [24] Kumar D, Wong A, Clausi D. Lung nodule classification using deep features in CT images[C]. Conference on Computer& Robot Vision, 2015. DOI:10.1109/CRV.2015.25. [25] Cheng JZ,Ni D, Chou YH, et al. Computer-aided diagnosis with deep learning architecture:applications to breast lesions in US images and pulmonary nodules in CT scans[J]. Sci Rep, 2016, 6(4):24454. DOI:10.1038/srep24454. [26] Kim JH. Estimating classification error rate:repeated cross-validation, repeated hold-out and bootstrap[J]. Comput Statist Data Anal, 2009, 53(11):3735-3745. DOI:10.1016/j.csda.2009.04.009. [27] Li N,Jin J, Yu J, et al. Down-staging depth score to predict outcomes in locally advanced rectal cancer achieving ypI stage after neoadjuvant chemo-radiotherapy versus de novo stage pI cohort:A propensity score-matched analysis[J]. Chin J Cancer Res, 2018, 30(3):373-381. DOI:10.21147/j.issn.1000-9604.2018.03.09.
2020, Vol. 29 
