{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:39:26Z","timestamp":1783575566298,"version":"3.55.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The detection of Kirsten rat sarcoma viral oncogene homolog (KRAS) gene mutations in colorectal cancer (CRC) is key to the optimal design of individualized therapeutic strategies. The noninvasive prediction of the KRAS status in CRC is challenging. Deep learning (DL) in medical imaging has shown its high performance in diagnosis, classification, and prediction in recent years. In this paper, we investigated predictive performance by using a DL method with a residual neural network (ResNet) to estimate the KRAS mutation status in CRC patients based on pre-treatment contrast-enhanced CT imaging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We have collected a dataset consisting of 157 patients with pathology-confirmed CRC who were divided into a training cohort (n = 117) and a testing cohort (n = 40). We developed an ResNet model that used portal venous phase CT images to estimate KRAS mutations in the axial, coronal, and sagittal directions of the training cohort and evaluated the model in the testing cohort. Several groups of expended region of interest (ROI) patches were generated for the ResNet model, to explore whether tissues around the tumor can contribute to cancer assessment. We also explored a radiomics model with the random forest classifier (RFC) to predict KRAS mutations and compared it with the DL model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The ResNet model in the axial direction achieved the higher area under the curve (AUC) value (0.90) in the testing cohort and peaked at 0.93 with an input of \u2019ROI and 20-pixel\u2019 surrounding area. AUC of radiomics model in testing cohorts were 0.818. In comparison, the ResNet model showed better predictive ability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our experiments reveal that the computerized assessment of the pre-treatment CT images of CRC patients using a DL model has the potential to precisely predict KRAS mutations. This new model has the potential to assist in noninvasive KRAS mutation estimation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-020-00457-4","type":"journal-article","created":{"date-parts":[[2020,6,2]],"date-time":"2020-06-02T14:05:26Z","timestamp":1591106726000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on CT imaging"],"prefix":"10.1186","volume":"20","author":[{"given":"Kan","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hualin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,6,1]]},"reference":[{"issue":"5","key":"457_CR1","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1002\/ijc.29210","volume":"136","author":"J Ferlay","year":"2015","unstructured":"Ferlay J, Soerjomataram I, Dikshit R. Cancer incidence and mortality worldwide: sources, methods and major patterns in globocan 2012. Int J Cancer. 2015; 136(5):359\u201386.","journal-title":"Int J Cancer"},{"issue":"3","key":"457_CR2","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1200\/JCO.2009.23.3452","volume":"28","author":"AD Roth","year":"2010","unstructured":"Roth AD, Tejpar S, Delorenzi M. Prognostic role of kras and braf in stage ii and iii resected colon cancer: results of the translational study on the petacc-3, eortc 40993, sakk 60-00 trial. J Clin Oncol. 2010; 28(3):466\u201374.","journal-title":"J Clin Oncol"},{"issue":"7","key":"457_CR3","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1200\/JCO.2014.59.4812","volume":"33","author":"E Van Cutsem","year":"2015","unstructured":"Van Cutsem E, Lenz HJ, Kohne CH. Fluorouracil, leucovorin, and irinotecan plus cetuximab treatment and ras mutations in colorectal cancer. J Clin Oncol. 2015; 33(7):692\u2013700.","journal-title":"J Clin Oncol"},{"issue":"24","key":"457_CR4","doi-asserted-by":"crossref","first-page":"5469","DOI":"10.1158\/1078-0432.CCR-15-0526","volume":"21","author":"M Peeters","year":"2015","unstructured":"Peeters M, Oliner KS, Price TJ. Analysis of kras\/nras mutations in a phase iii study of panitumumab with folfri compared with folfri alone as second-line treatment for metastatic colorectal cancer. Clin Cancer Res. 2015; 21(24):5469\u201379.","journal-title":"Clin Cancer Res"},{"issue":"6","key":"457_CR5","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1158\/1078-0432.CCR-11-1909","volume":"18","author":"K Kawada","year":"2012","unstructured":"Kawada K, Nakamoto Y, Kawada M. Relationship between 18f-uorodeoxyglucose accumulation and kras\/braf mutations in colorectal cancer. Clin Cancer Res. 2012; 18(6):1696\u2013703.","journal-title":"Clin Cancer Res"},{"issue":"8","key":"457_CR6","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1097\/RLU.0000000000000481","volume":"39","author":"SW Chen","year":"2014","unstructured":"Chen SW, Chiang HC, Chen WT. Correlation between pet\/ct parameters and kras expression in colorectal cancer. Clin Nucl Med. 2014; 39(8):685\u20139.","journal-title":"Clin Nucl Med"},{"issue":"1063","key":"457_CR7","doi-asserted-by":"crossref","first-page":"20160212","DOI":"10.1259\/bjr.20160212","volume":"89","author":"P Lovinfosse","year":"2016","unstructured":"Lovinfosse P, Koopmansch B, Lambert F. (18)f-fdg pet\/ct imaging in rectal cancer: relationship with the ras mutational status. Br J Radiol. 2016; 89(1063):20160212.","journal-title":"Br J Radiol"},{"issue":"5","key":"457_CR8","doi-asserted-by":"crossref","first-page":"2058","DOI":"10.1007\/s00330-017-5146-8","volume":"28","author":"L Yang","year":"2018","unstructured":"Yang L, Dong D, Fang M. Can ct-based radiomics signature predict kras\/nras\/braf mutations in colorectal cancer?Eur Radiol. 2018; 28(5):2058\u201367.","journal-title":"Eur Radiol"},{"issue":"4","key":"457_CR9","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1118\/1.4944498","volume":"43","author":"KH Cha","year":"2016","unstructured":"Cha KH, Hadjiiski L, Samala RK. Urinary bladder segmentation in ct urography using deep-learning convolutional neural network and level sets. Med Phys. 2016; 43(4):1882.","journal-title":"Med Phys"},{"issue":"7660","key":"457_CR10","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/nature22985","volume":"546","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA. Corrigendum: Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 546(7660):686.","journal-title":"Nature"},{"issue":"1","key":"457_CR11","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1038\/s41598-017-01931-w","volume":"7","author":"L Oakden-Rayner","year":"2017","unstructured":"Oakden-Rayner L, Carneiro G, Bessen T. Precision radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework. Sci Rep. 2017; 7(1):1684.","journal-title":"Sci Rep"},{"issue":"4","key":"457_CR12","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1007\/s10278-017-9984-3","volume":"30","author":"Z Akkus","year":"2017","unstructured":"Akkus Z, Ali I, Sedlar J. Deletion of chromosomal arms 1p\/19q in low-grade gliomas from mr images using machine intelligence. J Digit Imaging. 2017; 30(4):469\u201376.","journal-title":"J Digit Imaging"},{"issue":"5","key":"457_CR13","doi-asserted-by":"crossref","first-page":"622","DOI":"10.1007\/s10278-017-0009-z","volume":"30","author":"P Korfiatis","year":"2017","unstructured":"Korfiatis P, Kline TL, Lachance DH. Residual deep convolutional neural network predicts mgmt methylation status. J Digit Imaging. 2017; 30(5):622\u20138.","journal-title":"J Digit Imaging"},{"key":"457_CR14","doi-asserted-by":"publisher","unstructured":"He KM, Zhang XY, Ren SQ. Deep residual learning for image recognition. In: 2016 Ieee Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition: 2016. p. 770\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.90.","DOI":"10.1109\/cvpr.2016.90"},{"key":"457_CR15","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.ebiom.2018.12.028","volume":"39","author":"T Chen","year":"2019","unstructured":"Chen T, Liu S, Li Y. Developed and validated a prognostic nomogram for recurrence-free survival after complete surgical resection of local primary gastrointestinal stromal tumors based on deep learning. EBioMedicine. 2019; 39:272\u20139.","journal-title":"EBioMedicine"},{"issue":"5","key":"457_CR16","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1158\/1078-0432.CCR-17-2236","volume":"24","author":"K Chang","year":"2018","unstructured":"Chang K, Bai HX, Zhou H. Residual convolutional neural network for the determination of idh status in low- and high-grade gliomas from mr imaging. Clin Cancer Res. 2018; 24(5):1073\u201381.","journal-title":"Clin Cancer Res"},{"issue":"6","key":"457_CR17","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","volume":"29","author":"NJ Tustison","year":"2010","unstructured":"Tustison NJ, Avants BB, Cook PA. N4itk: improved n3 bias correction. IEEE Trans Med Imaging. 2010; 29(6):1310\u201320.","journal-title":"IEEE Trans Med Imaging"},{"issue":"3","key":"457_CR18","doi-asserted-by":"crossref","first-page":"1679","DOI":"10.1007\/s11192-014-1294-7","volume":"101","author":"ZH ZZhang","year":"2014","unstructured":"ZZhang ZH, Cheng Y, Liu NC. Comparison of the effect of mean-based method and z-score for field normalization of citations at the level of web of science subject categories. Scientometrics. 2014; 101(3):1679\u201393.","journal-title":"Scientometrics"},{"key":"457_CR19","doi-asserted-by":"crossref","unstructured":"Hara K, Saito D, Shouno H. Analysis of function of rectified linear unit used in deep learning. In: International Joint Conference on Neural Networks. IEEE International Joint Conference on Neural Networks (IJCNN): 2015.","DOI":"10.1109\/IJCNN.2015.7280578"},{"issue":"1","key":"457_CR20","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1198\/106186006X94072","volume":"15","author":"T Shi","year":"2005","unstructured":"Shi T, Horvath S. Unsupervised learning with random forest predictors. J Comput Graph Stat. 2005; 15(1):118\u201338.","journal-title":"J Comput Graph Stat"},{"key":"457_CR21","first-page":"3133","volume":"15","author":"M Fernandez-Delgado","year":"2014","unstructured":"Fernandez-Delgado M, Cernadas E, Barro S. Do we need hundreds of classifiers to solve real world classification problems?J Mach Learn Res. 2014; 15:3133\u201381.","journal-title":"J Mach Learn Res"},{"issue":"9","key":"457_CR22","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1016\/S1470-2045(18)30413-3","volume":"19","author":"R Sun","year":"2018","unstructured":"Sun R, Limkin EJ, Vakalopoulou M. A radiomics approach to assess tumour-infiltrating cd8 cells and response to anti-pd-1 or anti-pd-l1 immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol. 2018; 19(9):1180\u201391.","journal-title":"Lancet Oncol"},{"issue":"1","key":"457_CR23","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1148\/radiol.2017161845","volume":"286","author":"M Zhou","year":"2018","unstructured":"Zhou M, Leung A, Echegaray S. Non-small cell lung cancer radiogenomics map identifies relationships between molecular and imaging phenotypes with prognostic implications. Radiology. 2018; 286(1):307\u201315.","journal-title":"Radiology"},{"issue":"9","key":"457_CR24","doi-asserted-by":"crossref","first-page":"3692","DOI":"10.1007\/s00330-017-5180-6","volume":"28","author":"S Zhang","year":"2018","unstructured":"Zhang S, Song G, Zang Y. Non-invasive radiomics approach potentially predicts non-functioning pituitary adenomas subtypes before surgery. Eur Radiol. 2018; 28(9):3692\u2013701.","journal-title":"Eur Radiol"},{"issue":"7","key":"457_CR25","doi-asserted-by":"crossref","first-page":"2772","DOI":"10.1007\/s00330-017-5221-1","volume":"28","author":"X Zhu","year":"2018","unstructured":"Zhu X, Dong D, Chen Z. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol. 2018; 28(7):2772\u20138.","journal-title":"Eur Radiol"},{"key":"457_CR26","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.ebiom.2018.12.028","volume":"39","author":"T Chen","year":"2019","unstructured":"Chen T, Liu SQ, Li Y. Developed and validated a prognostic nomogram for recurrence-free survival after complete surgical resection of local primary gastrointestinal stromal tumors based on deep learning. Ebiomedicine. 2019; 39:272\u20139.","journal-title":"Ebiomedicine"},{"issue":"4","key":"457_CR27","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1007\/s10278-018-0167-7","volume":"32","author":"G Kitamura","year":"2019","unstructured":"Kitamura G, Chung CY, Moore BE. 2nd.ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample, de novo training, and multiview incorporation. J Digit Imaging. 2019; 32(4):672\u20137.","journal-title":"J Digit Imaging"},{"key":"457_CR28","doi-asserted-by":"crossref","first-page":"34921","DOI":"10.1038\/srep34921","volume":"6","author":"L He","year":"2016","unstructured":"He L, Huang Y, Ma Z. Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule. Sci Rep. 2016; 6:34921.","journal-title":"Sci Rep"},{"issue":"11","key":"457_CR29","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1080\/0284186X.2017.1351624","volume":"56","author":"R Larue","year":"2017","unstructured":"Larue R, van Timmeren JE, de Jong EEC. Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses: a comprehensive phantom study. Acta Oncol. 2017; 56(11):1544\u201353.","journal-title":"Acta Oncol"},{"issue":"21","key":"457_CR30","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1158\/0008-5472.CAN-17-0339","volume":"77","author":"JJM van Griethuysen","year":"2017","unstructured":"van Griethuysen JJM, Fedorov A, Parmar C. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017; 77(21):104\u20137.","journal-title":"Cancer Res"},{"issue":"11","key":"457_CR31","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y. Gradient-based learning applied to document recognition. Proc IEEE. 1998; 86(11):2278\u2013324.","journal-title":"Proc IEEE"},{"issue":"1","key":"457_CR32","doi-asserted-by":"crossref","first-page":"16914","DOI":"10.1038\/s41598-018-35359-7","volume":"8","author":"JE Bibault","year":"2018","unstructured":"Bibault JE, Giraud P, Housset M. Author correction: Deep learning and radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer. Sci Rep. 2018; 8(1):16914.","journal-title":"Sci Rep"},{"issue":"1","key":"457_CR33","doi-asserted-by":"crossref","first-page":"8738","DOI":"10.1038\/s41598-017-09315-w","volume":"7","author":"KH Cha","year":"2017","unstructured":"Cha KH, Hadjiiski L, Chan HP. Bladder cancer treatment response assessment in ct using radiomics with deep-learning. Sci Rep. 2017; 7(1):8738.","journal-title":"Sci Rep"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-020-00457-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-020-00457-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-020-00457-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T19:43:00Z","timestamp":1622490180000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-020-00457-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,1]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["457"],"URL":"https:\/\/doi.org\/10.1186\/s12880-020-00457-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.2.22851\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.3.rs-29491\/v1","asserted-by":"object"}]},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,1]]},"assertion":[{"value":"16 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This research was approved by the First Hospital of Jilin University medical ethics committee and carried out in accordance with the guidelines and regulations of NCCN and Helsinki, and the need for informed consent was waived by the retrospective nature of the study.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not Applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"59"}}